Efficient Channel Autoencoders for Wideband Communications leveraging Walsh-Hadamard interleaving
🤖 AI Summary
This work addresses the challenge of jointly optimizing energy efficiency and computational complexity in wideband communications by proposing an end-to-end neural channel autoencoder based on Walsh-Hadamard interleaved transforms. The framework co-optimizes analog front-end power consumption, signal-to-noise ratio (SNR), and baseband computational complexity under short blocklength constraints. By introducing Walsh-Hadamard interleaving into neural coded modulation for the first time, the method enables hardware-transparent, high-energy-efficiency transmission that seamlessly adapts to practical radio-frequency front ends without requiring algorithmic reconfiguration. Experimental results demonstrate that, at equivalent reliability, the proposed system achieves an average 29% improvement in energy efficiency (measured in bits per joule) over the best neural baseline, incurs only a 0.14 dB SNR penalty relative to 5G Polar codes, and operates at comparable or lower total power consumption.
Application Category
📝 Abstract
This paper investigates how end-to-end (E2E) channel autoencoders (AEs) can achieve energy-efficient wideband communications by leveraging Walsh-Hadamard (WH) interleaved converters. WH interleaving enables high sampling rate analog-digital conversion with reduced power consumption using an analog WH transformation. We demonstrate that E2E-trained neural coded modulation can transparently adapt to the WH-transceiver hardware without requiring algorithmic redesign. Focusing on the short block length regime, we train WH-domain AEs and benchmark them against standard neural and conventional baselines, including 5G Polar codes. We quantify the system-level energy tradeoffs among baseband compute, channel signal-to-noise ratio (SNR), and analog converter power. Our analysis shows that the proposed WH-AE system can approach conventional Polar code SNR performance within 0.14dB while consuming comparable or lower system power. Compared to the best neural baseline, WH-AE achieves, on average, 29% higher energy efficiency (in bit/J) for the same reliability. These findings establish WH-domain learning as a viable path to energy-efficient, high-throughput wideband communications by explicitly balancing compute complexity, SNR, and analog power consumption.
Problem
Research questions and friction points this paper is trying to address.
wideband communications
energy efficiency
channel autoencoders
Walsh-Hadamard interleaving
analog-digital conversion
Innovation
Methods, ideas, or system contributions that make the work stand out.
Walsh-Hadamard interleaving
channel autoencoder
energy-efficient communication
neural coded modulation
wideband communications
🔎 Similar Papers
No similar papers found.
