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).

翻译：气候变化加剧的极端天气事件日益挑战老化的合流制排水系统，增加了未经处理污水溢流的风险。准确预测污水溢流调蓄池的填充水位可为早期干预提供可操作的见解，有助于缓解不受控的排放。近年来，基于人工智能的预测方法为传统物理模型提供了可扩展的替代方案，但其对云计算的依赖在通信中断期间限制了可靠性。为此，我们提出一种端到端预测框架，支持直接在边缘设备上进行高效节能的推理。我们的解决方案集成了轻量级Transformer与长短期记忆（LSTM）模型，并通过纯整数量化压缩以实现高效的设备端执行。此外，采用自动化硬件感知部署流水线，通过在AMD Spartan-7 XC7S15 FPGA上联合最小化预测误差与能耗来搜索最优模型配置。基于真实污水数据的评估表明，经过24小时历史数据训练的8位Transformer模型在每次推理能耗为0.370 mJ的条件下实现了高精度（MSE 0.0376）。相比之下，最优的8位LSTM模型能耗显著更低（0.009 mJ，降低40倍以上），但精度下降14.89%（MSE 0.0432）且训练时间大幅延长。这种权衡凸显了模型选择需与部署优先级相匹配：LSTM适用于超低能耗场景，而Transformer更适合高预测精度需求。总体而言，我们的工作实现了本地化、高能效的预测，有助于构建更具韧性的合流制排水系统。所有代码可在GitHub仓库（https://github.com/tianheng-ling/EdgeOverflowForecast）中获取。