Deep Learning based Three-stage Solution for ISAC Beamforming Optimization

TL;DR

This paper introduces a three-stage deep learning framework for optimizing beamforming in integrated sensing and communication (ISAC) systems, enhancing performance in multi-user scenarios with target detection.

Contribution

The paper proposes a novel three-stage deep learning approach combining unsupervised, reinforcement, and supervised learning for ISAC beamforming optimization, outperforming baseline RL methods.

Findings

Outperforms baseline RL algorithms in beamforming optimization

Effective extraction of channel features from variable CSI

Improved beampattern design for ISAC systems

Abstract

In this paper, a general ISAC system where the base station (BS) communicates with multiple users and performs target detection is considered. Then, a sum communication rate maximization problem is formulated, subjected to the constraints of transmit power and the minimum sensing rates of users. To solve this problem, we develop a framework that leverages deep learning algorithms to provide a three-stage solution for ISAC beamforming. The three-stage beamforming optimization solution includes three modules: 1) an unsupervised learning based feature extraction algorithm is proposed to extract fixed-size latent features while keeping its essential information from the variable channel state information (CSI); 2) a reinforcement learning (RL) based beampattern optimization algorithm is proposed to search the desired beampattern according to the extracted features; 3) a supervised learning based beamforming reconstruction algorithm is proposed to reconstruct the beamforming vector from beampattern given by the RL agent. Simulation results demonstrate that the proposed three-stage solution outperforms the baseline RL algorithm by optimizing the intuitional beampattern rather than beamforming.