Hybrid algorithm–driven optimal configuration of energy storage systems based on renewable generation forecasting
Journal of Renewable and Sustainable Energy · 01.11.2026 · 18 (6)
DOI: 10.1063/5.0339087 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Renewable and Sustainable Energy, online erschienen am 19.11.2026. Verfasst von Chunxue Wen und 6 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: North China University of Technology.
Abstract (Originalsprache)
The large-scale integration of renewable energy introduces volatility that poses challenges to distribution network reliability. Properly configured energy storage systems (ESS) can mitigate these fluctuations; however, forecasting and storage planning are often treated as separate stages, which limits the traceability of renewable-generation inputs in the planning process. To address these issues, this paper proposes an integrated forecasting-optimization framework for ESS planning. First, a hybrid algorithm combining the gray wolf optimizer (GWO) and adaptive particle swarm optimization (APSO), termed GWO-APSO, is developed to optimize long short-term memory network parameters, creating a high-precision prediction model. Second, using these forecasting results, a multi-objective model is formulated to minimize node voltage vulnerability, network losses, and total ESS capacity. This model is efficiently solved using a hybrid algorithm combining the non-dominated sorting genetic algorithm II (NSGA-II) and APSO, termed NSGA-II-APSO. Ultimately, the entropy-weighted technique for order preference by similarity to ideal solution (TOPSIS) method selects the optimal configuration from the Pareto front. Simulations using real-world data from Zhangjiakou, China, demonstrate that the proposed model reduces the root mean square error and mean absolute error by 26.2% and 29.35%, respectively, and increases the coefficient of determination (R2) by 15.58% compared to standard unoptimized models. Furthermore, validation on the IEEE 33-bus system confirms that the proposed strategy reduces network losses by 9.03%, achieving superior fluctuation suppression with a reduced ESS footprint compared with a random configuration.
Förderung
- North China University of Technology
Zitieren
APA
Wen, C., Zhang, L., Zhou, J., Wang, P., Wen, C., Bakhodir, R., & Mukhriddin, T. (2026). Hybrid algorithm–driven optimal configuration of energy storage systems based on renewable generation forecasting. Journal of Renewable and Sustainable Energy, 18(6). https://doi.org/10.1063/5.0339087
Vancouver
Wen C, Zhang L, Zhou J, Wang P, Wen C, Bakhodir R, et al. Hybrid algorithm–driven optimal configuration of energy storage systems based on renewable generation forecasting. Journal of Renewable and Sustainable Energy. 2026;18(6). doi:10.1063/5.0339087
BibTeX
@article{Wen2026,
author = {Wen, Chunxue and Zhang, Longling and Zhou, Jinghua and Wang, Peng and Wen, Caifeng and Bakhodir, Ramazonov and Mukhriddin, Tuyqulov},
title = {Hybrid algorithm–driven optimal configuration of energy storage systems based on renewable generation forecasting},
journal = {Journal of Renewable and Sustainable Energy},
year = {2026},
volume = {18},
number = {6},
doi = {10.1063/5.0339087}
}
EUVIMED