轻量级网络提升工业用电设备分解精度与速度
SEDR-Seq2P: A Lightweight Dilated Residual Sequence-to-Point Network for Multi-Task Industrial NILM
- 用空洞残差块和注意力机制改进序列到点模型
- 在IMDELD数据集上MAE降7%，匹配率升0.8%
- 推理延迟比WaveNet低58%，适合工业部署
工业级非侵入式负载监测（NILM）因测量噪声和多设备并发运行，导致基于住宅数据训练的模型泛化能力差。本文采用一对多、多任务分解框架，用单个网络从总功率中估计多个工业设备负载。在IMDELD数据集上，统一评估了Seq2Seq、Seq2SubSeq、Seq2Point、GRU和WaveNet，以能量估计算法和准确率-延迟标准为指标。虽然Seq2Point在准确率-延迟平衡上优于Seq2Seq/Seq2SubSeq，但GRU和WaveNet虽精度更高，计算成本显著增加。为此，提出SEDR-Seq2P，一种轻量级的Seq2Point扩展，引入空洞残差块和挤压-激励注意力机制。相较于基准模型Seq2Point，SEDR-Seq2P将平均绝对误差（MAE）降低约7%，决定系数（R²）提升约1%，匹配率提高约0.8%。相比WaveNet，其推理延迟降低约58%，实现了更优的准确率-延迟权衡，适用于可扩展的工业部署。
原文摘要 · Abstract (English)
Industrial NILM remains challenging because measurement noise and widespread concurrent machine operation reduce the generalization of models tuned on residential data. This work adopts a one-to-many, multi-task disaggregation setting, in which a single network estimates multiple industrial machine loads from aggregate power. Under a unified evaluation protocol on IMDELD, we benchmark Seq2Seq, Seq2SubSeq, Seq2Point, GRU, and WaveNet using energy-estimation metrics and the accuracy-delay criterion. While Seq2Point offers a stronger accuracy-delay balance than Seq2Seq/Seq2SubSeq, GRU and WaveNet achieve higher accuracy at markedly higher computational cost. To close this gap, we propose SEDR-Seq2P, a lightweight Seq2Point extension with dilated residual blocks and squeeze-and-excitation attention. Relative to the Seq2Point baseline, SEDR-Seq2P reduces MAE by approximately 7%, improves the coefficient of determination by approximately 1%, and increases the match rate by approximately 0.8%. In addition, compared to WaveNet, SEDR-Seq2P reduces inference latency by approximately 58%, yielding a favorable accuracy-delay trade-off for scalable industrial deployment.
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。