ML-Based Massive MIMO Channel Prediction: Does It Work on Real-World Data?
Muhammad Karam Shehzad, Luca Rose, Stefan Wesemann, Mohamad Assaad
Abstract
Accurate channel state information (CSI) acquisition is hindered by CSI estimation errors, compression, feedback, and processing delays. We propose a machine learning (ML)-based massive multiple-input multiple-output (mMIMO) channel predictor (CP), which can work on the estimated channel and the compressed version of the estimated channel as well. While existing work has evaluated the performance of ML algorithms by only using the artificially generated channel realizations, this letter reports the results of the ML algorithm using the real-world channel realizations from a measurement campaign performed at Nokia Bell-Labs. The results corroborate the validity of the proposed ML-based CP.