BuildingsBench: A Benchmark for Universal Building Load Forecasting [SWR-23-51]

RESOURCE

Abstract

The residential and commercial building stock in the United States is responsible for a significant percentage of energy consumption and greenhouse gas emissions. Electrification of end-uses, as well as decarbonizing the electrical grid through renewable energy sources such as solar and wind, constitutes the pathway to zero-emission buildings. Forecasting day-ahead building energy consumption is an integral part of this solution. Currently, specialized forecasting models are hand-made for each individual building, which is time-consuming, expensive, and leads to duplicated efforts. BuildingsBench is a Python software framework for training and comparing generalized machine learning models for universal building load forecasting. This challenge tasks a single foundational model to generalize its forecasts for a wide variety of buildings, across geographic regions, building types, weather patterns, and more. This software provide code for pre-training such models and subsequently evaluating their performance on a suite of hundreds of diverse real and synthetic buildings. BuildingsBench is a platform for: - Large-scale pretraining with the synthetic Buildings-900K dataset for short-term load forecasting (STLF). Buildings-900K is statistically representative of the entire U.S. building stock and is extracted from the NREL End-Use Load Profiles database. - Benchmarking on two tasks evaluating generalization: zero-shot STLF and transfer learning for STLF. We provide an index-based  More>>
Developers:
Emami, Patrick [1] Graf, Peter [1]
  1. National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Release Date:
2023-06-01
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Programming Languages:
Jupyter Notebook
Python
Licenses:
BSD 3-clause "New" or "Revised" License
Sponsoring Org.:
Code ID:
107854
Site Accession Number:
NREL SWR-23-51
Research Org.:
National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Country of Origin:
United States

RESOURCE

Citation Formats

Emami, Patrick, and Graf, Peter. BuildingsBench: A Benchmark for Universal Building Load Forecasting [SWR-23-51]. Computer Software. https://github.com/NREL/BuildingsBench. USDOE Laboratory Directed Research and Development (LDRD) Program. 01 Jun. 2023. Web. doi:10.11578/dc.20230828.3.
Emami, Patrick, & Graf, Peter. (2023, June 01). BuildingsBench: A Benchmark for Universal Building Load Forecasting [SWR-23-51]. [Computer software]. https://github.com/NREL/BuildingsBench. https://doi.org/10.11578/dc.20230828.3.
Emami, Patrick, and Graf, Peter. "BuildingsBench: A Benchmark for Universal Building Load Forecasting [SWR-23-51]." Computer software. June 01, 2023. https://github.com/NREL/BuildingsBench. https://doi.org/10.11578/dc.20230828.3.
@misc{ doecode_107854,
title = {BuildingsBench: A Benchmark for Universal Building Load Forecasting [SWR-23-51]},
author = {Emami, Patrick and Graf, Peter},
abstractNote = {The residential and commercial building stock in the United States is responsible for a significant percentage of energy consumption and greenhouse gas emissions. Electrification of end-uses, as well as decarbonizing the electrical grid through renewable energy sources such as solar and wind, constitutes the pathway to zero-emission buildings. Forecasting day-ahead building energy consumption is an integral part of this solution. Currently, specialized forecasting models are hand-made for each individual building, which is time-consuming, expensive, and leads to duplicated efforts. BuildingsBench is a Python software framework for training and comparing generalized machine learning models for universal building load forecasting. This challenge tasks a single foundational model to generalize its forecasts for a wide variety of buildings, across geographic regions, building types, weather patterns, and more. This software provide code for pre-training such models and subsequently evaluating their performance on a suite of hundreds of diverse real and synthetic buildings. BuildingsBench is a platform for: - Large-scale pretraining with the synthetic Buildings-900K dataset for short-term load forecasting (STLF). Buildings-900K is statistically representative of the entire U.S. building stock and is extracted from the NREL End-Use Load Profiles database. - Benchmarking on two tasks evaluating generalization: zero-shot STLF and transfer learning for STLF. We provide an index-based PyTorch Dataset for large-scale pretraining, easy data loading for multiple real building energy consumption datasets as PyTorch Tensors or Pandas DataFrames, simple (persistence) to advanced (transformer) baselines, metrics management, and more.},
doi = {10.11578/dc.20230828.3},
url = {https://doi.org/10.11578/dc.20230828.3},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20230828.3}},
year = {2023},
month = {jun}
}