Forecasting of Energy Production for Photovoltaic Systems Based on ARIMA and ANN Advanced Models

Accurate forecasting of solar energy is essential for photovoltaic (PV) plants, to facilitate their participation in the market and efficient resource planning. This article dedicated two models: (1) ARIMA (Autoregressive Integrated Moving Average) statistical approach time series forecasting, using measured historical data, (2) ANN (Artificial Neural Network) machine learning techniques. The main contributions authors could be synthetized as follows: analysis discussion experimental simulated results regarding radiation forecast, well production prediction based on models case studies: (a) laboratory BIPV system developed at Polytechnic University Bucharest (b) large PV park placed a specific site south Romania. A variability index was introduced model improvement; comparison between highlight which more than one; (3) optimized method defined by GMDH (Group Method Data Handling) proposed provide software program calculation production.