Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Automatic building energy model development and debugging using large language models agentic workflow

Journal Article · · Energy and Buildings
 [1];  [2];  [3];  [4]
  1. University of Arizona, Tucson, AZ (United States); National Renewable Energy Laboratory (NREL), Golden, CO (United States)
  2. Arcadia University, Glenside, PA (United States)
  3. Drexel University, Philadelphia, PA (United States)
  4. Tongji University, Shanghai (China); University of Utah, Salt Lake City, UT (United States)

Building energy modeling (BEM) is a complex process that demands significant time and expertise, limiting its broader application in building design and operations. While Large Language Models (LLMs) agentic workflow have facilitated complex engineering processes, their application in BEM has not been specifically explored. This paper investigates the feasibility of automating BEM using LLM agentic workflow. Here, we developed a generic LLM-planning-based workflow that takes a building description as input and generates an error-free EnergyPlus building energy model. Our robust workflow includes four core agents: 1) Building Description Pre-Processing, 2) IDF Object Information Extraction, 3) Single IDF Object Generator Suite, and 4) IDF Debugging Agent. These agents divide the complex tasks into manageable sub-steps, enabling LLMs to generate accurate and reliable results at each stage. The case study demonstrates the successful translation of a building description into an error-free EnergyPlus model for the iUnit modular building at the National Renewable Energy Laboratory. The effectiveness of our workflow surpasses: 1) naive prompt engineering, 2) other LLM-based workflows, and 3) manual modeling, in terms of accuracy, reliability, and time efficiency. The paper concludes with a discussion on the interplay between foundational models and LLM agent planning design, advocating for the use of fine-tuned, specialized models to advance this field.

Research Organization:
National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Sponsoring Organization:
USDOE
Grant/Contract Number:
AC36-08GO28308
OSTI ID:
2480816
Report Number(s):
NREL/JA--5500-92419
Journal Information:
Energy and Buildings, Journal Name: Energy and Buildings Vol. 327; ISSN 0378-7788
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (4)

EnergyPlus: creating a new-generation building energy simulation program journal April 2001
EPlus-LLM: A large language model-based computing platform for automated building energy modeling journal August 2024
Advancing building energy modeling with large language models: Exploration and case studies journal November 2024
Automated Building Energy Modeling and Assessment Tool (ABEMAT) journal March 2018

Similar Records

Scalable workflow for evaluating and optimizing large language models
Technical Report · Sat May 31 20:00:00 EDT 2025 · OSTI ID:3002371

Calibrating Building Energy Models Using Supercomputer Trained Machine Learning Agents
Journal Article · Tue Dec 31 23:00:00 EST 2013 · Concurrency and Computation. Practice and Experience · OSTI ID:1127381

Empirical validation of building energy modeling for multi-zones commercial buildings in cooling season
Journal Article · Wed Jan 08 23:00:00 EST 2020 · Applied Energy · OSTI ID:1761716