BL‐Hybrid: A graph‐theoretic approach to improving software‐defined networking‐based data center network performance

Abstract

AbstractExisting data centers can handle a massive amount of data transmitted in a short time with minimum errors. Data center networks (DCNs) use cost‐effective, multipath topologies to distribute flows through alternative paths between core layers and hosting servers. Software‐defined networking (SDN) separates the control plane from the data plane to ease network management. To perform active load balancing among different paths, we address the challenges of load balancing in multipath DCNs. However, most DCNs' load balancing systems rely on a static approach that distributes flows among different paths sequentially, regardless of the path status. Consequently, some paths become congested, degrading the overall performance of the DCN in terms of throughput and delay. Increasing the number of requests worsens the congestion problem, causing some connections to become overwhelmed, thereby decreasing DCN efficiency. In this paper, we propose and evaluate the performance of a novel dynamic load‐balancing system named BL‐Hybrid, which uses the graph‐theoretical centrality of betweenness as a base metric for data forwarding. We perform a comprehensive comparative analysis of our proposed method relative to the round‐robin and least‐congested algorithms in different traffic scenarios, using the most popular SDN‐based DCNs, namely, fat tree, BCube, and DCell. Our evaluation results show that BL‐Hybrid outperforms the round‐robin and least‐congested schemes. It maximizes the average throughput by 4% and 11% and the average data transferred by 7% and 13%, respectively. Also, it reduces the average round‐trip time latency by 14% and 41%, respectively.