Improving of the Generation Accuracy Forecasting of Photovoltaic Plants Based on k-Means and k-Nearest Neighbors Algorithms

Renewable energy sources (RES) are seen as a means of the fuel and energy complex carbon footprint reduction but the stochastic nature of generation complicates RES integration with electric power systems. Therefore, it is necessary to develop and improve methods for forecasting of the power plants generation using the energy of the sun, wind and water flows. One of the ways to improve the accuracy of forecast models is a deep analysis of meteorological conditions as the main factor affecting the power generation. In this paper, a method for adapting of forecast models to the meteorological conditions of photovoltaic stations operation based on machine learning algorithms was proposed and studied. In this case, unsupervised learning is first performed using the k-means method to form clusters. For this, it is also proposed to use studied the feature space dimensionality reduction algorithm to visualize and estimate the clustering accuracy. Then, for each cluster, its own machine learning model was trained for generation forecasting and the k-nearest neighbours algorithm was built to attribute the current conditions at the model operation stage to one of the formed clusters. The study was conducted on hourly meteorological data for the period from 1985 to 2021. A feature of the approach is the clustering of weather conditions on hourly rather than daily intervals. As a result, the mean absolute percentage error of forecasting is reduced significantly, depending on the prediction model used. For the best case, the error in forecasting of a photovoltaic plant generation an hour ahead was 9 %.

1. El hendouzi A., Bourouhou A. (2020) Solar Photovoltaic Power Forecasting. Journal of Electrical and Computer Engineering, 2020, 1–21. https://doi.org/10.1155/2020/8819925.

2. Antonanzas J., Osorio N., Escobar R., Urraca R., Martinez-de-Pison F. J., Antonanzas-Torres F. (2016) Review of Photovoltaic Power Forecasting Solar Energy, 136, 78–111. https://doi.org/10.1016/j.solener.2016.06.069.

3. Voyant С., Notton G., Kalogirou S., Nivet M. L., Paoli C., Motte F., Fouilloy A. (2017) Machine Learning Methods for Solar Radiation Forecasting: а Review. Renewable Energy, 105, 569–582. https://doi.org/10.1016/j.renene.2016.12.095.

4. Bramm A. M., Khalyasmaa A. I., Eroshenko S. A., Matrenin P. V., Papkova N. A., Sekatski D. A. (2022) Topology Optimization of the Network with Renewable Energy Sources Generation Based on a Modified Adapted Genetic Algorithm. Enеrgеtika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, 65 (4), 341–354. https://doi.org/10.21122/1029-7448-2022-65-4-341-354 (in Russian).

5. Khalyasmaa A. I., Eroshenko S. A., Tashchilin V. A., Ramachandran H., Piepur Chakravarthi T., Butusov D. N. (2020) Industry Experience of Developing Day-Ahead Photovoltaic Plant Forecasting System Based on Machine Learning. Remote Sensing, 12 (20), 3420. https://doi.org/10.3390/rs12203420.

6. Eroshenko S. A., Khalyasmaa A. I., Snegirev D. A., Dubailova V. V., Romanov A. M., Butusov D. N. (2020) The Impact of Data Filtration on the Accuracy of Multiple Time-Domain Forecasting for Photovoltaic Power Plants Generation. Applied Sciences, 10 (22), 8265. https://doi.org/10.3390/app10228265.

7. Rana M., Koprinska I., Agelidis V. G. (2016) Solar Power Forecasting Using Weather Type Clustering and ensembles of Neural Networks International Joint Conference on Neural Networks (IJCNN). Vancouver, BC, Canada: IEEE, 4962–4969. https://doi.org/10.1109/IJCNN.2016.7727853.

8. Zhang Z., Wang C., Peng X., Qin H., Lv H., Fu J., Wang H. (2021) Solar Radiation Intensity Probabilistic Forecasting Based on K-Means Time Series Clustering and Gaussian Process Regression IEEE Access, 9, 89079–89092. https://doi.org/10.1109/ACCESS.2021.3077475.

9. Feng C., Cui M., Hodge B. M., Lu S., Hamann H. F., Zhang J. (2021) Unsupervised Clustering-Based Short-Term Solar Forecasting. IEEE Transactions on Sustainable Energy, 10 (4), 2174–2185. https://doi.org/10.1109/TSTE.2018.2881531.

10. Sanz-Gorrachategui I., Pastor-Flores P., Guillén-Asensio A., Artal-Sevil J. S., Bono-Nuez A., Martín-del-Brío B., Bernal-Ruiz C. (2020) Unsupervised Clustering of Battery Waveforms in Off-Grid PV Installations. 2020 Fifteenth International Conference on Ecological Vehicles and Renewable Energies (EVER). Monte-Carlo, Monaco, 1–6. https://doi.org/10.1109/EVER48776.2020.9242942.

11. Kang M. C., Sohn J. M., Park J. Y., Lee S. K., Yoon Y. T. (2011) Development of Algorithm for Day Ahead PV Generation Forecasting Using Data Mining Method. IEEE 54th International Midwest Symposium on Circuits and Systems (MWSCAS), Seoul, Korea (South), IEEE, 1–4. https://doi.org/10.1109/MWSCAS.2011.6026333.

12. Wang F., Pang S., Zhen Z., Li K., Ren H, Shafie-Khah M., Catalão J. P. S. (2018) Pattern Classification and PSO Optimal Weights Based Sky Images Cloud Motion Speed Calculation Method for Solar PV Power Forecasting IEEE Industry Applications Society Annual Meeting (IAS). Portland, OR, USA, IEEE, 1–9. https://doi.org/10.1109/IAS.2018.8544468.

13. Lai C. S., Jia Y., McCulloch M. D., Xu Z. (2017) Daily Clearness Index Profiles Cluster Analysis for Photovoltaic System IEEE Transactions on Industrial Informatics, 13 (5), 2322–2332 https://doi.org/10.1109/TII.2017.2683519.

14. Severiano C., Guimarães F. G., Cohen M. W. (2016) Very Short-Term Solar Forecasting Using Multi-Agent System Based on Extreme Learning Machines and Data Clustering. 2016 IEEE Symposium Series on Computational Intelligence (SSCI). Athens, Greece, IEEE, 1–8. https://doi.org/10.1109/SSCI.2016.7850162.

15. Yang Y., Dong L. (2013) Short-Term PV Generation System Direct Power Prediction Model on Wavelet Neural Network and Weather Type Clustering 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics. Hangzhou, China, IEEE, 207–211. https://doi.org/10.1109/IHMSC.2013.56.

16. Alfredo N., Ogliari E., Leva S., Pavan A. M., Mellit A., Lughi V., Dolara A. (2019) Day-Ahead Photovoltaic Forecasting: A Comparison of the Most Effective Techniques Energies, 12 (9), 1621. https://doi.org/10.3390/en12091621.

17. Meteoblue. Available at: https://www.meteoblue.com/en/weather.

18. Gorban, A. N., Kegl B., Wunsch D. C., Zinovyev A. (2008) Principal Manifolds for Data Visualization and Dimension Reduction. Lecture Notes in Computational Science and Enginee, Vol 58. Berlin, Springer. 364. https://doi.org/10.1007/978-3-540-73750-6_5.

19. Hartigan J. A., Wong M. A. (1979) Algorithm AS 136: A K-Means Clustering Algorithm Journal of the Royal Statistical Society. Series C (Applied Statistics), 28 (1), 100–108. https://doi.org/10.2307/2346830.

20. Matrenin P. V., Manusov V. Z., Khalyasmaa A. I., Antonenkov D. V., Eroshenko S. A., Butusov D. A. (2020) Improving Accuracy and Generalization Performance of Small-Size Recurrent Neural Networks Applied to Short-Term Load Forecasting Mathematics, 8 (12), 2169. https://doi.org/10.3390/math8122169.

21. Matrenin P. V., Manusov V. Z., Igumnova E. A. (2020) Robust Short-Term Wind Speed Forecasting Using Adaptive Shallow Neural Networks. Problems of The Regional Energetics, 3 (47), 69–80. https://doi.org/10.5281/zenodo.4018960 (in Russian).

22. Clustering. Scikit-Learn. Machine Learning in Python. Available at: https://scikit-learn.org/stable/modules/clustering.html.

23. Drucker H. (1997) Improving Regressors using Boosting Techniques. Proceedings of the 14th International Conference on Machine Learning (ICML). Citeseer, 107–115.

24. Adaptive Boosting. Scikit-Learn. Machine learning in Python. Available at: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.SGDRegressor.html?highlight=adaptive+busting.