A synthetic dataset of French electric load curves with temperature conditioning

2025-04-18

AI Summary

Addressing the dual challenges of evolving residential electricity consumption patterns amid Europe’s energy transition and stringent GDPR compliance requirements in France, this paper proposes the first Conditional Latent Diffusion Model (CLDM) tailored for electrical load curve synthesis. The model generates high-fidelity, privacy-preserving smart-meter-level synthetic data conditioned on temperature, contracted power, and time-of-use tariffs. Its key innovations include: (i) the first application of CLDMs to load synthesis; (ii) explicit incorporation of physical constraints—particularly temperature-dependent load dynamics; and (iii) concurrent release of multidimensional auxiliary metadata. Extensive evaluation demonstrates that the synthetic data achieves over 92% utility relative to real data across statistical distributions, temporal dynamics, and downstream modeling tasks, while resisting privacy attacks with success rates below 3.1%. It significantly outperforms GAN- and VAE-based baselines, achieving a balanced trade-off among fidelity, utility, and GDPR compliance.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

The undergoing energy transition is causing behavioral changes in electricity use, e.g. with self-consumption of local generation, or flexibility services for demand control. To better understand these changes and the challenges they induce, accessing individual smart meter data is crucial. Yet this is personal data under the European GDPR. A widespread use of such data requires thus to create synthetic realistic and privacy-preserving samples. This paper introduces a new synthetic load curve dataset generated by conditional latent diffusion. We also provide the contracted power, time-of-use plan and local temperature used for generation. Fidelity, utility and privacy of the dataset are thoroughly evaluated, demonstrating its good quality and thereby supporting its interest for energy modeling applications.

Problem

• Generating synthetic French electric load curves
• Ensuring privacy compliance with GDPR regulations
• Evaluating dataset fidelity for energy modeling

Innovation

• Conditional latent diffusion for synthetic data
• Privacy-preserving electric load dataset
• Comprehensive fidelity, utility, privacy evaluation