Application of deep neural network and deep reinforcement learning in wireless communication.

Ming Li,Hui Li,Zhihan Lv

doi:10.1371/journal.pone.0235447

Ming Li, Hui Li + Show 1 more

Open Access

https://doi.org/10.1371/journal.pone.0235447

Copy DOI

Journal: PloS one	Publication Date: Jul 2, 2020
Citations: 20	License type: CC BY 4.0

Affiliation: State Intellectual Property Office

Abstract

ObjectiveTo explore the application of deep neural networks (DNNs) and deep reinforcement learning (DRL) in wireless communication and accelerate the development of the wireless communication industry.MethodThis study proposes a simple cognitive radio scenario consisting of only one primary user and one secondary user. The secondary user attempts to share spectrum resources with the primary user. An intelligent power algorithm model based on DNNs and DRL is constructed. Then, the MATLAB platform is utilized to simulate the model.ResultsIn the performance analysis of the algorithm model under different strategies, it is found that the second power control strategy is more conservative than the first. In the loss function, the second power control strategy has experienced more iterations than the first. In terms of success rate, the second power control strategy has more iterations than the first. In the average number of transmissions, they show the same changing trend, but the success rate can reach 1. In comparison with the traditional distributed clustering and power control (DCPC) algorithm, it is obvious that the convergence rate of the algorithm in this research is higher. The proposed DQN algorithm based on DRL only needs several steps to achieve convergence, which verifies its effectiveness.ConclusionBy applying DNNs and DRL to model algorithms constructed in wireless scenarios, the success rate is higher and the convergence rate is faster, which can provide experimental basis for the improvement of later wireless communication networks.

Highlights

With the rapid development of science and technology, the development of mobile networks is faster than ever
This study proposes a simple cognitive radio scenario consisting of only one primary user and one secondary user
In comparison with the traditional distributed clustering and power control (DCPC) algorithm, it is obvious that the convergence rate of the algorithm in this research is higher

Summary

Introduction

With the rapid development of science and technology, the development of mobile networks is faster than ever. In the wireless communication network, the electromagnetic spectrum resources of the radio are very precious, and the government has rationally allocated them. As the number of Internet of Things (IoT) terminals increases, the congestion situation still cannot be alleviated It doesn’t mean that the resources have been exhausted. For dynamic spectrum resource allocation, unlicensed users and authorized users are allowed to share the current frequency band. As the utilization of spectrum resources by authorized users changes over time, non-authorized users need to intelligently sense the current frequency band usage [6]. Choosing a reasonable time and communicating with appropriate power to maximize the utilization of spectrum resources and alleviating the pressure of insufficient spectrum resources have become the problems that need to be urgently solved at present. It is of great practical significance to introduce DRL into wireless communication technology

Methods

Results

Conclusion