Access Point Deployment for Localizing Accuracy and User Rate in Cell-Free Systems

TL;DR

This work addresses the challenge of deploying access points in cell-free ISAC systems to balance sensing accuracy and user rate. It proposes a unified objective that blends sensing via the Fisher information determinant with Euclidean geometric considerations and the sum-rate, and tackles the resulting non-convex, high-dimensional optimization with Soft Actor-Critic reinforcement learning. The approach is instantiated as a Markov decision process with discrete states and actions, and SAC is used to learn deployment policies that optimize the joint metric across trajectories, achieving robust convergence and fairness. Empirical results show SAC outperforming other DRL methods, with gains that scale as more APs are deployed, highlighting the practical impact for scalable, integrated sensing and communication in next-generation networks.

Abstract

Evolving next-generation mobile networks is designed to provide ubiquitous coverage and networked sensing. With utility of multi-view sensing and multi-node joint transmission, cell-free is a promising technique to realize this prospect. This paper aims to tackle the problem of access point (AP) deployment in cell-free systems to balance the sensing accuracy and user rate. By merging the D-optimality with Euclidean criterion, a novel integrated metric is proposed to be the objective function for both max-sum and max-min problems, which respectively guarantee the overall and lowest performance in multi-user communication and target tracking scenario. To solve the corresponding high dimensional non-convex multi-objective problem, the Soft actor-critic (SAC) is utilized to avoid risk of local optimal result. Numerical results demonstrate that proposed SAC-based APs deployment method achieves $20\%$ of overall performance and $120\%$ of lowest performance.

Figures (5)

• Figure 1: Cell-free ISAC systems.
• Figure 2: Architecture of SAC-based cell-free ISAC APs deployment system.
• Figure 3: Accumulative ISAC rewards of different DRL Algorithms. (a) Max-sum problem. (b) Max-min problem.
• Figure 4: APs deployment results of max-sum problem.
• Figure 5: APs deployment results of max-min problem.