A reinforcement learning approach for widest path routing in software-defined networks
Chih‐Heng Ke, Yi-Hao Tu, Yi‐Wei Ma
Abstract
In this paper, a routing method based on reinforcement learning (RL) under software-defined networks (SDN), namely the Q-learning widest-path routing algorithm (Q-WPRA), is proposed. This algorithm processes the reward function according to the link bandwidth in the execution environment to find the optimal (i.e., widest) transmission path with the maximum bandwidth between the source and the destination through RL. The experimental results reveal that the Q-WPRA is outperformance than Dijkstra’s algorithm and Dijkstra’s widest-path algorithm to find the widest transmission path in SDN environment under different bandwidths, loss rates, and background traffic.
Topics & Concepts
Dijkstra's algorithmReinforcement learningComputer sciencePath (computing)Routing (electronic design automation)Routing algorithmBandwidth (computing)Shortest path problemEqual-cost multi-path routingQ-learningComputer networkSoftwareSoftware-defined networkingDistributed computingLink-state routing protocolAlgorithmRouting protocolArtificial intelligenceTheoretical computer scienceGraphProgramming languageSoftware-Defined Networks and 5GAdvanced Photonic Communication SystemsAdvancements in Semiconductor Devices and Circuit Design