Fair cooperation unloading method between edge servers in edge-edge cooperation scene

By adopting a fair cooperation strategy method in the edge computing system, we optimize task offloading and resource allocation between edge servers, solving the problem of imbalance in computing resource allocation in edge computing, and achieving more efficient task processing and system performance.

CN119718645APending Publication Date: 2025-03-28SOUTHWEAT UNIV OF SCI & TECH
0 Cites 0 Cited by

Patent Information

Application Number
CN202411787738.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-06
Publication Date
2025-03-28

AI Technical Summary

Technical Problem

In edge computing, computing resources are allocated unbalanced among edge servers, resulting in the inability to effectively handle computationally intensive and latency-sensitive tasks.

Method used

A fair cooperation uninstall method between edge servers in the edge-side collaboration scenario is proposed. By constructing a decision vector set, edge server selection matrix and resource allocation matrix, a fair cooperation strategy is adopted to optimize the uninstallation and allocation of tasks, ensuring the reasonable allocation of resources and low-latency processing of tasks.

Benefits of technology

It realizes fair distribution of resources between edge servers, improves task processing efficiency and system load balancing, reduces task processing delay, and improves the overall performance of edge computing systems.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a fair cooperation unloading method among edge servers in an edge-edge cooperation scene, which performs modeling for an edge computing system of multiple edge servers in the edge-edge cooperation scene, and provides more suitable computing migration services for a large number of computing tasks which are not uniformly distributed. According to the method, the fairness of task scheduling in an edge cooperation scene is considered, when the edge server is selected, a weight factor is introduced, four evaluation indexes including the computing power, the transmission distance, the resource contribution degree and the number of parallel tasks are comprehensively considered, and edge server selection and computing resource allocation are achieved; four evaluation indexes and weight factors are utilized to generate a weighted comprehensive evaluation model, the edge server with the lowest evaluation value is used as a selection result, the resource utilization rate of adjacent idle edge servers is increased, the edge system is enabled to have balanced load, and the edge system is enabled to have high task concurrency. And it is ensured that each edge server in the system has certain available computing resources and has lower task processing delay.
Need to check novelty before this filing date? Find Prior Art