Optimizing incremental SDN upgrades for load balancing in ISP networks

Abstract

Software defined network (SDN) can dynamically and timely reply to the changes of network states, thus enabling advance traffic engineering mechanisms. To enhance the management ability of the network, Internet Service Providers (ISPs) are upgrading traditional network devices to SDN devices incrementally. In this paper, we study the k-LB problem, i.e., upgrading at most k legacy switches to SDN switches to achieve load balance. We prove that k-LB problem is NP-hard and there is no polynomial time (N+M)1−ϵ-approximation algorithm for any constant ϵ>0 unless P=NP, where N (M) is the number of switches (links) in the network. Nevertheless, we propose an effective greedy algorithm and prove that it reaches an approximation guarantee of cavgcminM, where cavg (cmin) is the average (minimum) link capacity. Furthermore, we show that the greedy algorithm touches the tight lower bound of approximation ratio by extending the inapproximability result. The simulation results from large-scale ISP network topologies illustrate the effectiveness of our algorithm and show that the maximum link utilization can be decreased by 30% on average compared with the SOTA.