Analyzing the Performance of Time Series Foundation Models for Short-term Load Forecasting

Saravanan, HK and Dwivedi, S and Praveen, P and Arjunan, P (2024) Analyzing the Performance of Time Series Foundation Models for Short-term Load Forecasting. In: 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2024, 7 November 2024 through 8 November 2024, Hangzhou, pp. 346-349.

PDF Bui_Pro_11th_ACM_Int_Con_Sys_Ene_Eff_Bui_CitTra_2024(2).pdf - Published Version Restricted to Registered users only Download (587kB) | Request a copy

Abstract

Accurate short-term load forecasting (STLF) is essential for energy management in buildings and promoting sustainability. While various methods�ranging from statistical to machine learning�have been proposed, their evaluation often focuses on a limited number of buildings, hindering scalability and generalizability. Recent advancements in Time Series Foundation Models (TSFMs), pre-trained on extensive time series data from diverse domains, offer a promising domain-agnostic solution that can handle universal forecasting tasks without requiring task-specific training. In this paper, we analyze the performance of four open-source TSFMs � Chronos, Lag-Llama, Moirai, and TimesFM � for STLF in both commercial and residential buildings. Specifically, we benchmark these models� zero-shot prediction capabilities, assessing their ability to perform STLF on unseen buildings, and compare them to state-of-the-art models. Our experimental results, conducted on a large-scale dataset of over 1,900 real-world residential and commercial buildings, reveal that the Chronos model achieves the lowest Normalized Root Mean Squared Error compared to the contemporary models and demonstrates comparable performance with an existing pre-trained TSFM for the energy domain from the BuildingsBench platform. Moreover, our analysis of the forecasting errors of Chronos reveals no significant deviation in errors across different building types. Finally, we share insights to further improve the performance of TSFMs for STLF tasks. © 2024 Copyright held by the owner/author(s).

Item Type:	Conference Paper
Publication:	BuildSys 2024 - Proceedings of the 2024 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation
Publisher:	Association for Computing Machinery, Inc
Additional Information:	The copyright for this article belongs to Association for Computing Machinery, Inc
Keywords:	Demand response; Demand side management; Electric load forecasting; Information management; Mortar; Prediction models, Demand-side; Demand-side load management; Foundation models; Performance; Short term load forecasting; Short-term load forecasting; Side loads; Time series foundation model; Times series; Zero-shot forecasting, Mean square error
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering Division of Interdisciplinary Sciences > Robert Bosch Centre for Cyber Physical Systems
Date Deposited:	30 Dec 2024 06:37
Last Modified:	30 Dec 2024 06:37
URI:	http://eprints.iisc.ac.in/id/eprint/87197

Actions (login required)

View Item