Research on Topology Planning for Wireless Mesh Networks Based on Deep Reinforcement Learning

Abstract

Focus on the access point deployment and topology control problem in Wireless Mesh Networks (WMNs), a topology planning method based on deep reinforcement learning was proposed. Developing a method of sample data generation using monte-carlo tree search and self-game, then a policy and value network based on residual network was established. A model based on Tensorflow was developed to solve the training problem. Finally, simulation results show that the proposed method can provide efficient network planning solution with high performance on timeliness and validity.