A methodology for short-term forecasting of solar generation to manage power quality in distribution networks

Purpose of research. With the increasing share of generation from solar plants in distribution networks, the requirements for the quality of supplied electricity are growing, as the instability of solar generation directly affects the network load and the voltage parameters of the electricity supplied to the consumer. The purpose of the research is experimental validation of methods for forecasting the output of a PV plant for the next day with hourly planning, which makes it possible to link the magnitude of the forecast error with the electric power quality indicators according to GOST 32144-2013.

Methods. To solve this problem, a comparative study of three approaches was carried out: ARIMA/ARIMAX models, the Random Forest ensemble, and the hybrid STL+RF scheme. In all cases, the influence of meteorological factors on the accuracy of solar generation forecasting was analyzed.

Results. It was found that the inclusion of weather data significantly improves the forecast quality compared to models using only the history of consumption. The best results were shown by the hybrid STL+RF model with meteorological features, which provided an optimal compromise between forecast accuracy and stability. This assessment shows that in the tasks of network operation management, the use of hybrid models is more justified than the use of statistical models alone.

Conclusion. The proposed approach can be used as a basis for early warning systems for the risks of electric power quality deterioration in networks with a high share of RES. The practical value of the work lies in linking the results of solar generation forecasting with the regulatory requirements of GOST 32144-2013 and the tasks of dispatch control.

1. Al-Dahidi S., Ayadi O., Adeeb J., Louzazni M. PV Power Forecasting Based on Data- Driven Models: A Review. International Journal of Sustainable Engineering. 2021;14(4):1733-1755.

2. Tyunkov D.A. Sapilova A.A., Gritsai A.S., Alekseenko D.A., Khamitov R.N. Methods for short-term forecasting of solar power plant generation and their. Elektrotekhnicheskie sistemy i kompleksy = Electrical Systems and Complexes. 2020;(3):4-10.

3. Sergeev N.N., Matrenin P.V. Review of international experience in forecasting renewable energy generation using machine learning methods. iPolytech Journal. 2023;27(2):354-369. (In Russ.)

4. Nielsen E. Practical time series analysis: forecasting with statistics and machine learning. Saint Petersburg: Dialektika, 2021. 544 p. (In Russ.)

5. Nikolaev A.A., Ismagilov N.V. Application of neural network technologies for calculating total solar radiation fluxes. Izvestiya vysshikh uchebnykh zavedenii. Povolzhskii region. Estestvennye nauki = University Proceedings. Volga Region. Natural Sciences. 2017;(3):68- 77. (In Russ.)

6. Ahmad T.A, Zhang H. Data-Driven Approach to Composite Building Energy Modeling with Machine Learning Algorithms. Applied Energy. 2020;267: 114863.

7. Konchakov V.Yu., Panov A.I., Yusupov R.M. Intelligent methods for controlling power systems with renewable sources. Informatsionnye i matematicheskie tekhnologii v nauke i upravlenii = Information and Mathematical Technologies in Science and Management. 2023;(3):15-28. (In Russ.)

8. Kuznetsov A.V., Ivanov S.P. Renewable energy sources in autonomous power supply systems: impact on electric energy quality. Elektroenergetika = Electric Power Engineering. 2020;(4):112–120. (In Russ.)

9. Chodakowska E., Nazarko J., Nazarko Ł. ARIMA Models in Solar Radiation Forecasting. Energies. 2023;16(13):5029.

10. Breiman L. Random Forests. Machine Learning. 2001;45(1):5-32.

11. Losev A.S., Massel A.G. Solar radiation forecasting and data imputation for a digital twin of a solar power plant. Informatsionnye i matematicheskie tekhnologii v nauke i upravlenii = Information and Mathematical Technologies in Science and Management. 2022;(1):91-101. (In Russ.)

12. Cleveland R.B., Cleveland W.S., McRae J.E., Terpenning I. STL: A Seasonal-Trend Decomposition Procedure Based on Loess. Journal of Official Statistics. 1990;6(1):3-73.

13. Hyndman R.J., Athanasopoulos G. Forecasting: Principles and Practice. 3rd ed. Melbourne: OTexts; 2021. 442 p.

14. Sokur P.V., Polyakova A.S. Forecasting solar power plant generation based on machine learning algorithms. Vestnik Toraigyrov universiteta. Energeticheskaya seriya = Bulle- tin of Toraighyrov University. Energy Series. 2022;(1):45-52. (In Russ.)

15. Meng M., Song C. Daily Photovoltaic Power Generation Forecasting Model Based on Random Forest Algorithm for North China in Winter. Sustainability. 2020;12(6):2247.

16. Mellit A., Pavan A. M., Lughi V. Deep Learning Neural Networks for Short-Term PV Output Forecasting. Energies. 2021;14(1):112. 17. Zamo M., Meunier P. Quantile-Based Probabilistic Forecasts of Solar Irradiance Using Quantile Regression Forests. Energies. 2016;9(6):494.

17. Aslam S., Herodotou H., Mohsin S. M., Javaid N., Ashraf N., Aslam S. A Survey on Deep Learning Methods for Power Load and Renewable Energy Forecasting in Smart Microgrids. Renewable and Sustainable Energy Reviews. 2021;144;110992.