在嵌入式FPGA上实现低功耗时序预测，提升暴雨下合流制污水系统韧性。
Automated Energy-Aware Time-Series Model Deployment on Embedded FPGAs for Resilient Combined Sewer Overflow Management
- 轻量级Transformer与LSTM模型经整数量化后部署于FPGA，支持边缘端高效推理。
- 8位量化Transformer模型每推理耗能0.370 mJ，MSE达0.0376；LSTM仅0.009 mJ，但准确率略低。
- 自动化硬件感知部署框架可平衡精度与能耗，适合应急场景下的本地化决策。
气候变化加剧极端天气，使老旧合流制污水系统面临更高溢流风险。准确预测污水池水位可为早期干预提供依据，缓解未经处理的污水排放。近年来，基于AI的预测方法取代了传统物理模型，但依赖云端计算，在通信中断时可靠性下降。为此，本文提出端到端预测框架，实现边缘设备上的节能推理。通过整数仅量化压缩轻量Transformer与LSTM模型，并利用自动化硬件感知部署流程，在AMD Spartan-7 XC7S15 FPGA上联合优化预测误差与能耗。基于真实污水数据评估，8位量化Transformer模型（训练用24小时历史数据）达到高精度（MSE 0.0376），单次推理能耗0.370 mJ；而最优8位LSTM模型能耗仅为0.009 mJ（低于40倍），但准确率下降14.89%（MSE 0.0432），且训练时间更长。该权衡凸显需根据部署目标选择模型：优先超低功耗选LSTM，追求高精度则选Transformer。本工作实现了本地化、低功耗预测，助力更韧性的合流制污水系统。代码开源于GitHub。
原文摘要 · Abstract (English)
Extreme weather events, intensified by climate change, increasingly challenge aging combined sewer systems, raising the risk of untreated wastewater overflow. Accurate forecasting of sewer overflow basin filling levels can provide actionable insights for early intervention, helping mitigating uncontrolled discharge. In recent years, AI-based forecasting methods have offered scalable alternatives to traditional physics-based models, but their reliance on cloud computing limits their reliability during communication outages. To address this, we propose an end-to-end forecasting framework that enables energy-efficient inference directly on edge devices. Our solution integrates lightweight Transformer and Long Short-Term Memory (LSTM) models, compressed via integer-only quantization for efficient on-device execution. Moreover, an automated hardware-aware deployment pipeline is used to search for optimal model configurations by jointly minimizing prediction error and energy consumption on an AMD Spartan-7 XC7S15 FPGA. Evaluated on real-world sewer data, the selected 8-bit Transformer model, trained on 24 hours of historical measurements, achieves high accuracy (MSE 0.0376) at an energy cost of 0.370 mJ per inference. In contrast, the optimal 8-bit LSTM model requires significantly less energy (0.009 mJ, over 40x lower) but yields 14.89% worse accuracy (MSE 0.0432) and much longer training time. This trade-off highlights the need to align model selection with deployment priorities, favoring LSTM for ultra-low energy consumption or Transformer for higher predictive accuracy. In general, our work enables local, energy-efficient forecasting, contributing to more resilient combined sewer systems. All code can be found in the GitHub Repository (https://github.com/tianheng-ling/EdgeOverflowForecast).
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。