Department of Hydrology and Water Resources, Faculty of Water & Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.
Ph. D. Graduate of Water Resources Engineering, Department of Hydrology and Water Resources, Faculty of Water & Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.
Sci Rep. 2022 May 11;12(1):7739. doi: 10.1038/s41598-022-11915-0.
The use of evolutionary algorithms (EAs) for solving complex engineering problems has been very promising, so the application of EAs for optimal operation of hydropower reservoirs can be of great help. Accordingly, this study investigates the capability of 14 recently-introduced robust EAs in optimization of energy generation from Karun-4 hydropower reservoir. The best algorithm is the one that produces the largest objective function (energy generation) and has the minimum standard deviation (SD), the minimum coefficient of variations (CV), and the shortest time of CPU usage. It was found that the best solution was achieved by the moth swarm algorithm (MSA), with the optimized energy generation of 19,311,535 MW which was 65.088% more than the actual energy generation (11,697,757). The values of objective function, SD and CV for MSA were 0.147, 0.0029 and 0.0192, respectively. The next ranks were devoted to search group algorithm (SGA), water cycle algorithm (WCA), symbiotic organism search algorithm (SOS), and coyote optimization algorithm (COA), respectively, which have increased the energy generation by more than 65%. Some of the utilized EAs, including grasshopper optimization algorithm (GOA), dragonfly algorithm (DA), antlion optimization algorithm (ALO), and whale optimization algorithm (WOA), failed to produce reasonable results. The overall results indicate the promising capability of some EAs for optimal operation of hydropower reservoirs.
进化算法（EAs）在解决复杂工程问题方面非常有前景，因此将 EAs 应用于水电站的优化运行可以提供很大的帮助。因此，本研究调查了 14 种最近引入的强大进化算法在优化 Karun-4 水电站发电方面的能力。最佳算法是产生最大目标函数（发电量）和最小标准差（SD）、最小变异系数（CV）以及最短 CPU 使用时间的算法。结果发现， moth swarm algorithm (MSA) 可以达到最佳的解决方案，其优化后的发电量为 19,311,535 MW，比实际发电量（11,697,757 MW）多 65.088%。MSA 的目标函数、SD 和 CV 值分别为 0.147、0.0029 和 0.0192。其次是 search group algorithm (SGA)、water cycle algorithm (WCA)、symbiotic organism search algorithm (SOS) 和 coyote optimization algorithm (COA)，它们的发电量都增加了 65%以上。一些使用的 EAs，包括 grasshopper optimization algorithm (GOA)、dragonfly algorithm (DA)、antlion optimization algorithm (ALO) 和 whale optimization algorithm (WOA)，未能产生合理的结果。总的来说，结果表明一些 EAs 具有优化水电站运行的巨大潜力。
