ARIMA Method Implementation for Electricity Demand Forecasting with MAPE Evaluation

Supriyadi La Wungo; Firman Aziz; Jeffry Jeffry; Mardewi Mardewi; Nasruddin Nasruddin

doi:10.61628/jsce.v6i1.1666

Supriyadi La Wungo STMIK Kreatindo Manokwari, Indonesia
Firman Aziz Universitas Pancasakti Makassar, Indonesia
Jeffry Jeffry Institut Teknologi Bacharuddin Jusuf Habibie
Mardewi Mardewi STMIK Kreatindo Manokwari, Indonesia
Nasruddin Nasruddin Student Ilmu Komputer Universitas Pancasakti, Makassar, Indonesia

DOI: https://doi.org/10.61628/jsce.v6i1.1666

Keywords: ARIMA, Electricity Demand Forecasting, Time Series Analysis, MAPE, Forecasting Models

Abstract

Electricity demand forecasting is critical for efficient energy management and planning. This study focuses on the development and implementation of the Autoregressive Integrated Moving Average (ARIMA) method for forecasting electricity demand in South Sulawesi's power system. The evaluation of forecasting accuracy was conducted using the Mean Absolute Percentage Error (MAPE), which measures the percentage error between predicted and actual values. Two experiments were conducted with different ARIMA models: ARIMA(5,1,0) and ARIMA(2,0,1). Results showed that the ARIMA(5,1,0) model achieved a MAPE of 2.15%, while the ARIMA(2,0,1) model performed slightly better with a MAPE of 1.91%, indicating highly accurate predictions. The findings highlight the effectiveness of the ARIMA method in forecasting electricity demand, providing a reliable tool for energy providers to optimize resource allocation and enhance operational efficiency. Future research may explore integrating ARIMA with other advanced methods to further improve forecasting performance.

References

Ahmad, T., & Zhang, H, B. Y. (2020). A review on renewable energy and electricity requirement forecasting models for smart grid and buildings. Elsevier. https://www.sciencedirect.com/science/article/pii/S2210670720300391

Alizadegan, H., Rashidi Malki, B., Radmehr, A., Karimi, H., & Ilani, M. A. (2024). Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction. Energy Exploration and Exploitation. https://doi.org/10.1177/01445987241269496

Jeffry, J., Usman, S., & Aziz, F. (2023). Analisis Perilaku Pelanggan menggunakan Metode Ensemble Logistic Regression. JURNAL TEKNOLOGI DAN ILMU KOMPUTER PRIMA (JUTIKOMP), 6(2), 90–97

Kondaiah, V. Y., Saravanan, B., Sanjeevikumar, P., & Khan, B. (2022). A review on short‐term load forecasting models for micro‐grid application. The Journal of Engineering, 2022(7), 665–689. https://doi.org/10.1049/TJE2.12151

Mystakidis, A., Koukaras, P., Tsalikidis, N., & Energies, D. I. (2024). Energy Forecasting: A Comprehensive Review of Techniques and Technologies. Mdpi.Com. https://www.mdpi.com/1996-1073/17/7/1662

Nepal, B., Yamaha, M., Yokoe, A., & Yamaji, T. (2020). Electricity load forecasting using clustering and ARIMA model for energy management in buildings. Japan Architectural Review, 3(1), 62–76. https://doi.org/10.1002/2475-8876.12135

Schaffer, A. L., Dobbins, T. A., & Pearson, S. A. (2021). Interrupted time series analysis using autoregressive integrated moving average (ARIMA) models: a guide for evaluating large-scale health interventions. BMC Medical Research Methodology, 21(1). https://doi.org/10.1186/S12874-021-01235-8

Song, Y., & Cao, J. (2022). An ARIMA-based study of bibliometric index prediction. Aslib Journal of Information Management, 74(1), 94–109. https://doi.org/10.1108/AJIM-03-2021-0072/FULL/HTML