An End-to-End Neural Network Transceiver Design for OFDM System with FPGA-Accelerated Implementation

TL;DR

This paper introduces neural network models to replace traditional OFDM transceiver modules, achieving improved performance and efficiency on FPGA hardware for 6G wireless systems.

Contribution

It proposes end-to-end trained neural networks for OFDM transceivers and a specialized FPGA accelerator, enhancing performance and reducing latency.

Findings

Achieves approximately 1.5 dB BER gain over conventional systems.

Reduces execution time by up to 66%.

Maintains operator equivalence for hybrid deployment.

Abstract

The evolution toward sixth-generation (6G) wireless networks demands high-performance transceiver architectures capable of handling complex and dynamic environments. Conventional orthogonal frequency-division multiplexing (OFDM) receivers rely on cascaded discrete Fourier transform (DFT) and demodulation blocks, which are prone to inter-stage error propagation and suboptimal global performance. In this work, we propose two neural network (NN) models DFT-Net and Demodulation-Net (Demod-Net) to jointly replace the IDFT/DFT and demodulation modules in an OFDM transceiver. The models are trained end-to-end (E2E) to minimize bit error rate (BER) while preserving operator equivalence for hybrid deployment. A customized DFT-Demodulation Net Accelerator (DDNA) is further developed to efficiently map the proposed networks onto field-programmable gate array (FPGA) platforms. Leveraging fine-grained pipelining and block matrix operations, DDNA achieves high throughput and flexibility under stringent latency constraints. Experimental results show that the DL-based transceiver consistently outperforms the conventional OFDM system across multiple modulation schemes. With only a modest increase in hardware resource usage, it achieves approximately 1.5 dB BER gain and up to 66\% lower execution time.