EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector Quantization

TL;DR

EdgeCodec is a lightweight neural compression system for wind turbine sensor data, achieving high compression rates with low error and real-time operation on microcontrollers, reducing energy use and extending sensor lifetime.

Contribution

It introduces a novel autoencoder-based neural compressor with residual vector quantization optimized for edge devices and variable bitrate adaptation.

Findings

Achieves compression rates up to 10,240:1 with less than 3% error.

Operates in real time on microcontrollers like GAP9.

Reduces energy consumption of wireless transmission by up to 2.9x.

Abstract

We present EdgeCodec, an end-to-end neural compressor for barometric data collected from wind turbine blades. EdgeCodec leverages a heavily asymmetric autoencoder architecture, trained with a discriminator and enhanced by a Residual Vector Quantizer to maximize compression efficiency. It achieves compression rates between 2'560:1 and 10'240:1 while maintaining a reconstruction error below 3%, and operates in real time on the GAP9 microcontroller with bitrates ranging from 11.25 to 45 bits per second. Bitrates can be selected on a sample-by-sample basis, enabling on-the-fly adaptation to varying network conditions. In its highest compression mode, EdgeCodec reduces the energy consumption of wireless data transmission by up to 2.9x, significantly extending the operational lifetime of deployed sensor units.