Three Hour Ahead PV Power Forecasting with Bidirectional Recurrent Networks: Insights into Monthly Variability
Main Article Content
Abstract
Despite extensive research into PV power forecast models, their monthly performance is rarely thoroughly examined, creating gaps in our understanding of their accuracy and applicability across different times of the year. This paper focuses on evaluating the monthly performance of four predictive models designed for a three-hour forecast horizon. The studied models are based on distinct architectures of Recurrent Neural Networks (RNNs): Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), Gated Recurrent Unit (GRU), and Bidirectional GRU (Bi-GRU). By analyzing statistical indicators across various months, we uncover seasonal fluctuations, with performance hitting its lowest points in winter (November and December) and peaking in summer (June to August). Notably, Bi-GRU consistently outperforms the other models, displaying lower error rates and higher accuracy across diverse months. As a result, it emerges as the preferred choice for forecasting due to its superior predictive capability. Additionally, we observe variations in daily performance across seasons, highlighting the complexities of data sequences and underscoring the importance of careful model selection. This research significantly contributes to the advancement of predictive modeling in time-series analysis, providing valuable insights into model performance and seasonal variations, and equipping practitioners and researchers with enhanced methodologies for improving forecast accuracy.
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
-
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
-
ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
How to Cite
References
Agga, A., Abbou, A., Labbadi, M., & El Houm, Y. (2021). Short-term self consumption PV plant power production forecasts based on hybrid CNN-LSTM, ConvLSTM models. Renewable Energy, 177, 101 112. https://doi.org/10.1016/j.renene.2021.05.095.
Al-Ja’afreh, M. A. A., Mokryani, G., & Amjad, B. (2023). An enhanced CNN-LSTM based multi-stage framework for PV and load short-term forecasting: DSO scenarios. Energy Reports, 10, 1387 1408. https://doi.org/10.1016/j.egyr.2023.08.003.
Benmouiza, K., & Cheknane, A. (2013). Forecasting hourly global solar radiation using hybrid k-means and nonlinear autoregressive neural network models. Energy Conversion and Management, 75, 561 569. https://doi.org/10.1016/j.enconman.2013.07.003.
Benmouiza, K., & Cheknane, A. (2019). Clustered ANFIS network using fuzzy c-means, subtractive clustering, and grid partitioning for hourly solar radiation forecasting. Theoretical and Applied Climatology, 137(1 2), 31 43. https://doi.org/10.1007/s00704-018-2576-4.
Cao, Y., Liu, G., Luo, D., Bavirisetti, D. P., & Xiao, G. (2023). Multi-timescale photovoltaic power forecasting using an improved Stacking ensemble algorithm based LSTM-Informer model. Energy, 283. https://doi.org/10.1016/j.energy.2023.128669.
Cryer, J. D., & Chan, K.-S. (s.d.). Springer Texts in Statistics Time Series Analysis With Applications in R Second Edition.
Dairi, A., Harrou, F., Sun, Y., & Khadraoui, S. (2020). Short-term forecasting of photovoltaic solar power production using variational auto-encoder driven deep learning approach. Applied Sciences (Switzerland), 10(23), 1 20. https://doi.org/10.3390/app10238400.
Dhaked, D. K., Dadhich, S., & Birla, D. (2023). Power output forecasting of solar photovoltaic plant using LSTM. Green Energy and Intelligent Transportation, 2(5). https://doi.org/10.1016/j.geits.2023.100113.
El Robrini, F., & Amrouche, B. (2023). Support Vector Regression for Predicting Intra-day Photovoltaic Generation in Algeria. In International Conference on Electronics, Energy, and Measurement. Medea. https://doi.org/10.1109/IC2EM59347.2023.10419659.
El Robrini, F., Bukhari, S. M. S., Zafar, M. H., Al-Tawalbeh, N., Akhtar, N., & Sanfilippo, F. (2024). Federated learning and non-federated learning based power forecasting of photovoltaic/wind power energy systems: A systematic review. Energy and AI, 18, 100438. https://doi.org/10.1016/j.egyai.2024.100438.
Feroz Mirza, A., Mansoor, M., Usman, M., & Ling, Q. (2023). Hybrid Inception-embedded deep neural network ResNet for short and medium-term PV-Wind forecasting. Energy Conversion and Management, 294. https://doi.org/10.1016/j.enconman.2023.117574.
Gandhi, O., Kumar, D. S., Rodríguez-Gallegos, C. D., & Srinivasan, D. (2020a). Review of power system impacts at high PV penetration Part I: Factors limiting PV penetration. Solar Energy, 210, 181 201. https://doi.org/10.1016/j.solener.2020.06.097.
Gandhi, O., Kumar, D. S., Rodríguez-Gallegos, C. D., & Srinivasan, D. (2020b). Review of power system impacts at high PV penetration Part I: Factors limiting PV penetration. Solar Energy, 210, 181 201. https://doi.org/10.1016/j.solener.2020.06.097.
Geng, D., Wang, B., & Gao, Q. (2023). A hybrid photovoltaic/wind power prediction model based on Time2Vec, WDCNN and BiLSTM. Energy Conversion and Management, 291. https://doi.org/10.1016/j.enconman.2023.117342.
Guermoui, M., Bouchouicha, K., Bailek, N., & Boland, J. W. (2021a). Forecasting intra-hour variance of photovoltaic power using a new integrated model. Energy Conversion and Management, 245. https://doi.org/10.1016/j.enconman.2021.114569.
Guermoui, M., Gairaa, K., Boland, J., & Arrif, T. (2021b). A Novel Hybrid Model for Solar Radiation Forecasting Using Support Vector Machine and Bee Colony Optimization Algorithm: Review and Case Study. Journal of Solar Energy Engineering, Transactions of the ASME, 143(2). https://doi.org/10.1115/1.4047852.
Hamza Zafar, M., Mujeeb Khan, N., Mansoor, M., Feroz Mirza, A., Kumayl Raza Moosavi, S., & Sanfilippo, F. (2022). Adaptive ML-based technique for renewable energy system power forecasting in hybrid PV-Wind farms power conversion systems. Energy Conversion and Management, 258. https://doi.org/10.1016/j.enconman.2022.115564.
Harrou, F., Kadri, F., & Sun, Y. (2020). Forecasting of Photovoltaic Solar Power Production Using LSTM Approach. Dans F. Harrou (Éd.), Advanced Statistical Modeling, Forecasting, and Fault Detection in Renewable Energy Systems. (S.l.) : IntechOpen. https://doi.org/10.5772/intechopen.91248.
Hassan, M. A., Bailek, N., Bouchouicha, K., & Nwokolo, S. C. (2021). Ultra-short-term exogenous forecasting of photovoltaic power production using genetically optimized non-linear auto-regressive recurrent neural networks. Renewable Energy, 171, 191 209. https://doi.org/10.1016/j.renene.2021.02.103.
Hosseini Dolatabadi, S. H., Soleimani, A., Maghanaki, M., & Ilinca, A. (2024). Enhancing Photovoltaic Farm Capacity Estimation: A Comprehensive Analysis with a Novel Approach. Energy Technology, 12(4). https://doi.org/10.1002/ente.202301294.
Huang, J., Korolkiewicz, M., Agrawal, M., & Boland, J. (2013). Forecasting solar radiation on an hourly time scale using a Coupled AutoRegressive and Dynamical System (CARDS) model. Solar Energy, 87(1), 136 149. https://doi.org/10.1016/j.solener.2012.10.012.
Keddouda, A., Ihaddadene, R., Boukhari, A., Atia, A., Arici, M., Lebbihiat, N., & Ihaddadene, N. (2023). Solar photovoltaic power prediction using artificial neural network and multiple regression considering ambient and operating conditions. Energy Conversion and Management, 288. https://doi.org/10.1016/j.enconman.2023.117186.
Khelifi, R., Guermoui, M., Rabehi, A., & Lalmi, D. (2020). Multi-step-ahead forecasting of daily solar radiation components in the Saharan climate. International Journal of Ambient Energy, 41(6), 707 715. https://doi.org/10.1080/01430750.2018.1490349.
Khelifi, R., Guermoui, M., Rabehi, A., Taallah, A., Zoukel, A., Ghoneim, S. S. M., … Zaitsev, I. (2023). Short-Term PV Power Forecasting Using a Hybrid TVF-EMD-ELM Strategy. International Transactions on Electrical Energy Systems, 2023. https://doi.org/10.1155/2023/6413716.
Kuppusamy, M., & Balaraman, S. (2024). Long Short Term Memory Tracker-Based Modified DC-DC Converter for Power Quality Improvement in Grid-PV Systems under Uniform and Partial Shading Environments. Energy Technology, 12(3). https://doi.org/10.1002/ente.202300648.
Kushwaha, V., & Pindoriya, N. M. (2019). A SARIMA-RVFL hybrid model assisted by wavelet decomposition for very short-term solar PV power generation forecast. Renewable Energy, 140, 124 139. https://doi.org/10.1016/j.renene.2019.03.020.
Liu, Q., Darteh, O. F., Bilal, M., Huang, X., Attique, M., Liu, X., & Acakpovi, A. (2023). A cloud-based Bi-directional LSTM approach to grid-connected solar PV energy forecasting for multi-energy systems. Sustainable Computing: Informatics and Systems, 40. https://doi.org/10.1016/j.suscom.2023.100892.
Mamdouh, M., Ezzat, M., & Hefny, H. (2024). Improving flight delays prediction by developing attention-based bidirectional LSTM network. Expert Systems with Applications, 238. https://doi.org/10.1016/j.eswa.2023.121747.
Mansoor, M., Feroz Mirza, A., Usman, M., & Ling, Q. (2023). Hybrid forecasting models for wind-PV systems in diverse geographical locations: Performance and power potential analysis. Energy Conversion and Management, 287. https://doi.org/10.1016/j.enconman.2023.117080.
Rabehi, A., Guermoui, M., & Lalmi, D. (2020). Hybrid models for global solar radiation prediction: a case study. International Journal of Ambient Energy, 41(1), 31 40. https://doi.org/10.1080/01430750.2018.1443498.
Raza, M. Q., Nadarajah, M., & Ekanayake, C. (2016, 15 octobre). On recent advances in PV output power forecast. Solar Energy. Elsevier Ltd. https://doi.org/10.1016/j.solener.2016.06.073.
Sadeghi, D., Golshanfard, A., Eslami, S., Rahbar, K., & Kari, R. (2023). Improving PV power plant forecast accuracy: A hybrid deep learning approach compared across short, medium, and long-term horizons. Renewable Energy Focus, 45, 242 258. https://doi.org/10.1016/j.ref.2023.04.010.
Sahin, G., Isik, G., & van Sark, W. G. J. H. M. (2023). Predictive modeling of PV solar power plant efficiency considering weather conditions: A comparative analysis of artificial neural networks and multiple linear regression. Energy Reports, 10, 2837 2849. https://doi.org/10.1016/j.egyr.2023.09.097.
Sampath Kumar, D., Gandhi, O., Rodríguez-Gallegos, C. D., & Srinivasan, D. (2020). Review of power system impacts at high PV penetration Part II: Potential solutions and the way forward. Solar Energy, 210, 202 221. https://doi.org/10.1016/j.solener.2020.08.047.
Shab, G. (2022). Prévision multi-horizon de l’éclairement global horizontal pour la gestion intelligente du réseau électrique de distribution en région Occitanie. Université de Perpignan.
Ssekulima, E. B., Anwar, M. B., Al Hinai, A., & El Moursi, M. S. (2016, 1 juillet). Wind speed and solar irradiance forecasting techniques for enhanced renewable energy integration with the grid: A review. IET Renewable Power Generation. Institution of Engineering and Technology. https://doi.org/10.1049/iet-rpg.2015.0477.
Thaker, J., & Höller, R. (2024). Hybrid model for intra-day probabilistic PV power forecast. Renewable Energy, 232, 121057. https://doi.org/10.1016/j.renene.2024.121057.
Wang, F., Xuan, Z., Zhen, Z., Li, K., Wang, T., & Shi, M. (2020). A day-ahead PV power forecasting method based on LSTM-RNN model and time correlation modification under partial daily pattern prediction framework. Energy Conversion and Management, 212. https://doi.org/10.1016/j.enconman.2020.112766.
Wu, F., Wang, S., Liu, D., Cao, W., Fernandez, C., & Huang, Q. (2024). An improved convolutional neural network-bidirectional gated recurrent unit algorithm for robust state of charge and state of energy estimation of new energy vehicles of lithium-ion batteries. Journal of Energy Storage, 82. https://doi.org/10.1016/j.est.2024.110574.
Yang, D. (2019). Making reference solar forecasts with climatology, persistence, and their optimal convex combination. Solar Energy, 193, 981 985. https://doi.org/10.1016/j.solener.2019.10.006.
Ziane, A., Necaibia, A., Sahouane, N., Dabou, R., Mostefaoui, M., Bouraiou, A., … Blal, M. (2021). Photovoltaic output power performance assessment and forecasting: Impact of meteorological variables. Solar Energy, 220, 745 757. https://doi.org/10.1016/j.solener.2021.04.004.
Web sites :
Bilan des Capacités d’Energies Renouvelables Installées en Algérie à Fin 2023. (2024). Algeria. https://www.cerefe.gov.dz/wp-content/uploads/2024/09/Bilan-des-secteurs-jusqua-fin-2023_.pdf.
Commissariat aux Energies Renouvelables et à l’Efficacité Energétique. (2020). Transition Energétique en Algérie. www.cerefe.gov.dz.
Ministère de la Transition Energétique et des Energies Renouvelables. (2021, 26 novembre). AVIS D’APPEL D’OFFRES A INVESTISSEURS N°01/MTEER/2021.
SONELGAZ-EnR. (2023, 27 février). NATIONAL AND INTERNATIONAL OPEN TO TENDER N°01:CEEG/2023. BAOSEM EDITION & PUBLICITE. https://moit.gov.vn/upload/2005517/fck/files/Thong_tin_moi_thau_xay_dung_15_nha_may_dien_mat_troi_2226c.pdf.