Tree-based machine learning models for photovoltaic output power forecasting that consider photovoltaic panel soiling
Duško M. Tovilović, Željko Đurišić
Abstract
This article presents direct regression models for forecasting photovoltaic (PV) system output power based on machine learning (ML) methods, in which the Cleanness Index (CI) was introduced as an indicator of the PV panel soiling level. Three different ML methods based on decision trees were used: random forests (RF), extra trees (ET) and gradient boosting (GB). The research results showed that the introduction of the CI has significant potential to improve the forecasting of tree-based ML models. The mean average error of forecasts of the best model, which contained CI, and the model created by excluding CI from the set of input variables were 0.22% and 1.24%, respectively, as related to the nominal power of the PV panel. For the observed models, it was shown that the CI is the second-most important input variable and more significant than the PV panel temperature.