Joint Optimizations for Double-IRS' Cooperative Positioning and Beamforming Over Massive-MIMOAP Based 6G Secure Mobile Wireless Networks

Intelligent reflecting surface (IRS) has been widely recognized as one of the key techniques to improve secure communications performances. However, most existing works mainly focus on the passive beamforming, i.e., phase-shifts, design of a single IRS, without taking into account the cooperations among multiple IRSs and the optimizations of their relative positions. To overcome these deficiencies, in this paper we propose the joint optimizations between the transmit beamforming of massive multiple-input multiple-output (massive-MIMO) access point (AP) and double-IRS' positions and passive beamforming over 6G secure mobile networks. In our proposed networking architectures, AP transmits data to multiple mobile users (MUs) through reflections of two cooperative IRSs under the existence of one eavesdropper (Eve). First, we formulate a secrecy rate optimization problem to maximize the expectations of all MUs' aggregate secrecy rates when Eve's exact position is unknown. Second, leveraging the deep reinforcement learning (DRL), we develop two joint deploying and beamforming schemes to tackle the uncertainty of Eve's exact position. Finally, we validate and evaluate our developed schemes by conducting the extensive simulations, showing the significant performances improvements of our developed schemes through jointly optimizing IRSs' positions/orientations and transmit-beamforming of massive-MIMOAP as the function of the predicted Eve's deploying areas.