A photovoltaic power prediction approach enhanced by feature engineering and stacked machine learning model

Abstract

The rapid depletion of world reserves of fossil fuels escalates energy costs, raises concerns regarding energy supplies, and increases climate impacts. The deployment of renewable energy has therefore become a worldwide trend. Among the other known forms of energy, solar energy is unquestionably the cleanest. In an era of widespread deployment of solar photovoltaic plants, research and development activities have made significant progress in assessing and investigating the behavior of solar installations in order to increase their reliability; however, there is still a local component that has not been thoroughly considered in many climate areas, including the semi-arid one. Understanding the distinctive features of each environment as well as how they affect photovoltaic power is the first step towards developing intelligent and data-driven maintenance algorithms suited to the region’s environmental context. This study proposes a stacked machine learning model making hourly predictions of two PV systems varying in size and age. Three machine learning algorithms were compared with a baseline linear regression model and a reference physical model for the PV prediction. The algorithms were also evaluated in terms of the input predictors. The findings demonstrate that the stacked ensemble model outperforms the individual models chosen for comparison in both systems and offers new perspectives for improving PV prediction in this area.

Keywords

• Solar energy
• Meteorological parameters
• Semi-arid
• Machine learning
• Power output