Short-term photovoltaic power prediction based on dual decomposition with TCN-Informer-xLSTM

Guancheng Jin; He Jiang; Mofan Wei; Rui Guo

doi:10.4108/ew.10415

Authors

Guancheng Jin Shenyang Institute of Engineering
He Jiang Shenyang Institute of Engineering
Mofan Wei Shenyang Institute of Engineering
Rui Guo Shenyang Institute of Engineering

DOI:

https://doi.org/10.4108/ew.10415

Keywords:

Photovoltaic Prediction, Dual Decomposition, Deep Learning

Abstract

As renewable energy generation is increasingly integrated into power grids worldwide, the random nature of renewable energy output poses significant challenges to the stability of power systems. Therefore, it is essential to accurately predict the output of renewable energy sources. In this paper, a dual decomposition algorithm based on variational mode decomposition (VMD) and improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is proposed to decompose the original photovoltaic power sequence and combine the entropy values of the subsequences to obtain the predicted sequences for the high frequency and low frequency components. Then, different prediction models are used for the high-frequency and low-frequency sequences to predict the photovoltaic outputs, where the Temporal Convolutional Networks (TCN)-Informer model is used for the high-frequency component and the xLSTM model is used for the low-frequency component, and finally, the RIME algorithm is applied to find the optimization of the hyperparameters. The results of simulation analysis show that the quadratic decomposition method proposed in this paper significantly improves the prediction accuracy of photovoltaic sequences and reduces the computational complexity

Downloads

Download data is not yet available.

References

[1] Qazi, A.: A Systematic Review of Renewable Energy Sources. Technologies, and Public Opinions (7), 63837-638512 (2019).

[2] Rasoul, S.: Energy’s international history and future. Sci-ence 388, 711-711 (2025).

[3] Salman, D., Direkoglu, C., Kusaf, M. et al.: Hybrid deep learning models for time series forecasting of solar power. Neural Comput & Applic 36, 9095–9112 (2024).

[4] Shi, S., Liu, B., Ren, L. et al.: Short time solar power fore-casting using P-ELM approach. Sci Rep 14, 30999 (2024).

[5] Singh, P., Singh, N.K. & Singh, A.K.: Wavelet Transform Based Gated-Recurrent Unit Deep Learning Approach for Power Output of Solar Photovoltaic System Forecasting. SN COMPUT. SCI 6, 243 (2025).

[6] Goya, A., Bhattacharya, K.: Design of Multi-Settlement Electricity Markets Considering Demand Response and Battery Energy Storage Systems Participation. Policy and Regulation 2(2), 226-239 (2024).

[7] Bin, H.: A study on the prediction of photovoltaic day-ahead output based on FCM-WS-BP. Control Engineering. 30(12), 2254-2260 (2023).

[8] Bai, M., Wang, R., Lin, C. et al.: Deep multivariable spatial attention CNN-based spatial grid NWP error correction for accurate one-day-ahead photovoltaic power forecast. Earth Sci Inform 18, 427 (2025).

[9] Fu, Y., Chai H., Zhen Z., et al.: Sky image prediction mod-el based on convolutional auto-encoder for minutely solar PV power forecasting. IEEE Transactions on Industry Ap-plications 57(4), 3272-3281 (2021).

[10] R. Asghar, M., Quercio, L., Sabino, A.: A Novel Dual-Stream Attention-Based Hybrid Network for Solar Power Forecasting. IEEE Access 13, 59596-59609 (2025).

[11] Rahimi, N., Park, S., Choi, W. et al.: A Comprehensive Review on Ensemble Solar Power Forecasting Algorithms. Elec. Eng. Technol 18, 719–733 (2023).

[12] Souhe, F.G.Y., Mbey, C.F., Kakeu, V.J.F. et al.: Optimized forecasting of photovoltaic power generation using hybrid deep learning model based on GRU and SVM. Electric En-ergy 106, 7879–7898 (2024).

[13] Horat, N., Klerings, S. & Lerch, S.: Improving Model Chain Approaches for Probabilistic Solar Energy Forecast-ing through Post-processing and Machine Learning. Adv. Atmos. Sci 42, 297–312 (2025).

[14] Zhang, X.: Prediction Interval Estimation and Determinis-tic Forecasting Model Using Ground-Based Sky Image. IEEE Transactions on Industry Applications 59(2), 2210-2224 (2023).

[15] Xu, B., Huang, Y., et al.: Day-ahead probabilistic forecast-ing of photovoltaic power based on vine copulaquantile re-gression. Power system technology, 4426-4435 (2022).

[16] C. Yuanjun.: Short-Term Prediction of Photovoltaic Power Based on TCN-LSTM-Attention Model and Kmeans++. 10th International Conference on Power Electronics Sys-tems and Applications 2024, PESA, pp. 1-5, (2024).

[17] Ge, W., Wang, X.: PSO–LSTM–Markov Coupled Photovol-taic Power Prediction Based on Sunny, Cloudy and Rainy Weather. Electric Energy Technology 20, 935–945 (2025).

[18] Zhu, R., Li, T. & Tang, B.: Research on short-term photo-voltaic power generation forecasting model based on multi-strategy improved squirrel search algorithm and support vector machine. Sci Rep 14, 14348 (2024).

[19] Zhang, J., Xu, R., et al.: Short-term photovoltaic power prediction based on similar day clustering and PCC-VMD-SSA-KELM model. Solar Energy 45(2), 460-468 (2023).

[20] Qi, L., Xiaoying, R., Zhang, F., Lu, G., Hao, B.: A novel ultra-short-term wind power forecasting method based on TCN and Informer models. Computers and Electrical Engi-neering 7(A1), 0045-7906 (2024).

[21] Deng, T., Liu, J., Wang, B., et al.: A photovoltaic power prediction method based on multimodal fusion of ground-based cloud maps and meteorological factors. Chinese Journal of Electrical Engineering, 1-14 (2023).