What question did this study set out to answer?

To develop a predictive model for short-term load forecasting in electrical power systems.

March 14, 2026Open Access

Load Forecasting Based on Machine Learning Techniques

Key Points

To develop a predictive model for short-term load forecasting in electrical power systems.
Developed predictive model using machine learning techniques.
Implemented ARIMA as a conventional time series forecasting approach.
Employed Linear Regression, Random Forest, and XG Boost to capture complex patterns in the dataset.
Improved accuracy in short-term load forecasting with machine learning models.
Demonstrated effective learning of nonlinear relationships within the dataset.

Abstract

Load forecasting is a critical phenomenon in the planning and operation of electrical power systems, enabling utility providers to ensure reliable and cost-effective energy distribution. This main objective of work is to develop a predictive model for short-term load forecasting using advanced machine learning techniques. The methodology involves the implementation of the ARIMA (Auto Regressive Integrated Moving Average) model as a conventional statistical approach for time series forecasting. In parallel, machine learning models such as Linear Regression, Random Forest and XG Boost are employed to learn complex patterns and nonlinear relationships within the dataset.

Load Forecasting Based on Machine Learning Techniques

Key Points

Abstract

Cite This Study