Advanced ML-Based Ensemble and Deep Learning Models for Short-Term Load Forecasting: Comparative Analysis Using Feature Engineering

Short-term load forecasting (STLF) plays a pivotal role in the electricity industry because it helps reduce, generate, and operate costs by balancing supply demand. Recently, challenge STLF has been variation that occurs each period, day, seasonality. This work proposes bagging ensemble combining two machine learning (ML) models—linear regression (LR) support vector (SVR). For comparative analysis, performance of proposed model is evaluated compared with three advanced deep (DL) models, namely, neural network (DNN), long short-term memory (LSTM), hybrid convolutional (CNN)+LSTM models. These models are trained tested on data collected from Electricity Generating Authority Thailand (EGAT) four different input features. The measured considering mean absolute percentage error (MAPE), (MAE), squared (MSE) parameters. Using several features, experimental results show integrated provides better accuracy than others. Therefore, can be revealed our approach could improve using fields.