@inbook{f645220dfbf1496e983a6e8bd31c21fa,
title = "Machine Learning-Based Analysis and Forecasting of Electricity Demand in Misamis Occidental, Philippines",
abstract = "This research paper investigates the application of the ARIMA model for forecasting household electricity demand in Misamis Occidental, Philippines. Through a detailed analysis of electricity demand data from 2005 to 2020, the study identifies the ARIMA (1,1,2) model as the most accurate, demonstrating its efficacy in capturing the region{\textquoteright}s consumption trends. The results show that the ARIMA model forecasts an upward trend in electricity demand, with the forecasts being within 5.76\% of actual values in terms of Root Mean Square Error (RMSE) and 4.46\% in terms of Mean Absolute Error (MAE), indicating a continuation of the historical increasing demand trend over the next five years. This finding supports the potential of machine learning models to significantly improve energy management in smaller urban areas, addressing the need for accurate and reliable electricity demand forecasting. ARIMA, Machine Learning, Electricity Demand Forecasting, Energy Management, Sustainability, Misamis Occidental.",
keywords = "ARIMA, electricity demand forecasting, energy management, machine learning, sustainability",
author = "Saumat, \{Murphy T.\} and Abid Yahya",
note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.",
year = "2024",
doi = "10.1007/978-3-031-65392-6\_8",
language = "English",
series = "Learning and Analytics in Intelligent Systems",
publisher = "Springer Nature",
pages = "81--90",
booktitle = "Learning and Analytics in Intelligent Systems",
address = "United States",
}
