Enabling Time-series Foundation Model for Building Energy Forecasting via Contrastive Curriculum Learning

Rui LIANG, Yang Deng, xiedonghua, Dan Wang

Keywords: foundation model, model training, building energy forecasting

TL;DR: We propose a contrastive curriculum learning-based training method to adapt general time series foundation model to the building energy domain.

Abstract: Advances in time-series forecasting are driving a shift from conventional machine learning techniques to foundation models (FMs) that are trained with generalized knowledge. However, existing FMs still perform poorly in the energy fields, such as building energy forecasting (BEF). This paper studies the adaptation of FM to BEF tasks. We demonstrate the shortcomings of fine-tuning FM straightforwardly from both the perspectives of FM and the data. To overcome these limitations, we propose a new contrastive curriculum learning-based training method. Our method optimizes the ordering of training data in the context of TSFM adaptation. Experiments show that our method can improve the zero/few-shot performance by 14.6\% compared to the existing FMs.

Submission Number: 6