Optimization of Computing-Storage-Network Resource Configuration in Power Dispatch Center Using Improved NSGA-II

Read full text Summarise with VIRAT
Authors: Zhen Huang, Kaiyuan Hou, Fei Peng, Tianyu An, Xuerui Yang
Cited by: 0
References: 8

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Abstract In power dispatch, the dispatch stability of the original computing-storage-network resource set is poor. Therefore, an optimization method for computing-storage-network resource configuration in a power dispatch center using improved NSGA-II is proposed. With the help of a probability statistics model, the original resource set is generated, and then the nearest neighbor clustering method is used to screen and construct the resource model. The characteristics of improved NSGA-II are used to set computing, storage, and network resource constraints, covering total resource, capacity, and bandwidth constraints. The business load is accurately predicted, and the Pareto optimization is used to solve the computing-storage-network resource configuration optimization strategy. The correlation value is determined, the final solution is screened after analyzing the characteristics of non-dominated solutions, and a dynamic adjustment mechanism is established. The experimental results show that under extreme load disturbance, the frequency drop of the design method is the smallest, and it recovers within 8 seconds. The resource utilization rate of each time period is higher than that of the literature [1]-[4], reaching 0.83 in 12 time periods. It has better stability under complex working conditions.

Fields of Study & Subjects

Cloud Computing and Resource Management Smart Grid and Power Systems Electric Power System Optimization

Publication details

Journal / source
Journal of Physics Conference Series
Volume
3198
Issue
1
Pages
012004–012004
Publication date
1 March 2026
Language
EN