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

TL;DR

This paper proposes a novel two-stage distributed collaborative user positioning system using multi-agent reinforcement learning for cell-free massive MIMO, significantly improving accuracy over traditional fingerprint methods.

Contribution

It introduces a new two-stage distributed positioning architecture with MARL, combining signal strength and angle of arrival for enhanced accuracy in cell-free massive MIMO.

Findings

Outperforms traditional fingerprint positioning in accuracy

Demonstrates effectiveness of MARL in distributed positioning

Enhances resource allocation and interference management

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.