A PREDICTIVE MODEL FOR ENERGY CONSUMPTION USING GRADIENT BOOSTING MACHINE
Abstract
The rising demand for efficient energy management in Nigeria, driven by population growth and industrialization, has intensified challenges in power supply reliability. Traditional energy forecasting methods often fail to account for dynamic factors like weather variability and regional disparities, leading to inefficiencies. This study proposes a machine learning (ML) framework using the Gradient Boosting Machine (GBM) model to develop a predictive model tailored to Nigeria's energy landscape. Historical energy consumption data, weather variables, and regional demographics were integrated to train the model. The model achieved a coefficient of determination (R²) of 0.92, with a Mean Absolute Error (MAE) of 16.66 GWh and Root Mean Squared Error (RMSE) of 21.16 GWh, demonstrating strong predictive performance. By optimizing resource allocation and reducing operational costs, this framework provides actionable insights for energy providers to mitigate power outages and enhance grid management.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.