Application of hybrid genetic algorithm in large traffic scheduling in SDN architecture
Yuhan Feng · International Journal of Wireless and Mobile Computing · 2023
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.