.png){kind=icon}
.png){kind=icon}
Return
Enhanced Power Plant Generation Management through an Improved Grasshopper Optimization Algorithm
.png){kind=icon}
PRE
AI
DOI：10.1061/JHYEFF.HEENG-6411.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study introduces an improved algorithm called modified Grasshopper Optimization Algorithm [Modified-GOA (M-GOA)], designed to prevent the Grasshopper Optimization Algorithm (GOA) from getting trapped in local optima. The findings demonstrate that even small modifications can significantly enhance an optimization algorithm's performance. To evaluate M-GOA's effectiveness, it was applied to the optimization problem of multireservoir hydropower systems under baseline conditions and two future periods, capturing a range of climate change scenarios, namely RCP2.6, RCP4.5, and RCP8.5. The results indicate that M-GOA outperforms both GOA and particle swarm optimization (PSO) in achieving optimal objective function values, with a significantly lower standard deviation across five operating modes. In the Seimareh single-reservoir system, M-GOA achieves 93% of the total energy production capacity, compared to 70% and 91% for GOA and PSO, respectively. Additionally, M-GOA exhibits strong performance in multireservoir systems, consistently yielding low objective function values under various conditions. The algorithm demonstrates high adaptability to diverse climatic scenarios and long-term resource planning, highlighting its flexibility and efficiency in complex optimization tasks.
Keywords:
Metaheuristic optimization
Climate change
Particle Swarm Optimization (PSO)
Modified-Grasshopper Optimization Algorithm (M-GOA)
Hydropower
Artificial neural networks
Journal
J
IF:
1.9
Papers:
60
Citations:
5.0K