# FETS Benchmark: Foundation Models Enable Scalable and Generalizable Energy Time Series Forecasting

arXiv: https://arxiv.org/abs/2604.22328 · HTML: https://mlsanity.com/paper/2604.22328/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 51 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Conformalized Quantile Regression](https://mlsanity.com/paper/1905.03222/) (2019)
- [Tabular Data: Deep Learning is Not All You Need](https://mlsanity.com/paper/2106.03253/) (2021)
- [Tackling Climate Change with Machine Learning](https://mlsanity.com/paper/1906.05433/) (2019)
- [When Do Neural Nets Outperform Boosted Trees on Tabular Data?](https://mlsanity.com/paper/2305.02997/) (2023)
- [SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting Challenge at KDD Cup 2022](https://mlsanity.com/paper/2208.04360/) (2022)
- [The ASHRAE Great Energy Predictor III competition: Overview and results](https://mlsanity.com/paper/2007.06933/) (2020)
- [Benchmarking Time Series Foundation Models for Short-Term Household Electricity Load Forecasting](https://mlsanity.com/paper/2410.09487/) (2024)
- [Benchmarking Pre-Trained Time Series Models for Electricity Price Forecasting](https://mlsanity.com/paper/2506.08113/) (2025)
- [On the retraining frequency of global models in retail demand forecasting](https://mlsanity.com/paper/2505.00356/) (2025)
- [Electricity Demand Forecasting in Future Grid States: A Digital Twin-Based Simulation Study](https://mlsanity.com/paper/2503.04757/) (2025)
- [A Hybrid Strategy for Probabilistic Forecasting and Trading of Aggregated Wind-Solar Power: Design and Analysis in HEFTCom2024](https://mlsanity.com/paper/2505.10367/) (2025)
- [Explainable time-series forecasting with sampling-free SHAP for Transformers](https://mlsanity.com/paper/2512.20514/) (2025)
- [EVARS-GPR: EVent-triggered Augmented Refitting of Gaussian Process Regression for Seasonal Data](https://mlsanity.com/paper/2107.02463/) (2021)

## Built on by (most cited first, 2 of 2)

- [A Unified Scaling Law for Time Series Foundation Models](https://mlsanity.com/paper/2610.05269/) (2026)
- [On the Encoding of Calendar Features in Covariate-Informed Time Series Foundation Models](https://mlsanity.com/paper/2610.13676/) (2026)

## Abstract (arXiv)

Driven by the transition towards a climate-neutral energy system, accurate energy time series forecasting is critical for planning and operations. Yet, it remains a dataset-specific task, requiring comprehensive training data, limiting scalability, and resulting in high model development and maintenance effort. Recently, foundation models aiming to learn generalizable patterns via extensive pretraining have shown strong performance in multiple prediction tasks. Despite their success and strong potential in energy forecasting, a systematic, use-case-differentiated evaluation is still missing. We address this gap by presenting the Foundation Models in Energy Time Series Forecasting (FETS) benchmark. We (1) provide a structured overview of energy forecasting use cases along three main dimensions, i.e., stakeholders, attributes, and data categories, (2) curate 54 datasets across 9 data categories, guided by typical stakeholder interests, and (3) benchmark foundation models against task-specific machine learning across different forecasting settings. In our benchmark study, covariate-informed zero-shot foundation models perform best in aggregate, with Chronos-2 attaining the lowest overall median NRMSE (0.472), closely followed by TiRex-2 (0.474). Both perform better than XGBoost (0.611) and random forest (0.696), although they were trained task-specifically on the full historic target data. Further analysis reveals a strong correlation between predictive performance and spectral entropy. Performance saturates beyond a certain context length and improves with aggregation level, e.g., for national load, district heating, and power grid data. Overall, with the lowest median error, limited data requirements, and low inference and hardware demands, foundation models reduce development and maintenance effort, emerging as scalable and generalizable energy forecasting solutions.