Efficient design of a hybrid power system incorporating resource variability

The optimal design of small-scale energy systems is a critical step in rural electrification projects, offering valuable insights for integrating renewable energy sources on a broader scale. This paper analyzes the sizing of isolated energy systems using the Genghis Khan Shark Optimizer, taking into account the variability of wind and solar resources across diverse scenario groups to enhance computational efficiency. Specifically, three scenario sets were utilized: training, validation, and testing. The training set was applied to assess the objective function across all optimization agents, while the validation set was used to independently evaluate the performance of the agent with the highest fitness score. Finally, the testing set was employed to verify the performance of the accepted solution. By selecting a limited number of scenarios for the training set and a moderate number for the validation and testing sets, we reduced the computational load associated with analyzing the entire population, allowing for greater focus on the most promising agent identified at each iteration. Results from a case study revealed that the proposed method identified an energy system configuration 8.05 % better than the configuration obtained using a genetic algorithm.