Time Series Forecasting of Active Power Using ARIMA, SARIMA and Hybrid Models

DOI

10.2991/978-94-6463-720-5_18How to use a DOI?

Keywords

ARIMA; SARIMA; SARIMAX

Abstract

This research compares the ARIMA, SARIMAX, and hybrid Holt-Winters with SARIMAX models for projecting Active Power consumption using hourly observational data from January 1, 2023, to December 31, 2023. For effective energy management and resource allocation in situations with fluctuating demand, an accurate Active Power forecast is essential. By evaluating each model’s performance using RMSE, MAE, and MAPE measures, distinct benefits and drawbacks are shown. In short-term projections, the ARIMA model’s low RMSE and MAE demonstrated accuracy, despite its MAPE indicating variability concerns. However, SARIMA’s performance was balanced across all parameters, indicating that it is appropriate for data that exhibits seasonal tendencies. The ensemble stacking model enhanced RMSE, which suggests that increased forecasting capabilities come at the expense of additional processing power.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Khairul Eahsun Fahim
AU  - Liyanage C. De Silva
AU  - Hayati Yassin
PY  - 2025
DA  - 2025/06/30
TI  - Time Series Forecasting of Active Power Using ARIMA, SARIMA and Hybrid Models
BT  - Proceedings of the Smart Sustainable Development Conference 2025 (SSD 2025)
PB  - Atlantis Press
SP  - 203
EP  - 219
SN  - 3005-155X
UR  - https://doi.org/10.2991/978-94-6463-720-5_18
DO  - 10.2991/978-94-6463-720-5_18
ID  - Fahim2025
ER  -