SICNN: Soft Interference Cancellation Inspired Neural Network Equalizers

TL;DR

This work addresses equalization in SC-FDE systems by introducing SICNN, a neural network equalizer created through deep unfolding of a soft interference cancellation algorithm. SICNNv1 is tailored for SC-FDE, while SICNNv2 offers broader applicability to block-based systems such as UW-OFDM; parameter-reduced variants further cut training complexity. A novel training-set generation method markedly improves high-SNR BER performance, and extensive simulations show SICNNv1 achieving state-of-the-art BER, with SICNNv2 demonstrating universal applicability. The study also provides a comprehensive complexity analysis, highlighting practical advantages and guiding design choices for NN-based equalizers in communications receivers.

Abstract

In recent years data-driven machine learning approaches have been extensively studied to replace or enhance traditionally model-based processing in digital communication systems. In this work, we focus on equalization and propose a novel neural network (NN-)based approach, referred to as SICNN. SICNN is designed by deep unfolding a model-based iterative soft interference cancellation (SIC) method. It eliminates the main disadvantages of its model-based counterpart, which suffers from high computational complexity and performance degradation due to required approximations. We present different variants of SICNN. SICNNv1 is specifically tailored to single carrier frequency domain equalization (SC-FDE) systems, the communication system mainly regarded in this work. SICNNv2 is more universal and is applicable as an equalizer in any communication system with a block-based data transmission scheme. Moreover, for both SICNNv1 and SICNNv2, we present versions with highly reduced numbers of learnable parameters. Another contribution of this work is a novel approach for generating training datasets for NN-based equalizers, which significantly improves their performance at high signal-to-noise ratios. We compare the bit error ratio performance of the proposed NN-based equalizers with state-of-the-art model-based and NN-based approaches, highlighting the superiority of SICNNv1 over all other methods for SC-FDE. Exemplarily, to emphasize its universality, SICNNv2 is additionally applied to a unique word orthogonal frequency division multiplexing (UW-OFDM) system, where it achieves state-of-the-art performance. Furthermore, we present a thorough complexity analysis of the proposed NN-based equalization approaches, and we investigate the influence of the training set size on the performance of NN-based equalizers.

Figures (10)

• Figure 1: Schematic structure of one stage of SICNNv1.
• Figure 2: Schematic structure of one stage of SICNNv2.
• Figure 3: BER performance of the iterative SIC method and SICNNv1 for different numbers of iterations / stages $Q$ (SC-FDE with UW guard, QPSK).
• Figure 4: BER performance of NN-based and model-based equalizers for SC-FDE with a UW guard interval and QPSK alphabet.
• Figure 5: BER performance comparison of NN-based equalizers for SC-FDE with a UW guard interval and QPSK alphabet, when being trained with randomly generated training data (rand. tr. data), or on a training set generated by the proposed approach.