Deep Reinforcement Learning-Based Intelligent Reflecting Surface for Cooperative Jamming Model Design

• Published in: IEEE access Vol. 11; pp. 98764 - 98775
• Main Authors: Lu, Shaofang, Shen, Xianhao, Zhang, Panfeng, Wu, Zhen, Chen, Yi, Wang, Li, Xie, Xiaolan
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Array signal processing; beam forming; Beamforming; Collaboration; collaborative jamming; Communication; Communication system security; Constraint modelling; Context; Deep learning; deep reinforcement learning; Energy efficiency; Intelligent reflective surface; Intelligent systems; Jamming; Markov processes; Optimization; power allocation; Reconfigurable intelligent surfaces; Reinforcement learning; Signal to noise ratio; Wireless communication; Wireless communications; Wireless networks
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3312546

Owing to the nature of wireless channels, wireless transmission is vulnerable to attacks by adversaries; therefore, security has always been a critical issue in wireless networks. In this context, intelligent reflecting surfaces (IRS), as an emerging and promising technology, synergize with physical layer security (PLS), offering novel avenues to enhance privacy and resistance against interference in wireless communication. This paper investigates a cooperative jamming communication model assisted by IRS. Under the constraints of minimum safe rate and inaccurate channel state information (CSI), a deep reinforcement learning (DRL)-based framework is proposed to jointly optimize the BS transmitting beamforming power distribution and IRS phase shift matrix to maximize the system energy efficiency. We first formulate an anti-jamming communication optimization problem as a Markov decision process (MDP) framework and then design a DRL-based algorithm, in which the joint design is obtained through trial-and-error interactions with the environment by observing predefined rewards in the context of continuous state and action to generate an optimal policy. The simulation results show that when the number of IRS components is increased from 20 to 100, the proposed scheme can improve energy efficiency by 40.1%, which is better than other schemes.