Author(s): Duan Chen; Xue Luo; Shiji Qian
Linked Author(s): Duan Chen
Keywords: Computational efficiency; Evolutionary algorithms; Modelling strategy; NSGA-II; Reservoir operation optimization
Abstract: Evolutionary Algorithms (EAs) are increasingly applied in reservoir operation optimization for their capability to explore global optima under complex, nonlinear, and constrained conditions. However, their performance strongly depends on algorithmic design and parameterization. This study systematically examines key factors affecting the effectiveness of EA-based reservoir optimization and proposes strategies to enhance robustness. Using the Non-dominated Sorting Genetic Algorithm II (NSGA-II) as a representative framework, numerical experiments were conducted on a complicated real-world reservoir operation under uncertainty to evaluate different configurations. Results informed the development of a comprehensive modeling strategy that integrates expert-informed initialization and adaptive constraint-handling to improve convergence and solution quality.
Year: 2026