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

TL;DR

This paper evaluates the zero-shot prediction capabilities of five Time-Series Foundation Models for short-term load prediction, showing they can outperform traditional models like GP and SVR without task-specific training.

Contribution

It introduces and assesses the zero-shot capabilities of TSFMs in STLP, demonstrating their potential to outperform classical models without training.

Findings

TSFMs like Chronos, TimesFM, and TimeGPT outperform GP and SVR in zero-shot STLP.

Zero-shot TSFMs achieve comparable or better accuracy without task-specific training.

The study highlights the potential of foundation models in power system load forecasting.

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.