Multivariate PV Power Forecasting via CPO-Optimized Deep Spatiotemporal Networks
DOI:
https://doi.org/10.63313/JCSFT.9049Keywords:
Photovoltaic power forecasting, SOFTS architecture, Variational Mode Decomposition, Crested Porcupine OptimizerAbstract
Accurate photovoltaic (PV) power forecasting is critical for grid stability, yet it remains challenging due to the inherent volatility of meteorological conditions. Existing hybrid models often struggle with manual parameter sensitivity, inadequate local feature extraction, and computationally expensive cross-channel interactions. To address these gaps, this paper proposes a novel multivariate forecasting framework: CPO-VMD-TCN-SOFTS. The Crested Porcupine Optimizer (CPO) is employed to adaptively optimize Variational Mode Decomposition (VMD), effectively mitigating mode mixing. A Temporal Convolutional Network (TCN) extracts deep temporal dependencies, while the SOFTS architecture utilizes a centralized STAR mechanism to achieve cross-channel feature fusion with strict linear complexity. Comprehensive multi-resolution, all-season, and cross-site experiments demonstrate the model's superiority. The proposed architecture significantly enhances predictive accuracy and exhibits robust generalization, maintaining an average R2 above 0.9860 across diverse sites, thereby providing reliable support for smart grid dispatching.
References
[1] Shi, J. and Zhao, Y. (2025) Challenges and Pathways for Tripling Renewable Energy Capacity Globally by 2030. Chinese Journal of Urban and Environmental Studies, 13, 2550004. http://dx.doi.org/10.1142/S2345748125500046
[2] Wang, Z., Huang, C., Zhang, Y. et al. (2024) Tackling Carbon Peak and Carbon Neutrality Challenges: A Method with Long-Range Energy Alternatives Planning System and Logarithmic Mean Divisia Index Integration. Energy, 311, 133465.
[3] Du, W., Peng, S.T., Wu, P.S. et al. (2024) High-Accuracy Photovoltaic Power Prediction under Varying Meteorological Conditions: Enhanced and Improved Beluga Whale Optimization Extreme Learning Machine. Energies, 17, 2309. http://dx.doi.org/10.3390/en17102309
[4] Al-Dahidi, S., Madhiarasan, M., Al-Ghussain, L. et al. (2024) Forecasting Solar Photovoltaic Power Production: A Comprehensive Review and Innovative Data-Driven Modeling Framework. Energies, 17, 4145. http://dx.doi.org/10.3390/en17164145
[5] Wang, H., Lei, Z., Zhang, X., Zhou, B. and Peng, J. (2019) A Review of Deep Learning for Renewable Energy Forecasting. Energy Conversion and Management, 198, 111799. https://doi.org/10.1016/j.enconman.2019.111799
[6] Dragomiretskiy, K. and Zosso, D. (2014) Variational Mode Decomposition. IEEE Transactions on Signal Processing, 62, 531-544. https://doi.org/10.1109/TSP.2013.2288675
[7] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł. and Polosukhin, I. (2017) Attention Is All You Need. Advances in Neural Information Processing Systems, 30, 5998-6008. https://doi.org/10.48550/arXiv.1706.03762
[8] Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H. and Zhang, W. (2021) Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 11106-11115. https://doi.org/10.1609/aaai.v35i12.17325
[9] Wang, Y., Wang, J. and Wei, W. (2020) A Hybrid Forecasting Model Based on CEEMDAN and CNN-LSTM for Short-Term Photovoltaic Power Prediction. Energy Conversion and Management, 205, 112446. https://doi.org/10.1016/j.enconman.2019.112446
[10] Liu, Y., Hu, T., Zhang, H., Wu, H., Wang, J. and Long, M. (2024) iTransformer: Inverted Transformers Are Effective for Time Series Forecasting. International Conference on Learning Representations. https://doi.org/10.48550/arXiv.2310.06625
[11] Lim, B. and Zohren, S. (2021) Time-Series Forecasting with Deep Learning: A Survey. Philosophical Transactions of the Royal Society A, 379, 20200209. https://doi.org/10.1098/rsta.2020.0209
[12] Nie, Y., Nguyen, N.H., Sinthong, P. and Kalagnanam, J. (2023) A Time Series Is Worth 64 Words: Long-Term Forecasting with Transformers. International Conference on Learning Representations. https://doi.org/10.48550/arXiv.2211.14730
[13] Liu, Y., Gu, Y., Long, Y., Zhang, Q., Zhang, Y. and Zhou, X. (2025) Research on Physically Constrained VMD-CNN-BiLSTM Wind Power Prediction. Sustainability, 17, 1058. https://doi.org/10.3390/su17031058
[14] Elizaveta, E., May, D. and Musilek, P. (2020) Forecasting Photovoltaic Power Production Using a Deep Learning Sequence to Sequence Model with Attention. arXiv preprint, arXiv:2008.02775. https://doi.org/10.48550/arXiv.2008.02775
[15] Abdel-Basset, M., Mohamed, R. and Abouhawwash, M. (2024) Crested Porcupine Optimizer: A New Nature-Inspired Metaheuristic. Knowledge-Based Systems, 284, 111257. https://doi.org/10.1016/j.knosys.2023.111257
[16] Putra, H.R.K., Novanto, Y. and Fatyanosa, T.N. (2024) Variational Mode Decomposition and Linear Embeddings Are What You Need for Time Series Forecasting. arXiv preprint, arXiv:2408.16122. https://doi.org/10.48550/arXiv.2408.16122
[17] Lim, B. and Zohren, S. (2021) Time-Series Forecasting with Deep Learning: A Survey. Philosophical Transactions of the Royal Society A, 379, 20200209. https://doi.org/10.1098/rsta.2020.0209
[18] Bai, S., Kolter, J.Z. and Koltun, V. (2018) An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv preprint, arXiv:1803.01271. https://doi.org/10.48550/arXiv.1803.01271
[19] Han, L., Chen, X.Y., Ye, H.J. and Zhan, D.C. (2024) SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion. Advances in Neural Information Processing Systems. https://doi.org/10.48550/arXiv.2404.14197
[20] Luo, X., Zhang, D. and Zhu, X. (2021) Deep Learning Based Forecasting of Photovoltaic Power Generation by Incorporating Domain Knowledge. Energy, 225, 120240. https://doi.org/10.1016/j.energy.2021.120240
[21] Yu, M., Niu, D., Wang, K., Du, R., Yu, X., Sun, L. and Wang, F. (2023) Short-Term Photovoltaic Power Point-Interval Forecasting Based on Double-Layer Decomposition and WOA-BiLSTM-Attention and Considering Weather Classification. Energy, 275, 127348. https://doi.org/10.1016/j.energy.2023.127348
Downloads
Published
Issue
Section
License
Copyright (c) 2026 by author(s) and Erytis Publishing Limited.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
