WO2018153357A1

WO2018153357A1 - Application instance relocation

Info

Publication number: WO2018153357A1
Application number: PCT/CN2018/077135
Authority: WO
Inventors: David Huo
Original assignee: ZTE Corp
Current assignee: ZTE Corp
Priority date: 2017-02-24
Filing date: 2018-02-24
Publication date: 2018-08-30
Anticipated expiration: 2019-08-24

Abstract

Techniques for relocating an application instance include a preparation phase in which an image of an application instance at a source mobile edge host is prepared by making, at a predetermined timing, a complete copy of the application instance to be transmitted to a target mobile edge host, and an adaptation phase in which a difference between a current application instance and the complete copy that was previously transmitted is measured and whether to switch bearers is decided. The method may further include a switch phase in which, upon making the decision to switch, the application instance is relocated. A seamless mobile computing experience may be achieved using the described techniques.

Description

APPLICATION INSTANCE RELOCATION

CROSS REFERENCE TO RELATED APPLICATIONS

This patent application claims the benefit of priority of U.S. Provisional Patent Application No. 62/463,527, filed on February 24, 2017. The entire content of the before-mentioned patent application is incorporated by reference as part of the disclosure of this application.

TECHNICAL FIELD

This document relates to mobile computing.

BACKGROUND

Efforts are currently underway to define next generation communication networks that provide greater deployment flexibility, support for a multitude of devices and services and different technologies for efficient bandwidth utilization.

SUMMARY

This document describes technologies, among other things, providing seamless application instance relocation in mobile communication networks.

In one example aspect, a method of relocating an application instance is disclosed. The method includes a preparation phase in which an image of an application instance at a source mobile edge host is prepared by making, at a predetermined timing, a complete copy of the application instance to be transmitted to a target mobile edge host, and an adaptation phase in which a difference between a current application instance and the complete copy that was previously transmitted is measured and whether to switch bearers is decided. The method may further include a switch phase in which, upon making the decision to switch, the application instance is relocated.

In another example aspect, an apparatus for relocating an application instance is disclosed. The apparatus includes a memory, a processor and a network interface, wherein the memory stores processor-executable instructions and the processor is enabled to read the instructions from the memory and implement a method of relocating an application instance between mobile edge hosts (MEHs) using the network interface for communication with other network entities. The method includes a preparation phase in which an image of an application instance at a source mobile edge host is prepared by making, at a predetermined timing, a complete copy of the application instance to be transmitted to a target mobile edge host, and an adaptation phase in which a difference between a current application instance and the complete copy that was previously transmitted is measured and whether to switch bearers is decided.

In another example aspect, a communication system that implements application instance relocation techniques is disclosed. The communication system includes a network including one or more mobile edge hosts, and a computer platform. The computer platform implements a preparation phase in which an image of the application instance at a source mobile edge host is prepared by making a complete copy of the application instance for transmission to a target mobile edge host, and implements an adaptation phase in which a difference between a current application instance and the complete copy that was previously transmitted is measured and a decision is made to switch bearers.

The details of one or more implementations are set forth in the accompanying attachments, the drawings, and the description below. Other features will be apparent from the description and drawings, and from the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 shows three basic scenarios for application instance relocation (AIR) .

FIG. 2 shows an example method of creating virtual machine (VM) overlay from base VM.

FIG. 3 is a flowchart showing an example method of implementing a procedure for application instance relocation.

FIG. 4 is a flowchart showing an example application instance relocation method.

FIG. 5 shows entities involved in application instance relocation (AIR) from source mobile edge host (S_MEH) to target mobile edge host (T_MEH) .

FIG. 6 shows dynamics of data amount transmitted from source mobile edge host (S_MEH) to target mobile edge host (T_MEH) during AIR.

FIG. 7 shows an example for consecutive segmented transmission of instance data in AIR.

FIG. 8A shows scenarios of attach point changes from source attach point (S_AtP) to target attach point (T_AtP) , and FIG. 8B shows scenarios of unchanged attach point (AtP) .

FIG. 9 shows an example of software architecture in the virtual infrastructure.

FIG. 10 is a block diagram showing an example of an apparatus used to implement a disclosed technique.

FIG. 11 is a block diagram of an example communication system.

Like reference symbols in the various drawings indicate like elements.

DETAILED DESCRIPTION

For the next generation 5G systems, architectures for new services and new devices are continually evolving. One feature offered by these architectures is to simultaneously connect through multiple interfaces for variety of radio technologies such as Wi-Fi, 4G, 5G sub 6 GHz and 5G high band or mmwave. Various industry standards organizations are in the process of specifying network architecture and device functionality for next generation networks (NextGen) , which are expected to be deployed in near future and be used for many years thereafter. Therefore, it would be beneficial to specify and deploy techniques that are future-proof and meet the challenges not just in near term but many years down the road also.

Examples of next generation network architectures include Edge Computing (EC) , which enables cloud computing capabilities at edge layers of the network. The EC attempts to leverages the storage and processing capacities of the edge layers between end devices and data centers by handling some of the requests directed to the data centers at the edge layers. Example implementations of the EC include Mobile Edge Computing (MEC) and Cloudlet Computing (CC) . In these environments, a virtualized application may be migrated between mobile edge hosts (MEHs) , which are entities that contain the mobile edge platform and a virtualization infrastructure which provides compute, storage, and network resources for the mobile edge applications. The virtualization infrastructure includes a data plane that executes the traffic rules received by the mobile edge platform, and routes the traffic among applications, services, DNS server/proxy, cellular network, local networks and external networks.

In many situations, there is a need to migrate a virtualized application between mobile edge hosts (MEHs) without service interruption. One of those situations is given by Use Case 4.3 (mission critical low latency critical application) of MEC0018. Since user mobility in mobile systems is inevitable, when a user equipment (UE) moves in a mobile network, the mobile edge host that runs the application which serves the UE can change. At this point, the application can react to such handover events by application-specific means, or the mobile edge system relocates the application instance serving the UE to the target host. Reducing the relocation failure rate will be the key to improving the quality of experience (QoE) .

There is a subtle trade-off between service continuity and quality of service during the application instance relocation. Any technical solution that handles an application instance relocation (AIR) should minimize the degradation of user experience while maximizing the service continuity. Software technologies known today to solve this problem focus often on the software migration aspect. Deploying those technologies in conjunction with the connectivity provider will provide a full solution under the MEC specific circumstance. Various embodiments of the disclosed technology provide solutions for the application instance relocation that can minimize service interruption.

FIG. 1 shows three basic scenarios for application instance relocation (AIR) . Depending on the capability of a user equipment (UE) and the application involved, there are three basic scenarios for AIR within a mobile edge (ME) system. The first scenario concerns AIR from a source mobile edge host S_MEH to a target mobile edge host T_MEH. This is the scenario where the majority of the resource consumed by the application instance is located on the MEH side, e.g. via server-client relation. The second scenario concerns AIR from UE to a source mobile edge host S_MEH and to a target mobile edge host T_MEH. This is the scenario where the resource consumed by the application is distributed in UE and MEH, e.g. via peer to peer relation. The third scenario concerns AIR from UE to the target mobile edge host T_MEH. This is the scenario where the majority of the resource consumed by the application instance is on the UE. Various embodiments of the disclosed technology are applicable to the first scenario. The same technique can be applied to the second and third scenarios with appropriate additional procedures.

FIG. 2 shows an example method of creating virtual machine (VM) overlay from base VM. A mobile device delivers a VM overlay to a cloudlet that already possesses a base VM from which this overlay was derived. Here, the delivery can form either the cloud or the storage on the mobile device. The cloudlet decompresses the overlay, applies it to the base to derive a launch VM, and then creates a VM instance from it to perform offload operations on this instance. This example applies to the second and third scenarios, but lacks UE mobility aspect, in particular, when UE is resource limited. Various embodiments of the disclosed technology may concern the ME system specific issues, while making use of the available software technology. In an example embodiment, the first scenario may be used as a basic scheme to serve a rather broader spectrum of scenarios.

There are some assumptions made in relation to various implementations of the disclosed technology. First, an application is implemented in the MEH virtually on a cloudlet or a cloud. Second, a live migration of the application is to be performed with minim service interruption. Third, a connection between the source mobile edge host S_MEH and the target mobile edge host T_MEH is provided with limited capacity. Fourth, a mobile edge platform (MEP) is in the position to coordinate code, data and environment (CDE) for the migration. Fifth, AIR procedure is triggered so that the source mobile edge host S_MEH and the target mobile edge host T_MEH know each other.

A low service continuity can be provided by the technique of state information transfer between MEHs, in particular when assistance of connectivity provider network (CPN) is available. With the same technique, however, high service continuity is much harder to achieve. Hence more complicated technologies are needed for provisioning of high service continuity. Generally speaking, an application instance relocation (AIR) is in the position to support high service continuity, when some quality of service (QoS) degradation is tolerable. To achieve AIR, software specific algorithms as well as cooperation with CPN are necessary.

Various embodiments of the disclosed technology described here assume standard network interfaces of the CPN and availability of CPN information through MEC specific means, such Radio Network Information Service (RNIS) . However, the disclosed technology is not limited thereto, and thus various implementations may be made available independently of CPN.

In some networks, when UE moves out of the coverage of the MEH, computer capability in the MEH may be insufficient for certain applications, and power supply in the MEH may be under stress. The CPN may also have problem to provide connectivity to the MEH. Various embodiments of the disclosed technology may minimize such potential problems.

According to an example MEC architecture, a mobile edge orchestrator (MEO) works with virtualization infrastructure (VI) to accomplish on-boarding, installing and maintaining the applications running on virtual machines hosted by the MEH. This software environment is referred to as “data plane” as service provided by the virtualization infrastructure hosted by the MEH. The application instances are carried by the data plane. Hence, capability of the data plane can be measured by computing speed, storage space, communications capacity and dependency scope. An application instance relocation (AIR) implies moving information regarding these from one MEH to another MEH, i.e. image migration between clouds or cloudlets. This can take place at different levels of the software architecture, for example, via OS migration, VIM migration or application migration.

In implementing a live migration, VM synthesis, App virtualization, and VM handoff may be used. Data segments are selected based on application specific criteria and host specific environment. This is software intensive work and is subject to the virtualization infrastructure of the host system. In an implementation of the disclosed technology, selective packaging, including compression and encryption, and scheduled transmission can be deployed to further reduce the latency and enhance customer experience, and a data transport can be made adaptive to the transport capacity and resource sharing policy. As this is application specific and host specific, it should be controlled and coordinated by MEP.

FIG. 3 is a flowchart for a method 300 for application instance relocation. In order to enable AIR, MEP performs a plurality of steps. At 302, images may be generated with respect to the application instance. At 304, necessary AIR data may be prepared. At 306, proper scheduler may be enabled for the data transmission, and iterative delta data transmission may be provided to achieve state synchronization. At 308, the application instance may be encapsulated to a VIM that is adequate for migration. At 310, static information and dynamic information related to the instance may be separated. At 312, the data segments may be packaged to be transmitted, with appropriate compression and encryption. At 314, transmission at the source mobile edge host S_MEH and unpacking and installation at the target mobile edge host T_MEH may be scheduled. At 316, URL for resources that are available at centralized location may be provided. At 318, the application state and transport channel may be monitored to allow for adaptive packaging, scheduling, configuration and synchronization. At 320, switch decision may be made based on multiple factors, e.g. instance transfer progress, transmission resource status and target service quality, etc. One issue not explicitly discussed here is the MEH discovery procedure, and it can take place either through CPN’s assistance via the RNIS or on service level mechanism via a hyper text transfer protocol (HTTP) server implemented on designated network entity.

FIG. 4 is a flowchart for a method 400 for application instance relocation. At 402, the method 100 includes a preparation phase. At 404, the method 400 includes an adaptation phase. At 406, the method 400 includes a switching phase.

In the preparation phase, some processes are performed to prepare for graceful transmission of instance data from the source mobile edge host S_MEH to the target mobile edge host T_MEH. The major challenge in this phase is to maximal transmission speed under minimal bandwidth usage. In the adaptation phase, synchronization of state information is performed between the source mobile edge host S_MEH and the target mobile edge host T_MEH. The completion of this phase can be subject to many criteria, and the MEC operator decides which criterion is the best for the given circumstance. In the switching phase, an old bearer release and a new bearer establishment may be carried out in an optimal way and at an optimal time point. This phase may be omitted if the UE’s access point to the CPN does not need to change for the AIR.

FIG. 5 shows entities involved in application instance relocation (AIR) from the source mobile edge host S_MEH to the target mobile edge host T_MEH. At any given time during the live migration, there are two application instances that must be relocated from the source mobile edge host S_MEH to the target mobile edge host T_MEH:

A (x) = A _s (t) +A _t (t) Eq. (1)

where A_s (t) refers to the data associated with the instance running at the source mobile edge host S_MEH, and A_s (t) refers to the instance to be installed and running at the target mobile edge host T_MEH. At the end of the instance relocation, A_s (t) will be removed and A_t (t) will be initiated and running at the target mobile edge host T_MEH.

In the preparation phase, the image of the application instance at the source mobile edge host S_MEH is copied and transmitted to the target mobile edge host T_MEH. Depending on applications and virtualized environment, the duration of the preparation phase may vary. During this phase, UE is connected to the source mobile edge host S_MEH via the same channel provided by CPN. At the end of this phase, a temporary complete copy of the application instance at that time is installed and ready to run at the target mobile edge host T_MEH.

In contrast, the duration of the adaptation phase can be determined. The duration is either predefined, e.g., via a timer, or through an adaptive decision process, e.g., through a process in which the difference of the transmitted image and the current instance is measured as delta data D (t) =|A_t (t) -A_s (t) |. In the adaptation phase, a decision to switch the MEH is made based on whether D (t) is under a given threshold or not. At the end of this phase, a decision for switching MEH is made, UE starts to maintain a single channel with mobile edge systems via CPN.

In the switching phase, UE is connected to the target mobile edge host T_MEH only, but data transmission and related signaling between the source mobile edge host S_MEH and the target mobile edge host T_MEH have not been finished yet. Final copy is to be completed at the target mobile edge host T_MEH and the copy at the source mobile edge host S_MEH needs to be cleaned up.

To reduce the total latency, mobile edge platform (MEP) , mobile edge platform manager (MEPM) and connectivity provider network (CPN) cooperate with each other, so that a single CPN channel between UE and the source mobile edge host S_MEH is present during the preparation phase, two simultaneous CPN channels are present during the adaptation phase and a single CPN channel between UE and the target mobile edge host T_MEH is established.

Because of the displacement of the source mobile edge host S_MEH and the target mobile edge host T_MEH and the time needed for transmission data from the source mobile edge host S_MEH to the target mobile edge host T_MEH, it is difficult to obtain complete identical copies. Hence, the operational goal is to achieve maximal synchronization of two copies of the application instance. The final switch decision is made with awareness that quality degradation is tolerated or accepted.

FIG. 6 shows dynamics of data amount transmitted from the source mobile edge host S_MEH to the target mobile edge host T_MEH during AIR. The difference between images on the data plane of the target mobile edge host T_MEH and that on the data plane of the source mobile edge host S_MEH is not zero during the preparation phase and can still be larger than zero in the adaptation phase. Even in the switching phase, there can be artefacts due to CPN issues (route change, channel quality, handover failure, etc. ) . Hence, QoS degradation is expected during the entire process of AIR.

In the preparation phase, segmentation, packaging and scheduling may be performed. FIG. 7 shows an example for consecutive segmented transmission of instance data in AIR. As a first step of the preparation phase, the application is divided into pieces in terms of instance resource, given as data in appropriate format:

where i refers to data segment and k refers to application instance.

Under this circumstance, the information contained in A_ (i, k) is compressed to E_ (i, k) , so that:

E _i, k＜A _i, k Eq. (3)

and encrypted for the protection, before transmission.

The application is transferred or isolated, i.e. relocated within the MEH, to a VIM of appropriate size, so that:

CDE _i-1 <E _i, k≤ CDE _i=V _i, k Eq. (4)

Transport channel between the target mobile edge host T_MEH and the source mobile edge host S_MEH has the capacity C, and is shared by n VIMs (or application instances) , so that:

where assignment of capacity to each application instance is assured by a scheduler on the source mobile edge host S_MEH. The allocated capacity C (i, k) to segment I of application instance k leads to a latency:

Here, Equation (6) indicates the latency of the i-th segment of k-th VIM, i.e. Vi, k, excluding the processing time on both end.

To satisfy the latency requirements of all the application instances being relocated, the scheduler at the transmitter side, should be aware of all the applications being involved in live migration at any given time. That means it is necessary for MEP, to configure and control by scheduler and packaging, assisted by MEPM and MEO, so that:

for all k=1, 2, …, and m, where L_k is the accumulated latency budget for application instance k.

In the adaptation phase, a complete copy of the application instance image is transmitted from the source mobile edge host S_MEH to the target mobile edge host T_MEH. This basic copy is also kept by the source mobile edge host S_MEH, referred to as A_0. Then, a timer is set and when the time expires a new copy A_i of the instance is made, from which delta data D=|A_i-A_0| is determined.

If D is larger than a given threshold, then D is transmitted to the target mobile edge host T_MEH. Then, the same timer is reset. The delta data is used to update the installed image. When D is smaller than the given threshold, then host switch command is sent to the target mobile edge host T_MEH, which, on receiving the command, requests CPN to establish the new bearer and release the old bearer, if applicable, and starts to serve the client of the transferred application instance and send a confirmation to the source mobile edge host S_MEH. Next, a transition to the switching phase takes place.

In the switching phase, MEC is concerned primarily with the procedure of switching the role of serving entity from the source mobile edge host S_MEH to the target mobile edge host T_MEH for the client UE. The responsibility for connectivity between MEH and UE lies with CPN. In implementing the disclosed technology, there are some scenarios that the UE is connected to the application server. First, the UE releases the old bearer and establishes the new bearer, without changing IP address. Second, the UE releases the old bearer and establishes the new bearer, while changing the IP address. Third, the UE maintains the same single bearer and IP address. Fourth, the UE maintains the same single bearer, but changes IP address.

In addition, regardless of the bearer status, the UE can also be served with multiple IP addresses, all pointing to the same server that is relocated from the source mobile edge host S_MEH to the target mobile edge host T_MEH. Given that complexity, at this stage of MEC development, only the switching of MEH with respect to the same CPN at the same attach point, both for the source mobile edge host S_MEH and the target mobile edge host T_MEH, or at the different attach points, one for the source S_MEH and the other for the target mobile edge host T_MEH is discussed here, under the presumption that UE connectivity is provided by CPN, with a certain measurable provision time.

FIG. 8A shows scenarios of attach point changes from a source attach point S_AtP to a target attach point T_AtP. The target mobile edge host T_MEH uses the topology information obtained from MEHM to find the IP address of the target attach point T_AtP. The target mobile edge host T_MEH contacts the target attach point T_AtP and starts the mutual authentication and authorization protocols. The target mobile edge host T_MEH sets up a secure connection between the target mobile edge host T_MEH and CPN at the target attach point T_AtP. On receiving a “switch command” from the source mobile edge host S_MEH, the target mobile edge host T_MEH sends a “bearer establishment” request to CPN at the target attach point T_AtP and wait for confirmation. On receiving a “bearer establishment” confirmation from CPN at the target attach point T_AtP, the target mobile edge host T_MEH starts to send application data to UE via the target attach point T_AtP. When the first transmission is acknowledged by the UE, the target mobile edge host T_MEH sends “switch confirmation” to the source mobile edge host S_MEH, so that this release the connection to a source attach point S_AtP.

FIG. 8B shows scenarios of unchanged attach point (AtP) . The target mobile edge host T_MEH contacts the attach point AtP, using its IP address, which is obtained from the source mobile edge host S_MEH before AIR, to start mutual authentication and authorization protocols. Unless this fails, the operation continues. The target mobile edge host T_MEH sets up a secure connection between the target mobile edge host T_MEH and CPN at the attach point AtP. Upon receiving a “switch command” from the source mobile edge host S_MEH, the target mobile edge host T_MEH starts to send application data to the UE via the attach point AtP. When the first transmission is acknowledged by the UE, the target mobile edge host T_MEH sends “switch confirmation” to the source mobile edge host S_MEH, which then release the connection to the attach point AtP.

During AIR, data plane at the MEH exchanges information with the peer entity. The information includes static part of the instance image via direct data transmission or passing ULR pointer, dependency information via direct data transmission or passing URL pointer, and rules and polices via direct data transmission or passing URL pointer. In case ULR is transferred, the pointed server constitutes an ME system entity that has a clearly defined function, such as service continuity manger (SCM) .

FIG. 9 shows an example of software architecture in the virtual infrastructure. On the transmission side (i.e., the source mobile edge host S_MEH) , compression, encryption, VIM adaption and scheduled transmission of the VIM are needed. At the receiving side (i.e., the target mobile edge host T_MEH) , decompression, decryption, VIM re-adaptation, and reassemble of segment are needed. General requirement on MEH includes coordination by MEP between application and data plane, whenever application instance handover is identified, control of migration procedure via MEO to assure resources are available and applicable, enforce necessary actions, e.g. adaptive compression and encryption, depending on application and transport capacity, and perform scheduling, with application aware priority setting. This implies a need for a MEC specific transport interface between MEH data planes.

Table 1 shows an impact of different aspect of the live migration on different layers of the virtual infrastructure:

Success of AIR depends on data volume, processing speed, compression ratio, transport bandwidth and tolerable quality degradation. How to balance those factors is a decision to be made by the MEC operator based on customer expectation, operation budget and maintenance complexity.

FIG. 10 is a block diagram of an example communication apparatus 1000. The apparatus 1000 may include one or more memories 1002, one or more processors 1004 and a network interface front end 1006 that is coupled with a communication link 1008. The memory 1002 may store processor-executable instructions and/or data during processor operation. The processor 1004 may read instructions from the one or memories 1002 and implement a technique described in the present document. The apparatus 1000 may implement various methods (e.g., the method 400) described herein.

FIG. 11 is a block diagram of an example communication system 1100. The communication system 1100 includes a network 1102 including one or more mobile edge hosts 1104, and a computer platform 1106. For example, the computer platform may be similar to the apparatus 1000. The computer platform 1106 implements a preparation phase in which an image of the application instance at a source mobile edge host is prepared by making a complete copy of the application instance for transmission to a target mobile edge host, and implements an adaptation phase in which a difference between a current application instance and the complete copy that was previously transmitted is measured and a decision is made to switch bearers. In some embodiments, the decision regarding switching the bearer is based on an absolute value of a difference between data associated with an instance running at the source mobile edge host and data associated with an instance to be installed and running at the target mobile edge host. For example, the absolute value of the difference is above the threshold, a host switch command is sent to the target mobile edge host and a request is sent to a connectivity provider network to establish a new bearer and release an old bearer. In some embodiments, the computer platform may be configured to implement a switch phase as described in the present document.

In an embodiment of the disclosed technology, a method of relocating an application instance between mobile edge hosts (MEHs) may include a preparation phase in which an image of an application instance at a source mobile edge host is prepared by making, at a predetermined timing, a complete copy of the application instance to be transmitted to a target mobile edge host, and an adaptation phase in which a difference between a current application instance and the complete copy that was previously transmitted is measured and whether to switch bearers is decided. The method of relocating an application instance between MEHs may further include a switch phase in which, upon making the decision to switch, the application instance is relocated.

Here, the preparation phase may further include, for example, encapsulating the application instance to a virtualized infrastructure manager that is adequate for migration, separating static information and dynamic information related to the application instance, and selecting data segments based on application specific criteria and host specific environment and packaging the data segments to be transmitted with appropriate compression and encryption.

The complete copy is kept by the source mobile edge host to compare the difference between the current application instance and the previously transmitted complete copy. In the adaptation phase, whether to switch bearers is decided based on delta data is larger than a threshold. The delta data is an absolute value of a difference between data associated with an instance running at the source mobile edge host and data associated with an instance to be installed and running at the target mobile edge host. When the delta data is above the threshold, a host switch command is sent to the target mobile edge host and a request is sent to a connectivity provider network to establish a new bearer and release an old bearer. When the delta data is below the threshold, the delta data is transmitted to the target mobile edge host.

In the switch phase, upon making the decision to switch, the application instance is relocated. The switch phase may include completing a copy of the application at the target mobile edge host, and cleaning up the complete copy at the source mobile edge host. In the switch phase, a connectivity of a user equipment with mobile edge hosts is provided by a connectivity provider network at the same attach point for the source mobile edge host and the target mobile edge host. In the switch phase, a connectivity of a user equipment with mobile edge hosts is provided by a connectivity provider network at different attach points for the source mobile edge host and the target mobile edge host.

In another embodiment of the disclosed technology, an apparatus comprising a memory, a processor and a network interface, wherein the memory stores processor-executable instructions and the processor is enabled to read the instructions from the memory and implement a method of relocating an application instance between mobile edge hosts (MEHs) using the network interface for communication with other network entities. The method may include the preparation phase, the adaptation phase, and switch phase discussed above.

It will be appreciated that technologies, among other things, for application instance relocation have been disclosed. The disclosed techniques can be used in a mobile computing framework for achieving seamless mobility of computing devices.

The disclosed and other embodiments, modules and the functional operations described in this document can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this document and their structural equivalents, or in combinations of one or more of them. The disclosed and other embodiments can be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a computer readable medium for execution by, or to control the operation of, data processing apparatus. The computer readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter effecting a machine-readable propagated signal, or a combination of one or more them. The term “data processing apparatus” encompasses all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. The apparatus can include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them. A propagated signal is an artificially generated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode information for transmission to suitable receiver apparatus.

A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document) , in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code) . A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

The processes and logic flows described in this document can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit) .

Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read only memory or a random access memory or both. The essential elements of a computer are a processor for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks. However, a computer need not have such devices. Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto optical disks; and CD ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

While this document contains many specifics, these should not be construed as limitations on the scope of an invention that is claimed or of what may be claimed, but rather as descriptions of features specific to particular embodiments. Certain features that are described in this document in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a sub-combination or a variation of a sub-combination. Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results.

Only a few examples and implementations are disclosed. Variations, modifications, and enhancements to the described examples and implementations and other implementations can be made based on what is disclosed.

Claims

A method of relocating an application instance, including

implementing a preparation phase in which an image of the application instance at a source mobile edge host is prepared by making a complete copy of the application instance for transmission to a target mobile edge host; and

implementing an adaptation phase in which a difference between a current application instance and the complete copy that was previously transmitted is measured and a decision is made to switch bearers.
The method of claim 1, wherein the complete copy is kept by the source mobile edge host to compare the difference between the current application instance and the previously transmitted complete copy.
The method of claim 1, wherein whether to switch bearers is decided based on an absolute value of a difference between data associated with an instance running at the source mobile edge host and data associated with an instance to be installed and running at the target mobile edge host.
The method of claim 3, wherein, when the absolute value of the difference is above the threshold, a host switch command is sent to the target mobile edge host and a request is sent to a connectivity provider network to establish a new bearer and release an old bearer.
The method of claim 1, further including:

a switch phase in which, upon making the decision to switch, the application instance is relocated.
The method of claim 5, wherein the switch phase includes:

completing a copy of the application at the target mobile edge host; and

cleaning up the complete copy at the source mobile edge host.
The method of claim 5, wherein, in the switch phase, a connectivity of a user equipment with mobile edge hosts is provided by a connectivity provider network at the same attach point for the source mobile edge host and the target mobile edge host.
The method of claim 5, wherein, in the switch phase, a connectivity of a user equipment with mobile edge hosts is provided by a connectivity provider network at different attach points for the source mobile edge host and the target mobile edge host.
An apparatus comprising a memory, a processor and a network interface, wherein the memory stores processor-executable instructions and the processor is enabled to read the instructions from the memory and implement a method of relocating an application instance using the network interface for communication with other network entities, the method including:

implementing a preparation phase in which an image of the application instance at a source mobile edge host is prepared by making a complete copy of the application instance for transmission to a target mobile edge host; and

implementing an adaptation phase in which a difference between a current application instance and the complete copy that was previously transmitted is measured and a decision is made to switch bearers.
The apparatus of claim 9, wherein whether to switch bearers is decided based on an absolute value of a difference between data associated with an instance running at the source mobile edge host and data associated with an instance to be installed and running at the target mobile edge host.
The apparatus of claim 10, wherein, when the absolute value of the difference is above the threshold, a host switch command is sent to the target mobile edge host and a request is sent to a connectivity provider network to establish a new bearer and release an old bearer.
The apparatus of claim 9, further including:

a switch phase in which, upon making the decision to switch, the application instance is relocated.
The apparatus of claim 12, wherein the switch phase includes:

completing a copy of the application at the target mobile edge host; and

cleaning up the complete copy at the source mobile edge host.
The apparatus of claim 12, wherein a connectivity of a user equipment with mobile edge hosts is provided by a connectivity provider network at the same attach point for the source mobile edge host and the target mobile edge host.
The apparatus of claim 12, wherein a connectivity of a user equipment with mobile edge hosts is provided by a connectivity provider network at different attach points for the source mobile edge host and the target mobile edge host.
A communication system, comprising:

a network including one or more mobile edge hosts; and

a computer platform configured to:

implement a preparation phase in which an image of the application instance at a source mobile edge host is prepared by making a complete copy of the application instance for transmission to a target mobile edge host; and

implement an adaptation phase in which a difference between a current application instance and the complete copy that was previously transmitted is measured and a decision is made to switch bearers.
The system of claim 16, wherein the computer platform is configured to decide whether to switch bearers based on an absolute value of a difference between data associated with an instance running at the source mobile edge host and data associated with an instance to be installed and running at the target mobile edge host.
The system of claim 16, wherein, when the absolute value of the difference is above the threshold, a host switch command is sent to the target mobile edge host and a request is sent to a connectivity provider network to establish a new bearer and release an old bearer.
The system of claim 16, wherein the computer platform is configured to implement:

a switch phase in which, upon making the decision to switch, the application instance is relocated.
The system of claim 19, wherein the switch phase includes:

completing a copy of the application at the target mobile edge host; and

cleaning up the complete copy at the source mobile edge host.