Trimming the Fat from OFDM: Pilot- and CP-less Communication with End-to-end Learning
This addresses spectral efficiency for wireless communication systems, offering a novel approach that is incremental in combining neural networks with OFDM.
The paper tackled the spectral efficiency loss in OFDM due to cyclic prefix and pilots by proposing a neural network-based receiver with learned constellation geometry, achieving at least 18% throughput gains over baseline methods without significant bit error rate loss.
Orthogonal frequency division multiplexing (OFDM) is one of the dominant waveforms in wireless communication systems due to its efficient implementation. However, it suffers from a loss of spectral efficiency as it requires a cyclic prefix (CP) to mitigate inter-symbol interference (ISI) and pilots to estimate the channel. We propose in this work to address these drawbacks by learning a neural network (NN)-based receiver jointly with a constellation geometry and bit labeling at the transmitter, that allows CP-less and pilotless communication on top of OFDM without a significant loss in bit error rate (BER). Our approach enables at least 18% throughput gains compared to a pilot and CP-based baseline, and at least 4% gains compared to a system that uses a neural receiver with pilots but no CP.