Distributed Collaborative User Positioning for Cell-Free Massive MIMO with Multi-Agent Reinforcement Learning

TL;DR

This work proposes a novel two-stage distributed collaborative positioning architecture with multi-agent reinforcement learning (MARL) network, consisting of a received signal strength-based preliminary positioning network and an angle of arrival-based auxiliary correction network.

Abstract

In this paper, we investigate a cell-free massive multiple-input multiple-output system, which exhibits great potential in enhancing the capabilities of next-generation mobile communication networks. We first study the distributed positioning problem to lay the groundwork for solving resource allocation and interference management issues. Instead of relying on computationally and spatially complex fingerprint positioning methods, we propose a novel two-stage distributed collaborative positioning architecture with multi-agent reinforcement learning (MARL) network, consisting of a received signal strength-based preliminary positioning network and an angle of arrival-based auxiliary correction network. Our experimental results demonstrate that the two-stage distributed collaborative user positioning architecture can outperform conventional fingerprint positioning methods in terms of positioning accuracy.

Figures (4)

• Figure 1: Illustration of the global positioning architecture mainly consists of three parts: a cell-free mMIMO system with collaborative positioning mechanism, a RSS-based preliminary positioning network, and an AOA-based auxiliary correction network.
• Figure 2: Convergence rate over different MARL-based positioning schemes with $M=36$, $K=\tau_p=6$, $L=8$, and $\Delta = \lambda/2$.
• Figure 3: The average RMSE versus the number of APs with $K=\tau_p=6$, $L=8$, and $\Delta = \lambda/2$.
• Figure 4: The average RMSE versus the number of antennas per AP with $M=36$, $K=\tau_p=6$, and $\Delta = \lambda/2$.