This paper presents a methodology for evaluating the amount of energy obtained from renewable energy sources (RES) using artificial intelligence (AI) technologies. The authors propose a comprehensive approach to assess solar and wind energy, which includes data preprocessing, forecasting, and control system integration. The relevance of the work lies in developing a general method for evaluating RES, particularly solar and wind energy, using AI. The paper reviews various AI methods, such as exponential smoothing, decision tree models, and long short-term memory (LSTM) models, and demonstrates their application in forecasting solar power generation using photovoltaic panels. The best results were obtained using a hybrid forecasting model that combines random forest, exponential smoothing, and LSTM models. The experimental results show that the proposed hybrid model outperforms existing forecasting models in terms of accuracy and reliability. The methodology is validated through a practical example, and the virtual part of the digital twin is used to forecast and plan the operation of power plants. The paper concludes by discussing the limitations of the model and suggesting future research directions.This paper presents a methodology for evaluating the amount of energy obtained from renewable energy sources (RES) using artificial intelligence (AI) technologies. The authors propose a comprehensive approach to assess solar and wind energy, which includes data preprocessing, forecasting, and control system integration. The relevance of the work lies in developing a general method for evaluating RES, particularly solar and wind energy, using AI. The paper reviews various AI methods, such as exponential smoothing, decision tree models, and long short-term memory (LSTM) models, and demonstrates their application in forecasting solar power generation using photovoltaic panels. The best results were obtained using a hybrid forecasting model that combines random forest, exponential smoothing, and LSTM models. The experimental results show that the proposed hybrid model outperforms existing forecasting models in terms of accuracy and reliability. The methodology is validated through a practical example, and the virtual part of the digital twin is used to forecast and plan the operation of power plants. The paper concludes by discussing the limitations of the model and suggesting future research directions.