Improving Triplet-Based Channel Charting on Distributed Massive MIMO Measurements

TL;DR

This paper enhances triplet-based channel charting for distributed massive MIMO systems by analyzing triplet selection, transferability, and performance on real and simulated datasets, aiming to improve radio environment mapping.

Contribution

It introduces improved triplet selection strategies and evaluates transferability of channel charting models across different radio environments.

Findings

Triplet selection significantly impacts charting accuracy.

Transferability of learned functions is feasible between similar environments.

Simulated triplets can approximate real-world measurements effectively.

Abstract

The objective of channel charting is to learn a virtual map of the radio environment from high-dimensional CSI that is acquired by a multi-antenna wireless system. Since, in static environments, CSI is a function of the transmitter location, a mapping from CSI to channel chart coordinates can be learned in a self-supervised manner using dimensionality reduction techniques. The state-of-the-art triplet-based approach is evaluated on multiple datasets measured by a distributed massive MIMO channel sounder, with both co-located and distributed antenna setups. The importance of suitable triplet selection is investigated by comparing results to channel charts learned from a genie-aided triplet generator and learned from triplets on simulated trajectories through measured data. Finally, the transferability of learned forward charting functions to similar, but different radio environments is explored.