Work

Comparative Analysis of Zero-Shot Capability of Time-Series Foundation Models in Short-Term Load Prediction

Year: 2025

Type: conference-paper

Abstract: Short-term load prediction (STLP) is critical for modern power distribution system operations, particularly as demand and generation uncertainties grow with the integration of low-carbon technologies, such as electric vehicles and photovoltaics. In this study, we evaluate the zero-shot prediction capabilities of five Time-Series Foundation Models (TSFMs)—a new approach for STLP where models perform predictions without task-specific training—against two classical models, Gaussian Process (GP) and Support Vector Regression (SVR), which are trained on task-specific datasets. Our findings indicate that even without training, TSFMs like Chronos, TimesFM, and TimeGPT can surpass the performance of GP and SVR. This finding highlights the potential of TSFMs in STLP.

DOI: 10.1109/powertech59965.2025.11180251

Authors: Nan Lin, Dong Yun, Weijie Xia, Peter Palensky, Pedro P. Vergara

Institutions: Delft University of Technology, Technical University of Denmark

Language: English

Topic: Energy Load and Power Forecasting

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure

Open Access status: green

Funder: Nederlandse Organisatie voor Wetenschappelijk Onderzoek

Award: Aligning citizens and systems - Combining digital citizen engagement and personalised behavioural interventions to enable system-optimal clean energy investments at scale (ALIGN4energy)