EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A CEEMDAN-CNN-BiLSTM-SDQN Framework for Photovoltaic Power Forecasting: Integrating Multi-Scale Decomposition with Adaptive Reinforcement Learning Compensation

Weijie Jia, Keying Liu, Jinghui Xu, Yapeng Zhu

Energies · 27.03.2026 · 19 (7) · 1649

DOI: 10.3390/en19071649 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 27.03.2026. Verfasst von Weijie Jia und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Water Conservancy Science and Technology Project of Shaanxi Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate photovoltaic (PV) power forecasting is crucial for grid stability and the integration of renewable energy. To address the multiscale, nonlinear characteristics of PV power series and the limitations of traditional methods in dynamic error compensation, a novel hybrid forecasting framework is proposed, integrating Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM), and a Simplified Deep Q-Network (SDQN). The framework first decomposes the power series into subcomponents across different frequency bands via CEEMDAN. Subsequently, dedicated CNN-BiLSTM sub-models are employed in parallel to extract spatiotemporal features from each component. Finally, an SDQN agent is introduced to perform real-time error compensation. Validation based on operational data from a PV plant in Ningxia, China, demonstrates that the proposed framework achieves RMSE, MAE, MAPE, and R2 values of 0.4463, 0.1256, 1.2814%, and 92.58%, respectively, significantly outperforming benchmark models. Specifically, the CEEMDAN decomposition effectively mitigates mode mixing. The CNN-BiLSTM as the base predictor reduces RMSE by 25.04–65.68% compared to mainstream models. Furthermore, the SDQN compensation mechanism delivers an additional 24.5% reduction in prediction error. The proposed approach thus constitutes a high-precision, adaptive solution for PV power forecasting.

Förderung

  • National Natural Science Foundation of China
  • Water Conservancy Science and Technology Project of Shaanxi Province

Zitieren

APA

Jia, W., Liu, K., Xu, J., & Zhu, Y. (2026). A CEEMDAN-CNN-BiLSTM-SDQN Framework for Photovoltaic Power Forecasting: Integrating Multi-Scale Decomposition with Adaptive Reinforcement Learning Compensation. Energies, 19(7), 1649. https://doi.org/10.3390/en19071649

Vancouver

Jia W, Liu K, Xu J, Zhu Y. A CEEMDAN-CNN-BiLSTM-SDQN Framework for Photovoltaic Power Forecasting: Integrating Multi-Scale Decomposition with Adaptive Reinforcement Learning Compensation. Energies. 2026;19(7):1649. doi:10.3390/en19071649

BibTeX
@article{Jia2026,
  author = {Jia, Weijie and Liu, Keying and Xu, Jinghui and Zhu, Yapeng},
  title = {A CEEMDAN-CNN-BiLSTM-SDQN Framework for Photovoltaic Power Forecasting: Integrating Multi-Scale Decomposition with Adaptive Reinforcement Learning Compensation},
  journal = {Energies},
  year = {2026},
  volume = {19},
  number = {7},
  pages = {1649},
  doi = {10.3390/en19071649}
}
Kostenlos starten →