# BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting

arXiv: https://arxiv.org/abs/2307.00142 · HTML: https://mlsanity.com/paper/2307.00142/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 53 references that are in the map.
- First posted on arXiv 30 Jun 2023.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case](https://mlsanity.com/paper/2001.08317/) (2020)
- [BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2109.13226/) (2021)

## Built on by (most cited first, 26 of 26)

- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation](https://mlsanity.com/paper/2410.10393/) (2024)
- [Timer: Generative Pre-trained Transformers Are Large Time Series Models](https://mlsanity.com/paper/2402.02368/) (2024)
- [Chronos-2: From Univariate to Universal Forecasting](https://mlsanity.com/paper/2510.15821/) (2025)
- [Towards Neural Scaling Laws for Time Series Foundation Models](https://mlsanity.com/paper/2410.12360/) (2024)
- [Scaling-laws for Large Time-series Models](https://mlsanity.com/paper/2405.13867/) (2024)
- [Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting](https://mlsanity.com/paper/2602.17634/) (2026)
- [TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding](https://mlsanity.com/paper/2509.19406/) (2025)
- [Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Models](https://mlsanity.com/paper/2602.06909/) (2026)
- [Adapting to Change: A Comparison of Continual and Transfer Learning for Modeling Building Thermal Dynamics under Concept Drifts](https://mlsanity.com/paper/2508.21615/) (2025)
- [PowerMamba: A Deep State Space Model and Comprehensive Benchmark for Time Series Prediction in Electric Power Systems](https://mlsanity.com/paper/2412.06112/) (2024)
- [Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models](https://mlsanity.com/paper/2506.00630/) (2025)
- [DELPHYNE: A Pre-Trained Model for General and Financial Time Series](https://mlsanity.com/paper/2506.06288/) (2025)
- [A synthetic dataset of French electric load curves with temperature conditioning](https://mlsanity.com/paper/2504.14046/) (2025)
- [SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems](https://mlsanity.com/paper/2405.19653/) (2024)
- [From RNNs to Foundation Models: An Empirical Study on Commercial Building Energy Consumption](https://mlsanity.com/paper/2411.14421/) (2024)
- [Are Time-Indexed Foundation Models the Future of Time Series Imputation?](https://mlsanity.com/paper/2511.05980/) (2025)
- [GHGbench: A Unified Multi-Entity, Multi-Task Benchmark for Carbon Emission Prediction](https://mlsanity.com/paper/2605.13743/) (2026)
- [RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models](https://mlsanity.com/paper/2607.06504/) (2026)
- [ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks](https://mlsanity.com/paper/2605.12768/) (2026)
- [RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting](https://mlsanity.com/paper/2606.02852/) (2026)
- [REGEN: Reference-Guided Synthetic Multivariate Time Series Generation for Forecasting](https://mlsanity.com/paper/2606.05264/) (2026)
- [A Multimodal Dataset for Large Language Model Applications in the Energy Domain](https://mlsanity.com/paper/2607.11459/) (2026)
- [ArchEGraph: A Large-Scale Graph Dataset for Geometry-Topology-Physics Aligned Building Energy Modeling](https://mlsanity.com/paper/2608.06772/) (2026)

## Abstract (arXiv)

Short-term forecasting of residential and commercial building energy consumption is widely used in power systems and continues to grow in importance. Data-driven short-term load forecasting (STLF), although promising, has suffered from a lack of open, large-scale datasets with high building diversity. This has hindered exploring the pretrain-then-fine-tune paradigm for STLF. To help address this, we present BuildingsBench, which consists of: 1) Buildings-900K, a large-scale dataset of 900K simulated buildings representing the U.S. building stock; and 2) an evaluation platform with over 1,900 real residential and commercial buildings from 7 open datasets. BuildingsBench benchmarks two under-explored tasks: zero-shot STLF, where a pretrained model is evaluated on unseen buildings without fine-tuning, and transfer learning, where a pretrained model is fine-tuned on a target building. The main finding of our benchmark analysis is that synthetically pretrained models generalize surprisingly well to real commercial buildings. An exploration of the effect of increasing dataset size and diversity on zero-shot commercial building performance reveals a power-law with diminishing returns. We also show that fine-tuning pretrained models on real commercial and residential buildings improves performance for a majority of target buildings. We hope that BuildingsBench encourages and facilitates future research on generalizable STLF. All datasets and code can be accessed from https://github.com/NREL/BuildingsBench.