Assessment of the use of nonlinear autoregressive neural network models for predicting technical and economic indicators of solar power plants

Currently, in the field of power supply for agricultural facilities, there is a growing interest in the development of engineering systems using renewable energy sources, in particular, photovoltaic systems. In view of the fact that the relationships between the technical and economic indicators of photovoltaic systems are difficult to identify, nonlinear autoregressive neural network models can be successfully applied in the field of forecasting and provide more reliable results than linear models. The paper presents the results of the development of mathematical models for predicting the daily variation of electrical power and the levelized cost of energy (LCOE) for solar photovoltaic systems based on a nonlinear autoregressive network with exogenous (NARX) neural network.