[go: up one dir, main page]

CN111158612B - A kind of edge storage acceleration method, device and device for collaborative mobile device - Google Patents

A kind of edge storage acceleration method, device and device for collaborative mobile device Download PDF

Info

Publication number
CN111158612B
CN111158612B CN202010252903.4A CN202010252903A CN111158612B CN 111158612 B CN111158612 B CN 111158612B CN 202010252903 A CN202010252903 A CN 202010252903A CN 111158612 B CN111158612 B CN 111158612B
Authority
CN
China
Prior art keywords
mobile device
data
storage
edge
mobile devices
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010252903.4A
Other languages
Chinese (zh)
Other versions
CN111158612A (en
Inventor
包卫东
朱晓敏
高雄
王吉
吴冠霖
闫辉
张耀鸿
周文
张雄涛
马力
张亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
National University of Defense Technology
Original Assignee
National University of Defense Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by National University of Defense Technology filed Critical National University of Defense Technology
Priority to CN202010252903.4A priority Critical patent/CN111158612B/en
Publication of CN111158612A publication Critical patent/CN111158612A/en
Application granted granted Critical
Publication of CN111158612B publication Critical patent/CN111158612B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/061—Improving I/O performance
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0614—Improving the reliability of storage systems
    • G06F3/0619—Improving the reliability of storage systems in relation to data integrity, e.g. data losses, bit errors
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/0671—In-line storage system
    • G06F3/0683—Plurality of storage devices

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Security & Cryptography (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

One or more embodiments of the present invention provide a method, an apparatus, and a device for edge storage acceleration in cooperation with a mobile device, where the method includes: establishing an edge collaborative storage task for transmitting data between mobile devices; edge-based collaborative storage tasksEstablishing an edge collaborative storage model, wherein the edge collaborative storage model comprises the following steps: mobile device collection
Figure 100004_DEST_PATH_IMAGE001
Sending mobile device
Figure 991390DEST_PATH_IMAGE002
Receiving mobile device
Figure 100004_DEST_PATH_IMAGE003
And network topology
Figure 705269DEST_PATH_IMAGE004
Set of mobile devices
Figure 78481DEST_PATH_IMAGE001
Comprises at least two mobile devices; calculating to obtain an A2CS acceleration algorithm based on the edge collaborative storage model; based on an edge collaborative storage model and an A2CS acceleration algorithm, an edge collaborative storage strategy is provided; and guiding the edge cooperative storage task by an edge cooperative storage strategy. The acceleration method provided by one or more embodiments of the present invention considers the unique characteristics of the mobile device and the dynamic network topology of the plurality of mobile devices, ensures flexible data backup, has low latency, and improves storage reliability.

Description

一种协同移动设备的边缘存储加速方法、装置及设备A kind of edge storage acceleration method, device and device for collaborative mobile device

技术领域technical field

本发明一个或多个实施例涉及边缘存储技术领域，尤其涉及一种协同移动设备的边缘存储加速方法、装置及设备。One or more embodiments of the present invention relate to the field of edge storage technologies, and in particular, to a method, apparatus, and device for accelerating edge storage in coordination with mobile devices.

背景技术Background technique

越来越多的移动设备用于收集和处理大量数据，一方面，在军事领域，士兵通过战术手持终端、UAV和UGV（无人地面车辆）等移动设备上传和共享数据。由于可能会造成人身伤亡，需要备份个人数据，以避免数据丢失。另一方面，在民用领域，移动设备可用于存储灾难或紧急情况的数据以执行实时灾情监视。数据存储方式。然而，解决协同存储问题仍然存在一些障碍。第一，与传统存储设备相比，边缘移动设备具有独特的特性。与服务器、计算机和其他传统存储设备的相对稳定的网络结构不同，由移动设备组成的边缘的网络拓扑是高度动态的。对于传统的存储问题，为了确保数据存储的可用性，通常使用分布式的数据备份方法。但是，随着移动设备资源的逐渐消耗，不正确的副本数量选择和不合理的备份数据分配都可能导致数据备份失败。副本数量的选择和备份数据的分配应随边缘移动设备资源的变化而调整。完成协同存储的时间是关键指标。一方面，随着协同存储时间的增长，很可能导致存储故障。另一方面，随着时间成本的增加，消耗了更多的能量。因此，低延迟时间的要求至关重要且值得关注。设计的算法应尽快收敛，以减少移动设备的时间开销和能耗。现有技术无法考虑高度动态的网络拓扑，存储可靠性低，数据备份失败率高，协同存储时间长，延迟高。More and more mobile devices are used to collect and process large amounts of data. On the one hand, in the military field, soldiers upload and share data through mobile devices such as tactical handheld terminals, UAVs and UGVs (unmanned ground vehicles). Personal data needs to be backed up to avoid data loss due to the potential for personal injury or death. On the other hand, in the civilian sector, mobile devices can be used to store disaster or emergency data to perform real-time disaster monitoring. Data storage method. However, there are still some obstacles to solving the co-storage problem. First, edge mobile devices have unique characteristics compared to traditional storage devices. Unlike the relatively stable network structures of servers, computers, and other traditional storage devices, the network topology at the edge consisting of mobile devices is highly dynamic. For traditional storage problems, in order to ensure the availability of data storage, a distributed data backup method is usually used. However, with the gradual consumption of mobile device resources, incorrect selection of the number of copies and unreasonable allocation of backup data may lead to data backup failure. The choice of the number of replicas and the allocation of backup data should be adjusted as the resources of the edge mobile device change. The time to complete the collaborative store is the key metric. On the one hand, with the growth of cooperative storage time, it is likely to lead to storage failure. On the other hand, as the time cost increases, more energy is consumed. Therefore, the requirement of low latency is critical and worthy of attention. The designed algorithm should converge as soon as possible to reduce the time overhead and energy consumption of mobile devices. The prior art cannot consider highly dynamic network topology, low storage reliability, high data backup failure rate, long collaborative storage time, and high latency.

发明内容SUMMARY OF THE INVENTION

有鉴于此，本发明一个或多个实施例的目的在于提出一种协同移动设备的边缘存储加速方法、装置及设备，以解决现有技术无法考虑高度动态的网络拓扑，存储可靠性低，数据备份失败率高，协同存储时间长，延迟高的问题。In view of this, the purpose of one or more embodiments of the present invention is to provide an edge storage acceleration method, device and device for collaborative mobile devices, so as to solve the problem that the prior art cannot consider highly dynamic network topology, storage reliability is low, data storage The backup failure rate is high, the collaborative storage time is long, and the delay is high.

基于上述目的，本发明一个或多个实施例提供了一种协同移动设备的边缘存储加速方法，包括：Based on the above objectives, one or more embodiments of the present invention provide an edge storage acceleration method for coordinated mobile devices, including:

建立移动设备间传输数据的边缘协同存储任务；Establish an edge cooperative storage task for data transmission between mobile devices;

基于所述边缘协同存储任务建立边缘协同存储模型，所述边缘协同存储模型包括：移动设备集合

Figure DEST_PATH_IMAGE001
、发送移动设备
Figure DEST_PATH_IMAGE002
、接收移动设备
Figure DEST_PATH_IMAGE003
和网络拓扑
Figure DEST_PATH_IMAGE004
，所述移动设备集合
Figure 440731DEST_PATH_IMAGE001
包括至少两个移动设备；An edge collaborative storage model is established based on the edge collaborative storage task, and the edge collaborative storage model includes: a set of mobile devices
Figure DEST_PATH_IMAGE001
, send mobile device
Figure DEST_PATH_IMAGE002
, receiving mobile device
Figure DEST_PATH_IMAGE003
and network topology
Figure DEST_PATH_IMAGE004
, the mobile device collection
Figure 440731DEST_PATH_IMAGE001
Include at least two mobile devices;

基于所述边缘协同存储模型计算得到A2CS加速算法；The A2CS acceleration algorithm is calculated based on the edge collaborative storage model;

基于所述边缘协同存储模型和A2CS加速算法，提出边缘协同存储策略；Based on the edge collaborative storage model and the A2CS acceleration algorithm, an edge collaborative storage strategy is proposed;

以所述边缘协同存储策略指导所述边缘协同存储任务。The edge cooperative storage task is guided by the edge cooperative storage policy.

可选的，所述建立移动设备间传输数据的边缘协同存储任务，包括：Optionally, the establishment of an edge cooperative storage task for data transmission between mobile devices includes:

所述移动设备收集数据；the mobile device collects data;

所述移动设备基于数据丢失概率

Figure DEST_PATH_IMAGE005
和能耗
Figure DEST_PATH_IMAGE006
将所述数据的副本发送至与所述移动设备相连的相邻移动设备，所述相邻移动设备至少有一个；The mobile device is based on data loss probability
Figure DEST_PATH_IMAGE005
and energy consumption
Figure DEST_PATH_IMAGE006
sending a copy of the data to adjacent mobile devices connected to the mobile device, at least one of the adjacent mobile devices;

所述移动设备集合

Figure 762733DEST_PATH_IMAGE001
基于所述相邻移动设备的存储容量和电池电量，确定所述副本的数量
Figure DEST_PATH_IMAGE007
和接收所述副本的所述相邻移动设备。the set of mobile devices
Figure 762733DEST_PATH_IMAGE001
The number of replicas is determined based on the storage capacity and battery level of the neighboring mobile device
Figure DEST_PATH_IMAGE007
and the neighboring mobile device that received the copy.

可选的，所述移动设备集合

Figure 135946DEST_PATH_IMAGE001
被建模为
Figure DEST_PATH_IMAGE008
，其中
Figure DEST_PATH_IMAGE009
是第
Figure DEST_PATH_IMAGE010
个所述移动设备，
Figure DEST_PATH_IMAGE011
是边缘中的所述移动设备的总数。Optionally, the mobile device set
Figure 135946DEST_PATH_IMAGE001
is modeled as
Figure DEST_PATH_IMAGE008
,in
Figure DEST_PATH_IMAGE009
is the first
Figure DEST_PATH_IMAGE010
said mobile device,
Figure DEST_PATH_IMAGE011
is the total number of said mobile devices in the edge.

可选的，所述第

Figure DEST_PATH_IMAGE012
个所述移动设备
Figure 235882DEST_PATH_IMAGE009
被建模为
Figure DEST_PATH_IMAGE013
，其中
Figure DEST_PATH_IMAGE014
表示
Figure 440467DEST_PATH_IMAGE009
的存储容量，
Figure DEST_PATH_IMAGE015
表示
Figure 387564DEST_PATH_IMAGE009
的电池电量，
Figure DEST_PATH_IMAGE016
表示
Figure 44810DEST_PATH_IMAGE009
收集的数据量大小，
Figure DEST_PATH_IMAGE017
表示
Figure 574536DEST_PATH_IMAGE009
收集的数据的数据副本数量，
Figure DEST_PATH_IMAGE018
表示
Figure 633628DEST_PATH_IMAGE009
的数据传输速率，
Figure DEST_PATH_IMAGE019
表示
Figure 830254DEST_PATH_IMAGE009
的数据接收速率。Optionally, the
Figure DEST_PATH_IMAGE012
said mobile devices
Figure 235882DEST_PATH_IMAGE009
is modeled as
Figure DEST_PATH_IMAGE013
,in
Figure DEST_PATH_IMAGE014
express
Figure 440467DEST_PATH_IMAGE009
storage capacity,
Figure DEST_PATH_IMAGE015
express
Figure 387564DEST_PATH_IMAGE009
battery power,
Figure DEST_PATH_IMAGE016
express
Figure 44810DEST_PATH_IMAGE009
The amount of data collected,
Figure DEST_PATH_IMAGE017
express
Figure 574536DEST_PATH_IMAGE009
the number of data copies of the collected data,
Figure DEST_PATH_IMAGE018
express
Figure 633628DEST_PATH_IMAGE009
the data transfer rate,
Figure DEST_PATH_IMAGE019
express
Figure 830254DEST_PATH_IMAGE009
data reception rate.

可选的，所述网络拓扑

Figure 37113DEST_PATH_IMAGE004
被建模为
Figure DEST_PATH_IMAGE020
，
Figure 102021DEST_PATH_IMAGE001
表示移动设备集合，
Figure DEST_PATH_IMAGE021
表示邻接矩阵，
Figure DEST_PATH_IMAGE022
表示距离矩阵，所述邻接矩阵
Figure 284128DEST_PATH_IMAGE021
包括：Optionally, the network topology
Figure 37113DEST_PATH_IMAGE004
is modeled as
Figure DEST_PATH_IMAGE020
,
Figure 102021DEST_PATH_IMAGE001
represents a collection of mobile devices,
Figure DEST_PATH_IMAGE021
represents the adjacency matrix,
Figure DEST_PATH_IMAGE022
represents the distance matrix, the adjacency matrix
Figure 284128DEST_PATH_IMAGE021
include:

对于任意所述移动设备

Figure DEST_PATH_IMAGE023
，与其他所述移动设备
Figure DEST_PATH_IMAGE024
的连通性由邻接矩阵中的元素表示，
Figure DEST_PATH_IMAGE025
表示所述邻接矩阵
Figure 697661DEST_PATH_IMAGE021
的第
Figure DEST_PATH_IMAGE026
行、第
Figure DEST_PATH_IMAGE027
列中的元素，它由以下表达式确定：for any of the mobile devices
Figure DEST_PATH_IMAGE023
, with other described mobile devices
Figure DEST_PATH_IMAGE024
The connectivity of is represented by the elements in the adjacency matrix,
Figure DEST_PATH_IMAGE025
represents the adjacency matrix
Figure 697661DEST_PATH_IMAGE021
First
Figure DEST_PATH_IMAGE026
row,
Figure DEST_PATH_IMAGE027
The element in the column, which is determined by the following expression:

Figure DEST_PATH_IMAGE028
Figure DEST_PATH_IMAGE028

所述距离矩阵

Figure 736024DEST_PATH_IMAGE022
包括：the distance matrix
Figure 736024DEST_PATH_IMAGE022
include:

对于任意所述移动设备

Figure 454888DEST_PATH_IMAGE023
，到其他所述移动设备
Figure DEST_PATH_IMAGE029
的距离是所述距离矩阵
Figure 567201DEST_PATH_IMAGE022
中元素的值，
Figure DEST_PATH_IMAGE030
代表所述距离矩阵
Figure 495843DEST_PATH_IMAGE022
的第
Figure 411715DEST_PATH_IMAGE026
行、第
Figure 756109DEST_PATH_IMAGE027
列中的元素，它由以下表达式确定：for any of the mobile devices
Figure 454888DEST_PATH_IMAGE023
, to the other said mobile device
Figure DEST_PATH_IMAGE029
The distance is the distance matrix
Figure 567201DEST_PATH_IMAGE022
the value of the element in ,
Figure DEST_PATH_IMAGE030
represents the distance matrix
Figure 495843DEST_PATH_IMAGE022
First
Figure 411715DEST_PATH_IMAGE026
row,
Figure 756109DEST_PATH_IMAGE027
The element in the column, which is determined by the following expression:

Figure DEST_PATH_IMAGE031
Figure DEST_PATH_IMAGE031

其中

Figure DEST_PATH_IMAGE032
表示
Figure DEST_PATH_IMAGE033
和
Figure DEST_PATH_IMAGE034
之间的距离。in
Figure DEST_PATH_IMAGE032
express
Figure DEST_PATH_IMAGE033
and
Figure DEST_PATH_IMAGE034
the distance between.

可选的，所述发送移动设备

Figure 771862DEST_PATH_IMAGE002
和接收移动设备
Figure 684455DEST_PATH_IMAGE003
组成收发移动设备组
Figure DEST_PATH_IMAGE035
，所述发送移动设备
Figure 25306DEST_PATH_IMAGE002
和接收移动设备
Figure 173391DEST_PATH_IMAGE003
之间进行数据存储和数据传输，所述数据存储产生数据存储能耗
Figure DEST_PATH_IMAGE036
，所述
Figure 119350DEST_PATH_IMAGE036
表述为Optionally, the sending mobile device
Figure 771862DEST_PATH_IMAGE002
and receiving mobile devices
Figure 684455DEST_PATH_IMAGE003
Form sending and receiving mobile device groups
Figure DEST_PATH_IMAGE035
, the sending mobile device
Figure 25306DEST_PATH_IMAGE002
and receiving mobile devices
Figure 173391DEST_PATH_IMAGE003
Data storage and data transmission are performed between the data storage and the data storage energy consumption.
Figure DEST_PATH_IMAGE036
, the
Figure 119350DEST_PATH_IMAGE036
expressed as

Figure DEST_PATH_IMAGE037
Figure DEST_PATH_IMAGE037

其中，

Figure DEST_PATH_IMAGE038
表示当
Figure DEST_PATH_IMAGE039
时从所述发送移动设备
Figure 376413DEST_PATH_IMAGE002
传输到接收移动设备
Figure 17609DEST_PATH_IMAGE003
的数据量大小，以及当
Figure DEST_PATH_IMAGE040
时所述发送移动设备
Figure 156336DEST_PATH_IMAGE002
存储的数据量大小，
Figure DEST_PATH_IMAGE041
表示上述组
Figure DEST_PATH_IMAGE042
中数据存储的能耗；in,
Figure DEST_PATH_IMAGE038
means when
Figure DEST_PATH_IMAGE039
when sending from the mobile device
Figure 376413DEST_PATH_IMAGE002
Transmission to the receiving mobile device
Figure 17609DEST_PATH_IMAGE003
size of data, and when
Figure DEST_PATH_IMAGE040
when the sending mobile device
Figure 156336DEST_PATH_IMAGE002
The amount of data stored,
Figure DEST_PATH_IMAGE041
represents the above group
Figure DEST_PATH_IMAGE042
energy consumption of data storage in

所述数据传输产生数据传输能耗

Figure DEST_PATH_IMAGE043
，所述
Figure 691222DEST_PATH_IMAGE043
表述为The data transmission generates data transmission energy consumption
Figure DEST_PATH_IMAGE043
, the
Figure 691222DEST_PATH_IMAGE043
expressed as

Figure 460464DEST_PATH_IMAGE044
Figure 460464DEST_PATH_IMAGE044

其中

Figure DEST_PATH_IMAGE045
表示所述发送移动设备
Figure 854536DEST_PATH_IMAGE002
的发射功率，
Figure DEST_PATH_IMAGE046
表示接收移动设备
Figure 675249DEST_PATH_IMAGE003
的接收功率，
Figure DEST_PATH_IMAGE047
表示数据从所述发送移动设备
Figure 454855DEST_PATH_IMAGE002
传输至所述接收移动设备
Figure 880151DEST_PATH_IMAGE003
所花费的时间，
Figure DEST_PATH_IMAGE048
表示所述接收移动设备
Figure 10787DEST_PATH_IMAGE003
接收所述发送移动设备
Figure 242049DEST_PATH_IMAGE002
发送的数据所花费的时间，
Figure DEST_PATH_IMAGE049
表示发射天线增益，
Figure DEST_PATH_IMAGE050
表示接收天线增益，
Figure DEST_PATH_IMAGE051
表示波长，
Figure DEST_PATH_IMAGE052
表示所述发送移动设备
Figure DEST_PATH_IMAGE053
和所述接收移动设备
Figure 77760DEST_PATH_IMAGE003
之间的距离，
Figure DEST_PATH_IMAGE054
表示与传播无关的系统损耗因子，
Figure DEST_PATH_IMAGE055
表示所述发送移动设备
Figure 392067DEST_PATH_IMAGE002
的数据传输速率，
Figure DEST_PATH_IMAGE056
表示所述接收移动设备
Figure 760731DEST_PATH_IMAGE003
的数据接收速率；in
Figure DEST_PATH_IMAGE045
represents the sending mobile device
Figure 854536DEST_PATH_IMAGE002
the transmit power,
Figure DEST_PATH_IMAGE046
Indicates the receiving mobile device
Figure 675249DEST_PATH_IMAGE003
the received power,
Figure DEST_PATH_IMAGE047
Indicates that data is sent from the mobile device
Figure 454855DEST_PATH_IMAGE002
transmitted to the receiving mobile device
Figure 880151DEST_PATH_IMAGE003
time spent,
Figure DEST_PATH_IMAGE048
represents the receiving mobile device
Figure 10787DEST_PATH_IMAGE003
receiving the sending mobile device
Figure 242049DEST_PATH_IMAGE002
the time it took to send the data,
Figure DEST_PATH_IMAGE049
represents the transmit antenna gain,
Figure DEST_PATH_IMAGE050
represents the receiving antenna gain,
Figure DEST_PATH_IMAGE051
represents the wavelength,
Figure DEST_PATH_IMAGE052
represents the sending mobile device
Figure DEST_PATH_IMAGE053
and the receiving mobile device
Figure 77760DEST_PATH_IMAGE003
the distance between,
Figure DEST_PATH_IMAGE054
represents the propagation-independent system loss factor,
Figure DEST_PATH_IMAGE055
represents the sending mobile device
Figure 392067DEST_PATH_IMAGE002
the data transfer rate,
Figure DEST_PATH_IMAGE056
represents the receiving mobile device
Figure 760731DEST_PATH_IMAGE003
data reception rate;

所述数据存储能耗

Figure 779372DEST_PATH_IMAGE036
和所述数据传输能耗
Figure DEST_PATH_IMAGE057
之和为边缘协同存储的总能耗
Figure DEST_PATH_IMAGE058
，所述总能耗
Figure 943024DEST_PATH_IMAGE058
表述为The data storage energy consumption
Figure 779372DEST_PATH_IMAGE036
and the data transmission energy consumption
Figure DEST_PATH_IMAGE057
The sum is the total energy consumption of edge collaborative storage
Figure DEST_PATH_IMAGE058
, the total energy consumption
Figure 943024DEST_PATH_IMAGE058
expressed as

Figure DEST_PATH_IMAGE059
。
Figure DEST_PATH_IMAGE059
.

可选的，所述A2CS加速算法包括：Optionally, the A2CS acceleration algorithm includes:

初始值

Figure DEST_PATH_IMAGE060
、
Figure DEST_PATH_IMAGE061
和
Figure DEST_PATH_IMAGE062
，所述初始值表示对任意一个移动设备
Figure DEST_PATH_IMAGE063
部署所述A2CS加速算法的初始数值，所述初始值表述为initial value
Figure DEST_PATH_IMAGE060
,
Figure DEST_PATH_IMAGE061
and
Figure DEST_PATH_IMAGE062
, the initial value indicates that for any mobile device
Figure DEST_PATH_IMAGE063
Deploy the initial value of the A2CS acceleration algorithm, the initial value is expressed as

Figure DEST_PATH_IMAGE064
Figure DEST_PATH_IMAGE064

其中

Figure DEST_PATH_IMAGE065
表示与所述
Figure 146341DEST_PATH_IMAGE063
连接的移动设备的数量，
Figure DEST_PATH_IMAGE066
表示
Figure 267881DEST_PATH_IMAGE065
维向量；in
Figure DEST_PATH_IMAGE065
expressed with the stated
Figure 146341DEST_PATH_IMAGE063
the number of connected mobile devices,
Figure DEST_PATH_IMAGE066
express
Figure 267881DEST_PATH_IMAGE065
dimensional vector;

停止准则，所述停止准则使所述A2CS加速算法获得可行解并确保所述A2CS加速算法快速收敛，所述停止准则表述为A stopping criterion that enables the A2CS acceleration algorithm to obtain a feasible solution and ensures rapid convergence of the A2CS acceleration algorithm, and the stopping criterion is expressed as

Figure DEST_PATH_IMAGE067
和
Figure DEST_PATH_IMAGE068
，
Figure DEST_PATH_IMAGE067
and
Figure DEST_PATH_IMAGE068
,

其中

Figure DEST_PATH_IMAGE069
表示第
Figure DEST_PATH_IMAGE070
次迭代时的原始残差，
Figure DEST_PATH_IMAGE071
表示第
Figure 624301DEST_PATH_IMAGE070
次迭代时的对偶残差，
Figure DEST_PATH_IMAGE072
表示绝对公差，
Figure DEST_PATH_IMAGE073
表示相对公差。in
Figure DEST_PATH_IMAGE069
means the first
Figure DEST_PATH_IMAGE070
the original residual at the next iteration,
Figure DEST_PATH_IMAGE071
means the first
Figure 624301DEST_PATH_IMAGE070
dual residuals at the next iteration,
Figure DEST_PATH_IMAGE072
represents the absolute tolerance,
Figure DEST_PATH_IMAGE073
Indicates relative tolerance.

可选的，所述边缘协同存储策略包括以下步骤：数据收集、请求分发、做出决策、决策反馈、多次交互和数据传输。Optionally, the edge cooperative storage strategy includes the following steps: data collection, request distribution, decision making, decision feedback, multiple interactions, and data transmission.

基于同一发明构思，本发明一个或多个实施例还提供了一种协同移动设备的边缘存储加速装置，包括：Based on the same inventive concept, one or more embodiments of the present invention further provide an edge storage acceleration apparatus for cooperating with mobile devices, including:

第一建立模块，被配置为建立移动设备间传输数据的边缘协同存储任务；a first establishment module, configured to establish an edge cooperative storage task for data transmission between mobile devices;

第二建立模块，被配置为基于所述边缘协同存储任务建立边缘协同存储模型，所述边缘协同存储模型包括：移动设备集合

Figure 905109DEST_PATH_IMAGE001
、发送移动设备
Figure 92377DEST_PATH_IMAGE002
、接收移动设备
Figure 232371DEST_PATH_IMAGE003
和网络拓扑
Figure 609126DEST_PATH_IMAGE004
，所述移动设备集合
Figure 278529DEST_PATH_IMAGE001
包括至少两个移动设备；The second establishment module is configured to establish an edge cooperative storage model based on the edge cooperative storage task, where the edge cooperative storage model includes: a set of mobile devices
Figure 905109DEST_PATH_IMAGE001
, send mobile device
Figure 92377DEST_PATH_IMAGE002
, receiving mobile device
Figure 232371DEST_PATH_IMAGE003
and network topology
Figure 609126DEST_PATH_IMAGE004
, the mobile device collection
Figure 278529DEST_PATH_IMAGE001
Include at least two mobile devices;

计算模块，被配置为基于所述边缘协同存储模型计算得到A2CS加速算法；a computing module, configured to calculate and obtain an A2CS acceleration algorithm based on the edge collaborative storage model;

策略模块，被配置为基于所述边缘协同存储模型和A2CS加速算法，提出边缘协同存储策略；a strategy module, configured to propose an edge collaborative storage strategy based on the edge collaborative storage model and the A2CS acceleration algorithm;

执行模块，被配置为以所述边缘协同存储策略指导所述边缘协同存储任务。An execution module configured to direct the edge cooperative storage task with the edge cooperative storage policy.

基于同一发明构思，本发明一个或多个实施例还提供了一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其特征在于，所述处理器执行所述程序时实现上述任意一种所述的方法。Based on the same inventive concept, one or more embodiments of the present invention further provide an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that the processor When the program is executed, any one of the methods described above is implemented.

从上面所述可以看出，本发明一个或多个实施例提供的一种协同移动设备的边缘存储加速方法、装置及设备，特别注意了移动设备的独特特性以及多个移动设备的动态网络拓扑，将协同存储问题转化为可解决的优化问题，通过研究加速策略，提出了A2CS加速算法，高效地解决协同存储的优化问题，在A2CS加速算法中，可以从理论上提高收敛速度，同时提出了一种协同存储策略，该策略包括六大步骤，可以表示协同存储的整个过程，A2CS加速算法应用贯穿于该策略的全部步骤，以该策略指导协同存储的整个循环周期。A2CS加速算法与两种现有方法ADMM基准和ADMM-OR（具有过度松弛的ADMM）相比，A2CS加速算法在不同的步长规则下提供了更好的收敛性能，加速百分比至少达到25.33％，最多可以达到64.01％。此外，通过使用现有的平均分配策略（ADS）和现有的距离优先分配策略（DPDS）进行效用性能比较分析，结果表明A2CS加速算法在总效用和能耗方面优于ADS策略和DPDS策略。As can be seen from the above, one or more embodiments of the present invention provide an edge storage acceleration method, apparatus, and device for cooperating with mobile devices, paying particular attention to the unique characteristics of mobile devices and the dynamic network topology of multiple mobile devices , transforming the cooperative storage problem into a solvable optimization problem. By studying the acceleration strategy, an A2CS acceleration algorithm is proposed to efficiently solve the optimization problem of cooperative storage. In the A2CS acceleration algorithm, the convergence speed can be theoretically improved. At the same time, the proposed A collaborative storage strategy includes six steps, which can represent the entire process of collaborative storage. A2CS acceleration algorithm is applied throughout all steps of the strategy, and the strategy guides the entire cycle of collaborative storage. Compared with the two existing methods ADMM benchmark and ADMM-OR (ADMM with over-relaxation), the A2CS acceleration algorithm provides better convergence performance under different step size rules, and the acceleration percentage reaches at least 25.33%, Up to 64.01% can be achieved. Furthermore, by using the existing average allocation strategy (ADS) and the existing distance-preferred allocation strategy (DPDS) to conduct a utility performance comparative analysis, the results show that the A2CS acceleration algorithm outperforms the ADS strategy and the DPDS strategy in terms of total utility and energy consumption.

附图说明Description of drawings

为了更清楚地说明本发明一个或多个实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明一个或多个实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to illustrate one or more embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that are needed in the description of the embodiments or the prior art. Obviously, in the following description The accompanying drawings are only one or more embodiments of the present invention, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative efforts.

图1为本发明一个或多个实施例中加速方法流程示意图；1 is a schematic flowchart of an acceleration method in one or more embodiments of the present invention;

图2为本发明一个或多个实施例中加速算法A2CS框架图；2 is a framework diagram of an acceleration algorithm A2CS in one or more embodiments of the present invention;

图3为本发明一个或多个实施例中协同存储策略示意图；3 is a schematic diagram of a collaborative storage strategy in one or more embodiments of the present invention;

图4为本发明一个或多个实施例中加速装置示意图；4 is a schematic diagram of an acceleration device in one or more embodiments of the present invention;

图5为本发明一个或多个实施例中电子设备示意图；5 is a schematic diagram of an electronic device in one or more embodiments of the present invention;

图6为本发明一个或多个实施例中数据量大小固定时的能耗和数据丢失的归一化值的实验数据图；6 is an experimental data diagram of normalized values of energy consumption and data loss when the data size is fixed in one or more embodiments of the present invention;

图7（a）为本发明一个或多个实施例中副本数与收敛数之间的关系以及使用步长规则

Figure DEST_PATH_IMAGE074
的A2CS的总效用与副本数之间的关系图；Figure 7(a) shows the relationship between the number of replicas and the number of convergence and the use of step size rules in one or more embodiments of the present invention
Figure DEST_PATH_IMAGE074
A graph of the relationship between the total utility of A2CS and the number of replicas;

图7（b）为本发明一个或多个实施例中副本数与收敛数之间的关系以及使用步长规则

Figure DEST_PATH_IMAGE075
的A2CS的总效用与副本数之间的关系图；Figure 7(b) shows the relationship between the number of replicas and the number of convergence and the use of step size rules in one or more embodiments of the present invention
Figure DEST_PATH_IMAGE075
A graph of the relationship between the total utility of A2CS and the number of replicas;

图7（c）为本发明一个或多个实施例中副本数与收敛数之间的关系以及使用步长规则

Figure DEST_PATH_IMAGE076
的A2CS的总效用与副本数之间的关系图；Figure 7(c) shows the relationship between the number of replicas and the number of convergence and the use of step size rules in one or more embodiments of the present invention
Figure DEST_PATH_IMAGE076
A graph of the relationship between the total utility of A2CS and the number of replicas;

图8（a）为本发明一个或多个实施例中当数据量大小固定时，A2CS算法使用不同的步长规则对收敛次数的影响关系图；Figure 8(a) is a graph showing the influence of the A2CS algorithm on the convergence times using different step size rules when the data size is fixed in one or more embodiments of the present invention;

图8（b）为本发明一个或多个实施例中当数据量大小固定时，ADMM算法使用不同的步长规则对收敛次数的影响关系图；Figure 8(b) is a graph showing the influence of the ADMM algorithm on the convergence times using different step size rules when the data size is fixed in one or more embodiments of the present invention;

图8（c）为本发明一个或多个实施例中当数据量大小固定时，ADMM-OR算法使用不同的步长规则对收敛次数的影响关系图；Figure 8(c) is a graph showing the influence of the ADMM-OR algorithm on the convergence times using different step size rules when the data size is fixed in one or more embodiments of the present invention;

图9（a）为本发明一个或多个实施例中使用不同的算法（A2CS，ADMM和ADMM-OR）结合步长规则

Figure DEST_PATH_IMAGE077
的情况下数据量大小和收敛次数之间的关系图；Figure 9(a) illustrates the use of different algorithms (A2CS, ADMM and ADMM-OR) combined with step size rules in one or more embodiments of the present invention
Figure DEST_PATH_IMAGE077
The relationship between the amount of data and the number of convergence times in the case of ;

图9（b）为本发明一个或多个实施例中使用不同的算法（A2CS，ADMM和ADMM-OR）结合步长规则

Figure 839961DEST_PATH_IMAGE076
的情况下数据量大小和收敛次数之间的关系图；；Figure 9(b) illustrates the use of different algorithms (A2CS, ADMM and ADMM-OR) combined with step size rules in one or more embodiments of the present invention
Figure 839961DEST_PATH_IMAGE076
The relationship diagram between the amount of data and the number of convergence times in the case of ;

图10（a）为本发明一个或多个实施例中分别使用A2CS加速算法，ADS算法和DPDS算法显示了总效用的关系图以及不同时间范围内A2CS加速算法相对于ADS算法和DPDS算法的优势百分比图；Figure 10(a) shows the A2CS acceleration algorithm used in one or more embodiments of the present invention. The ADS algorithm and the DPDS algorithm show the relationship diagram of the total utility and the advantages of the A2CS acceleration algorithm over the ADS algorithm and the DPDS algorithm in different time ranges. percentage chart;

图10（b）为本发明一个或多个实施例中分别使用A2CS加速算法，ADS算法和DPDS算法显示了能耗的关系图以及不同时间范围内A2CS加速算法相对于ADS算法和DPDS算法的优势百分比图；Figure 10(b) shows the A2CS acceleration algorithm used in one or more embodiments of the present invention. The ADS algorithm and the DPDS algorithm show the relationship between energy consumption and the advantages of the A2CS acceleration algorithm relative to the ADS algorithm and the DPDS algorithm in different time ranges. percentage chart;

图11（a）为本发明一个或多个实施例中使用A2CS加速算法的总效用的关系图以及不同时间范围数据量大小图；FIG. 11( a ) is a relationship diagram of the total utility of using the A2CS acceleration algorithm in one or more embodiments of the present invention and a diagram of the size of data in different time ranges;

图11（b）为本发明一个或多个实施例中使用A2CS加速算法的能耗的关系图以及不同时间范围数据量大小图。FIG. 11( b ) is a relationship diagram of energy consumption using the A2CS acceleration algorithm in one or more embodiments of the present invention and a diagram of the size of data in different time ranges.

具体实施方式Detailed ways

为使本公开的目的、技术方案和优点更加清楚明白，以下结合具体实施例，并参照附图，对本公开进一步详细说明。In order to make the objectives, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below with reference to the specific embodiments and the accompanying drawings.

需要说明的是，除非另外定义，本发明一个或多个实施例使用的技术术语或者科学术语应当为本公开所属领域内具有一般技能的人士所理解的通常意义。本发明一个或多个实施例中使用的“第一”、“第二”以及类似的词语并不表示任何顺序、数量或者重要性，而只是用来区分不同的组成部分。“包括”或者“包含”等类似的词语意指出现该词前面的元件或者物件涵盖出现在该词后面列举的元件或者物件及其等同，而不排除其他元件或者物件。“连接”或者“相连”等类似的词语并非限定于物理的或者机械的连接，而是可以包括电性的连接，不管是直接的还是间接的。“上”、“下”、“左”、“右”等仅用于表示相对位置关系，当被描述对象的绝对位置改变后，则该相对位置关系也可能相应地改变。It should be noted that, unless otherwise defined, technical terms or scientific terms used in one or more embodiments of the present invention shall have common meanings understood by those with ordinary skill in the art to which this disclosure belongs. The terms "first," "second," and similar terms used in one or more embodiments of the present invention do not denote any order, quantity, or importance, but are merely used to distinguish the various components. "Comprises" or "comprising" and similar words mean that the elements or things appearing before the word encompass the elements or things recited after the word and their equivalents, but do not exclude other elements or things. Words like "connected" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "Down", "Left", "Right", etc. are only used to represent the relative positional relationship, and when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

本发明一个或多个实施例提供了一种协同移动设备的边缘存储加速方法、装置及设备。One or more embodiments of the present invention provide an edge storage acceleration method, apparatus, and device for cooperating with mobile devices.

参考图1，本发明一个或多个实施例提供的方法，包括以下步骤：1, the method provided by one or more embodiments of the present invention includes the following steps:

S101建立移动设备间传输数据的边缘协同存储任务。S101 establishes an edge cooperative storage task for data transmission between mobile devices.

本实施例中，边缘协同存储任务建立再边缘协同存储框架的基础上，边缘存储框架中包括多个移动设备，每个移动设备包括：存储单元、数据处理器、调度器和数据接收器/发送器，不同移动设备的当前存储容量是不同的，边缘协同存储任务包括以下步骤：In this embodiment, the edge collaborative storage task is established on the basis of the edge collaborative storage framework. The edge storage framework includes multiple mobile devices, and each mobile device includes: a storage unit, a data processor, a scheduler, and a data receiver/transmitter The current storage capacity of different mobile devices is different. The edge collaborative storage task includes the following steps:

移动设备收集数据；Mobile devices collect data;

所述移动设备基于数据丢失概率

Figure DEST_PATH_IMAGE078
和能耗
Figure DEST_PATH_IMAGE079
将所述数据的副本发送至与所述移动设备相连的相邻移动设备，所述相邻移动设备至少有一个；The mobile device is based on data loss probability
Figure DEST_PATH_IMAGE078
and energy consumption
Figure DEST_PATH_IMAGE079
sending a copy of the data to adjacent mobile devices connected to the mobile device, at least one of the adjacent mobile devices;

所述移动设备集合

Figure 795147DEST_PATH_IMAGE001
基于所述相邻移动设备的存储容量和电池电量，确定所述副本的数量和
Figure DEST_PATH_IMAGE080
接收所述副本的所述相邻移动设备。the set of mobile devices
Figure 795147DEST_PATH_IMAGE001
Based on the storage capacity and battery level of the neighboring mobile device, the number of copies and
Figure DEST_PATH_IMAGE080
the neighboring mobile device that receives the copy.

为了降低数据丢失的概率

Figure DEST_PATH_IMAGE081
，移动设备在考虑能耗的同时将数据的副本发送至相连的移动设备，考虑到存储容量和电池电量，副本的数量
Figure 896964DEST_PATH_IMAGE080
和接收数据的移动设备的选择都由边缘中的多个移动设备共同确定，不同移动设备的电池电量不同，如果电池电量低，则发送数据的移动设备不会将副本发送至该电量低的移动设备，而是选择将数据的副本发送至其他与发送数据的移动设备相连的电量充足的移动设备中。To reduce the probability of data loss
Figure DEST_PATH_IMAGE081
, the mobile device sends a copy of the data to the connected mobile device taking into account energy consumption, the number of copies taking into account storage capacity and battery power
Figure 896964DEST_PATH_IMAGE080
And the selection of the mobile device to receive the data is determined jointly by multiple mobile devices in the edge, different mobile devices have different battery levels, if the battery is low, the mobile device sending the data will not send a copy to that low battery mobile device device, instead chooses to send a copy of the data to other mobile devices with sufficient power connected to the mobile device sending the data.

S102基于所述边缘协同存储任务建立边缘协同存储模型，所述边缘协同存储模型包括：移动设备集合

Figure 143576DEST_PATH_IMAGE001
、发送移动设备
Figure 813592DEST_PATH_IMAGE002
、接收移动设备
Figure 600282DEST_PATH_IMAGE003
和网络拓扑
Figure DEST_PATH_IMAGE082
，所述移动设备集合
Figure 771369DEST_PATH_IMAGE001
包括至少两个移动设备。S102 establishes an edge collaborative storage model based on the edge collaborative storage task, where the edge collaborative storage model includes: a set of mobile devices
Figure 143576DEST_PATH_IMAGE001
, send mobile device
Figure 813592DEST_PATH_IMAGE002
, receiving mobile device
Figure 600282DEST_PATH_IMAGE003
and network topology
Figure DEST_PATH_IMAGE082
, the mobile device collection
Figure 771369DEST_PATH_IMAGE001
Include at least two mobile devices.

本实施例中，首先将移动设备集合

Figure 959905DEST_PATH_IMAGE001
建模为
Figure DEST_PATH_IMAGE083
，其中
Figure DEST_PATH_IMAGE084
是第
Figure 394298DEST_PATH_IMAGE085
个所述移动设备，
Figure DEST_PATH_IMAGE086
是边缘中的所述移动设备的总数。对于任意一个边缘的移动设备
Figure DEST_PATH_IMAGE087
，所述第
Figure 792918DEST_PATH_IMAGE085
个所述移动设备
Figure DEST_PATH_IMAGE088
被建模为
Figure DEST_PATH_IMAGE089
，其中
Figure DEST_PATH_IMAGE090
表示
Figure 505047DEST_PATH_IMAGE087
的存储容量，
Figure DEST_PATH_IMAGE091
表示
Figure 735040DEST_PATH_IMAGE088
的电池电量，
Figure DEST_PATH_IMAGE092
表示
Figure 137071DEST_PATH_IMAGE088
收集的数据量大小，
Figure 632774DEST_PATH_IMAGE017
表示
Figure 880085DEST_PATH_IMAGE084
收集的数据的数据副本数量，
Figure DEST_PATH_IMAGE093
表示
Figure 308792DEST_PATH_IMAGE088
的数据传输速率，
Figure DEST_PATH_IMAGE094
表示
Figure 556759DEST_PATH_IMAGE088
的数据接收速率。In this embodiment, the mobile devices are first assembled
Figure 959905DEST_PATH_IMAGE001
modeled as
Figure DEST_PATH_IMAGE083
,in
Figure DEST_PATH_IMAGE084
is the first
Figure 394298DEST_PATH_IMAGE085
said mobile device,
Figure DEST_PATH_IMAGE086
is the total number of said mobile devices in the edge. For mobile devices on either edge
Figure DEST_PATH_IMAGE087
, the first
Figure 792918DEST_PATH_IMAGE085
said mobile devices
Figure DEST_PATH_IMAGE088
is modeled as
Figure DEST_PATH_IMAGE089
,in
Figure DEST_PATH_IMAGE090
express
Figure 505047DEST_PATH_IMAGE087
storage capacity,
Figure DEST_PATH_IMAGE091
express
Figure 735040DEST_PATH_IMAGE088
battery power,
Figure DEST_PATH_IMAGE092
express
Figure 137071DEST_PATH_IMAGE088
The amount of data collected,
Figure 632774DEST_PATH_IMAGE017
express
Figure 880085DEST_PATH_IMAGE084
the number of data copies of the collected data,
Figure DEST_PATH_IMAGE093
express
Figure 308792DEST_PATH_IMAGE088
the data transfer rate,
Figure DEST_PATH_IMAGE094
express
Figure 556759DEST_PATH_IMAGE088
data reception rate.

表1 符号描述Table 1 Symbol description

Figure DEST_PATH_IMAGE095
Figure DEST_PATH_IMAGE095

参考表1，边缘中的动态网络拓扑仍然是协同存储的巨大挑战，为了对网络拓扑进行建模，考虑了移动设备及其之间的关系，包括连接性和距离。因此，边缘中的动态网络拓扑

Figure DEST_PATH_IMAGE096
被建模为
Figure DEST_PATH_IMAGE097
，
Figure 992288DEST_PATH_IMAGE001
表示移动设备集合，
Figure DEST_PATH_IMAGE098
表示邻接矩阵，
Figure DEST_PATH_IMAGE099
表示距离矩阵，所述邻接矩阵
Figure 433502DEST_PATH_IMAGE098
包括：Referring to Table 1, the dynamic network topology in the edge remains a great challenge for collaborative storage. To model the network topology, mobile devices and their relationships, including connectivity and distance, are considered. Therefore, dynamic network topology in the edge
Figure DEST_PATH_IMAGE096
is modeled as
Figure DEST_PATH_IMAGE097
,
Figure 992288DEST_PATH_IMAGE001
represents a collection of mobile devices,
Figure DEST_PATH_IMAGE098
represents the adjacency matrix,
Figure DEST_PATH_IMAGE099
represents the distance matrix, the adjacency matrix
Figure 433502DEST_PATH_IMAGE098
include:

对于任意所述移动设备

Figure DEST_PATH_IMAGE100
，与其他所述移动设备
Figure 654399DEST_PATH_IMAGE101
的连通性由邻接矩阵中的元素表示，
Figure DEST_PATH_IMAGE102
表示所述邻接矩阵
Figure 729059DEST_PATH_IMAGE098
的第
Figure 402617DEST_PATH_IMAGE103
行、第
Figure DEST_PATH_IMAGE104
列中的元素，它由以下表达式确定：for any of the mobile devices
Figure DEST_PATH_IMAGE100
, with other described mobile devices
Figure 654399DEST_PATH_IMAGE101
The connectivity of is represented by the elements in the adjacency matrix,
Figure DEST_PATH_IMAGE102
represents the adjacency matrix
Figure 729059DEST_PATH_IMAGE098
First
Figure 402617DEST_PATH_IMAGE103
row,
Figure DEST_PATH_IMAGE104
The element in the column, which is determined by the following expression:

Figure 319626DEST_PATH_IMAGE105
Figure 319626DEST_PATH_IMAGE105

上面定义的邻接矩阵

Figure 129451DEST_PATH_IMAGE098
表示理想状态下移动设备之间的连接，这意味着连接足够鲁棒。但是，移动设备之间的通信中断和移动设备的退出可能导致连接丢失。对于每个移动设备，与另一个移动设备的连接丢失是随机的。在本实施例中中，它近似服从0-1分布，可以表示为：The adjacency matrix defined above
Figure 129451DEST_PATH_IMAGE098
Represents an ideal connection between mobile devices, which means the connection is robust enough. However, the interruption of communication between mobile devices and the withdrawal of mobile devices may result in loss of connectivity. For each mobile device, the loss of connection to another mobile device is random. In this embodiment, it approximately obeys the 0-1 distribution and can be expressed as:

Figure DEST_PATH_IMAGE106
Figure DEST_PATH_IMAGE106

其中

Figure 106503DEST_PATH_IMAGE103
是连接丢失的概率，k表示次序，
Figure 267357DEST_PATH_IMAGE107
时表示连接丢失。所述距离矩阵
Figure 269948DEST_PATH_IMAGE099
包括：in
Figure 106503DEST_PATH_IMAGE103
is the probability of connection loss, k represents the order,
Figure 267357DEST_PATH_IMAGE107
indicates that the connection is lost. the distance matrix
Figure 269948DEST_PATH_IMAGE099
include:

对于任意所述移动设备

Figure 245863DEST_PATH_IMAGE100
，到其他所述移动设备
Figure 816653DEST_PATH_IMAGE101
的距离是所述距离矩阵
Figure 259877DEST_PATH_IMAGE099
中元素的值，
Figure DEST_PATH_IMAGE108
代表所述距离矩阵
Figure 472684DEST_PATH_IMAGE099
的第
Figure 568685DEST_PATH_IMAGE103
行、第
Figure 435010DEST_PATH_IMAGE104
列中的元素，它由以下表达式确定：for any of the mobile devices
Figure 245863DEST_PATH_IMAGE100
, to the other said mobile device
Figure 816653DEST_PATH_IMAGE101
The distance is the distance matrix
Figure 259877DEST_PATH_IMAGE099
the value of the element in ,
Figure DEST_PATH_IMAGE108
represents the distance matrix
Figure 472684DEST_PATH_IMAGE099
First
Figure 568685DEST_PATH_IMAGE103
row,
Figure 435010DEST_PATH_IMAGE104
The element in the column, which is determined by the following expression:

Figure DEST_PATH_IMAGE109
Figure DEST_PATH_IMAGE109

其中

Figure DEST_PATH_IMAGE110
表示
Figure DEST_PATH_IMAGE111
和
Figure DEST_PATH_IMAGE112
之间的距离。根据上面的定义，邻接矩阵
Figure 882040DEST_PATH_IMAGE098
和距离矩阵
Figure 226434DEST_PATH_IMAGE099
都是对称矩阵。此外，
Figure 130936DEST_PATH_IMAGE098
和
Figure 92463DEST_PATH_IMAGE099
的维数表示边缘移动设备的数量。随着移动设备集合
Figure DEST_PATH_IMAGE113
，邻接矩阵
Figure 777523DEST_PATH_IMAGE098
和距离矩阵
Figure 315820DEST_PATH_IMAGE099
的变化，网络拓扑也
Figure DEST_PATH_IMAGE114
发生变化，从而可以表示边缘中网络拓扑的动态变化。由于完整而正确的数据在协同存储领域中很重要，因此本实施例专注于边缘协同存储的可靠性。此外，协同存储的可靠性与冗余机制，副本丢失的可能性以及数据对象的故障率密切相关，因此，为了提高存储可靠性，本实施例考虑了数据备份。将
Figure DEST_PATH_IMAGE115
定义为数据存储的失败率，
Figure DEST_PATH_IMAGE116
表示数据存储失败后的恢复概率。协同存储中的存储可靠性模型类似于马尔科夫过程，因此以任意一个移动设备
Figure DEST_PATH_IMAGE117
为例，移动设备
Figure 917572DEST_PATH_IMAGE117
数据丢失的概率可以表示为：in
Figure DEST_PATH_IMAGE110
express
Figure DEST_PATH_IMAGE111
and
Figure DEST_PATH_IMAGE112
the distance between. According to the above definition, the adjacency matrix
Figure 882040DEST_PATH_IMAGE098
and the distance matrix
Figure 226434DEST_PATH_IMAGE099
are all symmetric matrices. also,
Figure 130936DEST_PATH_IMAGE098
and
Figure 92463DEST_PATH_IMAGE099
The dimension of represents the number of edge mobile devices. With mobile device collection
Figure DEST_PATH_IMAGE113
, the adjacency matrix
Figure 777523DEST_PATH_IMAGE098
and the distance matrix
Figure 315820DEST_PATH_IMAGE099
changes, the network topology also
Figure DEST_PATH_IMAGE114
changes so that dynamic changes in the network topology in the edge can be represented. Since complete and correct data is important in the field of collaborative storage, this embodiment focuses on the reliability of collaborative storage at the edge. In addition, the reliability of cooperative storage is closely related to the redundancy mechanism, the possibility of copy loss, and the failure rate of data objects. Therefore, in order to improve storage reliability, this embodiment considers data backup. Will
Figure DEST_PATH_IMAGE115
Defined as the failure rate of the data store,
Figure DEST_PATH_IMAGE116
Represents the probability of recovery after data storage failure. The storage reliability model in cooperative storage is similar to the Markov process, so with any mobile device
Figure DEST_PATH_IMAGE117
For example, mobile devices
Figure 917572DEST_PATH_IMAGE117
The probability of data loss can be expressed as:

Figure DEST_PATH_IMAGE118
Figure DEST_PATH_IMAGE118

其中

Figure DEST_PATH_IMAGE119
是副本数量，
Figure DEST_PATH_IMAGE120
表示次序。假设在不同移动设备之间传输和存储的数据是独立的，而且不同移动设备中不同数据的丢失概率相同，使用数据丢失量来描述存储可靠性。显然，数据丢失越多，存储可靠性就越低。该公式可描述为：in
Figure DEST_PATH_IMAGE119
is the number of copies,
Figure DEST_PATH_IMAGE120
Indicates the order. Assuming that the data transmitted and stored between different mobile devices are independent, and the loss probability of different data in different mobile devices is the same, use the data loss amount to describe storage reliability. Obviously, the more data is lost, the lower the storage reliability. The formula can be described as:

Figure 925367DEST_PATH_IMAGE122
Figure 925367DEST_PATH_IMAGE122

其中

Figure DEST_PATH_IMAGE123
是移动设备
Figure DEST_PATH_IMAGE124
上的数据量大小。当副本数约为5时，可以满足较高的可靠性要求。当副本数大于5时，提高可靠性毫无意义，而且会增加数据维护成本。但是，固定的副本数可能过多而导致多余的能源成本，或者过少而导致可靠性降低。此外，当以分布式方式存储时，将数据传输到不同移动设备的能量消耗是动态变化的。为了平衡存储可靠性和能耗之间的关系，本实施例考虑了一种灵活的数据备份策略，该策略由副本数选择和数据副本的分配策略组成，本实施例专注于以尽可能低的能耗可靠地存储数据。in
Figure DEST_PATH_IMAGE123
is a mobile device
Figure DEST_PATH_IMAGE124
The amount of data on the . When the number of replicas is about 5, higher reliability requirements can be met. When the number of replicas is greater than 5, it is meaningless to improve reliability, and it will increase the cost of data maintenance. However, a fixed number of replicas can be too large and cause excess energy costs, or too few and cause reduced reliability. Furthermore, when stored in a distributed fashion, the energy consumption of transferring data to different mobile devices is dynamically changing. In order to balance the relationship between storage reliability and energy consumption, this embodiment considers a flexible data backup strategy, which consists of copy number selection and data copy allocation strategy. This embodiment focuses on using the lowest possible Power consumption to store data reliably.

对于协同存储，移动设备的续航时间是一种至关重要的因素。更长的续航时间意味着可以收集，传输和存储更多数据。此外，续航时间可以用能耗来描述，当能量消耗减少时，续航时间增加。边缘协同存储的能耗主要由两部分组成：数据存储的能耗和数据传输的能耗。本实施例中，假设数据发送和接收不会相互影响。另外，将所有移动设备分为发送设备

Figure DEST_PATH_IMAGE125
和接收设备
Figure DEST_PATH_IMAGE126
组成的小组，所述发送移动设备
Figure 409306DEST_PATH_IMAGE125
和接收移动设备
Figure 361082DEST_PATH_IMAGE127
组成收发移动设备组
Figure 36914DEST_PATH_IMAGE128
，所述发送移动设备
Figure 274997DEST_PATH_IMAGE125
和接收移动设备
Figure 403490DEST_PATH_IMAGE127
之间进行数据存储和数据传输，这些收发移动设备组可以公式为
Figure DEST_PATH_IMAGE129
。每个移动设备可以同时分为不同的组。所述数据存储产生数据存储能耗
Figure 348837DEST_PATH_IMAGE130
，所述
Figure 82438DEST_PATH_IMAGE130
表述为For collaborative storage, the battery life of the mobile device is a critical factor. Longer battery life means more data can be collected, transmitted and stored. Furthermore, battery life can be described in terms of energy consumption, and when energy consumption decreases, battery life increases. The energy consumption of edge collaborative storage is mainly composed of two parts: the energy consumption of data storage and the energy consumption of data transmission. In this embodiment, it is assumed that data transmission and reception do not affect each other. Also, divide all mobile devices into sending devices
Figure DEST_PATH_IMAGE125
and receiving equipment
Figure DEST_PATH_IMAGE126
composed of groups that send mobile devices
Figure 409306DEST_PATH_IMAGE125
and receiving mobile devices
Figure 361082DEST_PATH_IMAGE127
Form sending and receiving mobile device groups
Figure 36914DEST_PATH_IMAGE128
, the sending mobile device
Figure 274997DEST_PATH_IMAGE125
and receiving mobile devices
Figure 403490DEST_PATH_IMAGE127
For data storage and data transmission between the two, these sending and receiving mobile device groups can be formulated as
Figure DEST_PATH_IMAGE129
. Each mobile device can be divided into different groups at the same time. The data storage generates data storage energy consumption
Figure 348837DEST_PATH_IMAGE130
, the
Figure 82438DEST_PATH_IMAGE130
expressed as

Figure DEST_PATH_IMAGE131
Figure DEST_PATH_IMAGE131

其中，

Figure 84898DEST_PATH_IMAGE132
表示当
Figure DEST_PATH_IMAGE133
时从所述发送移动设备
Figure 90900DEST_PATH_IMAGE125
传输到接收移动设备
Figure 791003DEST_PATH_IMAGE126
的数据量大小，以及当
Figure 238164DEST_PATH_IMAGE134
时所述发送移动设备
Figure 145946DEST_PATH_IMAGE125
存储的数据量大小，
Figure DEST_PATH_IMAGE135
表示上述组
Figure 717873DEST_PATH_IMAGE136
中数据存储的能耗。对于所述数据传输产生数据传输能耗
Figure DEST_PATH_IMAGE137
，本实施例使用自由空间传播模型来描述多个移动设备中的数据传输。为了便于分析，假定
Figure 868670DEST_PATH_IMAGE125
将数据传输到
Figure 435918DEST_PATH_IMAGE126
。
Figure DEST_PATH_IMAGE138
表示所述发送移动设备
Figure 452284DEST_PATH_IMAGE125
的发射功率，
Figure DEST_PATH_IMAGE139
表示接收移动设备
Figure 760774DEST_PATH_IMAGE126
的接收功率。基于Friis转移公式，将
Figure 68259DEST_PATH_IMAGE138
与
Figure 880226DEST_PATH_IMAGE139
之间的关系建模为：in,
Figure 84898DEST_PATH_IMAGE132
means when
Figure DEST_PATH_IMAGE133
when sending from the mobile device
Figure 90900DEST_PATH_IMAGE125
Transmission to the receiving mobile device
Figure 791003DEST_PATH_IMAGE126
size of data, and when
Figure 238164DEST_PATH_IMAGE134
when the sending mobile device
Figure 145946DEST_PATH_IMAGE125
The amount of data stored,
Figure DEST_PATH_IMAGE135
represents the above group
Figure 717873DEST_PATH_IMAGE136
energy consumption for data storage. Data transfer energy consumption is generated for the data transfer
Figure DEST_PATH_IMAGE137
, this embodiment uses the free-space propagation model to describe data transmission among multiple mobile devices. For ease of analysis, it is assumed that
Figure 868670DEST_PATH_IMAGE125
transfer data to
Figure 435918DEST_PATH_IMAGE126
.
Figure DEST_PATH_IMAGE138
represents the sending mobile device
Figure 452284DEST_PATH_IMAGE125
the transmit power,
Figure DEST_PATH_IMAGE139
Indicates the receiving mobile device
Figure 760774DEST_PATH_IMAGE126
received power. Based on the Friis transfer formula, the
Figure 68259DEST_PATH_IMAGE138
and
Figure 880226DEST_PATH_IMAGE139
The relationship between is modeled as:

Figure DEST_PATH_IMAGE140
Figure DEST_PATH_IMAGE140

其中

Figure DEST_PATH_IMAGE141
表示发射天线增益，
Figure DEST_PATH_IMAGE142
表示接收天线增益，
Figure DEST_PATH_IMAGE143
表示波长，
Figure DEST_PATH_IMAGE144
表示所述发送移动设备
Figure 929478DEST_PATH_IMAGE125
和所述接收移动设备
Figure 803893DEST_PATH_IMAGE126
之间的距离，
Figure DEST_PATH_IMAGE145
表示与传播无关的系统损耗因子。在协同存储框架中，每个移动设备的发射功率、波长和系统损耗因子均可以视为常数。此外，数据从所述发送移动设备
Figure 836440DEST_PATH_IMAGE125
传输至所述接收移动设备
Figure 112701DEST_PATH_IMAGE126
所花费的时间和接收移动设备
Figure 283919DEST_PATH_IMAGE127
接收所述发送移动设备
Figure 35843DEST_PATH_IMAGE125
发送的数据所花费的时间可以表示为：in
Figure DEST_PATH_IMAGE141
represents the transmit antenna gain,
Figure DEST_PATH_IMAGE142
represents the receiving antenna gain,
Figure DEST_PATH_IMAGE143
represents the wavelength,
Figure DEST_PATH_IMAGE144
represents the sending mobile device
Figure 929478DEST_PATH_IMAGE125
and the receiving mobile device
Figure 803893DEST_PATH_IMAGE126
the distance between,
Figure DEST_PATH_IMAGE145
Represents the propagation-independent system loss factor. In the cooperative storage framework, the transmit power, wavelength and system loss factor of each mobile device can be regarded as constants. Additionally, data is sent from the mobile device
Figure 836440DEST_PATH_IMAGE125
transmitted to the receiving mobile device
Figure 112701DEST_PATH_IMAGE126
Time Spent and Receiving Mobile Devices
Figure 283919DEST_PATH_IMAGE127
receiving the sending mobile device
Figure 35843DEST_PATH_IMAGE125
The time it takes to send data can be expressed as:

Figure DEST_PATH_IMAGE146
Figure DEST_PATH_IMAGE146

其中

Figure DEST_PATH_IMAGE147
表示当
Figure DEST_PATH_IMAGE148
时从所述发送移动设备
Figure 875011DEST_PATH_IMAGE149
传输到接收移动设备
Figure DEST_PATH_IMAGE150
的数据量大小，另外，
Figure DEST_PATH_IMAGE151
表示所述发送移动设备
Figure 395991DEST_PATH_IMAGE125
的数据传输速率，
Figure DEST_PATH_IMAGE152
表示所述接收移动设备
Figure 206952DEST_PATH_IMAGE126
的数据接收速率。数据传输速率可以设置为常数，因为不存在由于传播引起的信号衰减，而数据接收速率与接收信号强度指示符（RSSI）有关，可以将其描述为：in
Figure DEST_PATH_IMAGE147
means when
Figure DEST_PATH_IMAGE148
when sending from the mobile device
Figure 875011DEST_PATH_IMAGE149
Transmission to the receiving mobile device
Figure DEST_PATH_IMAGE150
The size of the data volume, in addition,
Figure DEST_PATH_IMAGE151
represents the sending mobile device
Figure 395991DEST_PATH_IMAGE125
the data transfer rate,
Figure DEST_PATH_IMAGE152
represents the receiving mobile device
Figure 206952DEST_PATH_IMAGE126
data reception rate. The data transmission rate can be set to be constant because there is no signal attenuation due to propagation, while the data reception rate is related to the Received Signal Strength Indicator (RSSI), which can be described as:

Figure DEST_PATH_IMAGE153
Figure DEST_PATH_IMAGE153

然而，不能简单地通过线性模型来描述数据接收速率和RSSI之间的关系。参考表2，可以获得RSSI与数据传输速率之间的对应关系，However, the relationship between the data reception rate and RSSI cannot be described simply by a linear model. Referring to Table 2, the correspondence between RSSI and data transfer rate can be obtained,

表2 RSSI与数据传输速率之间的对应关系Table 2 Correspondence between RSSI and data transmission rate

Figure DEST_PATH_IMAGE154
Figure DEST_PATH_IMAGE154

根据（7），（8）和（9），数据传输的能耗

Figure DEST_PATH_IMAGE155
可以表示为：According to (7), (8) and (9), the energy consumption of data transmission
Figure DEST_PATH_IMAGE155
It can be expressed as:

Figure DEST_PATH_IMAGE156
Figure DEST_PATH_IMAGE156

其中

Figure DEST_PATH_IMAGE157
表示上述收发移动设备组
Figure DEST_PATH_IMAGE158
中数据传输的能耗。基于（6）和（11），边缘协同存储的总能耗可以表示为：in
Figure DEST_PATH_IMAGE157
Represents the above-mentioned sending and receiving mobile device group
Figure DEST_PATH_IMAGE158
energy consumption for data transmission. Based on (6) and (11), the total energy consumption of edge cooperative storage can be expressed as:

Figure DEST_PATH_IMAGE159
Figure DEST_PATH_IMAGE159

S103基于所述边缘协同存储模型计算得到A2CS加速算法。S103 calculates and obtains an A2CS acceleration algorithm based on the edge collaborative storage model.

本实施例中，A2CS加速算法选用的优化函数为优化函数F，优化函数

Figure DEST_PATH_IMAGE160
描述了上述步骤中的协同存储的总效用，包括存储的可靠性和续航时间。优化目标是最大程度地减少协同存储中的数据丢失和能耗。为了满足协同存储的高存储可靠性和长续航时间的要求，在上述存储可靠性和续航时间模型的基础上，将协同存储系统的优化功能定义为：In this embodiment, the optimization function selected by the A2CS acceleration algorithm is the optimization function F, and the optimization function
Figure DEST_PATH_IMAGE160
The overall utility of co-storage in the above steps is described, including storage reliability and battery life. The optimization goal is to minimize data loss and energy consumption in co-storage. In order to meet the requirements of high storage reliability and long battery life of collaborative storage, the optimization function of collaborative storage system is defined as:

Figure 432790DEST_PATH_IMAGE161
Figure 432790DEST_PATH_IMAGE161

其中

Figure DEST_PATH_IMAGE162
和
Figure DEST_PATH_IMAGE163
是权重系数，
Figure 807140DEST_PATH_IMAGE164
表示由发送移动设备
Figure DEST_PATH_IMAGE165
收集的数据量的大小，
Figure 713785DEST_PATH_IMAGE164
和
Figure 226806DEST_PATH_IMAGE166
之间的关系可以描述为
Figure DEST_PATH_IMAGE167
。in
Figure DEST_PATH_IMAGE162
and
Figure DEST_PATH_IMAGE163
is the weight coefficient,
Figure 807140DEST_PATH_IMAGE164
Indicates that the mobile device is sent by
Figure DEST_PATH_IMAGE165
the size of the amount of data collected,
Figure 713785DEST_PATH_IMAGE164
and
Figure 226806DEST_PATH_IMAGE166
The relationship between can be described as
Figure DEST_PATH_IMAGE167
.

协同存储问题已转化为优化问题，该问题与ADMM的应用领域非常接近。此外，优化函数由两个独立的函数组成，适合ADMM的可分解性。但是，ADMM也存在一些不足，比如现实中的收敛速度很慢，协同存储问题迫切需要快速的收敛速度，因此较慢的收敛速度这是不可接受的，但是现有技术表明，当前大多数研究都不适用于协同存储问题，因此，应考虑并修改加速策略，发明人为了使算法与优化问题更加兼容，需要进行一些调整，提出了对优化函数进行标准化和分解。对于边缘中的每个移动设备，数据存储过程始终相同，因此可以以分布式方式部署A2CS加速算法。为了使优化功能清晰可见，以满足A2CS的基本形式，以一个移动设备

Figure 891005DEST_PATH_IMAGE168
为例，收集的数据量大小为
Figure DEST_PATH_IMAGE169
，副本数为
Figure DEST_PATH_IMAGE170
。令The cooperative memory problem has been transformed into an optimization problem, which is very close to the application field of ADMM. Furthermore, the optimization function consists of two independent functions, suitable for the decomposability of ADMM. However, ADMM also has some shortcomings. For example, the convergence speed in reality is very slow, and the cooperative storage problem urgently needs a fast convergence speed, so the slow convergence speed is unacceptable, but the existing technology shows that most of the current research It is not suitable for the cooperative storage problem. Therefore, the acceleration strategy should be considered and modified. In order to make the algorithm more compatible with the optimization problem, the inventor needs to make some adjustments, and proposes to standardize and decompose the optimization function. The data storage process is always the same for each mobile device in the edge, so the A2CS acceleration algorithm can be deployed in a distributed fashion. In order to make the optimization function clearly visible to meet the basic form of A2CS to a mobile device
Figure 891005DEST_PATH_IMAGE168
For example, the size of the collected data is
Figure DEST_PATH_IMAGE169
, the number of copies is
Figure DEST_PATH_IMAGE170
. make

Figure DEST_PATH_IMAGE171
Figure DEST_PATH_IMAGE171

其中

Figure 614853DEST_PATH_IMAGE065
表示与
Figure 110425DEST_PATH_IMAGE172
连接的移动设备的数量，
Figure DEST_PATH_IMAGE173
。此外，
Figure DEST_PATH_IMAGE174
的分量表示在每个与
Figure 715719DEST_PATH_IMAGE172
连接的移动设备中传输的数据量，
Figure DEST_PATH_IMAGE175
的分量表示在每个与
Figure 477001DEST_PATH_IMAGE172
连接的移动设备中存储的数据量。对应于（13）中的
Figure DEST_PATH_IMAGE176
和
Figure DEST_PATH_IMAGE177
，本实施例中分别有
Figure 193153DEST_PATH_IMAGE178
和
Figure DEST_PATH_IMAGE179
用于移动设备
Figure 483845DEST_PATH_IMAGE172
。特别地，
Figure 587936DEST_PATH_IMAGE178
是表示由移动设备
Figure 898832DEST_PATH_IMAGE172
收集的数据量，而
Figure 497303DEST_PATH_IMAGE180
是一个向量，表示从移动设备
Figure 233047DEST_PATH_IMAGE172
发送到其他移动设备的数据。
Figure 462034DEST_PATH_IMAGE178
，
Figure DEST_PATH_IMAGE181
，
Figure 447177DEST_PATH_IMAGE182
和
Figure DEST_PATH_IMAGE183
之间的关系可以表示为：in
Figure 614853DEST_PATH_IMAGE065
means with
Figure 110425DEST_PATH_IMAGE172
the number of connected mobile devices,
Figure DEST_PATH_IMAGE173
. also,
Figure DEST_PATH_IMAGE174
The components are expressed in each with
Figure 715719DEST_PATH_IMAGE172
the amount of data transferred in the connected mobile device,
Figure DEST_PATH_IMAGE175
The components are expressed in each with
Figure 477001DEST_PATH_IMAGE172
The amount of data stored in the connected mobile device. corresponds to (13) in
Figure DEST_PATH_IMAGE176
and
Figure DEST_PATH_IMAGE177
, in this example, there are
Figure 193153DEST_PATH_IMAGE178
and
Figure DEST_PATH_IMAGE179
for mobile devices
Figure 483845DEST_PATH_IMAGE172
. Particularly,
Figure 587936DEST_PATH_IMAGE178
is indicated by a mobile device
Figure 898832DEST_PATH_IMAGE172
the amount of data collected, while
Figure 497303DEST_PATH_IMAGE180
is a vector representing the
Figure 233047DEST_PATH_IMAGE172
Data sent to other mobile devices.
Figure 462034DEST_PATH_IMAGE178
,
Figure DEST_PATH_IMAGE181
,
Figure 447177DEST_PATH_IMAGE182
and
Figure DEST_PATH_IMAGE183
The relationship between can be expressed as:

Figure DEST_PATH_IMAGE184
Figure DEST_PATH_IMAGE184

原始残差可以描述为

Figure DEST_PATH_IMAGE185
，可以将
Figure 914586DEST_PATH_IMAGE172
的优化函数标准化为：The original residual can be described as
Figure DEST_PATH_IMAGE185
,can
Figure 914586DEST_PATH_IMAGE172
The optimization function normalizes to:

Figure 35994DEST_PATH_IMAGE186
Figure 35994DEST_PATH_IMAGE186

其中

Figure DEST_PATH_IMAGE187
是与
Figure DEST_PATH_IMAGE188
相关的列向量，
Figure DEST_PATH_IMAGE189
与
Figure 357254DEST_PATH_IMAGE190
有关，而
Figure 111584DEST_PATH_IMAGE191
，
Figure 566705DEST_PATH_IMAGE192
，所有移动设备的总优化函数可以描述为
Figure 496614DEST_PATH_IMAGE193
。标准化之后，可以将
Figure 192038DEST_PATH_IMAGE194
分解为两个子函数
Figure DEST_PATH_IMAGE195
和
Figure 30068DEST_PATH_IMAGE196
，如下所示：in
Figure DEST_PATH_IMAGE187
With
Figure DEST_PATH_IMAGE188
the associated column vector,
Figure DEST_PATH_IMAGE189
and
Figure 357254DEST_PATH_IMAGE190
related, while
Figure 111584DEST_PATH_IMAGE191
,
Figure 566705DEST_PATH_IMAGE192
, the total optimization function for all mobile devices can be described as
Figure 496614DEST_PATH_IMAGE193
. After standardization, the
Figure 192038DEST_PATH_IMAGE194
Decompose into two sub-functions
Figure DEST_PATH_IMAGE195
and
Figure 30068DEST_PATH_IMAGE196
,As follows:

Figure 101930DEST_PATH_IMAGE198
Figure 101930DEST_PATH_IMAGE198

初始值可设置为：The initial value can be set to:

Figure DEST_PATH_IMAGE200
Figure DEST_PATH_IMAGE200

其中

Figure DEST_PATH_IMAGE201
是与
Figure DEST_PATH_IMAGE202
连接的移动设备的数量，下标表示移动设备
Figure 994668DEST_PATH_IMAGE202
的第0次迭代。
Figure DEST_PATH_IMAGE203
和
Figure DEST_PATH_IMAGE204
的分量设置为零，这意味着一开始没有存储任何数据。in
Figure DEST_PATH_IMAGE201
With
Figure DEST_PATH_IMAGE202
The number of connected mobile devices, the subscript indicates the mobile device
Figure 994668DEST_PATH_IMAGE202
The 0th iteration of .
Figure DEST_PATH_IMAGE203
and
Figure DEST_PATH_IMAGE204
The component of is set to zero, which means that no data is stored at first.

A2CS的局限性之一是子函数必须是凸函数。因此，有必要证明优化函数是凸的并且A2CS是适用的。对于函数

Figure 516785DEST_PATH_IMAGE205
，只有一个变量
Figure 386652DEST_PATH_IMAGE206
，并且可以根据背景技术的知识给其他参数赋值，这意味着
Figure 996625DEST_PATH_IMAGE205
是线性函数。对于函数
Figure DEST_PATH_IMAGE207
，变量包括
Figure 344868DEST_PATH_IMAGE208
和两个节点之间的距离
Figure DEST_PATH_IMAGE209
。一旦距离
Figure 772307DEST_PATH_IMAGE209
固定并视为常数，则只有一个变量，上述函数
Figure DEST_PATH_IMAGE210
可以简化为线性函数。基于协同存储框架和协同存储模型，每个移动设备都可以从连接的移动设备获取距离信息，这意味着该距离可以设置为常数，并且
Figure DEST_PATH_IMAGE211
可以进一步简化为线性函数。因此，子函数的凸性证明如下。One of the limitations of A2CS is that the subfunctions must be convex. Therefore, it is necessary to prove that the optimization function is convex and that A2CS is applicable. for function
Figure 516785DEST_PATH_IMAGE205
, with only one variable
Figure 386652DEST_PATH_IMAGE206
, and other parameters can be assigned values based on the knowledge of the background technology, which means that
Figure 996625DEST_PATH_IMAGE205
is a linear function. for function
Figure DEST_PATH_IMAGE207
, the variables include
Figure 344868DEST_PATH_IMAGE208
and the distance between two nodes
Figure DEST_PATH_IMAGE209
. once the distance
Figure 772307DEST_PATH_IMAGE209
fixed and treated as a constant, there is only one variable, the above function
Figure DEST_PATH_IMAGE210
can be simplified to a linear function. Based on the co-storage framework and co-storage model, each mobile device can obtain distance information from the connected mobile device, which means that the distance can be set as a constant, and
Figure DEST_PATH_IMAGE211
It can be further simplified to a linear function. Therefore, the convexity of the subfunction is proved as follows.

证明：prove:

如（17）和（18）中所定义，和的导数可以分别描述为：As defined in (17) and (18), the derivative of and can be described as:

Figure DEST_PATH_IMAGE213
Figure DEST_PATH_IMAGE213

Figure 644317DEST_PATH_IMAGE214
和
Figure DEST_PATH_IMAGE215
中的所有参数均为正数，因此
Figure DEST_PATH_IMAGE216
，
Figure DEST_PATH_IMAGE217
。令
Figure 57981DEST_PATH_IMAGE218
，
Figure DEST_PATH_IMAGE219
，可以得到：
Figure 644317DEST_PATH_IMAGE214
and
Figure DEST_PATH_IMAGE215
All parameters in are positive numbers, so
Figure DEST_PATH_IMAGE216
,
Figure DEST_PATH_IMAGE217
. make
Figure 57981DEST_PATH_IMAGE218
,
Figure DEST_PATH_IMAGE219
, you can get:

Figure DEST_PATH_IMAGE220
Figure DEST_PATH_IMAGE220

因此，

Figure 803608DEST_PATH_IMAGE221
和
Figure DEST_PATH_IMAGE222
均满足背景知识中的子函数凸性证明公式
Figure 401948DEST_PATH_IMAGE223
，即这两个子函数均为凸。therefore,
Figure 803608DEST_PATH_IMAGE221
and
Figure DEST_PATH_IMAGE222
Both satisfy the sub-function convexity proof formula in the background knowledge
Figure 401948DEST_PATH_IMAGE223
, that is, both subfunctions are convex.

证毕。Certificate completed.

因此，子函数

Figure 371041DEST_PATH_IMAGE221
和
Figure 260500DEST_PATH_IMAGE222
可被证明为凸，并且A2CS是适用的。Therefore, the subfunction
Figure 371041DEST_PATH_IMAGE221
and
Figure 260500DEST_PATH_IMAGE222
can be shown to be convex, and A2CS is applicable.

根据ADMM理论，本实施例中对于A2CS加速算法设置了合理的停止准则，以获得令人满意的可行解并确保快速收敛。当原始残差和对偶残差较小时，目标次优也必须较小。具体来说，对于移动设备

Figure 123282DEST_PATH_IMAGE202
，使用原始残差
Figure DEST_PATH_IMAGE224
和对偶残差
Figure 908836DEST_PATH_IMAGE225
的值来确定迭代次数，并可以在第
Figure DEST_PATH_IMAGE226
次迭代时公式化为：According to the ADMM theory, a reasonable stopping criterion is set for the A2CS acceleration algorithm in this embodiment to obtain a satisfactory feasible solution and ensure fast convergence. When the original and dual residuals are small, the objective suboptimal must also be small. Specifically, for mobile devices
Figure 123282DEST_PATH_IMAGE202
, using the original residuals
Figure DEST_PATH_IMAGE224
and dual residuals
Figure 908836DEST_PATH_IMAGE225
value to determine the number of iterations, and can be
Figure DEST_PATH_IMAGE226
The second iteration is formulated as:

Figure DEST_PATH_IMAGE227
Figure DEST_PATH_IMAGE227

于是，提出了一个合理的停止准则：Therefore, a reasonable stopping criterion is proposed:

Figure DEST_PATH_IMAGE228
Figure DEST_PATH_IMAGE228

其中

Figure DEST_PATH_IMAGE229
表示第k次迭代时的原始残差，
Figure DEST_PATH_IMAGE230
表示第k次迭代时的对偶残差，
Figure 351843DEST_PATH_IMAGE231
表示绝对公差，
Figure DEST_PATH_IMAGE232
表示相对公差。此外，公差选择的方法是使用绝对公差和相对公差，可以将其表达为：in
Figure DEST_PATH_IMAGE229
represents the original residual at the kth iteration,
Figure DEST_PATH_IMAGE230
represents the dual residual at the k-th iteration,
Figure 351843DEST_PATH_IMAGE231
represents the absolute tolerance,
Figure DEST_PATH_IMAGE232
Indicates relative tolerance. Also, the method of tolerance selection is to use absolute and relative tolerances, which can be expressed as:

Figure 294260DEST_PATH_IMAGE233
Figure 294260DEST_PATH_IMAGE233

其中

Figure DEST_PATH_IMAGE234
是绝对公差，
Figure 214812DEST_PATH_IMAGE235
是相对公差，
Figure 30321DEST_PATH_IMAGE201
是变量
Figure DEST_PATH_IMAGE236
的维数。in
Figure DEST_PATH_IMAGE234
is the absolute tolerance,
Figure 214812DEST_PATH_IMAGE235
is the relative tolerance,
Figure 30321DEST_PATH_IMAGE201
is a variable
Figure DEST_PATH_IMAGE236
dimension.

参考图2，综合了本方案中的优化函数、初始值和停止准则，基于加速梯度下降方案NA和ADMM算法，结合了ADMM算法的缩放形式和NA，得到了本实施例中的A2CS加速算法。Referring to FIG. 2 , the optimization function, initial value and stopping criterion in this scheme are synthesized, based on the accelerated gradient descent scheme NA and ADMM algorithm, combined with the scaling form and NA of the ADMM algorithm, the A2CS acceleration algorithm in this embodiment is obtained.

S104基于所述边缘协同存储模型和A2CS加速算法，提出边缘协同存储策略。S104 proposes an edge collaborative storage strategy based on the edge collaborative storage model and the A2CS acceleration algorithm.

为了详细、直观地显示协同存储的过程，本实施例在边缘协同存储模型和A2CS加速算法的基础上，提出了边缘协同存储策略，参考图3，在此策略中，添加了一个名为

Figure 849372DEST_PATH_IMAGE026
的属性，以区分中边缘每个移动设备的角色，其中
Figure 329901DEST_PATH_IMAGE237
。当
Figure DEST_PATH_IMAGE238
时，移动设备是将数据传输到其他相连的移动设备的请求节点。当
Figure DEST_PATH_IMAGE239
时，移动设备是从其他相连的移动设备接收数据的存储节点。显然，移动设备可以同时是请求节点和存储节点。对于某个移动设备
Figure DEST_PATH_IMAGE240
，它收集数据
Figure DEST_PATH_IMAGE241
，然后将消息发送到连接的移动设备。之后，它确定副本数量、选择要存储的移动设备以及确定每个选定移动设备的数据量分配。同时，它还可以从其他已连接的移动设备接收请求，并决定是否接收数据。In order to show the process of collaborative storage in detail and intuitively, this embodiment proposes an edge collaborative storage strategy on the basis of the edge collaborative storage model and the A2CS acceleration algorithm. Referring to Figure 3, in this strategy, a strategy named
Figure 849372DEST_PATH_IMAGE026
properties to distinguish the role of each mobile device in the edge, where
Figure 329901DEST_PATH_IMAGE237
. when
Figure DEST_PATH_IMAGE238
When the mobile device is the requesting node to transmit data to other connected mobile devices. when
Figure DEST_PATH_IMAGE239
When a mobile device is a storage node that receives data from other connected mobile devices. Obviously, a mobile device can be a request node and a storage node at the same time. for a mobile device
Figure DEST_PATH_IMAGE240
, which collects data
Figure DEST_PATH_IMAGE241
, and send the message to the connected mobile device. After that, it determines the number of copies, selects mobile devices to store, and determines the allocation of data volume for each selected mobile device. At the same time, it can also receive requests from other connected mobile devices and decide whether to receive data.

本实施例中，边缘协同存储策略包括六大步骤：数据收集、请求分发、做出决策、决策反馈、多次交互和数据传输。数据收集步骤参考图3中的（a），用矩形和圆形表示的不同类型的移动设备具有不同的角色。另外，移动设备同时处于不同状态。带阴影的矩形和圆形表示请求节点，而其他表示空闲的存储节点。图片中的实线表示不同移动设备之间的连接。请求节点正在收集数据并准备发送数据存储消息，而存储节点已准备好从请求节点接收数据存储消息。请求分发步骤参考图3中的（b），请求节点将数据存储消息发送到所连接的移动设备并等待反馈。实线箭头表示从请求节点到存储节点的数据存储消息。做出决策步骤参考图3中的（c），空闲的存储节点接收数据存储消息并变得繁忙，由阴影矩形和带虚线的圆表示。考虑到存储容量和电池电量，繁忙的存储节点然后决定如何响应请求消息。决策反馈步骤参考图3中的（d），繁忙存储节点根据(c)中的决策将反馈返回到(a)中的请求节点。决策包含是否存储以及存储量。(d)中的虚线箭头表示决策反馈。多次交互步骤参考图3中的（e），请求节点与存储节点进行多次交互以获得可行的解决方案。双向虚线箭头表示不同移动设备之间的交互。数据传输步骤参考图3中的（f），(a)中的请求节点接收并汇总反馈。根据汇总，请求节点首先计算并确定副本数。然后，他们选择数据副本并将其传输到某些存储节点。在(f)中，数据传输用实心箭头和数据图标表示。协同存储的整个过程从(a)重复到(f)，并且移动设备可能同时处于上述状态中的一种以上。In this embodiment, the edge cooperative storage strategy includes six steps: data collection, request distribution, decision making, decision feedback, multiple interactions, and data transmission. Data collection steps Referring to Fig. 3(a), different types of mobile devices represented by rectangles and circles have different roles. In addition, mobile devices are in different states at the same time. Shaded rectangles and circles represent request nodes, while others represent free storage nodes. The solid lines in the picture represent connections between different mobile devices. The requesting node is collecting data and ready to send data store messages, and the storage node is ready to receive data store messages from the requesting node. Request distribution step Referring to (b) in Figure 3, the requesting node sends a data storage message to the connected mobile device and waits for feedback. Solid arrows represent data storage messages from requesting nodes to storage nodes. Decision Making Step Referring to (c) in Figure 3, an idle storage node receives data storage messages and becomes busy, represented by shaded rectangles and circles with dashed lines. The busy storage node then decides how to respond to the request message, taking into account storage capacity and battery power. Decision feedback step Referring to (d) in Figure 3, the busy storage node returns feedback to the requesting node in (a) according to the decision in (c). Decisions include whether to store and how much. Dashed arrows in (d) indicate decision feedback. Multiple Interaction Steps Referring to (e) in Figure 3, the requesting node interacts with the storage node multiple times to obtain a feasible solution. Two-way dashed arrows indicate interactions between different mobile devices. The data transmission step refers to (f) in Figure 3, and the requesting node in (a) receives and aggregates the feedback. Based on the aggregation, the requesting node first calculates and determines the number of replicas. Then, they choose a copy of the data and transfer it to some storage node. In (f), data transfers are indicated by solid arrows and data icons. The entire process of co-storage repeats from (a) to (f), and the mobile device may be in more than one of the above states at the same time.

S105以所述边缘协同存储策略指导所述边缘协同存储任务。S105 guides the edge cooperative storage task with the edge cooperative storage policy.

边缘协同存储策略涵盖了协同存储的整个过程，以边缘协同存储策略指导上述步骤S101中建立的边缘协同存储任务，以便将其应用于边缘中移动设备分组的任务执行场景。The edge collaborative storage strategy covers the entire process of collaborative storage, and the edge collaborative storage task established in the above step S101 is guided by the edge collaborative storage strategy, so that it can be applied to the task execution scenario of grouping mobile devices in the edge.

从上面所述可以看出，本发明一个或多个实施例提供的一种协同移动设备的边缘存储加速方法、装置及设备，特别注意了移动设备的独特特性以及多个移动设备的动态网络拓扑，将协同存储问题转化为可解决的优化问题，通过研究加速策略，提出了A2CS加速算法，高效地解决协同存储的优化问题，在A2CS加速算法中，可以从理论上提高收敛速度，同时提出了一种协同存储策略，该策略包括六大步骤，可以表示协同存储的整个过程，A2CS加速算法应用贯穿于该策略的全部步骤，以该策略指导协同存储的整个循环周期。A2CS加速算法与两种现有方法ADMM基准和ADMM-OR（具有过度松弛的ADMM）相比，A2CS加速算法在不同的步长规则下提供了更好的收敛性能，加速百分比至少达到25.33％，最多可以达到64.01％。此外，通过使用现有的平均分配策略（ADS）和现有的距离优先分配策略（DPDS）进行效用性能比较分析，结果表明A2CS加速算法在总效用和能耗方面优于ADS和DPDS。As can be seen from the above, one or more embodiments of the present invention provide an edge storage acceleration method, apparatus, and device for cooperating with mobile devices, paying particular attention to the unique characteristics of mobile devices and the dynamic network topology of multiple mobile devices , transforming the cooperative storage problem into a solvable optimization problem. By studying the acceleration strategy, an A2CS acceleration algorithm is proposed to efficiently solve the optimization problem of cooperative storage. In the A2CS acceleration algorithm, the convergence speed can be theoretically improved. At the same time, the proposed A collaborative storage strategy includes six steps, which can represent the entire process of collaborative storage. A2CS acceleration algorithm is applied throughout all steps of the strategy, and the strategy guides the entire cycle of collaborative storage. Compared with the two existing methods ADMM benchmark and ADMM-OR (ADMM with over-relaxation), the A2CS acceleration algorithm provides better convergence performance under different step size rules, and the acceleration percentage reaches at least 25.33%, Up to 64.01% can be achieved. Furthermore, by using the existing average allocation strategy (ADS) and the existing distance priority allocation strategy (DPDS) for utility performance comparative analysis, the results show that the A2CS acceleration algorithm outperforms ADS and DPDS in terms of total utility and energy consumption.

需要说明的是，本发明一个或多个实施例的方法可以由单个设备执行，例如一台计算机或服务器等。本实施例的方法也可以应用于分布式场景下，由多台设备相互配合来完成。在这种分布式场景的情况下，这多台设备中的一台设备可以只执行本发明一个或多个实施例的方法中的某一个或多个步骤，这多台设备相互之间会进行交互以完成所述的方法。It should be noted that, the methods of one or more embodiments of the present invention may be executed by a single device, such as a computer or a server. The method in this embodiment can also be applied in a distributed scenario, and is completed by the cooperation of multiple devices. In the case of such a distributed scenario, one device among the multiple devices may only execute one or more steps in the method of one or more embodiments of the present invention, and the multiple devices may perform operations among each other. interact to complete the described method.

上述对本说明书特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中，多任务处理和并行处理也是可以的或者可能是有利的。The foregoing describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

参考图4，基于同一发明构思，本发明一个或多个实施例还提供了一种协同移动设备的边缘存储加速装置，包括：第一建立模块、第二建立模块、计算模块、策略模块和执行模块。Referring to FIG. 4 , based on the same inventive concept, one or more embodiments of the present invention further provide an edge storage acceleration apparatus for cooperating with mobile devices, including: a first establishment module, a second establishment module, a calculation module, a policy module, and an execution module. module.

其中，第一建立模块，被配置为建立移动设备间传输数据的边缘协同存储任务；Wherein, the first establishment module is configured to establish an edge cooperative storage task for data transmission between mobile devices;

第二建立模块，被配置为基于所述边缘协同存储任务建立边缘协同存储模型，所述边缘协同存储模型包括：移动设备集合

Figure DEST_PATH_IMAGE242
、发送移动设备
Figure 232522DEST_PATH_IMAGE243
、接收移动设备
Figure 953354DEST_PATH_IMAGE003
和网络拓扑
Figure DEST_PATH_IMAGE244
，所述移动设备集合
Figure 712231DEST_PATH_IMAGE242
包括至少两个移动设备；The second establishment module is configured to establish an edge cooperative storage model based on the edge cooperative storage task, where the edge cooperative storage model includes: a set of mobile devices
Figure DEST_PATH_IMAGE242
, send mobile device
Figure 232522DEST_PATH_IMAGE243
, receiving mobile device
Figure 953354DEST_PATH_IMAGE003
and network topology
Figure DEST_PATH_IMAGE244
, the mobile device collection
Figure 712231DEST_PATH_IMAGE242
Include at least two mobile devices;

计算模块，被配置为基于所述边缘协同存储模型计算得到A2CS加速算法；a computing module, configured to calculate and obtain an A2CS acceleration algorithm based on the edge collaborative storage model;

策略模块，被配置为基于所述边缘协同存储模型和A2CS加速算法，提出边缘协同存储策略；a strategy module, configured to propose an edge collaborative storage strategy based on the edge collaborative storage model and the A2CS acceleration algorithm;

执行模块，被配置为以所述边缘协同存储策略指导所述边缘协同存储任务。An execution module configured to direct the edge cooperative storage task with the edge cooperative storage policy.

为了描述的方便，描述以上装置时以功能分为各种模块分别描述。当然，在实施本发明一个或多个实施例时可以把各模块的功能在同一个或多个软件和/或硬件中实现。For the convenience of description, when describing the above device, the functions are divided into various modules and described respectively. Of course, when implementing one or more embodiments of the present invention, the functions of each module may be implemented in one or more software and/or hardware.

上述实施例的装置用于实现前述实施例中相应的方法，并且具有相应的方法实施例的有益效果，在此不再赘述。The apparatuses in the foregoing embodiments are used to implement the corresponding methods in the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

基于同一发明构思，本发明一个或多个实施例还提供了一种电子设备，该电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如上任意一实施例所述的方法。Based on the same inventive concept, one or more embodiments of the present invention also provide an electronic device, the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor The method described in any one of the above embodiments is implemented when the program is executed.

图5示出了本实施例所提供的一种更为具体的电子设备硬件结构示意图， 该设备可以包括：处理器501、存储器502、输入/输出接口503、通信接口504和总线505。其中处理器501、存储器502、输入/输出接口503和通信接口504通过总线505实现彼此之间在设备内部的通信连接。FIG. 5 shows a more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment. The device may include: a processor 501 , a memory 502 , an input/output interface 503 , a communication interface 504 and a bus 505 . The processor 501 , the memory 502 , the input/output interface 503 and the communication interface 504 realize the communication connection among each other within the device through the bus 505 .

处理器501可以采用通用的CPU（Central Processing Unit，中央处理器）、微处理器、应用专用集成电路（Application Specific Integrated Circuit，ASIC）、或者一个或多个集成电路等方式实现，用于执行相关程序，以实现本说明书实施例所提供的技术方案。The processor 501 may be implemented by a general-purpose CPU (Central Processing Unit, central processing unit), a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute related program to implement the technical solutions provided by the embodiments of this specification.

存储器502可以采用ROM（Read Only Memory，只读存储器）、RAM（Random AccessMemory，随机存取存储器）、静态存储设备，动态存储设备等形式实现。存储器502可以存储操作系统和其他应用程序，在通过软件或者固件来实现本说明书实施例所提供的技术方案时，相关的程序代码保存在存储器5020中，并由处理器501来调用执行。The memory 502 may be implemented in the form of a ROM (Read Only Memory, read only memory), a RAM (Random Access Memory, random access memory), a static storage device, a dynamic storage device, and the like. The memory 502 can store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 5020 and invoked by the processor 501 for execution.

输入/输出接口503用于连接输入/输出模块，以实现信息输入及输出。输入输出/模块可以作为组件配置在设备中（图中未示出），也可以外接于设备以提供相应功能。其中输入设备可以包括键盘、鼠标、触摸屏、麦克风、各类传感器等，输出设备可以包括显示器、扬声器、振动器、指示灯等。The input/output interface 503 is used for connecting input/output modules to realize information input and output. The input/output/module can be configured in the device as a component (not shown in the figure), or can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, and the like.

通信接口504用于连接通信模块（图中未示出），以实现本设备与其他设备的通信交互。其中通信模块可以通过有线方式（例如USB、网线等）实现通信，也可以通过无线方式（例如移动网络、WIFI、蓝牙等）实现通信。The communication interface 504 is used to connect a communication module (not shown in the figure), so as to realize the communication interaction between the device and other devices. The communication module can implement communication through wired means (such as USB, network cable, etc.), or can implement communication through wireless means (such as mobile network, WIFI, Bluetooth, etc.).

总线505包括一通路，在设备的各个组件（例如处理器501、存储器502、输入/输出接口503和通信接口504）之间传输信息。Bus 505 includes a path to transfer information between the various components of the device (eg, processor 501, memory 502, input/output interface 503, and communication interface 504).

需要说明的是，尽管上述设备仅示出了处理器501、存储器502、输入/输出接口503、通信接口504以及总线505，但是在具体实施过程中，该设备还可以包括实现正常运行所必需的其他组件。此外，本领域的技术人员可以理解的是，上述设备中也可以仅包含实现本说明书实施例方案所必需的组件，而不必包含图中所示的全部组件。It should be noted that although the above-mentioned device only shows the processor 501, the memory 502, the input/output interface 503, the communication interface 504 and the bus 505, in the specific implementation process, the device may also include necessary components for normal operation. other components. In addition, those skilled in the art can understand that, the above-mentioned device may only include components necessary to implement the solutions of the embodiments of the present specification, rather than all the components shown in the figures.

为了验证A2CS加速算法的性能，发明人设计和实施一系列实验，特别地，以无人飞行器（UAV）为例，并在后续中使用DJIUAV的参数。进行实验时使用步长规则。In order to verify the performance of the A2CS acceleration algorithm, the inventors designed and implemented a series of experiments, especially, taking the unmanned aerial vehicle (UAV) as an example, and used the parameters of DJIUAV in the follow-up. Use the step size rule when conducting experiments.

首先，假设边缘包含20架无人机。边缘的网络拓扑包括不同时刻无人机之间的连通性和距离。为了在协同存储方案中模拟边缘网络拓扑的动态，使用给定范围内的随机数表示无人机之间的连接性和距离。具体来说，首先生成1到19之间的随机数，以表示可以连接到请求UAV以便允许数据传输的UAV数量。这意味着请求无人机最多可以连接1架无人机，最多可以连接19架无人机，这与实际情况是一致的。此外，由于与另一移动设备的连接丢失近似服从0-1分布进行，因此使用随机数来生成0-1布尔变量，以表示连接状态。然后，无人机之间的距离也随机产生在[5,20]的范围内。上下界是从小规模无人机集群中无人机之间的距离典型值得出的。First, let's say the edge contains 20 drones. The network topology at the edge includes the connectivity and distance between drones at different times. To simulate the dynamics of edge network topology in a cooperative storage scheme, random numbers within a given range are used to represent the connectivity and distance between drones. Specifically, a random number between 1 and 19 is first generated to represent the number of UAVs that can be connected to the requesting UAV in order to allow data transfer. This means that the requesting drone can connect to a maximum of 1 drone and a maximum of 19 drones, which is consistent with the actual situation. Furthermore, since the loss of connection to another mobile device approximately follows a 0-1 distribution, a random number is used to generate a 0-1 Boolean variable to represent the connection state. Then, the distances between drones are also randomly generated in the range of [5, 20]. The upper and lower bounds are typically derived from distances between drones in small-scale drone swarms.

此外，为了验证协同存储模型的有效性并减少时间成本，对副本数量进行了简单的预实验。参考图6，图中表示固定数据量大小时的能耗和数据丢失的归一化值。随着副本数量的增加，能耗增加，而数据丢失减少，这意味着移动设备的续航时间和边缘存储可靠性增加。因此，副本数的选择应同时考虑能耗和数据丢失，这与上述协同存储模型是一致的。另外，多于8个副本并不能减少数据丢失，反而增加了能耗，这在本文中被视为不可接受的协同存储方法。因此，将副本数设置为1到8，以避免不必要的实验并减少时间成本。Furthermore, to verify the effectiveness of the cooperative storage model and reduce the time cost, a simple pre-experiment on the number of replicas is performed. Referring to Figure 6, the figure shows the normalized values of energy consumption and data loss for a fixed data size. As the number of replicas increases, power consumption increases while data loss decreases, which means increased battery life and edge storage reliability for mobile devices. Therefore, the choice of the number of replicas should consider both energy consumption and data loss, which is consistent with the above-mentioned cooperative storage model. In addition, more than 8 replicas does not reduce data loss, but increases energy consumption, which is regarded as an unacceptable cooperative storage method in this paper. Therefore, set the number of replicas from 1 to 8 to avoid unnecessary experiments and reduce the time cost.

经过多次测试，最终设定参数的值，增广拉格朗日参数设置为

Figure 809500DEST_PATH_IMAGE245
，权重系数
Figure 986535DEST_PATH_IMAGE162
和
Figure DEST_PATH_IMAGE246
是超参数，其设置为
Figure DEST_PATH_IMAGE247
，
Figure DEST_PATH_IMAGE248
，μ=0.001，θ=0.002，
Figure DEST_PATH_IMAGE249
，PT=100mW，GT=2dbi，GR=2dbi，λ=0.125m，L=1，c=[5,30]MB，设置
Figure DEST_PATH_IMAGE250
和
Figure 470080DEST_PATH_IMAGE251
经过多次测试得到满意的可行解。比较算法之间的性能，主要从三个指标上评价，包括：收敛次数、总体效用和能耗，收敛次数表示算法的收敛速度；总体效用表示使用不同算法的优化函数的值；能耗描述了移动设备的续航时间。After many tests, the value of the parameter is finally set, and the augmented Lagrangian parameter is set as
Figure 809500DEST_PATH_IMAGE245
, the weight coefficient
Figure 986535DEST_PATH_IMAGE162
and
Figure DEST_PATH_IMAGE246
is a hyperparameter, which is set to
Figure DEST_PATH_IMAGE247
,
Figure DEST_PATH_IMAGE248
, μ=0.001, θ=0.002,
Figure DEST_PATH_IMAGE249
, P T =100mW, G T =2dbi, G R =2dbi, λ=0.125m, L=1, c=[5,30]MB, set
Figure DEST_PATH_IMAGE250
and
Figure 470080DEST_PATH_IMAGE251
A satisfactory feasible solution was obtained after many tests. Comparing the performance between algorithms, it is mainly evaluated from three indicators, including: convergence times, overall utility and energy consumption. The convergence times indicate the convergence speed of the algorithm; overall utility indicates the value of the optimization function using different algorithms; energy consumption describes the Battery life of mobile devices.

ADMM-OR算法源于ADMM算法，添加了对

Figure DEST_PATH_IMAGE252
的更新，可以表示为：The ADMM-OR algorithm is derived from the ADMM algorithm, adding
Figure DEST_PATH_IMAGE252
The update can be expressed as:

Figure 450674DEST_PATH_IMAGE253
Figure 450674DEST_PATH_IMAGE253

其中

Figure DEST_PATH_IMAGE254
是松弛参数。特别是当
Figure 492579DEST_PATH_IMAGE255
时，此模式称为过松弛。在过度松弛之后，在接下来的步骤中使用
Figure DEST_PATH_IMAGE256
更新变量
Figure 632442DEST_PATH_IMAGE257
和对偶变量
Figure DEST_PATH_IMAGE258
。当
Figure 101601DEST_PATH_IMAGE259
中时，表明收敛性得到改善。因此，在实验中，设置
Figure 366229DEST_PATH_IMAGE260
。为了更好的收敛性能，发明人在进行实验时增加了步长规则。步长规则是指评估
Figure DEST_PATH_IMAGE261
的不同方法，这意味着
Figure 742984DEST_PATH_IMAGE261
在每次迭代中都不固定。此操作的优越之处在于，可以在实践中提高收敛速度，并降低性能对初始值的依赖。当
Figure 412387DEST_PATH_IMAGE261
在每次迭代中更改时，很难证明其收敛性，但是如果
Figure 583605DEST_PATH_IMAGE261
在有限次数的迭代之后可以变为某个固定值，则上述理论仍然适用。因此，提出了另外两种步长规则，其中
Figure 945317DEST_PATH_IMAGE262
可以在协同存储问题所需的精度范围内固定。它们可以分别表示为：in
Figure DEST_PATH_IMAGE254
is the relaxation parameter. especially when
Figure 492579DEST_PATH_IMAGE255
, this mode is called over-relaxation. After over-relaxing, use in the next steps
Figure DEST_PATH_IMAGE256
update variable
Figure 632442DEST_PATH_IMAGE257
and the dual variable
Figure DEST_PATH_IMAGE258
. when
Figure 101601DEST_PATH_IMAGE259
, indicating improved convergence. Therefore, in the experiment, set
Figure 366229DEST_PATH_IMAGE260
. For better convergence performance, the inventors increased the step size rule when conducting experiments. Step rules refer to evaluating
Figure DEST_PATH_IMAGE261
different methods, which means
Figure 742984DEST_PATH_IMAGE261
Not fixed in each iteration. The advantage of this operation is that, in practice, the speed of convergence can be increased and the dependence of performance on initial values is reduced. when
Figure 412387DEST_PATH_IMAGE261
It is difficult to prove its convergence when changing in each iteration, but if
Figure 583605DEST_PATH_IMAGE261
can become some fixed value after a finite number of iterations, the above theory still applies. Therefore, two other step size rules are proposed, where
Figure 945317DEST_PATH_IMAGE262
Can be fixed within the precision required for co-storage problems. They can be expressed as:

Figure DEST_PATH_IMAGE263
Figure DEST_PATH_IMAGE263

首先，进行了20个实验，并使用上述三种算法以及三种步长规则，基于相同实验设置分别对结果进行平均求值。具体来说，将数据量大小设置为

Figure 437347DEST_PATH_IMAGE264
。参考图7（a）、图7（b）和图7（c），直方图指示了副本数与收敛次数之间的关系，而折线图显示了使用具有不同步长规则的A2CS加速算法的总效用与副本数之间的关系。随着副本数量的增加，当
Figure DEST_PATH_IMAGE265
，
Figure 302535DEST_PATH_IMAGE266
和
Figure 97184DEST_PATH_IMAGE267
时，收敛次数也都增加。对于每种步长规则，所提出的A2CS加速算法收敛次数最少，表现出最佳的收敛性能。此外，使用A2CS加速算法的总效用首先减少，然后增加。当副本数等于4时达到最小值，这意味着边缘请求节点的最佳选择是备份4个副本并将它们发送到连接的存储节点。还可以得出结论，步长规则极大地影响了收敛速度，但对总效用影响很小。First, 20 experiments were conducted and the results were averaged separately based on the same experimental settings using the three algorithms described above and the three step size rules. Specifically, set the data volume size to
Figure 437347DEST_PATH_IMAGE264
. Referring to Fig. 7(a), Fig. 7(b) and Fig. 7(c), the histograms indicate the relationship between the number of replicas and the number of convergences, while the line graphs show the total amount of acceleration algorithms using A2CS with different step-length rules. The relationship between utility and replica count. As the number of copies increases, when
Figure DEST_PATH_IMAGE265
,
Figure 302535DEST_PATH_IMAGE266
and
Figure 97184DEST_PATH_IMAGE267
, the convergence times also increase. For each step size rule, the proposed A2CS acceleration algorithm has the fewest convergence times and exhibits the best convergence performance. Furthermore, the overall utility of using the A2CS acceleration algorithm first decreases and then increases. The minimum value is reached when the number of replicas equals 4, which means that the best option for an edge requesting node is to backup 4 replicas and send them to the connected storage node. It can also be concluded that the step size rule greatly affects the convergence speed, but has little effect on the overall utility.

参考图8（a）、图8（b）和图8（c），当数据量大小固定时，使用不同步长规则对收敛次数的影响。总体而言，使用步长规则

Figure 946191DEST_PATH_IMAGE265
和
Figure 602432DEST_PATH_IMAGE267
的结果要比使用固定步长规则
Figure 118864DEST_PATH_IMAGE266
的结果更好。尽管也有一些例外，但是使用三种步长规则的那些例外结果之间的差异是适度的，这是可以接受的。此外，发现与其他算法结合使用时，某个步长规则并不总是比其他步长规则具有更好的性能。特别地，为每种算法选择收敛速度最快的结果，并在表4中列出。比较这三种组合的结果。表3中用下划线标出了最佳性能，并计算了加速百分比。Referring to Figure 8(a), Figure 8(b), and Figure 8(c), when the data size is fixed, the effect of using different step length rules on the convergence times. In general, use the step size rule
Figure 946191DEST_PATH_IMAGE265
and
Figure 602432DEST_PATH_IMAGE267
results are better than using the fixed-step rule
Figure 118864DEST_PATH_IMAGE266
results are better. Although there are some exceptions, the difference between the results of those exceptions using the three-step rule is modest and acceptable. Furthermore, it was found that when combined with other algorithms, certain step rules did not always perform better than others. In particular, the results with the fastest convergence rate are selected for each algorithm and listed in Table 4. Compare the results of these three combinations. The best performance is underlined in Table 3 and the speedup percentage is calculated.

表3 副本数量对不同组合的平均数量收敛的影响Table 3 Influence of the number of replicas on the convergence of the average number of different combinations

Figure DEST_PATH_IMAGE269
Figure DEST_PATH_IMAGE269

参考图9（a）和图9（b），为了分析数据量大小对收敛性能的影响，进行了另外20个实验并对结果进行平均，根据图7中的结果将副本数设置为4。由于图8中的结果显示了使用

Figure 25027DEST_PATH_IMAGE266
的相对较慢的收敛速度，仅使用
Figure 361331DEST_PATH_IMAGE265
和
Figure 70530DEST_PATH_IMAGE267
来分析结果。直方图指定数据量大小和收敛次数之间的关系。通常，收敛次数随着数据量大小的增加而增加。值得注意的现象是，随着数据量大小的增加，A2CS的性能要比其他算法好得多，这意味着数据量大小对A2CS的性能影响不大，而对ADMM和ADMM-OR的影响却很大。特别是，对于每种算法，选择算法和收敛速度最快的步长规则的组合。所选结果显示在表4中，用下划线标出了最佳性能并计算了加速百分比。随着数据量大小的增加，加速百分比也增加，这意味着所提出的算法A2CS在处理大量数据时表现更好。Referring to Fig. 9(a) and Fig. 9(b), in order to analyze the influence of the data size on the convergence performance, another 20 experiments were conducted and the results were averaged, and the number of replicas was set to 4 according to the results in Fig. 7. Since the results in Figure 8 show that using
Figure 25027DEST_PATH_IMAGE266
The relatively slow convergence rate of , using only
Figure 361331DEST_PATH_IMAGE265
and
Figure 70530DEST_PATH_IMAGE267
to analyze the results. The histogram specifies the relationship between the amount of data and the number of convergence times. Typically, the number of convergence increases with the size of the data. It is worth noting that with the increase of the data size, the performance of A2CS is much better than other algorithms, which means that the size of the data has little effect on the performance of A2CS, while it has a great effect on ADMM and ADMM-OR. big. In particular, for each algorithm, the combination of the algorithm and the step size rule with the fastest convergence rate is chosen. The selected results are shown in Table 4, the best performance is underlined and the percentage of speedup is calculated. As the size of the data volume increases, the speedup percentage also increases, which means that the proposed algorithm A2CS performs better when dealing with large amounts of data.

表4 数据量大小对不同组合的平均数收敛的影响Table 4 Influence of data size on the mean convergence of different combinations

Figure 113572DEST_PATH_IMAGE271
Figure 113572DEST_PATH_IMAGE271

数据副本的分配与优化函数的效用密切相关，并在所提出的算法A2CS中进行了分析，因此效用性能分析被定义为A2CS与也进行数据分配的算法之间的比较。与A2CS加速算法比较的算法包括：The allocation of data copies is closely related to the utility of the optimization function and is analyzed in the proposed algorithm A2CS, so utility performance analysis is defined as a comparison between A2CS and an algorithm that also performs data allocation. Algorithms compared to A2CS accelerated algorithms include:

ADS（平均分配策略）：将数据副本均匀地分布到相连的存储节点；ADS (Average Distribution Strategy): Distribute data copies evenly to connected storage nodes;

DPDS（距离优先分配策略）：DPDS优先考虑请求节点和连接的存储节点之间的距离。距离越短，优先级越高。DPDS (Distance Priority Assignment Policy): DPDS prioritizes the distance between the requesting node and the connected storage node. The shorter the distance, the higher the priority.

基于上面的加速性能分析，当数据量大小分别在[5,30]MB的范围内随机选择时，将数据副本数设置为4，并进行了20个实验。Based on the above accelerated performance analysis, when the data size is randomly selected in the range of [5, 30]MB, the number of data copies is set to 4, and 20 experiments are carried out.

参考图10（a），直方图描述了使用不同算法的总效用，参考图10（b），直方图描述了使用不同算法的能耗，相应地，折线图分别表示在不同时间范围内A2CS相对于ADS和DPDS的优势百分比。总体而言，所提出的算法A2CS在总效用和能耗上均比ADS和DPDS表现出更好的性能。结果表明，A2CS的数据副本分发策略可以最大程度地降低总效用和能耗，从而满足移动设备边缘和长续航时间的高存储可靠性的优化目标。Referring to Fig. 10(a), the histogram depicts the total utility of using different algorithms, and referring to Fig. 10(b), the histogram depicts the energy consumption using different algorithms. Correspondingly, the line graphs represent the relative A2CS relative to each other over different time horizons. Dominance percentage over ADS and DPDS. Overall, the proposed algorithm A2CS exhibits better performance than ADS and DPDS in both total utility and energy consumption. The results show that the data copy distribution strategy of A2CS can minimize the total utility and energy consumption, thus meeting the optimization goal of high storage reliability at the edge of mobile devices and long battery life.

参考图11（a），A2CS加速算法的总效用，参考图11（b），A2CS加速算法的能耗，为了分析步长规则对效用的影响，使用A2CS进行了另外20个实验，其中

Figure 125390DEST_PATH_IMAGE272
，
Figure DEST_PATH_IMAGE273
和
Figure DEST_PATH_IMAGE274
。发现使用
Figure 11307DEST_PATH_IMAGE275
的A2CS在大多数实验中的表现与另两个组合几乎相同，并且仅在某些情况下更好。此外，值得注意的是，当副本数设置为4时，
Figure DEST_PATH_IMAGE276
的A2CS具有最佳的加速性能。尽管
Figure DEST_PATH_IMAGE277
的A2CS可以更好地加速收敛。在一些实验中，效用性能的结果表明步长规则对效用性能的影响很小。Referring to Fig. 11(a), the total utility of the A2CS acceleration algorithm, and referring to Fig. 11(b), the energy consumption of the A2CS acceleration algorithm, in order to analyze the effect of the step size rule on the utility, another 20 experiments were conducted using A2CS, where
Figure 125390DEST_PATH_IMAGE272
,
Figure DEST_PATH_IMAGE273
and
Figure DEST_PATH_IMAGE274
. find use
Figure 11307DEST_PATH_IMAGE275
The A2CS performed almost identically to the other two combinations in most experiments, and was only better in some cases. Also, it is worth noting that when the number of replicas is set to 4,
Figure DEST_PATH_IMAGE276
A2CS has the best acceleration performance. although
Figure DEST_PATH_IMAGE277
A2CS can better accelerate convergence. In some experiments, the results of the utility performance show that the step size rule has little effect on the utility performance.

所属领域的普通技术人员应当理解：以上任何实施例的讨论仅为示例性的，并非旨在暗示本公开的范围（包括权利要求）被限于这些例子；在本公开的思路下，以上实施例或者不同实施例中的技术特征之间也可以进行组合，步骤可以以任意顺序实现，并存在如上所述的本发明一个或多个实施例的不同方面的许多其它变化，为了简明它们没有在细节中提供。Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is only exemplary, and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; under the spirit of the present disclosure, the above embodiments or Technical features in different embodiments may also be combined, steps may be carried out in any order, and there are many other variations of the different aspects of one or more embodiments of the invention as described above, which are not in detail for the sake of brevity supply.

另外，为简化说明和讨论，并且为了不会使本发明一个或多个实施例难以理解，在所提供的附图中可以示出或可以不示出与集成电路（IC）芯片和其它部件的公知的电源/接地连接。此外，可以以框图的形式示出装置，以便避免使本发明一个或多个实施例难以理解，并且这也考虑了以下事实，即关于这些框图装置的实施方式的细节是高度取决于将要实施本发明一个或多个实施例的平台的（即，这些细节应当完全处于本领域技术人员的理解范围内）。在阐述了具体细节（例如，电路）以描述本公开的示例性实施例的情况下，对本领域技术人员来说显而易见的是，可以在没有这些具体细节的情况下或者这些具体细节有变化的情况下实施本发明一个或多个实施例。因此，这些描述应被认为是说明性的而不是限制性的。Additionally, in order to simplify the description and discussion, and in order not to obscure one or more embodiments of the invention, in the figures provided may or may not be shown in connection with integrated circuit (IC) chips and other components Well known power/ground connections. Furthermore, devices may be shown in block diagram form in order to avoid obscuring one or more embodiments of the invention, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the implementation of the invention (ie, these details should be well within the comprehension of those skilled in the art) of the invention of one or more embodiments. Where specific details (eg, circuits) are set forth to describe exemplary embodiments of the present disclosure, it will be apparent to those skilled in the art that these specific details may be made without or with changes One or more embodiments of the invention are implemented below. Accordingly, these descriptions are to be considered illustrative rather than restrictive.

本发明一个或多个实施例旨在涵盖落入所附权利要求的宽泛范围之内的所有这样的替换、修改和变型。因此，凡在本发明一个或多个实施例的精神和原则之内，所做的任何省略、修改、等同替换、改进等，均应包含在本公开的保护范围之内。The one or more embodiments of the invention are intended to cover all such alternatives, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the present invention should be included within the protection scope of the present disclosure.

Claims (9)

1.一种协同移动设备的边缘存储加速方法，其特征在于，包括：1. An edge storage acceleration method for collaborative mobile equipment, characterized in that, comprising: 建立移动设备间传输数据的边缘协同存储任务；Establish an edge cooperative storage task for data transmission between mobile devices; 基于所述边缘协同存储任务建立边缘协同存储模型，所述边缘协同存储模型包括：移动设备集合
Figure 766896DEST_PATH_IMAGE001
、发送移动设备
Figure 898800DEST_PATH_IMAGE002
、接收移动设备
Figure 249228DEST_PATH_IMAGE003
和网络拓扑
Figure 875512DEST_PATH_IMAGE004
，所述移动设备集合
Figure 966965DEST_PATH_IMAGE005
包括至少两个移动设备；An edge collaborative storage model is established based on the edge collaborative storage task, and the edge collaborative storage model includes: a set of mobile devices
Figure 766896DEST_PATH_IMAGE001
, send mobile device
Figure 898800DEST_PATH_IMAGE002
, receiving mobile device
Figure 249228DEST_PATH_IMAGE003
and network topology
Figure 875512DEST_PATH_IMAGE004
, the mobile device collection
Figure 966965DEST_PATH_IMAGE005
Include at least two mobile devices; 基于所述边缘协同存储模型计算得到A2CS加速算法，所述A2CS加速算法包括：An A2CS acceleration algorithm is calculated based on the edge collaborative storage model, and the A2CS acceleration algorithm includes: 初始值
Figure 82820DEST_PATH_IMAGE006
、
Figure 643245DEST_PATH_IMAGE007
和
Figure 322488DEST_PATH_IMAGE008
，所述初始值表示对任意一个移动设备
Figure 19180DEST_PATH_IMAGE009
部署所述A2CS加速算法的初始数值，所述初始值表述为initial value
Figure 82820DEST_PATH_IMAGE006
,
Figure 643245DEST_PATH_IMAGE007
and
Figure 322488DEST_PATH_IMAGE008
, the initial value indicates that for any mobile device
Figure 19180DEST_PATH_IMAGE009
Deploy the initial value of the A2CS acceleration algorithm, the initial value is expressed as
Figure 305936DEST_PATH_IMAGE010
Figure 305936DEST_PATH_IMAGE010
 其中
Figure 353658DEST_PATH_IMAGE011
表示与所述
Figure 367750DEST_PATH_IMAGE012
连接的移动设备的数量，
Figure 450107DEST_PATH_IMAGE013
表示
Figure 642185DEST_PATH_IMAGE011
维向量；in
Figure 353658DEST_PATH_IMAGE011
expressed with the stated
Figure 367750DEST_PATH_IMAGE012
the number of connected mobile devices,
Figure 450107DEST_PATH_IMAGE013
express
Figure 642185DEST_PATH_IMAGE011
dimensional vector; 停止准则，所述停止准则使所述A2CS加速算法获得可行解并确保所述A2CS加速算法快速收敛，所述停止准则表述为A stopping criterion that enables the A2CS acceleration algorithm to obtain a feasible solution and ensures rapid convergence of the A2CS acceleration algorithm, and the stopping criterion is expressed as
Figure 442782DEST_PATH_IMAGE014
，
Figure 442782DEST_PATH_IMAGE014
, 其中
Figure 339193DEST_PATH_IMAGE015
表示第
Figure 744898DEST_PATH_IMAGE016
次迭代时的原始残差，
Figure 373457DEST_PATH_IMAGE017
表示第
Figure 130191DEST_PATH_IMAGE016
次迭代时的对偶残差，
Figure 486086DEST_PATH_IMAGE018
表示绝对公差，
Figure 277456DEST_PATH_IMAGE019
表示相对公差；in
Figure 339193DEST_PATH_IMAGE015
means the first
Figure 744898DEST_PATH_IMAGE016
the original residual at the next iteration,
Figure 373457DEST_PATH_IMAGE017
means the first
Figure 130191DEST_PATH_IMAGE016
dual residuals at the next iteration,
Figure 486086DEST_PATH_IMAGE018
represents the absolute tolerance,
Figure 277456DEST_PATH_IMAGE019
Indicates relative tolerance; 优化函数
Figure 280178DEST_PATH_IMAGE020
，用于描述所述边缘协同存储任务的总效用，所述优化函数表述为optimization function
Figure 280178DEST_PATH_IMAGE020
, used to describe the total utility of the edge cooperative storage task, and the optimization function is expressed as
Figure 39055DEST_PATH_IMAGE021
Figure 39055DEST_PATH_IMAGE021
 其中
Figure 937655DEST_PATH_IMAGE022
和
Figure 521214DEST_PATH_IMAGE023
是权重系数，
Figure 6422DEST_PATH_IMAGE024
表示由发送移动设备
Figure 941011DEST_PATH_IMAGE025
收集的数据量的大小，
Figure 389441DEST_PATH_IMAGE024
和
Figure 139091DEST_PATH_IMAGE026
之间的关系可以描述为
Figure 545933DEST_PATH_IMAGE027
，
Figure 498977DEST_PATH_IMAGE028
表示所述发送移动设备
Figure 469207DEST_PATH_IMAGE029
收集的数据的数据副本数量，
Figure 620834DEST_PATH_IMAGE030
表示数据丢失量，
Figure 136260DEST_PATH_IMAGE031
表示数据存储的总能耗，
Figure 842179DEST_PATH_IMAGE032
表示发送移动设备
Figure 84941DEST_PATH_IMAGE033
的数据丢失概率，
Figure 887812DEST_PATH_IMAGE034
表示所述发送移动设备
Figure 370877DEST_PATH_IMAGE029
的数据传输速率，
Figure 298513DEST_PATH_IMAGE035
表示所述接收移动设备
Figure 344966DEST_PATH_IMAGE036
的数据接收速率，
Figure 940027DEST_PATH_IMAGE037
表示邻接矩阵
Figure 593993DEST_PATH_IMAGE038
的第
Figure 461455DEST_PATH_IMAGE039
行、第
Figure 859070DEST_PATH_IMAGE040
列中的元素，
Figure 308637DEST_PATH_IMAGE041
表示距离矩阵
Figure 586034DEST_PATH_IMAGE042
的第
Figure 499981DEST_PATH_IMAGE039
行、第
Figure 904549DEST_PATH_IMAGE040
列中的元素，
Figure 457890DEST_PATH_IMAGE043
表示存储单位数据的能耗，
Figure 656921DEST_PATH_IMAGE044
表示所述发送移动设备
Figure 312024DEST_PATH_IMAGE029
的发射功率，
Figure 300709DEST_PATH_IMAGE045
表示发射天线增益，
Figure 396972DEST_PATH_IMAGE046
表示接收天线增益，
Figure 94801DEST_PATH_IMAGE047
表示波长，
Figure 424151DEST_PATH_IMAGE048
表示所述发送移动设备
Figure 701680DEST_PATH_IMAGE029
和所述接收移动设备
Figure 167296DEST_PATH_IMAGE036
之间的距离，
Figure 36026DEST_PATH_IMAGE049
表示与传播无关的系统损耗因子；in
Figure 937655DEST_PATH_IMAGE022
and
Figure 521214DEST_PATH_IMAGE023
is the weight coefficient,
Figure 6422DEST_PATH_IMAGE024
Indicates that the mobile device is sent by
Figure 941011DEST_PATH_IMAGE025
the size of the amount of data collected,
Figure 389441DEST_PATH_IMAGE024
and
Figure 139091DEST_PATH_IMAGE026
The relationship between can be described as
Figure 545933DEST_PATH_IMAGE027
,
Figure 498977DEST_PATH_IMAGE028
represents the sending mobile device
Figure 469207DEST_PATH_IMAGE029
the number of data copies of the collected data,
Figure 620834DEST_PATH_IMAGE030
represents the amount of data loss,
Figure 136260DEST_PATH_IMAGE031
represents the total energy consumption of data storage,
Figure 842179DEST_PATH_IMAGE032
Indicates sending mobile device
Figure 84941DEST_PATH_IMAGE033
the probability of data loss,
Figure 887812DEST_PATH_IMAGE034
represents the sending mobile device
Figure 370877DEST_PATH_IMAGE029
the data transfer rate,
Figure 298513DEST_PATH_IMAGE035
represents the receiving mobile device
Figure 344966DEST_PATH_IMAGE036
the data reception rate,
Figure 940027DEST_PATH_IMAGE037
represents the adjacency matrix
Figure 593993DEST_PATH_IMAGE038
First
Figure 461455DEST_PATH_IMAGE039
row,
Figure 859070DEST_PATH_IMAGE040
the elements in the column,
Figure 308637DEST_PATH_IMAGE041
represents the distance matrix
Figure 586034DEST_PATH_IMAGE042
First
Figure 499981DEST_PATH_IMAGE039
row,
Figure 904549DEST_PATH_IMAGE040
the elements in the column,
Figure 457890DEST_PATH_IMAGE043
represents the energy consumption of storing unit data,
Figure 656921DEST_PATH_IMAGE044
represents the sending mobile device
Figure 312024DEST_PATH_IMAGE029
the transmit power,
Figure 300709DEST_PATH_IMAGE045
represents the transmit antenna gain,
Figure 396972DEST_PATH_IMAGE046
represents the receiving antenna gain,
Figure 94801DEST_PATH_IMAGE047
represents the wavelength,
Figure 424151DEST_PATH_IMAGE048
represents the sending mobile device
Figure 701680DEST_PATH_IMAGE029
and the receiving mobile device
Figure 167296DEST_PATH_IMAGE036
the distance between,
Figure 36026DEST_PATH_IMAGE049
represents the propagation-independent system loss factor; 基于所述边缘协同存储模型和A2CS加速算法，提出边缘协同存储策略；Based on the edge collaborative storage model and the A2CS acceleration algorithm, an edge collaborative storage strategy is proposed; 以所述边缘协同存储策略指导所述边缘协同存储任务。The edge cooperative storage task is guided by the edge cooperative storage policy. 2.根据权利要求1所述的方法，其特征在于，所述建立移动设备间传输数据的边缘协同存储任务，包括：2. The method according to claim 1, wherein the establishing an edge cooperative storage task for transmitting data between mobile devices comprises: 所述移动设备收集数据；the mobile device collects data; 所述移动设备基于数据丢失概率
Figure 868984DEST_PATH_IMAGE050
和能耗
Figure 668313DEST_PATH_IMAGE051
将所述数据的副本发送至与所述移动设备相连的相邻移动设备，所述相邻移动设备至少有一个；The mobile device is based on data loss probability
Figure 868984DEST_PATH_IMAGE050
and energy consumption
Figure 668313DEST_PATH_IMAGE051
sending a copy of the data to adjacent mobile devices connected to the mobile device, at least one of the adjacent mobile devices; 所述移动设备集合
Figure 801485DEST_PATH_IMAGE052
基于所述相邻移动设备的存储容量和电池电量，确定所述副本的数量
Figure 309958DEST_PATH_IMAGE053
和接收所述副本的所述相邻移动设备。the set of mobile devices
Figure 801485DEST_PATH_IMAGE052
The number of replicas is determined based on the storage capacity and battery level of the neighboring mobile device
Figure 309958DEST_PATH_IMAGE053
and the neighboring mobile device that received the copy. 3.根据权利要求1所述的方法，其特征在于，所述移动设备集合
Figure 348321DEST_PATH_IMAGE052
被建模为
Figure 498811DEST_PATH_IMAGE054
，其中
Figure 220910DEST_PATH_IMAGE055
是第
Figure 165864DEST_PATH_IMAGE011
个所述移动设备，
Figure 222681DEST_PATH_IMAGE056
是边缘中的所述移动设备的总数。3. The method of claim 1, wherein the set of mobile devices
Figure 348321DEST_PATH_IMAGE052
is modeled as
Figure 498811DEST_PATH_IMAGE054
,in
Figure 220910DEST_PATH_IMAGE055
is the first
Figure 165864DEST_PATH_IMAGE011
said mobile device,
Figure 222681DEST_PATH_IMAGE056
is the total number of said mobile devices in the edge. 4.根据权利要求3所述的方法，其特征在于，所述第
Figure 114545DEST_PATH_IMAGE011
个所述移动设备
Figure 956730DEST_PATH_IMAGE055
被建模为
Figure 525115DEST_PATH_IMAGE057
，其中
Figure 339401DEST_PATH_IMAGE058
表示
Figure 18644DEST_PATH_IMAGE055
的存储容量，
Figure 980915DEST_PATH_IMAGE059
表示
Figure 2092DEST_PATH_IMAGE055
的电池电量，
Figure 236764DEST_PATH_IMAGE060
表示
Figure 736009DEST_PATH_IMAGE055
收集的数据量大小，
Figure 287208DEST_PATH_IMAGE061
表示
Figure 259712DEST_PATH_IMAGE055
收集的数据的数据副本数量，
Figure 529150DEST_PATH_IMAGE062
表示
Figure 300928DEST_PATH_IMAGE055
的数据传输速率，
Figure 487059DEST_PATH_IMAGE063
表示
Figure 318880DEST_PATH_IMAGE055
的数据接收速率。4. The method according to claim 3, wherein the first
Figure 114545DEST_PATH_IMAGE011
said mobile devices
Figure 956730DEST_PATH_IMAGE055
is modeled as
Figure 525115DEST_PATH_IMAGE057
,in
Figure 339401DEST_PATH_IMAGE058
express
Figure 18644DEST_PATH_IMAGE055
storage capacity,
Figure 980915DEST_PATH_IMAGE059
express
Figure 2092DEST_PATH_IMAGE055
battery power,
Figure 236764DEST_PATH_IMAGE060
express
Figure 736009DEST_PATH_IMAGE055
The amount of data collected,
Figure 287208DEST_PATH_IMAGE061
express
Figure 259712DEST_PATH_IMAGE055
the number of data copies of the collected data,
Figure 529150DEST_PATH_IMAGE062
express
Figure 300928DEST_PATH_IMAGE055
the data transfer rate,
Figure 487059DEST_PATH_IMAGE063
express
Figure 318880DEST_PATH_IMAGE055
data reception rate. 5.根据权利要求1所述的方法，其特征在于，所述网络拓扑
Figure 528144DEST_PATH_IMAGE064
被建模为
Figure 900351DEST_PATH_IMAGE065
，
Figure 691720DEST_PATH_IMAGE052
表示移动设备集合，
Figure 943710DEST_PATH_IMAGE066
表示邻接矩阵，
Figure 656582DEST_PATH_IMAGE067
表示距离矩阵，所述邻接矩阵
Figure 832480DEST_PATH_IMAGE068
包括：5. The method of claim 1, wherein the network topology
Figure 528144DEST_PATH_IMAGE064
is modeled as
Figure 900351DEST_PATH_IMAGE065
,
Figure 691720DEST_PATH_IMAGE052
represents a collection of mobile devices,
Figure 943710DEST_PATH_IMAGE066
represents the adjacency matrix,
Figure 656582DEST_PATH_IMAGE067
represents the distance matrix, the adjacency matrix
Figure 832480DEST_PATH_IMAGE068
include: 对于任意所述移动设备
Figure 665307DEST_PATH_IMAGE069
，与其他所述移动设备
Figure 635668DEST_PATH_IMAGE070
的连通性由邻接矩阵中的元素表示，
Figure 366995DEST_PATH_IMAGE071
表示所述邻接矩阵
Figure 64692DEST_PATH_IMAGE066
的第
Figure 565075DEST_PATH_IMAGE072
行、第
Figure 503075DEST_PATH_IMAGE073
列中的元素，它由以下表达式确定：for any of the mobile devices
Figure 665307DEST_PATH_IMAGE069
, with other described mobile devices
Figure 635668DEST_PATH_IMAGE070
The connectivity of is represented by the elements in the adjacency matrix,
Figure 366995DEST_PATH_IMAGE071
represents the adjacency matrix
Figure 64692DEST_PATH_IMAGE066
First
Figure 565075DEST_PATH_IMAGE072
row,
Figure 503075DEST_PATH_IMAGE073
The element in the column, which is determined by the following expression:
Figure 671100DEST_PATH_IMAGE074
Figure 671100DEST_PATH_IMAGE074
 所述距离矩阵
Figure 641330DEST_PATH_IMAGE067
包括：the distance matrix
Figure 641330DEST_PATH_IMAGE067
include: 对于任意所述移动设备
Figure 261798DEST_PATH_IMAGE075
，到其他所述移动设备
Figure 26492DEST_PATH_IMAGE076
的距离是所述距离矩阵中
Figure 935673DEST_PATH_IMAGE077
元素的值，
Figure 257064DEST_PATH_IMAGE078
代表所述距离矩阵
Figure 184569DEST_PATH_IMAGE077
的第
Figure 933213DEST_PATH_IMAGE079
行、第
Figure 126428DEST_PATH_IMAGE073
列中的元素，它由以下表达式确定：for any of the mobile devices
Figure 261798DEST_PATH_IMAGE075
, to the other said mobile device
Figure 26492DEST_PATH_IMAGE076
The distances are in the distance matrix
Figure 935673DEST_PATH_IMAGE077
the value of the element,
Figure 257064DEST_PATH_IMAGE078
represents the distance matrix
Figure 184569DEST_PATH_IMAGE077
First
Figure 933213DEST_PATH_IMAGE079
row,
Figure 126428DEST_PATH_IMAGE073
The element in the column, which is determined by the following expression:
Figure 438461DEST_PATH_IMAGE080
Figure 438461DEST_PATH_IMAGE080
 其中
Figure 33521DEST_PATH_IMAGE081
表示
Figure 890750DEST_PATH_IMAGE082
和
Figure 758212DEST_PATH_IMAGE083
之间的距离。in
Figure 33521DEST_PATH_IMAGE081
express
Figure 890750DEST_PATH_IMAGE082
and
Figure 758212DEST_PATH_IMAGE083
the distance between. 6.根据权利要求1所述的方法，其特征在于，所述发送移动设备
Figure 155826DEST_PATH_IMAGE084
和接收移动设备
Figure 339814DEST_PATH_IMAGE085
组成收发移动设备组
Figure 679529DEST_PATH_IMAGE086
，所述发送移动设备
Figure 581757DEST_PATH_IMAGE084
和接收移动设备
Figure 720745DEST_PATH_IMAGE085
之间进行数据存储和数据传输，所述数据存储产生数据存储能耗
Figure 539665DEST_PATH_IMAGE087
，所述
Figure 738697DEST_PATH_IMAGE087
表述为6. The method of claim 1, wherein the sending mobile device
Figure 155826DEST_PATH_IMAGE084
and receiving mobile devices
Figure 339814DEST_PATH_IMAGE085
Form sending and receiving mobile device groups
Figure 679529DEST_PATH_IMAGE086
, the sending mobile device
Figure 581757DEST_PATH_IMAGE084
and receiving mobile devices
Figure 720745DEST_PATH_IMAGE085
Data storage and data transmission are performed between the data storage and the data storage energy consumption.
Figure 539665DEST_PATH_IMAGE087
, the
Figure 738697DEST_PATH_IMAGE087
expressed as
Figure 128221DEST_PATH_IMAGE088
Figure 128221DEST_PATH_IMAGE088
 其中，
Figure 585747DEST_PATH_IMAGE089
表示当
Figure 744327DEST_PATH_IMAGE090
时从所述发送移动设备
Figure 363527DEST_PATH_IMAGE084
传输到接收移动设备
Figure 771506DEST_PATH_IMAGE085
的数据量大小，以及当
Figure 302895DEST_PATH_IMAGE091
时所述发送移动设备
Figure 519244DEST_PATH_IMAGE084
存储的数据量大小，
Figure 371662DEST_PATH_IMAGE092
表示上述组
Figure 673462DEST_PATH_IMAGE093
中数据存储的能耗；in,
Figure 585747DEST_PATH_IMAGE089
means when
Figure 744327DEST_PATH_IMAGE090
when sending from the mobile device
Figure 363527DEST_PATH_IMAGE084
Transmission to the receiving mobile device
Figure 771506DEST_PATH_IMAGE085
size of data, and when
Figure 302895DEST_PATH_IMAGE091
when the sending mobile device
Figure 519244DEST_PATH_IMAGE084
The amount of data stored,
Figure 371662DEST_PATH_IMAGE092
represents the above group
Figure 673462DEST_PATH_IMAGE093
energy consumption of data storage in 所述数据传输产生数据传输能耗
Figure 285840DEST_PATH_IMAGE094
，所述
Figure 402700DEST_PATH_IMAGE094
表述为The data transmission generates data transmission energy consumption
Figure 285840DEST_PATH_IMAGE094
, the
Figure 402700DEST_PATH_IMAGE094
expressed as
Figure 114436DEST_PATH_IMAGE095
Figure 114436DEST_PATH_IMAGE095
 其中
Figure 231427DEST_PATH_IMAGE096
表示接收移动设备
Figure 116338DEST_PATH_IMAGE085
的接收功率，
Figure 353284DEST_PATH_IMAGE097
表示数据从所述发送移动设备
Figure 501500DEST_PATH_IMAGE084
传输至所述接收移动设备
Figure 27159DEST_PATH_IMAGE085
所花费的时间，
Figure 981340DEST_PATH_IMAGE098
表示所述接收移动设备
Figure 761208DEST_PATH_IMAGE085
接收所述发送移动设备
Figure 126330DEST_PATH_IMAGE084
发送的数据所花费的时间，in
Figure 231427DEST_PATH_IMAGE096
Indicates the receiving mobile device
Figure 116338DEST_PATH_IMAGE085
the received power,
Figure 353284DEST_PATH_IMAGE097
Indicates that data is sent from the mobile device
Figure 501500DEST_PATH_IMAGE084
transmitted to the receiving mobile device
Figure 27159DEST_PATH_IMAGE085
time spent,
Figure 981340DEST_PATH_IMAGE098
represents the receiving mobile device
Figure 761208DEST_PATH_IMAGE085
receiving the sending mobile device
Figure 126330DEST_PATH_IMAGE084
the time it took to send the data, 所述数据存储能耗
Figure 890018DEST_PATH_IMAGE087
和所述数据传输能耗
Figure 382310DEST_PATH_IMAGE094
之和为边缘协同存储的总能耗
Figure 531532DEST_PATH_IMAGE099
，所述总能耗
Figure 818288DEST_PATH_IMAGE099
表述为The data storage energy consumption
Figure 890018DEST_PATH_IMAGE087
and the data transmission energy consumption
Figure 382310DEST_PATH_IMAGE094
The sum is the total energy consumption of edge collaborative storage
Figure 531532DEST_PATH_IMAGE099
, the total energy consumption
Figure 818288DEST_PATH_IMAGE099
expressed as
Figure 318539DEST_PATH_IMAGE100
。
Figure 318539DEST_PATH_IMAGE100
. 7.根据权利要求1所述的方法，其特征在于，所述边缘协同存储策略包括以下步骤：数据收集、请求分发、做出决策、决策反馈、多次交互和数据传输。7. The method according to claim 1, wherein the edge cooperative storage strategy comprises the following steps: data collection, request distribution, decision making, decision feedback, multiple interactions, and data transmission. 8.一种协同移动设备的边缘存储加速装置，其特征在于，包括：8. An edge storage acceleration device for collaborative mobile equipment, characterized in that it comprises: 第一建立模块，被配置为建立移动设备间传输数据的边缘协同存储任务；a first establishment module, configured to establish an edge cooperative storage task for data transmission between mobile devices; 第二建立模块，被配置为基于所述边缘协同存储任务建立边缘协同存储模型，所述边缘协同存储模型包括：移动设备集合
Figure 817785DEST_PATH_IMAGE101
、发送移动设备
Figure 634562DEST_PATH_IMAGE084
、接收移动设备
Figure 544750DEST_PATH_IMAGE085
和网络拓扑
Figure 814188DEST_PATH_IMAGE102
，所述移动设备集合
Figure 100813DEST_PATH_IMAGE101
包括至少两个移动设备；The second establishment module is configured to establish an edge cooperative storage model based on the edge cooperative storage task, where the edge cooperative storage model includes: a set of mobile devices
Figure 817785DEST_PATH_IMAGE101
, send mobile device
Figure 634562DEST_PATH_IMAGE084
, receiving mobile device
Figure 544750DEST_PATH_IMAGE085
and network topology
Figure 814188DEST_PATH_IMAGE102
, the mobile device collection
Figure 100813DEST_PATH_IMAGE101
Include at least two mobile devices; 计算模块，被配置为基于所述边缘协同存储模型计算得到A2CS加速算法，所述A2CS加速算法包括：The computing module is configured to calculate and obtain an A2CS acceleration algorithm based on the edge collaborative storage model, and the A2CS acceleration algorithm includes: 初始值
Figure 65157DEST_PATH_IMAGE103
、
Figure 693716DEST_PATH_IMAGE104
和
Figure 902980DEST_PATH_IMAGE105
，所述初始值表示对任意一个移动设备
Figure 540766DEST_PATH_IMAGE106
部署所述A2CS加速算法的初始数值，所述初始值表述为initial value
Figure 65157DEST_PATH_IMAGE103
,
Figure 693716DEST_PATH_IMAGE104
and
Figure 902980DEST_PATH_IMAGE105
, the initial value indicates that for any mobile device
Figure 540766DEST_PATH_IMAGE106
Deploy the initial value of the A2CS acceleration algorithm, the initial value is expressed as
Figure 784666DEST_PATH_IMAGE107
Figure 784666DEST_PATH_IMAGE107
 其中
Figure 787388DEST_PATH_IMAGE108
表示与所述
Figure 31418DEST_PATH_IMAGE106
连接的移动设备的数量，
Figure 191004DEST_PATH_IMAGE109
表示
Figure 836880DEST_PATH_IMAGE108
维向量；in
Figure 787388DEST_PATH_IMAGE108
expressed with the stated
Figure 31418DEST_PATH_IMAGE106
the number of connected mobile devices,
Figure 191004DEST_PATH_IMAGE109
express
Figure 836880DEST_PATH_IMAGE108
dimensional vector; 停止准则，所述停止准则使所述A2CS加速算法获得可行解并确保所述A2CS加速算法快速收敛，所述停止准则表述为A stopping criterion that enables the A2CS acceleration algorithm to obtain a feasible solution and ensures rapid convergence of the A2CS acceleration algorithm, and the stopping criterion is expressed as
Figure 10504DEST_PATH_IMAGE110
Figure 10504DEST_PATH_IMAGE110
 其中
Figure 725519DEST_PATH_IMAGE111
表示第
Figure 908370DEST_PATH_IMAGE112
次迭代时的原始残差，
Figure 408752DEST_PATH_IMAGE113
表示第
Figure 64862DEST_PATH_IMAGE112
次迭代时的对偶残差，
Figure 221168DEST_PATH_IMAGE114
表示绝对公差，
Figure 738868DEST_PATH_IMAGE115
表示相对公差；in
Figure 725519DEST_PATH_IMAGE111
means the first
Figure 908370DEST_PATH_IMAGE112
the original residual at the next iteration,
Figure 408752DEST_PATH_IMAGE113
means the first
Figure 64862DEST_PATH_IMAGE112
dual residuals at the next iteration,
Figure 221168DEST_PATH_IMAGE114
represents the absolute tolerance,
Figure 738868DEST_PATH_IMAGE115
Indicates relative tolerance; 优化函数
Figure 811866DEST_PATH_IMAGE020
，用于描述所述边缘协同存储任务的总效用，所述优化函数表述为optimization function
Figure 811866DEST_PATH_IMAGE020
, used to describe the total utility of the edge cooperative storage task, and the optimization function is expressed as
Figure 592871DEST_PATH_IMAGE116
Figure 592871DEST_PATH_IMAGE116
 其中
Figure 751320DEST_PATH_IMAGE022
和
Figure 807132DEST_PATH_IMAGE023
是权重系数，
Figure 734637DEST_PATH_IMAGE024
表示由发送移动设备
Figure 420964DEST_PATH_IMAGE117
收集的数据量的大小，
Figure 348600DEST_PATH_IMAGE024
和
Figure 457370DEST_PATH_IMAGE026
之间的关系可以描述为
Figure 786852DEST_PATH_IMAGE027
，
Figure 429099DEST_PATH_IMAGE028
表示所述发送移动设备
Figure 296561DEST_PATH_IMAGE029
收集的数据的数据副本数量，
Figure 163017DEST_PATH_IMAGE030
表示数据丢失量，
Figure 65114DEST_PATH_IMAGE031
表示数据存储的总能耗，
Figure 155561DEST_PATH_IMAGE032
表示发送移动设备
Figure 261051DEST_PATH_IMAGE033
的数据丢失概率，
Figure 711624DEST_PATH_IMAGE034
表示所述发送移动设备
Figure 953381DEST_PATH_IMAGE029
的数据传输速率，
Figure 932838DEST_PATH_IMAGE035
表示所述接收移动设备
Figure 56783DEST_PATH_IMAGE036
的数据接收速率，
Figure 61779DEST_PATH_IMAGE037
表示邻接矩阵
Figure 672889DEST_PATH_IMAGE038
的第
Figure 449346DEST_PATH_IMAGE039
行、第
Figure 513117DEST_PATH_IMAGE040
列中的元素，
Figure 321805DEST_PATH_IMAGE041
表示距离矩阵
Figure 803733DEST_PATH_IMAGE042
的第
Figure 593834DEST_PATH_IMAGE039
行、第
Figure 692371DEST_PATH_IMAGE040
列中的元素，
Figure 835908DEST_PATH_IMAGE043
表示存储单位数据的能耗，
Figure 188654DEST_PATH_IMAGE044
表示所述发送移动设备
Figure 211974DEST_PATH_IMAGE029
的发射功率，
Figure 809526DEST_PATH_IMAGE045
表示发射天线增益，
Figure 507485DEST_PATH_IMAGE046
表示接收天线增益，
Figure 291902DEST_PATH_IMAGE047
表示波长，
Figure 423806DEST_PATH_IMAGE048
表示所述发送移动设备
Figure 824831DEST_PATH_IMAGE029
和所述接收移动设备
Figure 247854DEST_PATH_IMAGE036
之间的距离，
Figure 355618DEST_PATH_IMAGE049
表示与传播无关的系统损耗因子；in
Figure 751320DEST_PATH_IMAGE022
and
Figure 807132DEST_PATH_IMAGE023
is the weight coefficient,
Figure 734637DEST_PATH_IMAGE024
Indicates that the mobile device is sent by
Figure 420964DEST_PATH_IMAGE117
the size of the amount of data collected,
Figure 348600DEST_PATH_IMAGE024
and
Figure 457370DEST_PATH_IMAGE026
The relationship between can be described as
Figure 786852DEST_PATH_IMAGE027
,
Figure 429099DEST_PATH_IMAGE028
represents the sending mobile device
Figure 296561DEST_PATH_IMAGE029
the number of data copies of the collected data,
Figure 163017DEST_PATH_IMAGE030
represents the amount of data loss,
Figure 65114DEST_PATH_IMAGE031
represents the total energy consumption of data storage,
Figure 155561DEST_PATH_IMAGE032
Indicates sending mobile device
Figure 261051DEST_PATH_IMAGE033
the probability of data loss,
Figure 711624DEST_PATH_IMAGE034
represents the sending mobile device
Figure 953381DEST_PATH_IMAGE029
the data transfer rate,
Figure 932838DEST_PATH_IMAGE035
represents the receiving mobile device
Figure 56783DEST_PATH_IMAGE036
the data reception rate,
Figure 61779DEST_PATH_IMAGE037
represents the adjacency matrix
Figure 672889DEST_PATH_IMAGE038
First
Figure 449346DEST_PATH_IMAGE039
row,
Figure 513117DEST_PATH_IMAGE040
the elements in the column,
Figure 321805DEST_PATH_IMAGE041
represents the distance matrix
Figure 803733DEST_PATH_IMAGE042
First
Figure 593834DEST_PATH_IMAGE039
row,
Figure 692371DEST_PATH_IMAGE040
the elements in the column,
Figure 835908DEST_PATH_IMAGE043
represents the energy consumption of storing unit data,
Figure 188654DEST_PATH_IMAGE044
represents the sending mobile device
Figure 211974DEST_PATH_IMAGE029
the transmit power,
Figure 809526DEST_PATH_IMAGE045
represents the transmit antenna gain,
Figure 507485DEST_PATH_IMAGE046
represents the receiving antenna gain,
Figure 291902DEST_PATH_IMAGE047
represents the wavelength,
Figure 423806DEST_PATH_IMAGE048
represents the sending mobile device
Figure 824831DEST_PATH_IMAGE029
and the receiving mobile device
Figure 247854DEST_PATH_IMAGE036
the distance between,
Figure 355618DEST_PATH_IMAGE049
represents the propagation-independent system loss factor; 策略模块，被配置为基于所述边缘协同存储模型和A2CS加速算法，提出边缘协同存储策略；a strategy module, configured to propose an edge collaborative storage strategy based on the edge collaborative storage model and the A2CS acceleration algorithm; 执行模块，被配置为以所述边缘协同存储策略指导所述边缘协同存储任务。An execution module configured to direct the edge cooperative storage task with the edge cooperative storage policy. 9.一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其特征在于，所述处理器执行所述程序时实现如权利要求1至7任意一项所述的方法。9. An electronic device, comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor implements any one of claims 1 to 7 when the processor executes the program method described in item.
CN202010252903.4A 2020-04-02 2020-04-02 A kind of edge storage acceleration method, device and device for collaborative mobile device Active CN111158612B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010252903.4A CN111158612B (en) 2020-04-02 2020-04-02 A kind of edge storage acceleration method, device and device for collaborative mobile device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010252903.4A CN111158612B (en) 2020-04-02 2020-04-02 A kind of edge storage acceleration method, device and device for collaborative mobile device

Publications (2)

Publication Number Publication Date
CN111158612A CN111158612A (en) 2020-05-15
CN111158612B true CN111158612B (en) 2020-07-24

Family

ID=70567659

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010252903.4A Active CN111158612B (en) 2020-04-02 2020-04-02 A kind of edge storage acceleration method, device and device for collaborative mobile device

Country Status (1)

Country Link
CN (1) CN111158612B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116776162B (en) * 2023-03-10 2025-12-16 中国人民解放军国防科技大学 Topology sequence time difference solving method considering communication delay

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110830520A (en) * 2020-01-13 2020-02-21 中国人民解放军国防科技大学 A robust and reliable edge storage method and system for the Internet of Things

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005157712A (en) * 2003-11-26 2005-06-16 Hitachi Ltd Remote copy network
WO2013076757A1 (en) * 2011-11-22 2013-05-30 Hitachi, Ltd. Storage system, storage apparatus and method of controlling storage system
CN104573119B (en) * 2015-02-05 2017-10-27 重庆大学 Towards the Hadoop distributed file system storage methods of energy-conservation in cloud computing
CN107370802A (en) * 2017-07-10 2017-11-21 中国人民解放军国防科学技术大学 A kind of collaboration storage dispatching method based on alternating direction multiplier method
CN108121511B (en) * 2017-12-21 2022-05-27 北京猫盘技术有限公司 Data processing method, device and equipment in distributed edge storage system
CN110471621B (en) * 2019-07-29 2020-12-29 东南大学 An edge collaborative storage method for real-time data processing applications
CN110443298B (en) * 2019-07-31 2022-02-15 华中科技大学 A DDNN based on cloud-edge collaborative computing and its construction method and application
CN110430266B (en) * 2019-08-06 2021-07-13 腾讯科技（深圳）有限公司 Edge cloud cooperative data transmission method, device, equipment and storage medium

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110830520A (en) * 2020-01-13 2020-02-21 中国人民解放军国防科技大学 A robust and reliable edge storage method and system for the Internet of Things

Also Published As

Publication number Publication date
CN111158612A (en) 2020-05-15

Similar Documents

Publication Publication Date Title
Xu et al. Adaptive computation offloading with edge for 5G-envisioned internet of connected vehicles
Abd Elaziz et al. IoT workflow scheduling using intelligent arithmetic optimization algorithm in fog computing
Zhu et al. BLOT: Bandit learning-based offloading of tasks in fog-enabled networks
Luo et al. Stability of cloud-based UAV systems supporting big data acquisition and processing
CN112911618B (en) A task offload scheduling method for drone server based on resource exit scenario
CN112291793A (en) Resource allocation method and device of network access equipment
CN107172166A (en) The cloud and mist computing system serviced towards industrial intelligentization
Khani et al. Deep reinforcement learning‐based resource allocation in multi‐access edge computing
CN114007231A (en) Heterogeneous unmanned aerial vehicle data unloading method and device, electronic equipment and storage medium
Li et al. Resource scheduling based on improved spectral clustering algorithm in edge computing
Qureshi et al. Asynchronous federated learning for resource allocation in software-defined internet of UAVs
CN111158612B (en) A kind of edge storage acceleration method, device and device for collaborative mobile device
Wei et al. Resource allocation scheduling scheme for task migration and offloading in 6G Cybertwin internet of vehicles based on DRL
CN117336789A (en) An energy-efficient video computing offloading optimization method, device and related equipment
CN114884957B (en) Method and device for unloading computing tasks in air-space-ground network and electronic equipment
CN111343602A (en) Joint layout and task scheduling optimization method based on evolutionary algorithm
CN114281527A (en) A low-complexity mobile edge computing resource allocation method
CN120166422A (en) Model task processing method, device, communication equipment, readable storage medium and program product
Li et al. A novel approach for computation offloading based on a parallel collaborative genetic algorithm in MEC
Zhu et al. Research on fog resource scheduling based on cloud-fog collaboration technology in the electric internet of things
CN111541781B (en) Distributed cooperative task scheduling method for mobile equipment in dense network
Deb et al. Loop-the-loops: Fragmented learning over networks for constrained IoT devices
Wang et al. Deep learning-driven differentiated traffic scheduling in cloud-iot data center networks
CN116996907A (en) Data processing methods, devices, equipment and computer-readable storage media
Xu et al. Enhancing fog computing through intelligent reflecting surface assistance: A Lyapunov driven reinforcement learning approach

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant