Estimation of production values in solar and wind power plants with artificial intelligence methods based on climate parameters and production estimation by developing solar energy feasibility software

Electricity energy is a type of energy that cannot be stored, consumed as soon as it is produced, and the supply-demand balance is constantly maintained by the system.Maintaining this balance requires serious planning. It is possible to achieve the balance in question by the moment coordination of production, transmission and consumption.For this reason, the estimation of electricity production is of great importance. In this study, production estimation of wind energy, one of the renewable energy sources, has been made.The production data has been estimated based on the meteorological and geological data of a wind power plant (RES) in Adıyaman province.In order to make the production estimation, feed forward back propagation artificial neural network (ANN) was used due to its success in predicting linear nonlinear models, which are artificial intelligence applications and Adaptive Network Based Fuzzy Inference System(ANFIS) and deep learning modeling Long/Short Term Memory-LSTM.It has been observed that the estimated production power values (MWh) are very close to the actual production power values. Estimates made by ANN, ANFIS and LSTM compared. In the future forecasting studies, it was shown that ANN, ANFIS and LSTM can be applied successfully as an alternative to conventional methods.In addition, Solar Power Plant Feasibility Software has been developed to analyze solar energy installation for a selected location.With the developed software, it can be analyzed whether the selected location is suitable for solar energy investment, and cost analysis can be made by calculating the number of panels and inverters.With the developed software, production estimation was made with LSTM, which is a deep learning model, over MATLAB software. Production estimations made are compared with other solar power plant production estimation programs. It has been seen that the estimation made with LSTM makes better estimation than other estimation programs.