Prediction of photovoltaic energy generation using recurrent and transformer neural networks

• Autorzy: Siwek Krzysztof , Świder Stanisław

Identyfikatory

DOI

10.24425/aee.2025.153900

• Języki publikacji: EN

Abstrakty

EN

Precise prediction of photovoltaic (PV) energy generation is essential for optimal, profitable and ecological management of electric energy resources all over the world. As a result, attempts are being made to develop more accurate prediction algorithms. This paper compares the application of Long Short-Term Memory (LSTM, a subtype of Recurrent Neural Networks), PatchTST (a type of Transformer Neural Network – TNN) and ensemble models (making use of these two approaches) for estimating PV energy production 24 hours ahead. The results indicate that both analysed single methods have comparable prediction accuracy, though the hybrid approach outperforms them. The experiments were conducted on data from PV sites deployed across campuses at Australian La Trobe University. However, future studies could verify this approach using different datasets. Algorithms and results presented in this study may especially contribute to the development of Recurrent and Transformer Neural Networks as prediction methods of PV energy production.

Słowa kluczowe

EN

LSTM; PatchTST; photovoltaic energy; PV; recurrent neural network; transformer neural network; TNN

• Wydawca: Polish Academy of Sciences, Committee on Electrical Engineering
• Czasopismo: Archives of Electrical Engineering
• Rocznik: 2025
• Tom: Vol. 74, nr 2
• Strony: 311--330
• Opis fizyczny: Bibliogr. 40 poz., rys., tab., wykr., wz.

Twórcy

autor

Siwek Krzysztof

• Institute of Theory of Electrical Engineering, Measurement and Information Systems, Faculty of Electrical Engineering, Warsaw University of Technology, Koszykowa 75, 00-662 Warsaw

• https://orcid.org/0000-0003-2642-2319

autor

Świder Stanisław

• Institute of Theory of Electrical Engineering, Measurement and Information Systems, Faculty of Electrical Engineering, Warsaw University of Technology, Koszykowa 75, 00-662 Warsaw

• https://orcid.org/0009-0004-7798-5773

Bibliografia

• [1] Singh G.K., Solar power generation by PV (photovoltaic) technology: A review, Energy, vol. 53 (2013), DOI: 10.1016/j.energy.2013.02.057.
• [2] Jobayer M., Shaikat M.A.H., Naimur R., Rakibul H., A systematic review on predicting PV system parameters using machine learning, Heliyon, vol. 9, no. 6, e16815 (2023), DOI: 10.1016/j.heliyon.2023.e16815.
• [3] Chandel S.S., Gupta A., Chandel R., Tajjour S., Review of deep learning techniques for power generation prediction of industrial solar photovoltaic plants, Solar Compass, vol. 8, 100061 (2023), DOI: 10.1016/j.solcom.2023.100061.
• [4] Tsai W.-C., Tu C.-S., Hong C.-M., Lin W.-M., A Review of State-of-the-Art and Short-Term Forecasting Models for Solar PV Power Generation, Energies, vol. 16, no. 14, 5436 (2023), DOI: 10.3390/en16145436.
• [5] Krechowicz M., Krechowicz A., Licholai L., Pawelec A., Piotrowski J.Z., Stępień A., Reduction of the Risk of Inaccurate Prediction of Electricity Generation from PV Farms Using Machine Learning, Energies, vol. 15, no. 11, 4006 (2022), DOI: https://doi.org/10.3390/en15114006.
• [6] Suksamosorn S., Hoonchareon N., Songsiri J., Post-Processing of NWP Forecasts Using Kalman Filtering with Operational Constraints for Day-Ahead Solar Power Forecasting in Thailand, IEEE Access, vol. 9, pp. 105409–105423 (2021), DOI: 10.1109/ACCESS.2021.3099481.
• [7] Shapsough S., Dhaouadi R., Zualkernan I., Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules, Procedia Computer Science, vol. 155, pp. 463–470 (2019), DOI: 10.1016/j.procs.2019.08.065.
• [8] Liu Y., Short-Term Prediction Method of Solar Photovoltaic Power Generation Based on Machine Learning in Smart Grid, Mathematical Problems in Engineering, vol. 2022, pp. 1–10 (2022), DOI: 10.1155/2022/8478790.
• [9] Vrettos E., Gehbauer C., A Hybrid Approach for Short-Term PV Power Forecasting in Predictive Control Applications, in 2019 IEEE Milan PowerTech, Milan, Italy, pp. 1–6 (2019), DOI: 10.1109/PTC.2019.8810672.
• [10] Nejati M., Amjady N., A New Solar Power Prediction Method Based on Feature Clustering and Hybrid Classification-Regression Forecasting, IEEE Trans. Sustain. Energy, vol. 13, no. 2, pp. 1188–1198 (2022), DOI: 10.1109/TSTE.2021.3138592.
• [11] Hochreiter S., Schmidhuber J., Long Short-Term Memory, Neural Computation, vol. 9, no. 8, pp. 1735–1780 (1997), DOI: 10.1162/neco.1997.9.8.1735.
• [12] Asghar R., Fulginei F.R., Quercio M., Mahrouch A., Artificial Neural Networks for Photovoltaic Power Forecasting: A Review of Five Promising Models, IEEE Access, vol. 12, pp. 90461–90485 (2024), DOI: 10.1109/ACCESS.2024.3420693.
• [13] Liu C.-H., Gu J.-C., Yang M.-T., A Simplified LSTM Neural Networks for One Day-Ahead Solar Power Forecasting, IEEE Access, vol. 9, pp. 17174–17195 (2021), DOI: 10.1109/ACCESS.2021.3053638.
• [14] Li G., Xie S., Wang B., Xin J., Li Y., Du S., Photovoltaic Power Forecasting with a Hybrid Deep Learning Approach, IEEE Access, vol. 8, pp. 175871–175880 (2020), DOI: 10.1109/ACCESS.2020.3025860.
• [15] Wang L., Mao M., Xie J., Liao Z., Zhang H., Li H., Accurate solar PV power prediction interval method based on frequency-domain decomposition and LSTM model, Energy, vol. 262, 125592 (2023), DOI: 10.1016/j.energy.2022.125592.
• [16] Tovar M., Robles M., Rashid F., PV Power Prediction, Using CNN-LSTM Hybrid Neural Network Model. Case of Study: Temixco-Morelos, México, Energies, vol. 13, no. 24, 6512 (2020), DOI: 10.3390/en13246512.
• [17] Succetti F., Rosato A., Araneo R., Panella M., Deep Neural Networks for Multivariate Prediction of Photovoltaic Power Time Series, IEEE Access, vol. 8, pp. 211490–211505 (2020), DOI: 10.1109/ACCESS.2020.3039733.
• [18] Vaswani A. et al., Attention Is All You Need, arXiv (2017), DOI: 10.48550/arXiv.1706.03762.
• [19] Tao K., Zhao J., Tao Y., Qi Q., Tian Y., Operational day-ahead photovoltaic power forecasting based on transformer variant, Applied Energy, vol. 373, 123825 (2024), DOI: 10.1016/j.apenergy.2024.123825.
• [20] Liu J., Fu Y., Renewable energy forecasting: A self-supervised learning-based transformer variant, Energy, vol. 284, 128730 (2023), DOI: 10.1016/j.energy.2023.128730.
• [21] Kim J., Obregon J., Park H., Jung J.-Y., Multi-step photovoltaic power forecasting using transformer and recurrent neural networks, Renewable and Sustainable Energy Reviews, vol. 200, 114479 (2024), DOI: 10.1016/j.rser.2024.114479.
• [22] Wu J., Zhao Y., Zhang R., Li X., Wu Y., Application of three transformer neural networks for short-term photovoltaic power prediction: A case study, Solar Compass, vol. 12, 100089 (2024), DOI: 10.1016/j.solcom.2024.100089.
• [23] Munsif M., Ullah F.U.M., Khan S.U., Khan N., Baik S.W., CT-NET: A Novel Convolutional Transformer Based Network for Short-Term Solar Energy Forecasting Using Climatic Information, Computer Systems Science and Engineering, vol. 47, no. 2, pp. 1751–1773 (2023), DOI: 10.32604/csse.2023.038514.
• [24] López Santos M., García-Santiago X., Echevarría Camarero F., Blázquez Gil G., Carrasco Ortega P., Application of temporal fusion transformer for day-ahead PV power forecasting, Energies, vol. 15, no. 14, 5232 (2022), DOI: 10.3390/en15145232.
• [25] Gokhale G., Van Gompel J., Claessens B., Develder C., Transfer learning in transformer-based demand forecasting for home energy management, arXiv (2023), DOI: 10.48550/arXiv.2310.19159.
• [26] Hu K., Fu Z., Lang C., Li W., Tao Q., Wang B., Short-Term Photovoltaic Power Generation Prediction Based on Copula Function and CNN-CosAttention-Transformer, Sustainability, vol. 16, no. 14, 5940 (2024), DOI: 10.3390/su16145940.
• [27] Sherozbek J., Park J., Akhtar M.S., Yang O.-B., Transformers-Based Encoder Model for Forecasting Hourly Power Output of Transparent Photovoltaic Module Systems, Energies, vol. 16, no. 3, 1353 (2023), DOI: 10.3390/en16031353.
• [28] Tian F., Fan X., Wang R., Qin H., Fan Y., A Power Forecasting Method for Ultra-Short-Term Photovoltaic Power Generation Using Transformer Model, Mathematical Problems in Engineering, vol. 2022, pp. 1–15 (2022), DOI: 10.1155/2022/9421400.
• [29] Yang T., Li B., Xun Q., LSTM-Attention-Embedding Model-Based Day-Ahead Prediction of Photovoltaic Power Output Using Bayesian Optimization, IEEE Access, vol. 7, pp. 171471–171484 (2019), DOI: 10.1109/ACCESS.2019.2954290.
• [30] Marhon S.A., Cameron C.J.F., Kremer S.C., Recurrent Neural Networks, Handbook on Neural Information Processing, vol. 49, Bianchini M., Maggini M., Jain L.C., Eds., in Intelligent Systems Reference Library, vol. 49, Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 29–65 (2013), DOI: 10.1007/978-3-642-36657-4_2.
• [31] Gers F.A., Schmidhuber J., Cummins F., Learning to forget: continual prediction with LSTM, 9th International Conference on Artificial Neural Networks: ICANN ’99, Edinburgh, UK: IEE, pp. 850–855 (1999), DOI: 10.1049/cp:19991218.
• [32] Nie Y., Nguyen N.H., Sinthong P., Kalagnanam J., A Time Series is Worth 64 Words: Long-term Forecasting with Transformers, arXiv (2023), DOI: 10.48550/arXiv.2211.14730.
• [33] Osowski S., Metody i narzędzia eksploracji danych, BTC (2013).
• [34] Yadav H., Thakkar A., NOA-LSTM: An efficient LSTM cell architecture for time series forecasting, Expert Systems with Applications, vol. 238, 122333 (2024), DOI: 10.1016/j.eswa.2023.122333.
• [35] Lindemann B., Muller T., Vietz H., Jazdi N., Weyrich M., A survey on long short-term memory networks for time series prediction, Procedia CIRP, vol. 99, pp. 650–655 (2021), DOI: 10.1016/ j.procir.2021.03.088.
• [36] Konstantinou M., Peratikou S., Charalambides A.G., Solar Photovoltaic Forecasting of Power Output Using LSTM Networks, Atmosphere, vol. 12, no. 1, 124 (2021), DOI: 10.3390/atmos12010124.
• [37] Géron A., Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: concepts, tools, and techniques to build intelligent systems, Second edition, O’Reilly Media, Inc (2019).
• [38] Wimalaratne S., Haputhanthri D., Kahawala S., Gamage G., Alahakoon D., Jennings A., UNISOLAR: An Open Dataset of Photovoltaic Solar Energy Generation in a Large Multi-Campus University Setting, 15th International Conference on Human System Interaction (HSI), Melbourne, Australia: IEEE (2022), DOI: 10.1109/HSI55341.2022.9869474.
• [39] Abadi M. et al., TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, arXiv (2016), DOI: 10.48550/arXiv.1603.04467.
• [40] Wolf T. et al., Transformers: State-of-the-Art Natural Language Processing, Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38–45 (2020), DOI: 10.18653/v1/2020.emnlp-demos.6.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).