Flow Path Computing in Software Defined Networking

Abstract

With the rapid growth of current network, the demand of resources is growing significantly. Insufficient bandwidth results unstable throughput in a network. Software-defined network (SDN) has been proposed to provide optimal routing decision in the presence of congestion. Equal Cost Multi-path (ECMP) routing cannot guarantee optimal resource utilization. ECMP causes the long flow collision in network because it does not consider the network parameter such as bandwidth. In this paper, the Flow Path Computing Algorithm (FPCA) is proposed to minimize the network congestion by rerouting the flows in SDN. This algorithm mainly focuses on rerouting the traffic flows over the alternative path when the network congestion is detected. If the flow demand is exceeded 10% of link bandwidth, the algorithm computes the light loaded path based on the port statistics and it shifts from the congested path to light loaded path. Simulation results are presented to show the effectiveness of the FPCA algorithm over ECMP.