Abstract
The accelerating shift toward low-carbon power systems, along with the widespread adoption of behind-the-meter technologies such as rooftop solar and electric vehicles, is placing new operational and analytical demands on electricity grids. At the same time, smart-grid research increasingly relies on machine learning (ML), yet progress is constrained by limited access to high-resolution household energy data due to privacy concerns, regulatory barriers, and collection costs. This work presents WattCouncil, a data-generation framework where household electricity demand is generated by a council of Large Language Model (LLM)-based agents operating in specialized roles to generate, audit, and validate structured energy scenarios under explicit cultural, temporal, and physical constraints.
Rather than acting as static predictors, these agents serve as adaptive decision-makers within a governed pipeline. Motivated by studies highlighting the importance of contextual factors in energy use, our framework produces context-sensitive daily routines through a guided reasoning process that incorporates household composition, temporal factors, and environmental conditions. We evaluate the generated profiles against the detailed CER dataset, which contains over a year of load measurements for 4232 households along with survey-based socio-economic information. We further assess the consistency of the framework through ablation studies.
Source code is available at GitHub.
Blogger's Review: WattCouncil demonstrates how to leverage LLMs for generating context-aware household energy scenarios. This innovative approach not only enhances the accuracy of electricity demand forecasting but also effectively addresses challenges related to privacy and data collection, providing new insights and solutions for the advancement of smart grids.