Comprehensive Review and Evaluation of Machine Learning Approaches for Solar PV Output Power Forecasting

Accurate forecasting of solar photovoltaic (PV) output power is a fundamental prerequisite to maintain the optimal management and stability of the grid. This paper presents a review and analysis of the solar photovoltaic power forecasting model based on machine learning techniques. Machine learning techniques are a subfield of artificial intelligence that is widely applied to solve different nonlinear and complex data type systems. The focus of this work is on machine learning methods, which give a thorough and critical analysis of the methodology used to predict PV power output. Furthermore, this study proposed an Ensemble (ENBG) Trees-based machine learning model to incorporate the effect of weather parameters on PV power forecasting. The performance of the proposed machine learning-based model is evaluated and compared with the help of Statistical indices such as Mean Absolute Error (MAE), Mean Square Error (MSE), and R² Error and found within desired limits. The proposed forecasting model is found to be more accurate, and it may be useful for smart grid applications to maintain grid stability, reliability, and power quality.