Research on Load Balancing Strategy of Data Center based on Yen Algorithm in SDN
Xiaoyong Sun, Guiqin Yang · 2022 IEEE 5th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · 2022
In this paper, based on SDN network architecture and Yen algorithm, Yen-M model is proposed to solve the difficult problem of load balancing and flow scheduling in traditional networks. In the stage of flow detection, a two-stage flow detection module is used to set the adaptive flow detection threshold according to the real-time state of the network, which improves the accuracy of flow detection. In order to improve the adaptability of the model of dynamic data, introduces the incremental learning modules, through training into the best route to SDN controller select the article k shortest path calculation module, solved the Yen algorithm in the most short circuit in large networks link calculation difficult problem, reduces the flow scheduling delay, greatly improve the efficiency of the network transmission, It makes the training model more extensible. The experimental results show that compared with the PureSDN model using Yen algorithm in high-speed links, the Yen-M model improves the throughput by 3.23%, reduces the transmission delay by 63.82%, and improves the average link utilization by 10.86%.