Edge Computing Blocking Recovery Method, Device, Electronic Device, and Storage Medium

Abstract

The present application provides a method, apparatus, device and medium for edge computing block recovery, including: determining the node type of a target node where network block occurs in an edge computing system; invoking an optimization method corresponding to the node type to optimize configuration parameters of the edge computing system so as to minimize the recovery time of network block, where the configuration parameters include task allocation ratio, computing resource allocation amount and communication resource allocation amount; the optimization method includes optimizing configuration parameters according to the cache ratio of each node, and the cache ratio refers to the ratio of the cached data amount to the total cache size of the node. Compared with the prior art, the present application is more applicable to a real network environment, fully considers the differences in the total cache sizes of different nodes when optimizing the configuration parameters of the edge computing system, and avoids the occurrence of packet loss in the system during block recovery.

Description

Technical Field

[0001] This application relates to the field of edge computing technology, and in particular, to an edge computing block recovery method, apparatus, electronic device, and storage medium. Background Art

[0002] By using an edge computing system composed of a mobile terminal, an edge server, and a cloud server, computing tasks can be assigned to different network nodes, making full use of the computing and communication resources of the system to complete computing tasks in less time.

[0003] However, when the rate at which computing tasks arrive at the mobile terminal is too high, the computing and communication resources of the node may not be able to process all computing tasks in time, thus causing network congestion, and too many computing tasks will be blocked in some nodes. How to minimize the block recovery time is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0004] Embodiments of the present invention provide an edge computing block recovery method, apparatus, device, and medium to solve the problem of edge computing block recovery.

[0005] Therefore, a first aspect of this application provides an edge computing block recovery method, including:

[0006] Determine the node type of the target node where network congestion occurs in the edge computing system;

[0007] Call the optimization method corresponding to the node type to optimize the configuration parameters of the edge computing system to minimize the recovery time of network congestion;

[0008] Wherein, the configuration parameters include task allocation ratio, computing resource allocation amount, and communication resource allocation amount; the optimization method includes optimizing the configuration parameters according to the cache ratio of each node, and the cache ratio refers to the ratio of the amount of cached data to the total cache size of the node.

[0009] In a possible implementation manner, in the above method provided by this application, the node type of the target node is a mobile terminal;

[0010] The calling the optimization method corresponding to the node type to optimize the configuration parameters of the edge computing system includes:

[0011] Determine all the computing resources and cache ratios of each mobile terminal under the edge server to which the target node belongs;

[0012] Adjust the configuration parameters according to all the computing resources of each mobile terminal so that the computing delay and communication delay of each mobile terminal itself are equal, and the computing delay and communication delay between each mobile terminal are equal;

[0013] Adjust the configuration parameters according to the cache ratios of the mobile terminals, so that the cache increase rates among the mobile terminals are equal.

[0014] In a possible implementation, in the above method provided by this application, the node type of the target node is an edge server;

[0015] Invoking the optimization method corresponding to the node type to optimize the configuration parameters of the edge computing system includes:

[0016] Determine all the computing resources and cache ratios of the edge servers in the edge computing system, and determine all the computing resources of the mobile terminals under each edge server;

[0017] Adjust the configuration parameters according to all the computing resources of the edge servers and the mobile terminals, so that the computing delays of the mobile terminals and their affiliated edge servers are equal, and the computing delays and communication delays of each edge server itself are equal, and the computing delays and communication delays among the edge servers are equal;

[0018] Adjust the configuration parameters according to the cache ratios of the edge servers, so that the cache increase rates among the edge servers are equal.

[0019] In a possible implementation, in the above method provided by this application, the node type of the target node is a cloud server;

[0020] Invoking the optimization method corresponding to the node type to optimize the configuration parameters of the edge computing system includes:

[0021] Determine all the computing resources of the cloud server, edge servers and mobile terminals under each edge server in the edge computing system;

[0022] Adjust the configuration parameters according to all the computing resources of the edge computing system, so that the computing delays of the mobile terminals, edge servers and cloud server are equal.

[0023] In a possible implementation, before determining the node type of the target node where network congestion occurs in the edge computing system in the above method provided by this application, it further includes:

[0024] Detect that the communication delay of the target node is greater than the preset delay threshold, and determine that the target node has network congestion.

[0025] A second aspect of this application provides an edge computing congestion recovery device, including:

[0026] A determination module, configured to determine the node type of the target node where network congestion occurs in the edge computing system;

[0027] An optimization module, configured to call an optimization method corresponding to the node type to optimize configuration parameters of the edge computing system, so as to minimize the recovery time of network congestion;

[0028] Wherein, the configuration parameters include a task allocation ratio, a computing resource allocation amount, and a communication resource allocation amount; the optimization method includes optimizing the configuration parameters according to the cache ratio of each node, and the cache ratio refers to the ratio of the cached data volume to the total cache size of the node.

[0029] In a possible implementation manner, in the above-mentioned apparatus provided in the present application, the node type of the target node is a mobile device; the optimization module is specifically configured to:

[0030] Determine all computing resources and cache ratios of all mobile devices under the edge server to which the target node belongs;

[0031] Adjust the configuration parameters according to all the computing resources of each mobile device, so that the computing delay and communication delay of each mobile device itself are equal, and the computing delay and communication delay among the mobile devices are equal;

[0032] Adjust the configuration parameters according to the cache ratios of the mobile devices, so that the cache increase rates among the mobile devices are equal.

[0033] In a possible implementation manner, in the above-mentioned apparatus provided in the present application, the node type of the target node is an edge server; the optimization module is specifically configured to:

[0034] Determine all computing resources and cache ratios of all edge servers in the edge computing system, and determine all computing resources of all mobile devices under each edge server;

[0035] Adjust the configuration parameters according to all the computing resources of the edge servers and the mobile devices, so that the computing delay of each mobile device and its affiliated edge server is equal, and the computing delay and communication delay of each edge server itself are equal, and the computing delay and communication delay among the edge servers are equal;

[0036] Adjust the configuration parameters according to the cache ratios of the edge servers, so that the cache increase rates among the edge servers are equal.

[0037] In a possible implementation manner, in the above-mentioned apparatus provided in the present application, the node type of the target node is a cloud server; the optimization module is specifically configured to:

[0038] Determine all computing resources of the cloud server, all edge servers, and all mobile devices under each edge server in the edge computing system;

[0039] Adjust the configuration parameters according to all the computing resources of the edge computing system so that the computing delays of each mobile device, each edge server, and the cloud server are equal.

[0040] In a possible implementation manner, in the above-mentioned device provided in this application, it further includes:

[0041] A detection module, configured to detect that the communication delay of a target node is greater than a preset delay threshold before the determination module determines the node type of the target node where network congestion occurs in the edge computing system, and determine that the target node has network congestion.

[0042] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor runs the computer program, it is executed to implement the method described in the first aspect of this application.

[0043] A fourth aspect of this application provides a computer-readable storage medium, on which computer-readable instructions are stored, and the computer-readable instructions can be executed by a processor to implement the method described in the first aspect of this application.

[0044] The beneficial effects of this application are as follows:

[0045] The edge computing congestion recovery method, device, electronic device, and storage medium provided in this application determine the node type of the target node where network congestion occurs in the edge computing system; call the optimization method corresponding to the node type to optimize the configuration parameters of the edge computing system to minimize the recovery time of network congestion, where the configuration parameters include the task allocation ratio, the computing resource allocation amount, and the communication resource allocation amount; the optimization method includes optimizing the configuration parameters according to the cache ratio of each node, and the cache ratio refers to the ratio of the cached data volume to the total cache size of the node. Compared with the prior art, this application is more applicable to the real network environment, and fully considers the differences in the total cache sizes of different nodes when optimizing the configuration parameters of the edge computing system, avoiding the occurrence of packet loss in the system during congestion recovery. Description of the Drawings

[0046] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of this application. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0047] Figure 1 is a flowchart of an edge computing congestion recovery method provided in this application;

[0048] Figure 2 is the architecture diagram of node data processing provided by this application;

[0049] Figure 3 is the schematic diagram of an edge computing blocking recovery device provided by this application. Detailed implementation manners

[0050] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0051] The existing methods for minimizing the maximum network blocking recovery time do not consider that the total cache sizes of different nodes are different. In fact, due to the different total cache sizes of different nodes, their speeds of reaching the cache usage limit are also different. In order to avoid packet loss, when designing an optimization algorithm, it is necessary to fully consider the cache factor. The existing methods do not consider that when the total cache sizes of different nodes are different, the existing optimization methods are not applicable to the real network environment. This application proposes a method for minimizing the network blocking recovery time under the actual situation of considering different caches.

[0052] The embodiments of this application provide an edge computing blocking recovery method, device, electronic device and storage medium, which will be described below with reference to the accompanying drawings.

[0053] Please refer to Figure 1 , which shows the flowchart of an edge computing blocking recovery method provided by this application. As Figure 1 shown, the method may include the following steps:

[0054] S101. Determine the node type of the target node where network blocking occurs in the edge computing system;

[0055] S102. Call the optimization method corresponding to the node type to optimize the configuration parameters of the edge computing system to minimize the recovery time of network blocking;

[0056] Specifically, the above-mentioned edge computing system may be a three-layer network structure composed of a mobile terminal, an edge server, and a cloud server. Each mobile terminal, each edge server, and the cloud server are nodes in the three-layer network. Each edge server can connect the mobile terminals within its coverage area, and the cloud server can connect all edge servers.

[0057] As Figure 2As shown, a node generally includes a computing module (providing computing resources), a transmission module (providing communication resources), and a cache of a certain size. The total cache sizes of different nodes are different. For example, Figure 2 As shown, when the original data ①②③ enter the node, and the node finds that the computing module and the transmission module are in a congested state, the original data ①②③ will be stored in the cache and wait for processing, which will cause a delay in the node's data processing.

[0058] Specifically, the configuration parameters of the edge computing system include the task allocation ratio s, the computing resource allocation amount θ, and the communication resource allocation amount φ. Among them, the task allocation ratio refers to the task allocation percentages of the mobile terminal, the edge server, and the cloud server; the computing resource allocation amount refers to the computing resources allocated by the edge server i to N mobile terminals and the computing resources allocated by the cloud server to M edge servers; the communication resource allocation amount refers to the communication resources allocated by the edge server i to N mobile terminals and the communication resources allocated by the cloud server to M edge servers.

[0059] Specifically, in the optimization method of the configuration parameters, it includes optimizing the configuration parameters according to the cache ratio of each node. The cache ratio refers to the ratio of the cached data volume to the total cache size of the node, and the cached data volume can be understood as the congested data volume.

[0060] Using MD to represent the mobile terminal, ES to represent the edge server, and CC to represent the cloud server, to minimize the recovery time of network congestion according to the configuration parameters, the following optimization problem is constructed:

[0061]

[0062] Among them,

[0063] represents the computing delay of each mobile terminal MD, and λ is the input data volume.

[0064] represents the communication delay of each mobile terminal MD, and ρ is the data compression ratio.

[0065] represents the computing delay of each edge server ES.

[0066] represents the communication delay of each edge server ES, and β is the data volume that has been processed by the mobile terminal MD.

[0067] represents the computing delay of the cloud server CC.

[0068] The constraint conditions of the above optimization problem include:

[0069] Indicates the communication resource allocation limit of the edge server ES.

[0070] Indicates the computing resource allocation limit of the edge server ES.

[0071] Indicates the communication resource allocation limit of the cloud server CC.

[0072] Indicates the computing resource allocation limit of the cloud server CC.

[0073] Indicates the cache limit of the mobile device MD, where B represents the total cache size and b represents the existing cache.

[0074] Indicates the edge server cache limit.

[0075] In the above-mentioned edge computing block recovery method of the present application, the steps to determine that the target node has a network block before step S101 are as follows:

[0076] It is detected that the communication delay of the target node is greater than the preset delay threshold, and it is determined that the target node has a network block. Among them, the preset delay threshold can be set according to the actual situation or according to the different node types, and the present application does not make a limitation.

[0077] In the above-mentioned edge computing block recovery method of the present application, the node type of the target node is a mobile device; step S102 specifically includes:

[0078] Determine all the computing resources and cache ratios of each mobile device under the edge server to which the target node belongs;

[0079] Adjust the configuration parameters according to all the computing resources of each mobile device so that the computing delay and communication delay of each mobile device itself are equal, and the computing delay and communication delay between each mobile device are equal;

[0080] Adjust the configuration parameters according to the cache ratios of each mobile device so that the cache increase rates between each mobile device are equal.

[0081] Specifically, when a mobile device under a certain edge server has a network block, the optimization method is as follows:

[0082] ① Make full use of the computing capabilities of all mobile devices;

[0083] ② Adjust the s, θ, φ parameters so that the computing delay and communication delay of each mobile device itself are equal;

[0084] ③ Adjust the s, θ, φ parameters so that the computing delay and communication delay between mobile devices are equal;

[0085] ④ Adjust the parameters s, θ, and φ according to the cache ratio to make the cache increase rates between mobile devices equal.

[0086] In the above-mentioned edge computing block recovery method of the present application, the node type of the target node is an edge server; step S102 specifically includes:

[0087] Determine all the computing resources and cache ratios of each edge server in the edge computing system, and determine all the computing resources of each mobile device under each edge server;

[0088] Adjust the configuration parameters according to all the computing resources of each edge server and each mobile device, so that the computing delays of each mobile device and its affiliated edge server are equal, and the computing delay and communication delay of each edge server itself are equal, and the computing delay and communication delay between edge servers are equal;

[0089] Adjust the configuration parameters according to the cache ratios of each edge server to make the cache increase rates between edge servers equal.

[0090] Specifically, when a network block occurs in a certain edge server, the optimization method is as follows:

[0091] ① Make full use of the computing capabilities of all mobile devices and edge servers;

[0092] ② Adjust the parameters s, θ, and φ to make the computing delays of mobile devices and edge servers equal;

[0093] ③ Adjust the parameters s, θ, and φ to make the computing delay and communication delay of each edge server itself equal;

[0094] ④ Adjust the parameters s, θ, and φ to make the computing delay and communication delay between edge servers equal;

[0095] ⑤ Adjust the parameters s, θ, and φ according to the cache ratio to make the cache increase rates between edge servers equal.

[0096] In the above-mentioned edge computing block recovery method of the present application, the node type of the target node is a cloud server; step S102 specifically includes:

[0097] Determine all the computing resources of the cloud server, each edge server, and each mobile device under each edge server in the edge computing system;

[0098] Adjust the configuration parameters according to all the computing resources of the edge computing system to make the computing delays of each mobile device, each edge server, and the cloud server equal.

[0099] Specifically, when network congestion occurs in the cloud server, the optimization method is as follows:

[0100] ① Make full use of the computing capabilities of all mobile devices, edge servers, and cloud servers;

[0101] ② Adjust the parameters s, θ, and φ to make the computing delays of the mobile devices, edge servers, and cloud servers equal.

[0102] The edge computing congestion recovery method provided in this application determines the node type of the target node where network congestion occurs in the edge computing system; calls the corresponding optimization method for the node type to optimize the configuration parameters of the edge computing system to minimize the network congestion recovery time. Compared with the prior art, this application is more suitable for the real network environment. When optimizing the configuration parameters of the edge computing system, it fully considers the differences in the total cache sizes of different nodes, avoiding packet loss in the system during congestion recovery.

[0103] In the above embodiment, an edge computing congestion recovery method is provided. Correspondingly, this application also provides an edge computing congestion recovery device.

[0104] As Figure 3 shown, an edge computing congestion recovery device 10 provided in this application includes:

[0105] A determination module 101, configured to determine the node type of the target node where network congestion occurs in the edge computing system;

[0106] An optimization module 102, configured to call the corresponding optimization method for the node type to optimize the configuration parameters of the edge computing system to minimize the network congestion recovery time;

[0107] Among them, the configuration parameters include task allocation ratio, computing resource allocation amount, and communication resource allocation amount; the optimization method includes optimizing the configuration parameters according to the cache ratio of each node, and the cache ratio refers to the ratio of the cached data volume to the total cache size of the node.

[0108] In a possible implementation manner, in the above device 10 provided in this application, the node type of the target node is a mobile device; the optimization module 102 is specifically configured to:

[0109] Determine all the computing resources and cache ratios of all mobile devices under the edge server to which the target node belongs;

[0110] Adjust the configuration parameters according to all the computing resources of each mobile device to make the computing delay and communication delay of each mobile device itself equal, and the computing delay and communication delay between each mobile device equal;

[0111] Adjust the configuration parameters according to the cache ratios of the mobile devices, so that the cache increase rates among the mobile devices are equal.

[0112] In a possible implementation manner, in the above-mentioned device provided in this application, the node type of the target node is an edge server; the optimization module 102 is specifically configured to:

[0113] Determine all the computing resources and cache ratios of the edge servers in the edge computing system, and determine all the computing resources of the mobile devices under each edge server;

[0114] Adjust the configuration parameters according to all the computing resources of the edge servers and the mobile devices, so that the computing delays of the mobile devices and their affiliated edge servers are equal, and the computing delays and communication delays of each edge server itself are equal, and the computing delays and communication delays among the edge servers are equal;

[0115] Adjust the configuration parameters according to the cache ratios of the edge servers, so that the cache increase rates among the edge servers are equal.

[0116] In a possible implementation manner, in the above-mentioned device provided in this application, the node type of the target node is a cloud server; the optimization module 102 is specifically configured to:

[0117] Determine all the computing resources of the cloud server, the edge servers, and the mobile devices under each edge server in the edge computing system;

[0118] Adjust the configuration parameters according to all the computing resources of the edge computing system, so that the computing delays of the mobile devices, the edge servers, and the cloud server are equal.

[0119] In a possible implementation manner, in the above-mentioned device provided in this application, it further includes:

[0120] A detection module, configured to detect that the communication delay of the target node is greater than a preset delay threshold before the determination module determines the node type of the target node where network congestion occurs in the edge computing system, and determine that the target node has network congestion.

[0121] The edge computing congestion recovery device provided in the embodiments of this application has the same inventive concept and the same beneficial effects as the edge computing congestion recovery method provided in the foregoing embodiments of this application.

[0122] The embodiments of the present application also provide an electronic device corresponding to the edge computing blocking recovery method provided in the foregoing embodiments. The electronic device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor runs the computer program, it is configured to implement the above-mentioned edge computing blocking recovery method. The electronic device may be a mobile phone, a laptop computer, a tablet computer, a desktop computer, etc.

[0123] The embodiments of the present application also provide a computer-readable storage medium corresponding to the edge computing blocking recovery method provided in the foregoing embodiments, such as an optical disc, a USB flash drive, etc., on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the edge computing blocking recovery method provided in any of the foregoing embodiments.

[0124] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other optical and magnetic storage media, which will not be elaborated here one by one.

[0125] The above are only the preferred specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An edge computing block recovery method, characterized in that, comprising: Determine the node type of the target node where network block occurs in the edge computing system; Invoke the optimization method corresponding to the node type to optimize the configuration parameters of the edge computing system to minimize the recovery time of network block; Wherein, the configuration parameters include task allocation ratio, computing resource allocation amount, and communication resource allocation amount; the optimization method includes optimizing the configuration parameters according to the cache ratio of each node, and the cache ratio refers to the ratio of the cached data volume to the total cache size of the node; When the node type of the target node is a mobile device, invoking the optimization method corresponding to the node type to optimize the configuration parameters of the edge computing system includes: Determine all the computing resources and cache ratios of all mobile devices under the edge server to which the target node belongs; Adjust the configuration parameters according to all the computing resources of each mobile device so that the computing delay and communication delay of each mobile device itself are equal, and the computing delay and communication delay between each mobile device are equal; Adjust the configuration parameters according to the cache ratios of each mobile device so that the cache increase rates between each mobile device are equal.

2. The edge computing block recovery method according to claim 1, characterized in that, The node type of the target node is an edge server; The invoking the optimization method corresponding to the node type to optimize the configuration parameters of the edge computing system includes: Determine all the computing resources and cache ratios of all edge servers under the edge computing system, and determine all the computing resources of all mobile devices under each edge server; Adjust the configuration parameters according to all the computing resources of each edge server and each mobile device so that the computing delay of each mobile device and its affiliated edge server is equal, and the computing delay and communication delay of each edge server itself are equal, and the computing delay and communication delay between edge servers are equal; Adjust the configuration parameters according to the cache ratios of each edge server so that the cache increase rates between each edge server are equal.

3. The edge computing block recovery method according to claim 1, characterized in that, The node type of the target node is a cloud server; The invoking the optimization method corresponding to the node type to optimize the configuration parameters of the edge computing system includes: Determine all the computing resources of the cloud server, each edge server, and all mobile devices under each edge server under the edge computing system; Adjust the configuration parameters according to all the computing resources of the edge computing system so that the computing delays of each mobile device, each edge server, and the cloud server are equal.

4. The edge computing block recovery method according to claim 1, characterized in that, Before determining the node type of the target node where network block occurs in the edge computing system, it further includes: Detect that the communication delay of the target node is greater than the preset delay threshold, and determine that the target node has a network block.

5. An edge computing block recovery device, characterized in that, comprising: A determination module, configured to determine the node type of a target node where network congestion occurs in an edge computing system; An optimization module, configured to call an optimization method corresponding to the node type to optimize configuration parameters of the edge computing system, so as to minimize the recovery time of network congestion; wherein the configuration parameters include a task allocation ratio, a computing resource allocation amount, and a communication resource allocation amount; the optimization method includes optimizing the configuration parameters according to the cache ratio of each node, and the cache ratio refers to the ratio of the cached data volume to the total cache size of the node; When the node type of the target node is a mobile device, the optimization module is specifically configured to: determine all computing resources and cache ratios of all mobile devices under the edge server to which the target node belongs; Adjust the configuration parameters according to all the computing resources of the mobile devices, so that the computing delay and communication delay of each mobile device itself are equal, and the computing delay and communication delay between the mobile devices are equal; Adjust the configuration parameters according to the cache ratios of the mobile devices, so that the cache increase rates between the mobile devices are equal.

6. The edge computing congestion recovery device according to claim 5, wherein, the node type of the target node is an edge server; the optimization module is specifically configured to: Determine all computing resources and cache ratios of all edge servers in the edge computing system, and determine all computing resources of all mobile devices under each edge server; Adjust the configuration parameters according to all the computing resources of the edge servers and the mobile devices, so that the computing delay of each mobile device and its affiliated edge server is equal, and the computing delay and communication delay of each edge server itself are equal, and the computing delay and communication delay between the edge servers are equal; Adjust the configuration parameters according to the cache ratios of the edge servers, so that the cache increase rates between the edge servers are equal.

7. An electronic device, including: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor runs the computer program, the method according to any one of claims 1 to 4 is implemented.

8. A computer-readable storage medium, wherein, Computer-readable instructions are stored thereon, and the computer-readable instructions can be executed by a processor to implement the method according to any one of claims 1 to 4.

Images