发表机构
The Chinese University of Hong Kong, Shenzhen; The Hong Kong University of Science and Technology (Guangzhou); Southern University of Science and Technology（香港中文大学（深圳）; 香港科技大学（广州）; 南方科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出FM4NILM，一个可提示编程的基础模型，通过自然语言和示例从聚合数据中估计任意电器的功率轨迹，以单一共享模型实现多电器分解，优于专用基线。
AI 中文摘要
非侵入式负荷监测（NILM）从整户电表中估算电器级能耗，但针对特定电器的模型和固定的输出清单使得扩展覆盖范围成本高昂。我们提出了FM4NILM（用于NILM的基础模型），这是一个单一的可提示编程模型，能够根据聚合测量数据、自然语言描述以及可选的激活示例来估算所请求电器的功率轨迹。一个轻量级的、感知采样频率的Transformer在来自七个公共语料库的645k个序列上通过掩码重建进行预训练，这些序列涵盖1-60秒的采样间隔，随后使用针对部分标记 households 的观测掩码损失与电器请求进行对齐。一个伯努利-对数正态解码器将活动检测与条件功率估计分离。在来自REDD、UK-DALE和REFIT的保留 households 和时间段上，一个冻结的文本提示模型服务于十二个电器-语料库请求，实现了0.556的事件F1分数、0.625的AUPRC，以及七个特定电器基线中最低的活动窗口MAE（251.8 W）。流式分数聚合将事件F1提高到0.582，聚合延迟为60秒。在另一个类别保留评估中，添加十个激活示例将微波炉的AUPRC从0.132提高到0.214，而无需更新参数。输入干预消融实验探究了模型对电器请求和聚合测量的依赖。这些结果表明，使用一个共享模型即可实现具有竞争力的分解性能，并支持通过提示和示例扩展电器覆盖范围，而无需额外的专用网络。
英文摘要
Non-intrusive load monitoring (NILM) estimates appliance-level consumption from a whole-home meter, but appliance-specific models and fixed output inventories make coverage costly to extend. We present FM4NILM (Foundation Model for NILM), a single prompt-programmable model that estimates a requested appliance's power trajectory from aggregate measurements, a natural-language description, and optional activation exemplars. A lightweight cadence-aware transformer is pretrained by masked reconstruction on 645k sequences from seven public corpora spanning 1-60 s sampling intervals, then aligned with appliance requests using observation-masked losses for partially labeled households. A Bernoulli-lognormal decoder separates activity detection from conditional power estimation. On held-out households and time periods from REDD, UK-DALE, and REFIT, one frozen text-prompted model serves twelve appliance-corpus requests, achieving 0.556 event F1, 0.625 AUPRC, and the lowest active-window MAE (251.8 W) among seven appliance-specific baselines. Streaming score aggregation raises event F1 to 0.582 with a 60 s aggregation delay. In a separate category-held-out evaluation, adding ten activation exemplars raises microwave AUPRC from 0.132 to 0.214 without parameter updates. Input-intervention ablations probe the model's dependence on appliance requests and aggregate measurements. These results demonstrate competitive disaggregation with one shared model and support extending appliance coverage through prompts and examples rather than additional specialist networks.
CommentsPreprint
