用提示词让大模型做不用训练的电器用电分解，泛化强还看得懂。
Prompting Large Language Models for Training-Free Non-Intrusive Load Monitoring
- 用提示词注入电器特征和时序样例，让大模型通过上下文学习完成分解。
- 在不同房屋和区域间迁移表现好，但复杂场景性能仍不如传统深度模型。
- 结果可读性强，适合需要解释性的能源管理场景。
非侵入式负载监测（NILM）旨在将总用电量分解为单个电器的使用情况，从而实现更有效的能源管理。尽管深度学习推动了NILM的发展，但仍受限于标注数据依赖、泛化能力差和缺乏可解释性。本文提出首个基于提示词的NILM框架，利用大语言模型（LLM）的上下文学习能力。我们设计并评估了融合电器特征、上下文信息与代表性时序样例的提示策略，通过大量案例研究验证其有效性。在REDD和UK-DALE数据集上的实验表明，仅靠提示引导的LLM仅具备基础的NILM能力，复杂场景下性能仍落后于传统深度学习模型。然而，实验也显示，仅通过调整注入的电器特征，即可实现跨房屋甚至跨区域的良好泛化。同时，该方法能提供清晰可读的推理解释。研究结果明确了纯提示驱动的LLM在NILM任务中的能力边界，其在泛化性和可解释性方面的优势为该领域开辟了新方向。
原文摘要 · Abstract (English)
Non-intrusive load monitoring (NILM) aims to disaggregate total electricity consumption into individual appliance usage, thus enabling more effective energy management. While deep learning has advanced NILM, it remains limited by its dependence on labeled data, restricted generalization, and lack of explainability. This paper introduces the first prompt-based NILM framework that leverages large language models (LLMs) with in-context learning. We design and evaluate prompt strategies that integrate appliance features, contextual information, and representative time-series examples through extensive case studies. Extensive experiments on the REDD and UK-DALE datasets show that LLMs guided solely by prompts deliver only basic NILM capabilities, with performance that lags behind traditional deep-learning models in complex scenarios. However, the experiments also demonstrate strong generalization across different houses and even regions by simply adapting the injected appliance features. It also provides clear, human-readable explanations for the inferred appliance states. Our findings define the capability boundaries of using prompt-only LLMs for NILM tasks. Their strengths in generalization and explainability present a promising new direction for the field.
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。