发表机构
EDF R&D; Université Paris Cité（法国电力集团研发部; 巴黎西岱大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
LoaDiff是一种基于扩散的生成模型，用于生成亚小时级居民电耗曲线，支持静态和动态条件控制，在保真度、多样性和下游应用上表现优异。
AI 中文摘要
能源转型正在通过分布式发电、电气化电器和需求响应项目的日益普及，重塑居民用电模式。理解这些不断演变的行为需要获取细粒度的智能电表数据，以用于负荷预测、电器检测和需求侧灵活性分析等应用。然而，此类数据受到严格的访问限制和数据保护法规的约束。因此，现实的合成替代数据是必要的。在本文中，我们提出了LoaDiff，一种基于扩散的生成模型，用于生成年度、亚小时级的智能电表负荷曲线。LoaDiff支持对静态家庭属性（如电器拥有情况）和动态上下文变量（包括日历信息和室外温度）进行灵活的条件控制。我们在三个居民用电数据集上，将该模型与多个生成基线进行了评估。我们的实验评估了四个互补维度：保真度和多样性、训练记录记忆风险、对负荷预测和电器检测的下游实用性，以及在不同温度条件下的条件可控性。结果表明，LoaDiff能够生成真实且多样的负荷曲线，在生成质量与有限的记忆证据之间实现了有利的权衡，保留了用于下游能源应用的有用信息，并对条件变量的变化做出连贯的响应。
英文摘要
The energy transition is reshaping residential electricity consumption through the increasing adoption of distributed generation, electrified appliances, and demand-response programs. Understanding these evolving behaviors requires access to granular smart-meter data for applications such as load forecasting, appliance detection, and demand-side flexibility analysis. However, such data are subject to strict access restrictions and data-protection regulations. Thus, realistic synthetic alternatives are necessary. In this paper, we introduce LoaDiff, a diffusion-based generative model for year-long, sub-hourly smart-meter load curves. LoaDiff supports flexible conditioning on static household attributes, such as appliance ownership, and dynamic contextual variables, including calendar information and outdoor temperature. We evaluate the model against multiple generative baselines on three residential electricity-consumption datasets. Our experiments assess four complementary dimensions: fidelity and diversity, training-record memorization risk, downstream utility for load forecasting and appliance detection, and conditional controllability under alternative temperature conditions. The results show that LoaDiff generates realistic and diverse load profiles, achieves a favorable trade-off between generation quality and limited evidence of memorization, preserves information useful for downstream energy applications, and responds coherently to changes in conditioning variables.
Comments10 pages, 5 figures. This paper appeared in IEEE ICDM 2026
