Adapting to Reality: Over-the-Air Validation of AI-Based Receivers Trained with Simulated Channels

TL;DR

This paper demonstrates that training AI-based wireless receivers on diverse simulated channels and validating over-the-air can significantly improve real-world performance and robustness, highlighting the importance of tailored channel models.

Contribution

It introduces a method for training CNN-based OFDM receivers with diversified simulated channels and validates their performance OTA, emphasizing the need for realistic testing environments.

Findings

DeepRx outperforms conventional receivers in diverse conditions.

Diverse training data improves OTA performance and robustness.

Narrowly scoped models may hinder generalization.

Abstract

Recent research shows that integrating artificial intelligence (AI) into wireless communication systems can significantly improve spectral efficiency. However, most AI-based receiver studies rely on simulated radio channel data for both training and validation, raising concerns about real-world generalization, which is vital for ensuring reliable field performance. In this study, we train DeepRx, a convolutional neural network (CNN)-based OFDM receiver, under various simulated channel scenarios and validate its performance over-the-air (OTA) using software-defined radio (SDR) technology in a small cell-type setup. To enhance receiver training, we investigate a randomized 3GPP TS38.901 channel model to diversify the training data, thereby improving performance over conventional receivers and matching or exceeding the performance of receivers trained on narrowly targeted channel models. These results demonstrate DeepRx's robust generalization capability and suggest that narrowly scoped, individual TS38.901 models can compromise both training and validation, underscoring the need for tailored channel models, careful training strategies, and OTA testing in learned receiver development.