EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Optimal scheduling of renewable power distribution systems combining deep learning and particle swarm optimization

Qiuyong Yang, Bin Chen, Yanlu Huang, Xudong Hu

EAI Endorsed Transactions on Energy Web · 01.06.2026 · 13

DOI: 10.4108/ew.12491 ↗

Kurz gefasst

Fachartikel in der Zeitschrift EAI Endorsed Transactions on Energy Web, online erschienen am 01.06.2026. Verfasst von Qiuyong Yang und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

To address the optimal scheduling problem of renewable power distribution systems, this paper proposes an integrated framework combining deep learning-based load forecasting with particle swarm optimization.

Objectives

The first objective is accurate multivariate load forecasting (cooling, heating, and electric loads). The second objective is minimizing network loss by optimally scheduling electric vehicle (EV) charging locations and times.

Methods

For load forecasting, a hybrid RCNN-SVR model is constructed. The convolutional neural network (CNN) acts as a feature extractor to implicitly capture representative patterns from input data, while support vector regression (SVR) produces the final load predictions. Missing and outlier data are pre-processed. For optimal scheduling, a dual-layer particle swarm optimization (PSO) algorithm is developed. The inner layer enforces system constraints, and the outer layer minimizes network loss. EV charging load is simulated using the Monte Carlo method, and two cases (variable vs. fixed charging addresses) are optimized.

Results

Experimental results demonstrate that the proposed RCNN-SVR model achieves high prediction accuracy, with mean absolute percentage error as low as 2.41% for winter electric loads. The dual-layer PSO reduces peak system load from 11.2×10³ kW to 10.5×10³ kW and decreases network loss by 2.13%, effectively smoothing grid fluctuations.

Conclusion

The RCNN-SVR model significantly improves multivariate load prediction accuracy compared to separate forecasting methods. The dual-layer PSO successfully converts disorderly EV charging into orderly scheduling, reducing peak load and network loss. Together, they provide a practical solution for renewable distribution system scheduling.

Zitieren

APA

Yang, Q., Chen, B., Huang, Y., & Hu, X. (2026). Optimal scheduling of renewable power distribution systems combining deep learning and particle swarm optimization. EAI Endorsed Transactions on Energy Web, 13. https://doi.org/10.4108/ew.12491

Vancouver

Yang Q, Chen B, Huang Y, Hu X. Optimal scheduling of renewable power distribution systems combining deep learning and particle swarm optimization. EAI Endorsed Transactions on Energy Web. 2026;13. doi:10.4108/ew.12491

BibTeX
@article{Yang2026,
  author = {Yang, Qiuyong and Chen, Bin and Huang, Yanlu and Hu, Xudong},
  title = {Optimal scheduling of renewable power distribution systems combining deep learning and particle swarm optimization},
  journal = {EAI Endorsed Transactions on Energy Web},
  year = {2026},
  volume = {13},
  doi = {10.4108/ew.12491}
}
Kostenlos starten →