Ensembled Model of Random Forest and Artificial Neural Network for Short-Term Electric Load Forecasting

Abstract

The research focuses on secure short-term electric load forecasting using Random Forest and Artificial Neural Network (RF-ANN) models. Accurate forecasting is crucial for maintaining power system stability and efficiency. Inaccurate forecasting can lead to financial losses, increased load shedding events, and decreased customer satisfaction. Techniques like the State Space Method, Stochastic Time Series, Multiple Linear Regression, General Exponential Smoothing, Knowledge-based Expert Approach, and Machine Learning Approach have been used. The dataset from Transmission Company of Nigeria(TCN) was divided into a 70% training and 30% testing set, and performance accuracies were evaluated using Mean Squared Error, Mean Absolute Error, Root Mean Squared Error, and Mean Absolute Percentage Error. The model achieved an accuracy of 1.73. While RMSE has an accuracy of 1.50899, MSE has 2.27704, and MAE accuracy of 0.00521. The study aims to strike a balance between accurate predictions and ethical data treatment.