Reinforcement Learning-Driven QoS-Aware Intelligent Routing for Software-Defined Networks

Software-defined network (SON) is an emerging computer networking technology that disjoints the data forwarding from the centralized control and enables a highly manageable and flexible networking paradigm. There has been intensive research developed for efficient routing and resource allocation for SDNs. However, there still remain essential challenges to achieve situation-awareness networking management to ensure the application-driven Quality-of-Service (QoS) even in the presence of cyber attacks. To address this issue, in this paper, we exploit reinforcement learning (RL) technologies to develop a situation-awareness and intelligent networking management from the perspective of routing management The performance of our proposed RL-enabled routing management method is evaluated in the simulation sections by considering various scenarios.