Long-Term Load Forecasting for Luzon, Philippines using Optimized Hybrid Machine Learning Algorithm

This research paper discusses the growing demand for electricity in the Philippines due to population growth, economic development, and the need for accurate long-term electrical load forecasting to sustain the power system since most load forecasting studies focus on short-term duration. The study aims to optimize, evaluate, and compare accurate load forecasting models for the load demand of Luzon. This study used machine learning techniques for forecasting, specifically Linear Support Vector Machine (Linear SVM), Multi-layer Perceptron (MLP), and Linear Regression with XGBoost (LR-XGBoost). The objectives include identifying and constructing relevant features, optimizing hyperparameters, and comparing performances using appropriate evaluation metrics. The study is significant to the power system industry. Electrical load forecasting equipped them to create operational decisions in energy management, generation scheduling, and assessment that maintain supply and demand. The comparison will solely focus on the three models and identify how the models performed using the Luzon hourly load demand from 2013 to 2022. Based on the results, the optimized LR-XGboost is the best-performing Long- Term Load Forecasting Model for the Load Demand of Luzon with a MAPE of 4.61 %, outperforming the optimized Linear SVR and MLP models. The researchers recommend adding external regressors such as historical weather and economic data, performing Scenario forecasting, and adding holiday indicators to improve the performance of each model.