EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Accelerating Multi-Objective Evolutionary Algorithms for Cascade Hydropower Scheduling via a Physics-Embedded TCN

Yaxin Liu, Junhuai Liu, Zhiyun Guo, Jia Lu, Qi Deng

Water · 18.05.2026 · 18 (10) · 1220

DOI: 10.3390/w18101220 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 18.05.2026. Verfasst von Yaxin Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hubei Technology Innovation Center for Smart Hydropower.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cascade hydropower scheduling is a high-dimensional, tightly constrained multi-objective optimization problem in which classical genetic and evolutionary algorithms struggle to find feasible solutions. Under random initialization, algorithms such as the Non-dominated Sorting Genetic Algorithm II (NSGA-II), the Non-dominated Sorting Genetic Algorithm III (NSGA-III), and the Constrained Two-Archive Evolutionary Algorithm (C-TAEA) rarely produce any feasible solution when the feasible region occupies a vanishingly small fraction of the search space. This paper presents a three-phase framework that combines physics-guided deep learning with evolutionary computation to accelerate both NSGA-II and NSGA-III. The method trains a Physics-Embedded Temporal Convolutional Network (PeTCN) as a differentiable surrogate model that explicitly incorporates physical constraints, applies gradient-based inverse optimization to obtain a feasible or near-feasible solution of high quality, and warm-starts NSGA-II or NSGA-III with that solution for efficient Pareto front exploration. Experiments on a real-world six-station cascade system show that, under a 1500 s fixed-time budget across 20 independent runs, Boosted NSGA-II and Boosted NSGA-III both find feasible solutions in all runs. Boosted NSGA-II and Boosted NSGA-III both reach the first feasible solution within roughly 50–60 generations of Phase 3 search on average, whereas standard NSGA-II produces no feasible run within the same budget and standard NSGA-III requires thousands of generations among its successful runs. The mean final hypervolume reaches 43.84×106 for Boosted NSGA-II and 46.52×106 for Boosted NSGA-III, and both boosted algorithms reach a target hypervolume of 35.00×106 in all 10 target-hypervolume runs. These results demonstrate that coupling physics-embedded surrogates with gradient-based initialization is an effective strategy for constrained multi-objective problems in which feasible solutions are extremely sparse.

Förderung

  • Hubei Technology Innovation Center for Smart Hydropower

Zitieren

APA

Liu, Y., Liu, J., Guo, Z., Lu, J., & Deng, Q. (2026). Accelerating Multi-Objective Evolutionary Algorithms for Cascade Hydropower Scheduling via a Physics-Embedded TCN. Water, 18(10), 1220. https://doi.org/10.3390/w18101220

Vancouver

Liu Y, Liu J, Guo Z, Lu J, Deng Q. Accelerating Multi-Objective Evolutionary Algorithms for Cascade Hydropower Scheduling via a Physics-Embedded TCN. Water. 2026;18(10):1220. doi:10.3390/w18101220

BibTeX
@article{Liu2026,
  author = {Liu, Yaxin and Liu, Junhuai and Guo, Zhiyun and Lu, Jia and Deng, Qi},
  title = {Accelerating Multi-Objective Evolutionary Algorithms for Cascade Hydropower Scheduling via a Physics-Embedded TCN},
  journal = {Water},
  year = {2026},
  volume = {18},
  number = {10},
  pages = {1220},
  doi = {10.3390/w18101220}
}
Kostenlos starten →