Verification of field research results and predicted values for solar energy production

   An increase in the control horizon is necessary to maintain a sufficient supply of resources in order to cover peak power consumption, as well as to optimize power and electricity reserves in isolated power systems. At present, two main approaches are used to solve this problem: mathematical modeling of the expected levels of solar insolation based on the analysis of retrospective data sets on the actual levels of insolation in the corresponding periods; current forecast level of insolation based on global and local climate research and forecasts. The development of systems for obtaining climatological information using ground-based and space-based systems tends to increase the level of weather forecasting to an acceptable level for applied energy problems.

   The purpose of this study is to improve the accuracy of medium-term forecasting of electricity consumption through the use of meteorological data and clustering of meteorological conditions.

   The paper examines the use of global climate models to predict energy production by renewable energy installations using the example of a solar module. A method for calculating the arrival of solar radiation on an inclined platform is considered. A comparison was made of the forecast data obtained using the climate models ECMWF, WRF and the actual energy production of the solar module.

1. Fedorov E. V., Shcheklein S. E., Akifieva N. N. Estimation of the dependence of the time spent by the energy system in the power deficit zone on the scale factor of the use of wind power plants. – 2018. – No 8. – pp. 52-59.

2. Russian Association of Wind Power Industry (RAWI): [website]. Available at: http://rawi.ru/ru/faq (accessed 12. 03. 2017).

3. System Operator of the Unified Energy System : [website]. Available at: http://so-ups.ru/ (accessed 15. 02. 2017).

4. Huber Matthias Integration of wind and solar power in Europe: Assessment of flexibility requirements / M. Huber, D. Dimkova, T. Hamacher // Energy. – 2014. – No. 69. – pp. 236-246.

5. Rudanets V. S. Sovremennye tendentsii RES v mire i Rossii [Modern trends in renewable energy sources in the world and Russia]. – 2023. – №. 8. – pp. 99-109

6. Khoroshko V. V., Aksenov O. D., Osmolovskaya T. N., Shneiderov E. N., Bruy N. M. Prediction of energy characteristics of photovoltaic power plants by methods of training decision trees // Big Data and Advanced Analytics. – 2021. – № 7-1. – pp. 390-394.

7. Anufriev O. V., Vorotyntsev D. V., Krapivko P. V., Tyagunov M. G. Forecast of hourly production of PVS for a day ahead using machine learning // In the collection: Fedorov readings. – 2017. XLVII International Scientific and Practical Conference with Elements of Scientific School. – 2017. – pp. 305-311.

8. Vorotyntsev D. V., Tyagunov M. G. Forecast of electricity generation by photovoltaic power plants (day ahead) using machine learning // Bulletin of the Moscow Power Engineering Institute. MPEI Bulletin. – 2018. – № 4. – pp. 53-57.

9. Bobyl A. V., Malyshkin V. G., Tarasenko A. B., Terukov E. I., Shakhrai I. S., Erk A. F. Analysis of the Applicability of Commercial Programs in the Problems of Technical and Economic Modeling of Solar Power Plants // Technologies and technical means of mechanized production of crop and livestock products. – 2019. – № 2 (99). – pp. 32-50.

10. Snegirev, D. A., – Pazderin, A. V., Samoylenko, V. O., Berdin, A. S. Short-term wind power forecasting based on gaussian process regression // 2023 6sup>th</sup> International Scientific and Technical Conference Relay Protection and Automation, RPA. – 2023.

11. Eroshenko, S. A., Khalyasmaa, A. I., Snegirev, D. A., Romanov, A. M., Butusov, D. N. The impact of data filtration on the accuracy of multiple time-domain forecasting for photovoltaic power plants generation // Applied Sciences (Switzerland), 2020, 10(22), pp. 1-22.

12. Khalyasmaa, A., Eroshenko, S., Chung Tran, D., Denis, S. Photovoltaic power plant production operational forecast based on its short-term forecasting model // Proceedings of the International Conference on Smart Technologies in Computing, Electrical and Electronics, ICSTCEE 2020, 2020, рр. 560-563, 9276846.

13. Kiseleva S. V., Lisitskaya N. V., Frid S. E. Forecasting the production of solar stations and photovoltaic installations: basic approaches and effectiveness. – 2020. – №. 7-18. – pp. 24-42.

14. Mustafaev A. G. Neural network model of forecasting the level of solar energy for problems of alternative energy. – 2016. – №. 2. – pp. 150-157.

15. Engel E. A., Engel N. E. Methods of Machine Learning for Forecasting and Maximizing the Generation of Electricity of a Solar Power Plant. Series: System Analysis and Information Technologies. – 2023. – №. 2. – pp. 146-170.

16. Abrukov, V. S., Kochakov, V. D., Abrukov, S. V., Anufrieva, D. A., Vasiliev, A. I., & Smirnov, A. V. (2017). Intelligent system for predicting the operation of solar power plants. International Scientific Journal Alternative Energy and Ecology, (16-18), pp. 30-42.

17. Weather and climate – weather and climate monitoring: [website]. Available at: http://pogodaiklimat.ru/ (accessed 10. 02. 2017).

18. Vissarionov V. I., Deryugina G. V., Kuznetsova V. A., Malinin N. K. Solnechnaya energetika : ucheb. Manual for Higher Educational Institutions. Moscow, MPEI Publ., 2008. – 320 p.

19. Denisov K. S., Velkin V. I., Tyrsin A. N. Solving the problem of integrated power supply. Denisov, K. S. Solving the Problem of Complex Energy Supply of an Autonomous Consumer with the Purpose of Reducing Economic Costs. «Energy» series. – 2019. – Vol. 19, No 3. – pp. 84-92.

20. Shcheklein, S. E., Matveev, A. V., Beloborodov, I. V., Nemikhin, Yu., Vlasov V. V. Study of the efficiency of a photovoltaic plant integrated into the power system in the annual cycle // International Scientific Journal Alternative Energy and Ecology, No 11-12 (199-200), 2016, pp. 37-51.

21. Windy.com // [Electronic resource]. Access mode: windy.com / (date of access 10. 10. 2023).

22. Meteoprog.com // [Electronic resource]. Available at: https://www.meteoprog.com/ru-UA/meteograms/Ekaterinburg/ / (accessed 10. 10. 2023).

23. VIESH // [Elektronnyi resurs]. Available at: https://viesh.ru/pre/catalog// (accessed 31. 10. 2023).