An Adaptive Multi-Path Routing Algorithm in Cognitive Wireless Mesh Networks

Nodes perceived environment and selected the appropriate route for business transfers in Cognitive Wireless Mesh Network. However, the variation of spectrum holes results in the change of routes which brings negative effects on the data transmission. An adaptive multi-path algorithm that uses reinforcement learning based on multi-agent is proposed in this paper. Better route can always be obtained to transmit data when route changes. The simulation results show that the algorithm can reduce network latency and improve network performance.