Artificial intelligence solution for managing a photovoltaic energy production unit

The aim of the paper is to investigate the possibility of using artificial intelligence in photovoltaic energy production forecasting. The presented approach is conceived as a module of energy management and production planning of a photovoltaic power plant located in central part of Romania. The main goal of the research is to develop a solution that provides the electricity production based on historical and current available solar radiation data in real-time. Different data input cases and configurations of feedforward neural network are tested and used as a basis for discussions and conclusions.