Collaborative optimization method and system for edge nodes of computing power network

By constructing a computing power network topology map and comprehensive reputation assessment, and combining multi-agent deep reinforcement learning, the energy consumption penalty weight is dynamically adjusted, solving the problem of insufficient resource allocation in the scheduling of edge nodes in existing computing power networks, and realizing an efficient, green and energy-saving scheduling strategy.

CN122027474APending Publication Date: 2026-05-12CHINESE PEOPLES LIBERATION ARMY INFORMATION SUPPORT CORPS ENGINEERING UNIVERSITY
0 Cites 2 Cited by

Patent Information

Application Number
CN202512053539.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-31
Publication Date
2026-05-12

AI Technical Summary

Technical Problem

Existing edge node scheduling methods for computing power networks lack a global perspective and a collaborative mechanism between nodes, making it impossible to achieve dynamic optimal resource allocation, failing to effectively identify nodes with high reliability, and making it difficult to achieve green and energy-saving goals due to the independent nature of energy consumption optimization and credibility assessment.

Method used

By collecting resource status and historical behavior data of edge nodes, a computing power network topology map is constructed. Graph neural networks are used to extract node features, calculate comprehensive reputation, establish a coupling and linkage mechanism between reputation and energy consumption perception, and use multi-agent deep reinforcement learning algorithms to train a collaborative optimization model. Energy consumption penalty weights are dynamically adjusted to achieve task scheduling decisions.

Benefits of technology

It achieves high resource utilization, low task latency, strong system robustness, rapid environmental adaptability and green energy saving in the scheduling of edge nodes of the computing power network, and improves the reliability and energy efficiency of nodes.

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

Abstract

The invention relates to the technical field of edge computing, in particular to an edge node collaborative optimization method and system of a computing power network. Comprising the steps of collecting resource state information and historical behavior data of a plurality of edge nodes to form a resource state data set; constructing a computing power network topological graph based on the resource state data set, and extracting node feature representation of each node through a graph neural network; calculating the comprehensive credibility of each edge node based on the historical behavior data, and integrating the comprehensive credibility into the node feature representation; collecting energy consumption state data of each edge node, and calculating an energy consumption efficiency index of each edge node; and a coupling linkage mechanism of credibility and energy consumption perception is established. Through a coupling linkage mechanism of credibility and energy consumption perception, high resource utilization rate, low task delay, strong system robustness and green energy conservation of computing power network edge node scheduling are realized.
Need to check novelty before this filing date? Find Prior Art