CSI-based Outdoor Localization for Massive MIMO: Experiments with a Learning Approach

TL;DR

This paper explores a learning-based method using CSI-derived covariance matrices for outdoor user localization in 5G Massive MIMO systems, validated through real-world experiments on a Huawei testbed.

Contribution

It introduces a novel approach leveraging learning algorithms, especially extreme learning machines, for accurate outdoor localization using Massive MIMO CSI data.

Findings

Effective localization accuracy demonstrated with experimental data

Extreme learning machines provide robust performance benchmarks

Practical deployment considerations discussed for 5G networks

Abstract

We report on experimental results on the use of a learning-based approach to infer the location of a mobile user of a cellular network within a cell, for a 5G-type Massive multiple input, multiple output (MIMO) system. We describe how the sample spatial covariance matrix computed from the CSI can be used as the input to a learning algorithm which attempts to relate it to user location. We discuss several learning approaches, and analyze in depth the application of extreme learning machines, for which theoretical approximate performance benchmarks are available, to the localization problem. We validate the proposed approach using experimental data collected on a Huawei 5G testbed, provide some performance and robustness benchmarks, and discuss practical issues related to the deployment of such a technique in 5G networks.