An indirect forecasting system of the generated electricity from a solar panel array based on modified fuzzy neural network

The forecast of the generated electricity of a solar power plant allows efficient and safe management of electrical grid that include solar power plants. The day-ahead market buys at penalty rates electricity from solar power plants, deviating by more than 5 % of the maximum solar power plant capacity from the provided hourly day-ahead market layout of electricity generated by the solar power plant. An analysis of existing software showed the lack of available software for effectively forecasting the production of a solar power plant. In this study, an indirect forecasting intelligent technology of a solar power plant production based on a modified fuzzy neural network with an attention mechanism was developed, tested and implemented. The UML class diagram and block-modular architecture of the indirect forecasting intelligent technology of a solar power plant production have been developed. This block-modular architecture provides flexibility and easy modification of the indirect forecasting intelligent technology of a solar power plant production. The approval of the indirect forecasting intelligent technology of a solar power plant production reflects its effective, robust results and the feasibility of its use for automatic generation of day-ahead market layouts.