An Intelligent Optimization Method for Wireless Communication Network Resources Based on Reinforcement Learning

Abstract

The scarcity of spectrum resources is becoming increasingly severe, and the traditional static spectrum allocation method leads to low spectrum utilization. To address these issues, this article introduces reinforcement learning (RL) into wireless communication systems and proposes an optimization method for wireless resource allocation in deep Q networks (DQN). This paper uses the deep reinforcement learning (DRL) method to model the selection process of cluster heads and relay nodes as a Markov decision process, and then uses DQN to establish a cluster head and relay node selection mechanism aimed at maximizing the life cycle of wireless sensor network (WSN). Experimental results show that compared with the existing algorithms, the proposed algorithm effectively reduces the energy consumption of the network and extends the life cycle of WSN. Ultimately, it is possible to reconfigure relevant spectrum resources to obtain available spectrum resources, and idle spectrum resources can be discovered at any time.