Benchmarking Time Series Foundation Models for Short-Term Household Electricity Load Forecasting
Open Access
- 24 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 218141-218153
Abstract
Accurate household electricity short-term load forecasting (STLF) is key to future and sustainable energy systems. While various studies have analyzed statistical, machine learning, or deep learning approaches for household electricity STLF, recently proposed time series foundation models such as Chronos, TimesFM or Time-MoE promise a new approach for household electricity STLF. These models are trained on a vast amount of time series data and are able to forecast time series without explicit task-specific training (zero-shot learning). In this study, we benchmark the forecasting capabilities of time series foundation models compared to Trained-from-Scratch (TFS) Transformer-based approaches. Our results suggest that foundation models perform comparably to TFS Transformer models, while certain time series foundation models outperform all TFS models when the input size increases. At the same time, they require less effort, as they need no domain-specific training and only limited contextual data for inference.Keywords
All Related Versions
Funding Information
- Federal Ministry for Environment, Nature Conservation, and Nuclear Safety of Germany (67KI32008B)
- Federal Ministry for Economic Affairs and Energy (03EN6024A)
This publication has 41 references indexed in Scilit:
- Intelligent deep learning techniques for energy consumption forecasting in smart buildings: a reviewArtificial Intelligence Review, 2024
- Techno-economic and environmental assessment of renewable energy sources, virtual synchronous generators, and electric vehicle charging stations in microgridsApplied Energy, 2023
- A novel Transformer-based network forecasting method for building cooling loadsEnergy and Buildings, 2023
- Transformers in Time-Series Analysis: A TutorialCircuits, Systems, and Signal Processing, 2023
- An adaptive deep-learning load forecasting framework by integrating transformer and domain knowledgeAdvances in Applied Energy, 2023
- Short-term multi-step wind power forecasting based on spatio-temporal correlations and transformer neural networksEnergy Conversion and Management, 2023
- Short-Term Electrical Load Forecasting Based on Time Augmented TransformerInternational Journal of Computational Intelligence Systems, 2022
- Review of low voltage load forecasting: Methods, applications, and recommendationsApplied Energy, 2021
- Evaluation of the Transformer Architecture for Univariate Time Series Forecasting2021
- A model for generating household electricity load profilesInternational Journal of Energy Research, 2005