Reliable Low Resolution OFDM Receivers via Deep Learning

This paper develops novel deep learning-based architectures and design methodologies for an orthogonal frequency division multiplexing (OFDM) receiver under the constraint of one-bit complex quantization. Single bit quantization greatly reduces complexity and power consumption, but makes accurate data detection difficult. This is particularly true for multicarrier waveforms, which have high peak-to-average ratio in the time domain and fragile subcarrier orthogonality in the frequency domain. The severe distortion for one-bit quantization typically results in an error floor even at moderately low signal-to-noise-ratio (SNR) such as 5 dB. A neural network-based receiver - specifically, an autoencoder - jointly learns a precoder and decoder for data symbol detection. Since quantization prevents end-to-end training, we propose a two-step sequential training policy for this model. Our proposed design achieves lower bit error rate (BER) in fading than unquantized (full-resolution) OFDM at average SNRs up to 10 dB.