Prediction of electricity generation from res by machine learning methods

RELEVANCE. Today, the degree of integration of renewable energy sources into the energy system is an indicator of the technological and industrial development of the state. Renewable energy is a driver for the development of the economy, science and education. In Russia, the largest technical potential from renewable energy sources in the Sun (in million tons of standard fuel) is 2.3 * 10³, the second place is occupied by wind energy - 2 * 10³. However, the use of solar energy is associated with great difficulties in predicting the generation of electricity due to its dependence on meteorological conditions, and there is an acute issue of forecasting the generation.

In this article, the authors propose a solution to the urgent problem of predicting energy generation from solar power plants using machine learning systems. TARGET. The purpose of this work is to study the performance of modern artificial intelligence methods to create a platform for predicting the power generated from a solar station to an existing network. Develop the architecture of the information and communication system of the distribution network and the model for predicting the photovoltaic power of the power plant based on machine learning methods. METHODS. One approach to solving this problem is to use machine learning algorithms. Such algorithms, with a correctly chosen training model, are capable of predicting the volume of electricity generation a day ahead with a high accuracy of up to 95%. RESULTS. The values of real generation and predicted generation were compared by five machine learning algorithms, such as neural networks, linear regression, decision tree, random forest, adaptive boosting. The random forest algorithm has the smallest mean square error on the test data. The problem of optimization of the radial topology of the network, which minimizes the total loss of active power, is solved. CONCLUSION. An analysis of the construction of a working machine learning model showed that in order to build an optimal model, only the history of the power generation of this plant, compared with the calculated and measured weather data, is needed. The stability of the model was tested by applying the cross-validation method under various training and testing conditions. The results obtained showed that the model works reliably, since the root-mean-square error of the most accurate model is in the region of 600 kWh (4%).

1. Surzhikova O.A. Problemy i osnovnye napravleniya razvitiya elektrosnabzheniya udalennykh i malonaselennykh potrebitelei Rossii. Bulletin of Siberian Science (Vestnik nauki Sibiri).2012; 4(3):103–108.

2. Suslov K.V. Razvitie sistem e`lektrosnabzheniya izolirovanny`kh territorij Rossii s ispol`zovaniem vozobnovlyaemy`kh istochnikov e`nergii. Bulletin of Irkutsk State Technical University (Vestnik Irkutskogo gosudarstvennogo tekhnicheskogo universiteta). 2017; 5:131–142.

3. International Energy Agency 2022 Renewables 2022 Analysys and Forecasts to 2023. Paris: International Energy Agency

4. Sokol`nikova T.V., Suslov K.V., Lombardy P. Opredelenie optimal`ny`kh parametrov nakopitelya dlya integraczii vozobnovlyaemy`kh istochnikov e`nergii v izolirovanny`kh e`nergosistemakh s aktivny`mi potrebitelyami). Bulletin of Irkutsk State Technical University (Vestnik Irkutskogo gosudarstvennogo tekhnicheskogo universiteta). 2017; 10:206–211.

5. Vinogradov A.V., Vinogradova A.V., Seyfullin A.Yu., et al. Principles of electrical grid configuration management and tasks of their implementation. Power engineering: research, equipment, technology. 2021;23(3):34-46. doi: 10.30724/1998-9903-2021-23-3-34-46.

6. Ivanov I.YU., Novokreshchenov V.V., Ivanova V.R. Sovremennoe sostoyanie problem funkcionirovaniya kompleksov relejnoj zashchity i avtomatiki, ispol'zuemyh v aktivnoj adaptivnoj seti. Energetika: issledovaniya, oborudovanie, tekhnologii. 2022;24(6):102-123. doi:10.30724/1998-9903-2022-24-6-102-123.

7. Zatsarinnaya Y., Logacheva A., Gainullin R., et al. Solution for renewable future. E3S Web of Conferences. 2019;124:04010. doi: 10.1051/e3sconf/201912404010.

8. Lavrik A.Y., Zhukovsky Y.L., Lavrik A.Y., Buldysko A.D. Fatures of the optimal composition of a wind-solar power plant with diesel generators. Power engineering: research, equipment, technology. 2020;22(1):10-17. doi: 10.30724/1998-9903-2020-22-1-10-17.

9. Ercan I., Ahmet O., Bihter Y., et al. Shortmid-term solar power prediction by using artificial neural networks, Solar Energy. 2012;86(2):725–733.

10. Gigoni L., Betti A., Crisostomi E., et al. Day-ahead hourly forecasting of power generation from photovoltaic plants. IEEE Trans Sustain Energy. 2018;9(2):831-42. doi: 10.1109/TSTE.2017.2762435.

11. Khan P., Byun Y., Lee S., et al. Machine learning-based approach to predict energy consumption of renewable and nonrenewable power sources. Energies. 2020;13(18):4870. doi: 10.3390/en13184870.

12. Khalyasmaa A., Eroshenko S., Tashchilin V., et al. Industry Experience of Developing Day-Ahead Photovoltaic Plant Forecasting System Based on Machine Learning. Remote Sens. 2020;12:3420. doi: 10.3390/rs12203420.

13. Ramazanova R.I., Isaeva O.V., Elektrosnabzhenie otdalennyh naselennyh punktov s pomoshch'yu vetrodizel'nyh ustanovok. Tinchurinskie chteniya - 2022 "Energetika i cifrovaya transformaciya": Sbornik statej po materialam konferencii.In 3 tomah; 27–29 Apr 2022 года; Kazan': Kazanskij gosudarstvennyj energeticheskij universitet, 2022. pp. 669-671.

14. Eltamaly A., Ahmed M., Alotaibi M., et al. Performance of Communication Network for Monitoring Utility Scale Photovoltaic Power Plants. Energies. 2020;13:5527. doi: 10.3390/en13215527.

15. Vorkunov O.V., Ikhsanova A.I., Gainutdinova A.M. Optimum orientation of solar pv modules in kazan. Power engineering: research, equipment, technology. 2015;(11-12):26-29. doi: 10.30724/1998-9903-2015-0-11-12-26-29.

16. Eroshenko S., Khalyasmaa A., Snegirev D. Machine learning techniques for short-term solar power stations operational mode planning. E3S Web of Conferences. 2018; 51:02004. doi: 10.1051/e3sconf/20185102004.

17. Lukutin B.V., Karrar Hameed K. Optimization of energy balances of a photovoltaic power plant with electrochemical and thermal storage of solar energy. Power engineering: research, equipment, technology. 2022;24(2):3-13. doi: 10.30724/1998-9903-2022-24-2-3-13.