A Data Center Load Balancing Algorithm Based on Artificial Bee Colony Algorithm

Aiming at the link congestion and unbalanced load for data center network when scheduling the elephant flow by traditional methods, a load balancing algorithm based on artificial bee colony algorithm IALB (improved artificial bee colony load balancing) is proposed. In the paper we introduce the concept of stability is devoted to selecting the best transmission path for the elephant flow under the multiple constraints of path length, link load, and link stability. In order to find the best path, the algorithm redefines the fitness function according to the number of large flows on the link, the real-time load of the link, and the link stability. Experimental results show that, compared with the traditional ECMP algorithm and Hedera algorithm, the IALB algorithm can perform better in terms of link utilization and network throughput.