PV Grid Forecasting Analysis using Artificial Neural Network

In addition to its use in building and agriculture, global solar irradiance is one of the most critical aspects in designing and considering any solar station's volume. Because the Iraqi metrological organization and seismology lack exact information regarding irradiance, this project aims to use historical global data, develop numerical analysis using artificial neural networks, and forecast hourly irradiance. The test is run over Basra to determine references to their nearest places. The learning technique in this study is a forward neural network (FNN) and time series neural network. Their comparison depends on seven input variables: temperature, wind speed, wind direction, sunshine duration, and date. One of the most essential integrated and impactful events for managing the system of new and renewable energy sources in the power grid is accurate solar energy forecasting. The study offers a valuable method for forecasting solar energy generation using neural networks. It is difficult to apply neural networks to anticipate PV power generation because of the unpredictability of variations in the weather; unlike traditional mathematical models, which struggle to handle complicated nonlinear interactions and provide poor predictions, neural network approaches achieve superior prediction performance. The suggested forecasting model based on neural networks provides a practical means of raising the accuracy of PV generation estimation