BuildEvo: Designing Building Energy Consumption Forcasting Heuristics via LLM-driven Evolution

Subin Lin, Chuanbo Hua

Keywords: Building Energy Forecasting, Large Language Models, Evolutionary Algorithms

TL;DR: We propose an evolutionary framework that leverages LLMs to automatically design building energy forecasting heuristics

Abstract: Accurate building energy forecasting is essential, yet traditional heuristics often lack precision, while advanced models can be opaque and struggle with generalization by neglecting physical principles. This paper introduces BUILDEVO, a novel framework that uses Large Language Models (LLMs) to automatically design effective and interpretable energy prediction heuristics. Within an [evolutionary/iterative-refinement] process, BUILDEVO guides LLMs to construct and enhance heuristics by systematically incorporating physical insights from building characteristics and operational data (e.g., from the Building Data Genome Project 2). Evaluations show BUILDEVO achieves state-of-the-art performance on benchmarks, offering improved generalization and transparent prediction logic. This work advances the automated design of robust, physically grounded heuristics, promoting trustworthy models for complex energy systems.

Submission Number: 12