DeepWiPHY: Deep Learning-based Receiver Design and Dataset for IEEE 802.11ax Systems

TL;DR

DeepWiPHY introduces a deep learning-based receiver for IEEE 802.11ax that replaces traditional modules, trained on synthetic and real-world data, achieving comparable or better performance in diverse conditions.

Contribution

This work presents a novel deep learning-based receiver architecture for IEEE 802.11ax, trained on extensive synthetic and real-world datasets, outperforming conventional methods without architecture fine-tuning.

Findings

DeepWiPHY achieves similar or better BER and PER than traditional receivers.

It performs well across various channel models and SNR levels.

The dataset includes 110 million synthetic and 14 million real-world OFDM symbols.

Abstract

In this work, we develop DeepWiPHY, a deep learning-based architecture to replace the channel estimation, common phase error (CPE) correction, sampling rate offset (SRO) correction, and equalization modules of IEEE 802.11ax based orthogonal frequency division multiplexing (OFDM) receivers. We first train DeepWiPHY with a synthetic dataset, which is generated using representative indoor channel models and includes typical radio frequency (RF) impairments that are the source of nonlinearity in wireless systems. To further train and evaluate DeepWiPHY with real-world data, we develop a passive sniffing-based data collection testbed composed of Universal Software Radio Peripherals (USRPs) and commercially available IEEE 802.11ax products. The comprehensive evaluation of DeepWiPHY with synthetic and real-world datasets (110 million synthetic OFDM symbols and 14 million real-world OFDM symbols) confirms that, even without fine-tuning the neural network's architecture parameters, DeepWiPHY achieves comparable performance to or outperforms the conventional WLAN receivers, in terms of both bit error rate (BER) and packet error rate (PER), under a wide range of channel models, signal-to-noise (SNR) levels, and modulation schemes.