DFRDRL: a dynamic fuzzy routing algorithm based on deep reinforcement learning with guaranteed latency and bandwidth for software-defined networks

作者：Yonghong Wang, Marini Othman, Wou Onn Choo, Ruiqing Liu, Xiaofeng Wang · 发表于：Journal Of Big Data · 年份：2024 · DOI：10.1186/s40537-024-01029-x · 被引用次数：20 · 研究领域：Software-Defined Networks and 5G、Advanced Optical Network Technologies、Software System Performance and Reliability

Traditional routing algorithms have several limitations that become increasingly significant in the context of Software-Defined Networking (SDN). Firstly, these algorithms often have limited support for Quality of Service (QoS) requirements, making them less suitable for handling diverse traffic types efficiently. Moreover, current SDN controllers leverage a default shortest-path routing approach, which does not allow for more dynamic and flexible traffic management based on real-time network policies. To address these issues, this paper introduces a Dynamic Fuzzy Routing algorithm based on Deep Reinforcement Learning (DRL) for SDN that provides guaranteed latency and bandwidth (DFRDRL). DFRDRL provides intelligent and efficient routing that adapts to dynamic traffic by considering path-state criteria and using DRL. Fuzzy logic mainly performs online routing between an ingress-egress pair. To adapt to dynamic traffic changes, DFRDRL can predict the traffic matrix in real time. Meanwhile, DFRDRL reduces the routing reliance on network topology by weighting the network based on critical nodes. Additionally, when the network experiences congestion based on the traffic matrix, a deferral mechanism is applied to prioritize requests with lower resource demands. This mechanism helps ensure efficient resource allocation by temporarily postponing or queuing higher-demand requests, thereby optimizing overall network performance during periods of congestion. The simulation results show ...