Neural Network-based OFDM Receiver for Resource Constrained IoT Devices

TL;DR

This paper introduces a modular neural network-based OFDM receiver for IoT devices, replacing traditional physical layer functions to enhance flexibility and reduce implementation costs, with demonstrated improvements in error rates.

Contribution

It proposes a novel, flexible, modular ML-based receiver design for OFDM in IoT, replacing key functions with neural networks and enabling resource-efficient deployment.

Findings

Improves bit error rate by 61% on simulated data

Achieves 10% error rate improvement over-the-air

Demonstrates cost-effective neural network compression techniques

Abstract

Orthogonal Frequency Division Multiplexing (OFDM)-based waveforms are used for communication links in many current and emerging Internet of Things (IoT) applications, including the latest WiFi standards. For such OFDM-based transceivers, many core physical layer functions related to channel estimation, demapping, and decoding are implemented for specific choices of channel types and modulation schemes, among others. To decouple hard-wired choices from the receiver chain and thereby enhance the flexibility of IoT deployment in many novel scenarios without changing the underlying hardware, we explore a novel, modular Machine Learning (ML)-based receiver chain design. Here, ML blocks replace the individual processing blocks of an OFDM receiver, and we specifically describe this swapping for the legacy channel estimation, symbol demapping, and decoding blocks with Neural Networks (NNs). A unique aspect of this modular design is providing flexible allocation of processing functions to the legacy or ML blocks, allowing them to interchangeably coexist. Furthermore, we study the implementation cost-benefits of the proposed NNs in resource-constrained IoT devices through pruning and quantization, as well as emulation of these compressed NNs within Field Programmable Gate Arrays (FPGAs). Our evaluations demonstrate that the proposed modular NN-based receiver improves bit error rate of the traditional non-ML receiver by averagely 61% and 10% for the simulated and over-the-air datasets, respectively. We further show complexity-performance tradeoffs by presenting computational complexity comparisons between the traditional algorithms and the proposed compressed NNs.