Adaptive boosting and bootstrapped aggregation based ensemble machine learning methods for photovoltaic systems output current prediction

Photovoltaics output current prediction received great deal of attention in recent years, due to the high penetration level of PV utilization. The intermittent nature of PV systems, in addition to the fast-varying irradiance levels, provoked the need for fast, accurate and reliable forecasting techniques. Machine Learning (ML) methods have been proven to effectively solve regression-based prediction problems. ML methods that utilize multiple models to construct decision trees are called Ensemble Machine Learning (EML) algorithms. This paper presents a comparison study of two EML methods namely; AdaBoost and Random Forest for photovoltaics application. A dataset of fast varying environmental conditions has been employed and the terminal current of the experimental setup has been augmented based on the mathematical model and the use of an evolutionary algorithm. The mathematical model has been examined for several irradiance and temperature levels and adjusted based on the manufacturer datasheet. Random Forest overall absolute error distribution had the lowest mean and standard deviation. Results shows the superior performance of Random Forest over AdaBoost in terms of absolute error, on the contrary, AdaBoost absolute error distribution is scattered with larger quartiles limits. Random Forest overall absolute error distribution had the lowest mean of 0.27% with a standard deviation of 0.91%, however, AdaBoost absolute error mean was as high as 34.5% with a standard deviation of 15.8% relative to the mathematical model. Accurate predictions can be integrated in an EML based maximum power point tracking (MPPT) scheme.