LoaDiff: Conditional Generation of Electricity Consumption Time Series for Energy Analytics
For energy analysts and researchers, LoaDiff provides a tool to generate realistic synthetic data for load forecasting and appliance detection, which is valuable when real-world data is restricted.
This paper introduces LoaDiff, a diffusion-based generative model for creating realistic synthetic smart-meter data.
The model can generate year-long, sub-hourly load curves and is conditioned on static household attributes and dynamic variables like calendar information and outdoor temperature.
It was evaluated against baselines on three residential electricity datasets, showing it generates realistic profiles while preserving useful information for downstream energy applications.
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.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include LoaDiff, time-series generation, diffusion models.
Source attribution: curated from arXiv cs.LG (@Mariia Baranova, Adrien Petralia, Etienne Le Naour, Nathan Etourneau, Guillaume Hofmann, Themis Palpanas).
