Traffic-aware optimal routing in software defined networks by predicting traffic using neural network

Abstract

Network infrastructure management has been completely transformed by Software-Defined Networking (SDN), allowing for centralized control and programmability. The significant challenge in SDN is to provide optimal routing decisions based on real-time network performance metrics. In this work, it is proposed to have Gated Recurrent Unit (GRU) based traffic prediction to dynamically adjust link weights in SDN. It facilitates real-time adaptation to traffic changes and optimal routing decisions for improved Quality of Service (QoS). This work is to provide optimal routing in SDN by leveraging the capability of GRU to predict future traffic based on network performance metrics sampled at different time sequences. It enables the network to adapt the changing traffic patterns in real-time. The predicted traffic is then used to determine the edge weights between links in the network, which are updated dynamically to reflect changes in the network. When an outbound packet is received, it can be routed optimally by selecting a path with less traffic, thereby reducing latency and improving the QoS of routing the packets. The simulation results reveals that the proposed methodology has the potential to reduce delay up to 9.16% and jitter up to 32.31%, coupled with significant throughput enhancements up to 26.81% compared to the default shortest path. These quantitative findings highlight its effective contribution towards optimizing network performance and QoS.