A method and system for dynamically allocating tasks to a mobile edge computing server

By dynamically evaluating the processing capabilities and congestion of local servers and edge servers and selecting appropriate servers to handle tasks, the problems of low resource allocation efficiency and increased latency in the prior art are solved, and efficient allocation and processing of tasks are achieved.

CN112559187BActive Publication Date: 2024-12-06LIANZIXIN INTELLIGENT TECHNOLOGY (HANGZHOU) CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202011525191.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-12-22
Publication Date
2024-12-06
Estimated Expiration
2040-12-22

AI Technical Summary

Technical Problem

The prior art cannot dynamically allocate tasks to a suitable server based on the matching situation between local servers and terminal tasks and the matching situation between edge servers and terminal tasks, resulting in low resource allocation efficiency and increased latency.

Method used

By obtaining the task information generated by the terminal, we can judge whether the task is processed locally based on the processing speed, processing energy consumption and congestion of the local server. If not, select a suitable edge server based on the distance between the edge server and the terminal, congestion situation and processing capacity. Processing is performed and tasks are assigned by matching values ​​to improve processing efficiency.

Benefits of technology

Effectively determine whether the local server can handle tasks, so as to prioritize tasks with small data volume and high latency requirements, and select appropriate edge servers based on multiple dimensions to improve task processing efficiency, ensure that tasks are distributed in parallel to each edge server, and improve multi-tasks Processing efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112559187B_ABST
    Figure CN112559187B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for dynamically allocating tasks to a mobile edge computing server, the method comprising the steps of: obtaining information on one or more tasks generated by a terminal in a region within a certain period of time, including the data volume of the task and the delay requirement information of the task; judging whether the task can be processed on the local server according to the processing speed and / or processing energy consumption and / or congestion of the local server in the region; if the task cannot be processed on the local server, selecting a suitable edge server for processing the task according to the distance between each edge server and the terminal where the task is located and / or the congestion of each edge server and / or the processing capacity of each edge server. The present invention solves the problem of how to dynamically allocate tasks to suitable servers according to the matching of the local server and the terminal task and the matching of the edge server and the terminal task.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of mobile edge computing, and in particular relates to a method and system for dynamically allocating tasks to a mobile edge computing server. Background Art

[0002] With the application scenarios of 5G technology such as augmented reality, virtual reality, industrial Internet of Things, telemedicine, etc., the data traffic is large and usually has high requirements for service quality (QoS). For this reason, a mobile edge computing system is proposed. In the mobile edge computing system, the tasks generated by the terminal application can be selected to run locally, or the tasks can be offloaded to the edge server through wireless transmission. How to offload tasks and allocate resources is one of the most important issues in mobile edge computing. Current related technologies, such as the Chinese patent "A hierarchical edge computing offloading method based on priority" with publication number CN111954236A, propose that edge nodes that are closer to user devices and have fewer computing resources process simple tasks to quickly return warning information, and servers that are farther away from user devices and have more computing resources process complex tasks and finally return accurate results. In view of the problem that limited resource competition will increase latency, a resource allocation and task scheduling optimization solution based on service emergency priority is proposed. The Chinese patent "A resource dynamic pricing method in edge computing" with publication number CN111885147A proposes to divide the tasks of the mobile terminal and calculate them locally and on the edge server respectively. After the terminal generates a task request, it first determines whether the task needs to be unloaded, and then determines the resource unit price according to the system resource surplus. If the resources are abundant, the resource price is lowered; if the resources are scarce, the price increases; determine the unloading size of the task according to the price; if unloading is not required, calculate directly on the terminal. The Chinese patent "Task unloading method and task unloading device based on mobile edge computing scenario" with publication number CN111372314A proposes to obtain the task information and system real-time parameter information of the tasks to be processed of the terminal device; determine the optimization objective equation for minimizing the system overhead based on the task information to be processed and the system real-time parameter information; decompose the optimization objective equation into two sub-problems: task unloading and channel allocation sub-problem and transmission power and edge server resource allocation sub-problem; and solve the sub-problems to obtain the final task unloading solution; and perform task unloading in the mobile edge computing scenario according to the task unloading solution.

[0003] The above technical solutions obtain unloading solutions from the perspectives of service emergency priority, dynamic pricing, and objective equation optimization. However, none of the above solutions can reasonably select a server for processing according to the matching of server and terminal tasks. At present, there is no technical solution for dynamically allocating tasks to suitable servers based on the matching of local servers and terminal tasks and the matching of edge servers and terminal tasks. Therefore, a method and system for dynamically allocating tasks to a mobile edge computing server are proposed. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes a method and system for dynamically allocating tasks for a mobile edge computing server.

[0005] The present invention relies on a mobile edge computing system. Mobile terminal applications in the area generate task information flows, and local base stations dynamically allocate tasks based on the task information.

[0006] The method for dynamically allocating tasks to a mobile edge computing server of the present invention is characterized by:

[0007] Obtain information about one or more tasks generated by terminals in the area within a certain period of time, including the data volume of the tasks and the delay requirement information of the tasks;

[0008] Determine whether the task can be processed on the local server based on the processing speed and / or processing energy consumption and / or congestion of the local server in the region;

[0009] If the task cannot be processed by the local server, a suitable edge server is selected for processing the task according to the distance between each edge server and the terminal where the task is located and / or the congestion of each edge server and / or the processing capacity of each edge server.

[0010] Preferably, the data volume of the task is any one or a combination of the data storage volume, data calculation volume, and program execution volume required to process the task.

[0011] Preferably, the delay requirement information of the task is any one or more combinations of the minimum delay requirement to ensure the normal operation of the terminal, the delay requirement set according to the task type, the delay requirement set according to the type of terminal where the task is located, and the delay requirement set according to the location of the terminal where the task is located.

[0012] Preferably, the congestion situation includes any one or more combinations of the following: a task processing queuing situation caused by the server's task queue being full, a situation where the server cannot process tasks due to a malfunction, a task processing queuing situation caused by the server being occupied, and a task processing queuing situation caused by the server's current task processing delay being too long.

[0013] Preferably, judging whether the task can be processed on the local server according to the processing speed and / or processing energy consumption and / or congestion condition of the local server in the region comprises the steps of:

[0014] Calculate the matching value between the local server and the task data volume according to the matching degree between the processing speed and / or processing energy consumption and / or congestion of the local server in the region and the task data volume;

[0015] Calculate the matching value between the local server and the task delay requirement according to the matching degree between the processing speed and / or processing energy consumption and / or congestion condition of the local server in the region and the task delay requirement;

[0016] Calculate the matching value between the local server and the task information according to the matching value between the local server and the task data volume and / or the matching value between the local server and the task delay requirement;

[0017] When the matching value between the local server and the task information is greater than a preset local matching threshold, it is determined that the task can be processed on the local server.

[0018] Preferably, the selecting a suitable edge server for processing the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the processing capacity of each edge server comprises the steps of:

[0019] Obtaining distance information between each edge server and the terminal where the task is located and / or congestion status of each edge server and / or processing capacity information of each edge server;

[0020] Calculate the matching value between each edge server and the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the matching degree between the processing capacity of each edge server and the data volume and / or delay requirement of the task;

[0021] Based on the task, the edge server corresponding to the maximum matching value is selected for processing.

[0022] Preferably, the selecting a suitable edge server for processing the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the processing capacity of each edge server comprises the steps of:

[0023] Obtaining distance information between each edge server and the terminal where the task is located and / or congestion status of each edge server and / or processing capacity information of each edge server;

[0024] Calculate the matching value between each edge server and the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the matching degree between the processing capacity of each edge server and the data volume and / or delay requirement of the task;

[0025] Based on each edge server, the task with the largest matching value is assigned to each edge server in turn for processing;

[0026] It is determined whether there is a task that does not select an edge server. If so, the above steps are executed again for the task that does not select an edge server.

[0027] Further preferably, the method further comprises the step of: when multiple edge servers are assigned duplicate tasks, the edge server with the largest matching value with the task is given priority in assigning the task, and the remaining edge servers are assigned the next task in the order of matching values.

[0028] A computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the above method.

[0029] A mobile edge computing server dynamic task allocation system, characterized by comprising:

[0030] terminal;

[0031] processor;

[0032] Memory;

[0033] as well as

[0034] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, the programs causing the computer to execute the method as claimed in claim 1.

[0035] The method and system of the present invention have the advantages that:

[0036] (1) Whether the task is processed on the local server is determined based on the degree of match between the processing speed and / or processing energy consumption and / or congestion of the local server in the region and the task information. This effectively determines whether the local server can process the task from multiple dimensions, so that the local server can give priority to processing tasks with smaller data volumes and higher latency requirements.

[0037] (2) Selecting a suitable edge server for processing the task based on the distance between each edge server and the terminal where the task is located and / or the congestion status of each edge server and / or the processing capacity of each edge server, and selecting the most suitable edge server for the task from multiple dimensions, thereby effectively improving the task processing efficiency;

[0038] (3) Based on each edge server, the task with the largest matching value is assigned to each edge server in turn for processing and repeated until all tasks are assigned to the edge server. This allows each task to be distributed to each edge server for parallel processing, thereby improving the processing efficiency of multiple tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flowchart of the steps of a method for dynamically allocating tasks to a mobile edge computing server according to an embodiment of the present invention;

[0040] Figure 2 It is a block diagram of a system for dynamically allocating tasks to a mobile edge computing server according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The preferred embodiments of the present invention are described in detail below.

[0042] The present invention relies on a mobile edge computing system. Mobile terminal applications in the area generate task information flows, and local base stations dynamically allocate tasks based on the task information.

[0043] The embodiment of the method for dynamically allocating tasks to a mobile edge computing server of the present invention is shown in the flowchart as follows: Figure 1 As shown, it is characterized by:

[0044] Obtain information about one or more tasks generated by terminals in the area within a certain period of time, including the data volume of the tasks and the delay requirement information of the tasks;

[0045] Determine whether the task can be processed on the local server based on the processing speed and / or processing energy consumption and / or congestion of the local server in the region;

[0046] If the task cannot be processed by the local server, a suitable edge server is selected for processing the task according to the distance between each edge server and the terminal where the task is located and / or the congestion of each edge server and / or the processing capacity of each edge server.

[0047] Preferably, the data volume of the task is any one or a combination of the data storage volume, data calculation volume, and program execution volume required to process the task. In this embodiment, all tasks generated by applications in terminals within a certain period of time in the area are obtained, and the data volume of each task refers to any one or a combination of the data storage volume, data calculation volume, and program execution volume required to process the task.

[0048] Preferably, the delay requirement information of the task is any one or more combinations of the minimum delay requirement to ensure the normal operation of the terminal, the delay requirement set according to the task type, the delay requirement set according to the type of terminal where the task is located, and the delay requirement set according to the location of the terminal where the task is located. In this embodiment, all tasks generated by applications in a certain time period of terminals in the area are obtained, and different delay requirement information is obtained according to different initiating terminals, terminal types, terminal locations or task types of each task. Therefore, the delay requirement information of the task refers to any one or more combinations of the minimum delay requirement to ensure the normal operation of the terminal, the delay requirement set according to the task type, the delay requirement set according to the type of terminal where the task is located, and the delay requirement set according to the location of the terminal where the task is located.

[0049] Preferably, the congestion situation includes any one or more combinations of a task processing queuing situation caused by a full task queue of the server, a situation where the server cannot process tasks due to a fault, a task processing queuing situation caused by being occupied, and a task processing queuing situation caused by a long delay in the current task processing. In this embodiment, congestion may exist in the local server or the edge server. According to one or more reasons for the congestion, the congestion situation includes any one or more combinations of a task processing queuing situation caused by a full task queue of the server, a situation where the server cannot process tasks due to a fault, a task processing queuing situation caused by being occupied, and a task processing queuing situation caused by a long delay in the current task processing.

[0050] Preferably, judging whether the task can be processed on the local server according to the processing speed and / or processing energy consumption and / or congestion condition of the local server in the region comprises the steps of:

[0051] Calculate the matching value between the local server and the task data volume according to the matching degree between the processing speed and / or processing energy consumption and / or congestion of the local server in the region and the task data volume;

[0052] Calculate the matching value between the local server and the task delay requirement according to the matching degree between the processing speed and / or processing energy consumption and / or congestion condition of the local server in the region and the task delay requirement;

[0053] Calculate the matching value between the local server and the task information according to the matching value between the local server and the task data volume and / or the matching value between the local server and the task delay requirement;

[0054] When the matching value between the local server and the task information is greater than a preset local matching threshold, it is determined that the task can be processed on the local server.

[0055] In this embodiment, the matching value between the local server and the task data volume is calculated based on the matching degree between the processing speed and / or processing energy consumption and / or congestion condition of the local server in the region and the task data volume. The method first calculates the amount of data p that the local server can process based on the processing speed and / or processing energy consumption and / or congestion condition of the local server (the amount of data p that the local server can process is positively correlated with the processing speed of the local server, and negatively correlated with the processing energy consumption and congestion condition of the local server. The amount of data p that the local server can process is obtained by data training based on the above relationship), and then the matching value m between the local server and the task data volume is obtained based on whether the amount of data p that the local server can process meets the requirements of the task data volume q and the degree of non-satisfaction. The value range of m is 0-1. If the amount of data p that the local server can process is greater than or equal to the task data volume q, the value is 1. If the amount of data p that the local server can process is less than the task data volume q, m is calculated based on the difference. The larger the difference, the smaller the value of m. For example o1, o2 are pre-set calculation coefficients, or m = o3 (qp) o4 +o5, o3, o4 (o4<0), and o5 are calculation coefficients set in advance.

[0056] The method of calculating the matching value of the local server and the task delay requirement according to the matching degree between the processing speed and / or processing energy consumption and / or congestion condition of the local server in the region and the task delay requirement is to first calculate the delay t of the local server processing the task according to the processing speed and / or processing energy consumption and / or congestion condition of the local server (the delay t of the local server processing the task is negatively correlated with the processing speed of the local server, and positively correlated with the processing energy consumption and congestion condition of the local server. The delay t of the local server processing the task is obtained according to data training based on the above relationship), and then obtain the matching value n of the local server and the task delay requirement according to whether the delay t of the local server processing the task meets the task delay requirement w and the degree of non-satisfaction. The value range of n is 0-1. If the delay t of the local server processing the task is less than or equal to the task delay requirement w, the value is 1. If the delay t of the local server processing the task is greater than the task delay requirement w, n is calculated according to the difference. The larger the difference, the smaller the value of n. For example o6, o7 are pre-set calculation coefficients, or m = o8 (tw) o9 +o10, o8, o9 (o9<0), and o10 are calculation coefficients set in advance.

[0057] The matching value x between the local server and the task information is positively correlated with the matching value m between the local server and the task data volume and the matching value n between the local server and the task delay requirement, and the matching value x between the local server and the task information is calculated based on this.

[0058] A1 to A3 in Table A represent different implementation methods for calculating the matching value between the local server and the task information, wherein the matching value m between the local server and the task data volume and the matching value n between the local server and the task delay requirement involved in Table A are obtained using the formula of the above implementation method.

[0059] Table A Different implementation methods for calculating the matching value between the local server and the task information

[0060]

[0061]

[0062]

[0063] A local matching threshold value X is set in advance according to the local network requirements and the terminal device type, and a matching value x between the local server and the task information is obtained according to any embodiment in Table A. When x is greater than X, it is determined that the task can be processed on the local server. In this embodiment, the local matching threshold value X=1 is set, and a matching value x=1.6>X between the local server and a certain task information is obtained according to A3 in Table A, and whether the task can be processed on the local server.

[0064] In a preferred embodiment, the step of selecting a suitable edge server for processing the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the processing capacity of each edge server comprises the following steps:

[0065] Obtaining distance information between each edge server and the terminal where the task is located and / or congestion status of each edge server and / or processing capacity information of each edge server;

[0066] Calculate the matching value between each edge server and the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the matching degree between the processing capacity of each edge server and the data volume and / or delay requirement of the task;

[0067] Based on the task, the edge server corresponding to the maximum matching value is selected for processing.

[0068] In this embodiment, the distance between the edge server and the terminal where the task is located is recorded as s, the congestion of the edge server is represented by the congestion degree ratio r, and the processing capacity of each edge server is represented by the processing efficiency d;

[0069] The method of calculating the matching value between each edge server and the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the matching degree between the processing capacity of each edge server and the data volume and / or delay requirement of the task comprises the steps of:

[0070] Calculate the amount of data u processed by the edge server and the processing delay v according to the distance s between the edge server and the terminal where the task is located and / or the congestion situation r of the edge server and / or the processing capacity d of the edge server; wherein the amount of data u processed by the edge server is inversely proportional to the distance s between the edge server and the terminal where the task is located and the congestion situation r of the edge server, and is directly proportional to the processing capacity d of the edge server;

[0071] The matching value a between the edge server and the task data volume is obtained according to whether the edge server processing data volume u meets the requirements of the task data volume q and the degree of non-satisfaction. The value range of a is 0-1. If the edge server processing data volume u is greater than or equal to the task data volume q, the value is 1. If the edge server processing data volume u is less than the task data volume q, a is calculated based on the difference. The larger the difference, the smaller the value of a. For example, e1, e2 are pre-set calculation coefficients, or a=e3·(qu) e4 +e5, e3, e4 (e4<0), o5 are the calculation coefficients set in advance;

[0072] According to whether the edge server processing delay v meets the task delay requirement w and the degree of non-satisfaction, the matching value b between the edge server and the task delay requirement is obtained. The value range of b is 0-1. If the edge server processing delay v is less than or equal to the task delay requirement w, b takes the value of 1. If the edge server processing delay v is greater than the task delay requirement w, b is calculated based on the difference. The larger the difference, the smaller the b value. For example, e6, e7 are pre-set calculation coefficients, or b = e8 (vw) e9 +e10, e8, e9 (e9<0), e10 are the calculation coefficients set in advance;

[0073] The matching value y between the edge server and the task is calculated according to the matching value between the edge server and the task data volume and / or the matching value between the edge server and the task delay requirement; the matching value y between the edge server and the task is calculated based on the positive correlation between the matching value a between the edge server and the task data volume and the matching value b between the edge server and the task delay requirement.

[0074] B1 to B3 in Table B represent different implementation methods for calculating the matching value between the edge server and the task, wherein the matching value a between the edge server and the task data volume and the matching value b between the edge server and the task delay requirement involved in Table B are obtained using the formula of the above implementation method.

[0075] Table B Different implementation methods for calculating the matching value between the local server and the task information

[0076]

[0077]

[0078]

[0079]

[0080] The matching value y between each edge server and the task is obtained according to any calculation method in Table B. ij , where i represents the number of the task, and j represents the number of each edge server; taking task i as the benchmark, the edge server corresponding to the maximum matching value is selected for processing.

[0081] In another preferred embodiment, the step of selecting a suitable edge server for processing the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the processing capacity of each edge server comprises the following steps:

[0082] Obtaining distance information between each edge server and the terminal where the task is located and / or congestion status of each edge server and / or processing capacity information of each edge server;

[0083] Calculate the matching value between each edge server and the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the matching degree between the processing capacity of each edge server and the data volume and / or delay requirement of the task;

[0084] Based on each edge server, the task with the largest matching value is assigned to each edge server in turn for processing;

[0085] It is determined whether there is a task that does not select an edge server. If so, the above steps are executed again for the task that does not select an edge server.

[0086] Further preferably, the method further comprises the step of: when multiple edge servers are assigned duplicate tasks, the edge server with the largest matching value with the task is given priority in assigning the task, and the remaining edge servers are assigned the next task in the order of matching values.

[0087] In this embodiment, the matching value y between each edge server and the task is obtained according to any calculation method described in Table B. ij, where i represents the number of the task, and j represents the number of each edge server; first, for each edge server, obtain the task with the largest matching value corresponding to each edge server. If there are duplicate tasks assigned to multiple edge servers, the task is assigned to the edge server with the largest matching value of the task first, and the remaining edge servers are assigned the next task in the order of matching values; determine whether there is a task that has not selected an edge server. If so, re-execute the above steps for the task that has not selected an edge server.

[0088] A computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the above method.

[0089] A dynamic task allocation system for mobile edge computing servers, as shown in the schematic diagram Figure 2 As shown, it is characterized by comprising:

[0090] terminal;

[0091] processor;

[0092] Memory;

[0093] as well as

[0094] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, the programs causing the computer to perform the above method.

[0095] Of course, those skilled in the art should realize that the above embodiments are only used to illustrate the present invention, and are not intended to limit the present invention. As long as they are within the scope of the present invention, any changes or modifications to the above embodiments will fall within the protection scope of the present invention.

Claims

1. A method for dynamically allocating tasks to a mobile edge computing server, characterized in that: include: Obtain information about one or more tasks generated by terminals in the area within a certain period of time, including the data volume of the tasks and the delay requirement information of the tasks; Determine whether the task can be processed on the local server based on the processing speed and / or processing energy consumption and / or congestion situation of the local server in the area; the method of determining whether the task can be processed on the local server based on the processing speed and / or processing energy consumption and / or congestion situation of the local server in the area comprises the following steps: calculating the matching value between the local server and the task data volume based on the matching degree between the processing speed and / or processing energy consumption and / or congestion situation of the local server in the area and the task data volume; calculating the matching value between the local server and the task delay requirement based on the matching degree between the processing speed and / or processing energy consumption and / or congestion situation of the local server in the area and the task delay requirement; calculating the matching value between the local server and the task information based on the matching value between the local server and the task data volume and / or the matching value between the local server and the task delay requirement; when the matching value between the local server and the task information is greater than a pre-set local matching threshold, determining that the task can be processed on the local server; If the task cannot be processed on the local server, a suitable edge server is selected for processing the task based on the distance between each edge server and the terminal where the task is located and / or the congestion of each edge server and / or the processing capacity of each edge server; The method of selecting a suitable edge server for processing a task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the processing capacity of each edge server comprises the steps of: obtaining the distance information between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the processing capacity information of each edge server; calculating the matching value between each edge server and the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the processing capacity of each edge server and the data volume and / or delay requirements of the task; Based on each edge server, the task with the largest matching value is sequentially assigned to each edge server for processing; it is determined whether there is a task that has not selected an edge server, and if so, the above steps are re-executed for the task that has not selected an edge server.

2. The method for dynamically allocating tasks to a mobile edge computing server according to claim 1, characterized in that: The data volume of the task refers to any one or a combination of the data storage volume, data calculation volume, and program execution volume required to process the task.

3. The method for dynamically allocating tasks to a mobile edge computing server according to claim 1, characterized in that: The delay requirement information of the task is any one or more combinations of the minimum delay requirement to ensure the normal operation of the terminal, the delay requirement set according to the task type, the delay requirement set according to the terminal type that initiates the task, and the delay requirement set according to the terminal location that initiates the task.

4. The method for dynamically allocating tasks to a mobile edge computing server according to claim 1, characterized in that: The congestion situation includes any one or more combinations of the task processing queuing situation caused by the server's task queue being full, the situation where the server cannot process tasks due to a failure, the task processing queuing situation caused by the server being occupied, and the task processing queuing situation caused by the server's current task processing delay being too long.

5. The method for dynamically allocating tasks to a mobile edge computing server according to claim 1, characterized in that: The step of selecting a suitable edge server for processing the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the processing capacity of each edge server comprises the following steps: Obtaining distance information between each edge server and the terminal where the task is located and / or congestion status of each edge server and / or processing capacity information of each edge server; Calculate the matching value between each edge server and the task according to the distance between each edge server and the terminal where the task is located and / or the congestion condition of each edge server and / or the matching degree between the processing capacity of each edge server and the data volume and / or delay requirement of the task; Based on the task, the edge server corresponding to the maximum matching value is selected for processing.

6. The method for dynamically allocating tasks to a mobile edge computing server according to claim 1, characterized in that: The method further includes the following steps: when multiple edge servers are assigned duplicate tasks, the edge server with the largest matching value for the task is given priority in assigning the task, and the remaining edge servers are assigned the next task in the order of matching values.

7. A computer-readable storage medium storing a computer program for electronic data exchange, wherein: The computer program enables a computer to execute the method according to any one of claims 1 to 6.

8. A mobile edge computing server dynamic task allocation system, characterized in that include: terminal; processor; Memory; as well as, One or more programs, wherein the one or more programs are stored in a memory and configured to be executed by the processor, the programs causing the computer to execute the method according to any one of claims 1 to 6.

Citation Information

Patent Citations

  • Task unloading method and task unloading device based on mobile edge computing scene

    CN111372314A

  • Resource dynamic pricing method in edge calculation

    CN111885147A

  • Hierarchical edge computing unloading method based on priority

    CN111954236A

  • Mobile user terminal task unloading method under distributed edge computing service system

    CN111262906A

  • Task scheduling method and device based on edge computing network

    CN111679904A