Congestion prevention mechanism based on Q-leaning for efficient routing in SDN
Seonhyeok Kim, Jaehyeok Son, Ashis Talukder, Choong Seon Hong · 2016
SDN (Software-Defined Networking) has been proposed to solve problems caused by difficulties in central management, vendor dependency, and increase in complexity of network due to individual process. In current SDN, however, routing algorithm is mainly based on Dijkstra's Algorithm and the shortest Flow Path is selected to deliver packets. This may result in network congestion since bandwidth overhead is not considered when a lot of traffic enters in the network. Therefore, we propose a mechanism to prevent network congestion based on Q-learning for efficient routing in SDN. In this paper, we show the network congestion can be improved by reselecting the path and changing Flow Table using predefined threshold and Q-learning routing algorithm.