Brain-Inspired Wireless Communications: Where Reservoir Computing Meets MIMO-OFDM

Abstract

Reservoir computing (RC) is a class of neuromorphic computing approaches that deals particularly well with time-series prediction tasks. It significantly reduces the training complexity of recurrent neural networks and is also suitable for hardware implementation whereby device physics are utilized in performing data processing. In this paper, the RC concept is applied to detecting a transmitted symbol in multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. Due to wireless propagation, the transmitted signal may undergo severe distortion before reaching the receiver. The nonlinear distortion introduced by the power amplifier at the transmitter may further complicate this process. Therefore, an efficient symbol detection strategy becomes critical. The conventional approach for symbol detection at the receiver requires accurate channel estimation of the underlying MIMO-OFDM system. However, in this paper, we introduce a novel symbol detection scheme where the estimation of the MIMO-OFDM channel becomes unnecessary. The introduced scheme utilizes an echo state network (ESN), which is a special class of RC. The ESN acts as a black box for system modeling purposes and can predict nonlinear dynamic systems in an efficient way. Simulation results for the uncoded bit error rate of nonlinear MIMO-OFDM systems show that the introduced scheme outperforms conventional symbol detection methods.

Learning for Detection: MIMO-OFDM Symbol Detection Through Downlink Pilots

“…In this paper, we considered the application of reservoir computing, a special RNN, to MIMO-OFDM symbol detection. Compared to our previous work [29], a new RC based detector, WESN, is introduced as the receiver to significantly improve the performance of interference…”

“…Meanwhile, the untrained layers are sampled from the distribution with well-designed conditions. An RC-based MIMO-OFDM symbol detector is first introduced in our previous work [29], [30]. With limited training, [29] shows that the RCbased symbol detector can effectively combat the non-linear distortion caused by PA.…”

“…An RC-based MIMO-OFDM symbol detector is first introduced in our previous work [29], [30]. With limited training, [29] shows that the RCbased symbol detector can effectively combat the non-linear distortion caused by PA. However, our previous introduced RC-based symbol detector has a very simple neural network architecture and does not work well for scattered pilot patterns.…”

Artificial Intelligence-Enabled Cellular Networks: A Critical Path to Beyond-5G and 6G

“…On the other hand, learning-based approaches can provide robust performance without relying on detailed channel models. For example, the works in [1], [2] show that through end-toend training of DNNs, AI models can outperform conventional MIMO symbol detection approaches even under imperfect receiver CSI. Meanwhile, AI models can also be applied for interference cancellation to improve receiver performance.…”

Deep Learning Enabled Optimization of Downlink Beamforming Under Per-Antenna Power Constraints: Algorithms and Experimental Demonstration

“…One of the areas of interest is to deal with scenarios in which the channel model does not exist, e.g., in underwater and molecular communications [26] or is difficult to characterize analytically due to imperfections and nonlinearities [27]. In these situations, DL based detection has been proposed to tackle the underlying unknown nonlinearities [28]. Another area of interest is to optimize the end-to-end system performance [29], [30].…”