边缘端实时压缩风力机传感器数据，压缩比超2560:1且误差低于3%。
EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector Quantization
- 采用非对称自编码器+残差向量量化，实现高效压缩
- 压缩率2560:1至10240:1，重建误差<3%，速率11.25~45bps
- 可动态调整比特率，适合低功耗无线传感部署
我们提出EdgeCodec，一种面向风力机叶片气压数据的端到端神经压缩器。该模型采用高度非对称自编码架构，结合判别器训练与残差向量量化（Residual Vector Quantizer），在保证高保真度的前提下最大化压缩效率。在真实硬件（GAP9微控制器）上实现实时运行，压缩率可达2560:1至10240:1，重建误差低于3%，比特率范围为11.25至45 bit/s。支持逐样本动态调节比特率，可适应不同网络条件。在最高压缩模式下，无线传输能耗降低2.9倍，显著延长了传感器节点的部署寿命。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。