Title: Application of hybrid genetic algorithm in large traffic scheduling in SDN architecture

Authors: Yuhan Feng

Addresses: School of Information Engineering, Xinyang Agriculture and Forestry University, Xinyang, Henan Province, China

Abstract: The scale of data centres and network traffic at the core of modern information service infrastructure is increasing. At present, there are many problems in network traffic management under the new architecture, such as too many large flow conflicts and low flexibility. A large flow scheduling mechanism for SDN architecture based on hybrid genetic algorithm is proposed. Based on the analysis of data centre network topology and architecture module, this paper focuses on HGSAFS traffic scheduling algorithm, which uses GA algorithm to make up for the problems of SA algorithm in global search ability and local solution. The four traffic scheduling algorithms have the highest average network delay when the network load is 90%, and the four traffic scheduling algorithms have the highest average network throughput. The highest average network delay algorithm is GFE algorithm, with a value of 119.3 ms, while the highest average network throughput is HGSAFS algorithm, with a value of 746.3 Mbps. The proposed SDN architecture scheduling algorithm has feasibility in large traffic scheduling.

Keywords: simulated annealing algorithm; genetic algorithm; SDN architecture; traffic scheduling.

DOI: 10.1504/IJWMC.2023.131324

International Journal of Wireless and Mobile Computing, 2023 Vol.24 No.3/4, pp.341 - 351

Received: 07 May 2022
Received in revised form: 07 Dec 2022
Accepted: 12 Dec 2022
Published online: 06 Jun 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article