CN111263303A - A method for self-organization and cooperation of fog nodes based on mobile IP - Google Patents

Abstract

The invention provides a fog node self-organizing cooperation method based on mobile IP, which comprises that a working fog node sends a node information frame to a management fog node at the beginning and the end of working or at regular intervals to update a routing table; the management fog nodes carry out task distribution decision according to task conditions, and a working domain is constructed by combining a plurality of working fog nodes according to requirements after receiving the tasks; the management fog node monitors the position of the mobile terminal after constructing a working domain, and after the mobile terminal leaves a subnet, the management fog node requests a care-of address to the management fog node newly entering the subnet and registers the care-of address to a local agent; after the task is finished, the local agent releases the occupation of the work fog node, releases the work domain and recovers the IP allocated for the mobile terminal. The method provided by the invention enables the nodes participating in the fog calculation to form a distributed calculation platform in real time, adapts to the change of the working load in time and reduces the calculation time delay; and the cloud node working domain group with dynamically variable topology is realized, and extensible computing resources are provided for the terminal.

Description

A method for self-organization and cooperation of fog nodes based on mobile IP

technical field

The invention relates to the field of communication technologies, in particular to a method for self-organization and cooperation of fog nodes based on mobile IP.

Background technique

In recent years, with the rapid development of the Internet of Things, emerging service models such as smart cities and smart homes are gradually entering people's lives. With the wide application of smart sensing devices and smart terminals, the amount of data generated and the demand for mobile computing have grown exponentially. Therefore, offloading some tasks of cloud computing to near user terminals for processing, while meeting the task time requirements, fog computing that reduces the overall operating cost is gradually becoming a popular solution. Fog computing can extend the cloud computing paradigm to the network edge and has broad application prospects in IoT services. Fog computing can effectively improve the data processing capability of the system, reduce the task load of cloud data centers, and provide storage, computing and communication services for terminals. Under the existing fog computing architecture, if the computing task exceeds the processing capacity of the fog node, it will be sent to the cloud data center for computing. However, the cloud computing big data analysis process has some shortcomings, such as high delay, long periodicity, and high network energy consumption. In the face of intensive mobile computing tasks, if it is directly delivered to the cloud server for processing, limited by the network connection and bandwidth, it will inevitably increase the communication overhead and prolong the delivery time of the task. If the fog node ad hoc network can be realized, and the working domain of the distributed computing system is composed of adjacent nodes with sufficient computing resources, it can cope with such computing tasks to a certain extent and effectively reduce the system overhead. In addition, in the application scenario of mobile computing covered by Wi-Fi, when the terminal device enters the coverage of another subnet from one subnet with the movement of the user, the original network connection needs to be disconnected due to the change of the gateway. Communication can be continued only after the IP address of the new subnet is re-acquired, which affects the delivery of mobile computing tasks to a certain extent. In the mobile computing scenario, the cross-domain delivery problem caused by terminal movement after the work domain is formed still needs to be solved.

SUMMARY OF THE INVENTION

The embodiments of the present invention provide a method for self-organization and cooperation of fog nodes based on mobile IP, which is used to solve the problem of realizing cooperation among multiple idle fog nodes and form a distributed system with stronger computing power to cope with mobile computing. The technical problem of providing real-time, energy-saving network services for terminal mobile users for computationally intensive tasks in scenarios.

In order to achieve the above objects, the present invention adopts the following technical solutions.

A method for self-organization and cooperation of fog nodes based on mobile IP, comprising:

The management fog node receives the node information frame sent by the working fog node for updating the routing table;

The management fog node receives the task request sent by the mobile terminal and evaluates the required computing resources of the task request based on the routing table, and obtains the evaluation result;

The management fog node determines whether to accept the task request based on the evaluation result; if the management fog node accepts the task request, the management fog node assigns a temporary IP of the work domain to the mobile terminal, receives the task data from the mobile terminal, and sends an occupation request to the work fog node;

The management fog node receives the confirmation information of the working fog node and starts the task processing;

Manage fog nodes to complete task processing and release the occupation of working fog nodes.

Preferably, the management fog node receives the task request sent by the mobile terminal and evaluates the required computing resources of the task request based on the routing table, and obtaining the evaluation result includes:

获得任务处理的总耗时

by formula

Get the total time spent processing the task

为每个子任务q_i的运算耗时，Q_task为管理雾节点的总计算量，d(e_i,j)为管理雾节点和/或工作雾节点g_i与g_j间的通信时延，c_i,j表示管理雾节点和/或工作雾节点g_i与g_j在任务计算期间是否存在通信关系，若不存在通信关系，则有c_i,j＝0；(2); in the formula, _ri is the computing power of each management fog node and working fog node,

is the operation time of each subtask qi, Q _task is the total calculation amount of the management fog node, d(e _{i ,j} ) is the communication delay between the management fog node and/or the working fog nodes g _i and g _j , c _i,j indicates whether there is a communication relationship between the management fog node and/or the working fog nodes _gi and g _j during the task calculation, if there is no communication relationship, then c _i,j =0;

Convert based on formula (2) to obtain question Q1

Based on question Q1, convert formula (2) to formula

Convert question Q1 to question Q2 based on formula (3)

Solve the problem Q1 and Q2, and obtain: a set C of management fog nodes and/or working fog nodes participating in task processing, a task assignment phasor Q, and an optimal set C ^* of management fog nodes and/or working fog nodes participating in task processing , the task processing shortest processing time T _min .

Preferably, the management fog node determines whether to accept the task request based on the evaluation result; if the management fog node accepts the task request, the management fog node allocates a temporary IP of the work domain to the mobile terminal, receives the task data from the mobile terminal, and sends the occupation to the work fog node. The request includes:

(4)获得分流决策D；by formula

(4) Obtaining the diversion decision D;

When the diversion decision D=0, the management fog node rejects the task request and sends the task request to the cloud computing center;

When the diversion decision D=1, the management fog node receives the task request;

In formula (4), τ _max represents the maximum delay that can be tolerated in the task processing process.

Preferably, in the step of the management fog node receiving the node information frame for updating the routing table sent by the working fog node, the node information frame includes frame identification, idle identification, node ID, node computing power, link cost and reserved bits. The table is used to record the IP address, occupancy status, link cost and computing capability of the management fog node of the working fog node connected to the pipeline fog node.

Preferably, the management fog node receives the confirmation information of the working fog node, and starting the task processing includes:

The management fog node receives the confirmation information sent by the working fog node;

Manage fog nodes to broadcast the algorithms and computing engines required for the task processing;

The management fog node starts task processing.

Preferably, it also includes:

When the location of the mobile terminal changes, the management fog node monitors whether the mobile terminal crosses the communication range;

When the mobile terminal crosses the communication range, the management fog node sends proxy request information to the external agent, the management fog node receives the address sent by the external agent, and the management fog node sends a task request to the external agent.

It can be seen from the technical solutions provided by the above embodiments of the present invention that the present invention provides a method for self-organization and cooperation of fog nodes based on mobile IP, which is a protocol for cooperative communication between fog nodes, and adopts mobile IP to solve the problem of mobile terminal computing. Cross-domain problems in the process; the work fog node sends node information frames to the management fog node at the beginning, end of work or every certain period T to update the routing table; the management fog node makes task distribution decisions according to the task situation, and after accepting the task, If necessary, combine multiple working fog nodes to build a working domain; after the management fog node (local agent) builds the working domain, it monitors the location of the mobile terminal. After the mobile terminal leaves the subnet, it requests handover to the management fog node (foreign agent) that has newly entered the subnet. address and register with the local agent. After the computing task ends, the local agent releases the occupation of the work fog node, releases the work domain, and reclaims the IP allocated for the mobile terminal. The method provided by the invention enables nodes participating in fog computing to form a distributed computing platform in real time, adapts to changes in workload in time, and reduces computing delay; realizes a fog node work domain group with dynamically variable topology, and provides terminals with Scalable computing resources.

Additional aspects and advantages of the present invention will be set forth in part in the following description, which will be apparent from the following description, or may be learned by practice of the present invention.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

FIG. 1 is a process flow diagram of a method for self-organized cooperation of fog nodes based on Mobile IP provided by the present invention;

FIG. 2 is a system frame diagram of a method for self-organization and cooperation of fog nodes based on Mobile IP provided by the present invention;

3 is a schematic diagram of a node information frame format of a method for self-organization and cooperation of fog nodes based on Mobile IP provided by the present invention;

Fig. 4 is a fog computing network topology diagram of a method for self-organization and cooperation of fog nodes based on mobile IP provided by the present invention;

FIG. 5 is a flow chart of another embodiment of a method for ad hoc cooperation of fog nodes based on Mobile IP provided by the present invention.

Detailed ways

Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but not to be construed as a limitation of the present invention.

It will be understood by those skilled in the art that the singular forms "a", "an", "the" and "the" as used herein can include the plural forms as well, unless expressly stated otherwise. It should be further understood that the word "comprising" used in the description of the present invention refers to the presence of stated features, integers, steps, operations, elements and/or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components and/or groups thereof. It will be understood that when we refer to an element as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Furthermore, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and, unless defined as herein, are not to be taken in an idealized or overly formal sense. explain.

In order to facilitate the understanding of the embodiments of the present invention, the following will take several specific embodiments as examples for further explanation and description in conjunction with the accompanying drawings, and each embodiment does not constitute a limitation to the embodiments of the present invention.

Referring to FIG. 1 , the present invention provides a method for self-organization and cooperation of fog nodes based on mobile IP, which performs real-time evaluation of available computing resources and link cost on idle fog nodes in a network segment, and makes statistics on remaining available computing resources in a timely manner; According to the computational complexity and data volume of the received task, an appropriate number of fog nodes are allocated to form a work domain; this method mainly includes two parts: node condition feedback and work domain construction, including:

The management fog node receives the node information frame sent by the working fog node for updating the routing table;

The management fog node receives the task request sent by the mobile terminal and evaluates the required computing resources of the task request based on the routing table, and obtains the evaluation result;

The management fog node determines whether to accept the task request based on the evaluation result; if the management fog node accepts the task request, the management fog node assigns a temporary IP of the work domain to the mobile terminal, receives the task data from the mobile terminal, and sends an occupation request to the work fog node;

The management fog node receives the confirmation information of the working fog node and starts the task processing;

Manage fog nodes to complete task processing and release the occupation of working fog nodes.

In the embodiment provided by the present invention, the types of fog nodes include:

Working Fog Node (WN): A node that provides computing resources and implements computing tasks, is connected to the management fog node, and can be used as a network access point for mobile terminals. It has certain computing power, data sending and receiving ability, data storage ability and network communication ability, communicates with the management fog node, and reports the available computing resources and communication link of the node. The working fog node can be either an idle node with computing capability, or a communication node that the mobile terminal accesses the network;

Fog node management (MN): It is used to organize and coordinate working fog nodes to form a working domain, and monitor the working status and connectivity of fog nodes within a certain range. The management fog node comprehensively evaluates the size of the received task calculation, the load of the working fog node, and the communication between the nodes, and decides that the task should be calculated locally or sent to the cloud computing center.

As shown in Figure 2, in this fog node self-organization cooperation framework, a management fog node and multiple working fog nodes form a work domain, namely a subnet; as shown in the figure, the whole framework includes multiple subnets, each Each subnet communicates with the cloud platform, and its management fog nodes are connected to each other; the working fog nodes regularly report the remaining computing resources to the management fog nodes and the communication delay with the management fog nodes. When a mobile terminal (ME) sends a task request to form a work domain, the work domain will configure a temporary IP for the terminal to avoid communication interruption due to terminal movement; each subnet is composed of a network with computing resources and algorithm pools. The fog node cluster is formed, and the mobile terminal (ME) sends task requests to the management fog nodes in this subnet. In the temporarily formed work domain, the work fog nodes are responsible for providing computing resources and undertaking computing work. Subnets are connected to the Internet through routers and to commercial and computing platforms.

In the embodiment provided by the present invention, the node information frame is responsible for sending the available computing resources of the node and dynamically updating the route to the management fog node. Because it does not contain other data information, the amount of data in a single packet is very small, thereby reducing the need for updating node information. Occupy bandwidth;

As shown in Figure 3, the size of the information frame is 2 bytes. Except for 4 bits used as reserved bits, the meanings of the remaining bits are as follows:

Frame identification (F): used to identify the type of the current frame, used to distinguish information frames from other types of frames. In the protocol, 1 bit is taken, that is, 1 is a beacon frame, and 0 is other frames.

Idle flag (V): Indicates whether the current node is occupied, 1 bit, where 0 indicates that the node is idle, and 1 indicates that the node is occupied.

Node ID (Node ID): as its own address. This bit can be dynamically adjusted according to the number of nodes in the network. In this method, the node ID is set to 6 bits, that is, a maximum of 64 nodes are supported;

Node computing power (C): represents the computing power of the current node relative to the management fog node, 4 bits, the first bit represents the relative computing power of the management fog node, 0 indicates that the node computing power is weaker than the management fog node, 1 indicates that the computing power is stronger than the management fog node. If the first digit is 0, the last three digits represent binary decimals, that is, the minimum representable node computing capability is 1/8 of the management fog node, the first digit is 1, the last three digits represent binary integers, and the maximum representable node computing capability is the management fog node. 7 times;

Link cost (Expected transmission expense, ETX): record the size of the data transmission cost between the sending node and the sink node. Because the work fog node and the management fog node that constitute the work domain are directly connected or limited within a certain number of hops, the work The packet loss rate between the fog node and the management is negligible, and the delay is taken as the link cost, which is set to 16 bits.

In the embodiment provided by the present invention, each management fog node maintains a routing table to record the IP address, occupancy status, corresponding link cost, and computing capability of the corresponding node of the working fog node connected to it. The cost refers to the transmission cost between the management fog node and the transit node. The node ID and the corresponding ETX value initialization value in the routing table are -1 and Inf respectively;

The routing table is sorted according to the link cost of available nodes from low to high, that is, the node with the smallest transmission cost is the preferred node, and the rest are candidate nodes. The order and number of nodes constituting the work domain can be adjusted according to actual needs. If the computing task requires a small delay and the task requires a small amount of computation, nodes can be selected according to the link cost; if the computing-intensive task requires sufficient delay, The work domain can be constructed by comprehensively considering the link cost and node computing power.

Further, the fog node cooperation architecture of the present invention is shown in FIG. 3 , the working fog nodes in the network need to regularly report the current remaining computing resources and the communication delay with the management fog node to the management fog node. When a mobile terminal (ME) sends a task request to form a work domain, the work domain will configure a temporary IP for the terminal to avoid communication interruption due to terminal movement; each subnet is composed of a network with computing resources and algorithm pools. There are two types of fog nodes: management fog nodes (MN) and working fog nodes (WN). The mobile terminal (ME) sends a task request to the management fog node in this subnet. In the temporarily formed work domain, the work fog node is responsible for providing computing resources and undertaking computing work. Subnets are connected to the Internet through routers and to commercial and computing platforms.

The above-mentioned management fog node receives the task request sent by the mobile terminal and evaluates the required computing resources of the task request based on the routing table, and the step of obtaining the evaluation result includes the following process:

In the scenario of mobile computing tasks, consider a fog computing network composed of k fog nodes (g ₁ ,...,g _k ). Since the calculation result needs to be sent by the management fog node to the mobile terminal, it is recorded as the cluster center as g ₁ . The fog node is abstracted into a weighted undirected graph G=(V,E), where V={g ₁ ,...,g _k } is the vertex set, E={e _1,2 ,...,e _k-1,k } is the edge set, the edge e _{k-1, k} represents the communication link between the vertex g _k-1 and g _k , the weight of the edge represents the communication delay between the nodes; Figure 4 represents the abstract undirected graph ( Topology);

The specific sub-steps are: set the computing capability of each fog node to be r _i ;

After receiving the task, the management node configures the work fog nodes that constitute the work domain according to the amount of computation required by the task;

并将其分配给工作域内各个节点进行计算；After the potential work domain is formed, the management node divides the target task with the calculation amount of Q _task into several sub-tasks _qi that satisfy distributed computing.

And assign it to each node in the work domain for calculation;

Based on this, the time-consuming of the entire work domain in processing task E can be expressed as

表示子任务q_i的运算耗时，d(e_i,j)表示节点g_i与g_j间的通信时延，c_i,j表示节点g_i与g_j在任务计算期间是否存在通信关系，若两节点间不存在通信关系，则有c_i,j＝0；根据分布式计算特点可知，任务的计算时延为所有子任务中最大的计算时延，因此该问题转化为问题Q1：求一组最优节点集合，使得任务完成时延最小；(2), where

represents the operation time of subtask qi, d(e _{i ,j} ) represents the communication delay between nodes _gi and g _j , _ci,j represents whether there is a communication relationship between nodes _gi and g _j during the task calculation, If there is no communication relationship between the two nodes, c _i,j = 0; according to the characteristics of distributed computing, the computing delay of the task is the largest computing delay among all subtasks, so the problem is transformed into the problem Q1: find A set of optimal node sets to minimize task completion delay;

其中Θ表示实际参与工作域构成的雾节点；可将任务在雾计算网络中的处理时间T表示为The k-dimensional vector Q=[q ₁ ,q ₂ ,...,q _k ] ^T is formed by the calculation subtasks that k fog nodes should handle. Not all fog nodes in the factor network participate in the composition of the work domain, so there are some nodes allocated The case where the subtask is 0, that is

where Θ represents the fog nodes that actually participate in the work domain; the processing time T of the task in the fog computing network can be expressed as

The original problem is transformed into Q2, that is, to solve the node set C participating in the calculation and the task allocation vector Q;

Using the discrete particle swarm algorithm to solve the above problem, a set of optimal nodes participating in the task C ^* and the optimal task assignment vector Q ^* can be obtained, and the shortest processing time T _min of the task can be calculated, that is, the evaluation result.

Further, the above-mentioned management fog node determines whether to accept the task request based on the evaluation result; if the management fog node accepts the task request, the management fog node assigns a temporary IP of the work domain to the mobile terminal, receives the task data from the mobile terminal, and sends the task request to the work fog. The process of sending an occupation request by a node includes the following steps:

After obtaining the optimal set of participating task nodes and the optimal task allocation vector, the management fog node obtains the task distribution decision D from the following formula to determine whether to accept the computing task;

Among them, τ _max represents the maximum delay that the task can tolerate, the offloading decision D=0 means that the task requirements cannot be met, and the task is forwarded to the cloud computing center for processing, and the offloading decision D=1 represents that the task requirements can be met, and then the work domain is formed. Tasks are split according to C ^* occupied job fog nodes and according to Q ^* .

Further, in some preferred embodiments, the above-mentioned management fog node receives the confirmation information of the working fog node, and the starting task processing includes:

The management fog node receives the confirmation information sent by the working fog node;

Manage fog nodes to broadcast the algorithms and computing engines required for the task processing;

Manage fog nodes to start task processing;

Further, it also includes the following follow-up process:

When the location of the mobile terminal changes, the management fog node monitors whether the mobile terminal crosses the communication range;

When the mobile terminal crosses the communication range, the management fog node sends proxy request information to the external agent, the management fog node receives the address sent by the external agent, and the management fog node sends a task request to the external agent.

The present invention also provides an embodiment for exemplarily showing the self-organizing collaboration process provided by the present invention. The method provided by the present invention is based on the premise of meeting the computing requirements of tasks, and the basic requirements are to reduce the delivery delay and to be efficient; The node initiates an occupation application, and the candidate work fog nodes then build a distributed computing work domain according to the management fog node requirements; each work domain includes:

To manage fog nodes, in the entire work domain construction process, the management fog node first needs to evaluate the received task, and the management fog node evaluates the computing resources required to complete the task, and according to the work fog node in its routing table can provide. The resource accepts or rejects the task's request. If this task is accepted, an occupation request is sent to the working fog node according to the available computing resources and network conditions, and the task algorithm is broadcast in the working domain, and the computing engine is selected; the control node can communicate with other control nodes to grasp the location of the mobile terminal and send the task result. If the task is rejected, send it to the cloud computing center for processing;

The work fog node, after receiving the work domain construction request, the work fog node sets the idle flag (V) in the node information frame to 1 to indicate that it is occupied, preventing the node from participating in multiple work domains at the same time. The work fog node allocates core computing power and memory resources to the virtual machine and runs the Spark platform, and calls the corresponding algorithm from the local algorithm pool according to the needs of the task;

As shown in Figure 5, the process is as follows:

Every period T, the working fog node sends a node information frame to the management fog node to inform its own information, and initiates a round of routing update process, and the management fog node updates the routing table after receiving the node information frame sent by other nodes;

After receiving the task request from the mobile terminal, the node forwards it to the management fog node, and the management fog node evaluates the computing resources required for the task. If it is rejected, it will be sent to the cloud computing center. If it is accepted, it will assign a fixed IP of the work domain to the mobile terminal and receive the task. data and send occupancy requests to the working fog nodes;

After the working fog node receives the occupancy request, it sets the idle flag (V) in the node information frame to 1 to indicate that it is occupied, and sends confirmation information to the management fog node;

After the management fog node confirms that the required work fog node is in place, it broadcasts the algorithm and computing engine required for the task in the work domain that constitutes the distributed computing system, and starts task processing;

In the calculation process, once the location of the mobile terminal changes, the management fog node monitors whether it crosses the range of the subnet, and updates its communication link in time. If the mobile terminal goes out of the subnet range, it will send a "proxy request" to the foreign agent, after obtaining the care-of address, it will send a "registration request" to the home agent and wait for a "response message";

After receiving the "registration request" from the mobile terminal, the home agent updates the routing table and returns the "response request";

After the calculation, the home agent sends the result to the mobile terminal according to the care-of address through the tunnel, and the tunnel output end unpacks the received data packet and forwards it to the mobile terminal;

After the transmission is completed, the management fog node acts as the home agent, releases the tunnel and releases the working domain, and releases the occupation of the working fog node.

In this embodiment, in the scenario of multiple mobile sensors or mobile terminal data, it is the same as the general network data transmission protocol. That is, a queue is maintained in the management fog node cache, and all task requests are queued in the queue for processing in a first-in, first-out order. If the queue overflows, newly arrived tasks are discarded. Return ACK information after accepting the task to assign a fixed IP. In addition, to avoid channel congestion, the data transmission process supports the CSMA/CA protocol.

To sum up, the present invention provides a method for self-organization and cooperation of fog nodes based on mobile IP, which is used to solve the problem that the computing resources that a single fog node can provide is limited, and when the computing task increases, it is difficult for a single working fog node to achieve the task. In the existing fog computing architecture, if it is difficult for a single fog node to meet the computing requirements, the task will be offloaded to the cloud computing data center for execution; the method provided by the present invention is aimed at the cooperation between fog nodes. The communication protocol adopts mobile IP to solve the cross-domain problem of the mobile terminal in the calculation process; the working fog node sends node information frames to the management fog node at the beginning, end of work or every certain period T to update the routing table; the management fog node According to the task situation, the task distribution decision is made. After accepting the task, according to the needs, combine multiple work fog nodes to build a work domain; after the management fog node (local agent) builds the work domain, it monitors the location of the mobile terminal. After the mobile terminal leaves the subnet, the new entry The subnet's managing fog node (foreign agent) requests a care-of address and registers with the home agent. After the computing task ends, the local agent releases the occupation of the work fog node, releases the work domain, and reclaims the IP allocated for the mobile terminal. The method provided by the invention enables nodes participating in fog computing to form a distributed computing platform in real time, adapts to changes in workload in time, and reduces computing delay; realizes a fog node work domain group with dynamically variable topology, and provides terminals with Scalable computing resources.

Those of ordinary skill in the art can understand that the accompanying drawing is only a schematic diagram of an embodiment, and the modules or processes in the accompanying drawing are not necessarily necessary to implement the present invention.

From the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art. The computer software products can be stored in storage media, such as ROM/RAM, magnetic disks, etc. , CD, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the apparatus or system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for related parts. The apparatus and system embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, It can be located in one place, or it can be distributed over multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited to this. Substitutions should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims (6)

1. a method for self-organized cooperation of fog nodes based on mobile IP, is characterized in that, comprising: The management fog node receives the node information frame sent by the working fog node for updating the routing table; The management fog node receives the task request sent by the mobile terminal and evaluates the required computing resources of the task request based on the routing table, and obtains the evaluation result; The management fog node determines whether to accept the task request based on the evaluation result; if the management fog node accepts the task request, the management fog node assigns a temporary IP of the work domain to the mobile terminal, receives the task data from the mobile terminal, and sends an occupation request to the work fog node; The management fog node receives the confirmation information of the working fog node and starts the task processing; Manage fog nodes to complete task processing and release the occupation of working fog nodes. 2. The method according to claim 1, wherein the management fog node receives the task request sent by the mobile terminal and evaluates the required computing resources of the task request based on the routing table, and obtaining the evaluation result comprises: by formula

Get the total time spent processing the task

where _ri is the computing power of each management fog node and working fog node,

is the operation time of each subtask qi, Q _task is the total calculation amount of the management fog node, d(e _{i ,j} ) is the communication delay between the management fog node and/or the working fog nodes g _i and g _j , c _i,j indicates whether there is a communication relationship between the management fog node and/or the working fog nodes _gi and g _j during the task calculation, if there is no communication relationship, then c _i,j =0; Convert based on formula (2) to obtain question Q1

Based on question Q1, convert formula (2) to formula

Convert question Q1 to question Q2 based on formula (3) P=arg min[T(Q,C)] stc _i ,j∈{0,1},i,j∈K

Solve the problem Q1 and Q2, and obtain: a set C of management fog nodes and/or working fog nodes participating in task processing, a task assignment phasor Q, and an optimal set C ^* of management fog nodes and/or working fog nodes participating in task processing , the task processing shortest processing time T _min . 3. The method according to claim 2, wherein the management fog node judges whether to accept the task request based on the evaluation result; if the management fog node accepts the task request, the management fog node assigns a temporary IP of the work domain to the mobile terminal , receive task data from the mobile terminal, and send an occupation request to the work fog node including: by formula

Obtain the triage decision D; When the diversion decision D=0, the management fog node rejects the task request and sends the task request to the cloud computing center; When the diversion decision D=1, the management fog node receives the task request; In formula (4), τ _max represents the maximum delay that can be tolerated in the task processing process. 4. The method according to any one of claims 1 to 3, wherein in the step of the management fog node receiving a node information frame for updating a routing table sent by a working fog node, the node information frame includes Frame identification, idle identification, node ID, node computing power, link cost and reserved bits, the routing table is used to record the IP address, occupancy, link cost and This manages the computing power of the fog nodes. 5. The method according to any one of claims 1 to 3, wherein the management fog node receives the confirmation information of the working fog node, and starting the task processing comprises: The management fog node receives the confirmation information sent by the working fog node; Manage fog nodes to broadcast the algorithms and computing engines required for the task processing; The management fog node starts task processing. 6. The method of claim 5, further comprising: When the location of the mobile terminal changes, the management fog node monitors whether the mobile terminal crosses the communication range; When the mobile terminal crosses the communication range, the management fog node sends proxy request information to the external agent, the management fog node receives the address sent by the external agent, and the management fog node sends a task request to the external agent.

Images