A novel Parrot Optimizer for robust and scalable PEMFC parameter optimization.

Area of Science:

• Sustainable Energy Technologies
• Computational Intelligence
• Optimization Algorithms

Background:

• Proton exchange membrane fuel cells (PEMFCs) are crucial for sustainable energy but face optimization challenges due to complex nonlinear relationships in design variables.
• Existing optimization methods like PSO, DE, and WOA suffer from slow convergence, sensitivity to initial parameters, and suboptimal solutions.

Purpose of the Study:

• To introduce the Parrot Optimizer (PO), a novel metaheuristic algorithm inspired by parrot behavior, for optimizing PEMFC design variables.
• To evaluate PO's performance against nine advanced algorithms in minimizing the Sum of Squared Error (SSE) for PEMFC stack voltage.

Main Methods:

• The Parrot Optimizer (PO) algorithm was developed, mimicking adaptive behaviors of Pyrrhura Molinae parrots.
• PO was applied to optimize six design variables across six different PEMFC stacks (BCS 500 W, Nedstack 600 W PS6, SR-12 W, Horizon H-12, Ballard Mark V, STD 250 W).
• Comparative analysis involved evaluating PO against PSO, DE, WOA, ROA, FHO, AOA, SCA, MVO, and BA using the SSE objective function.

Main Results:

• PO consistently achieved the lowest Mean SSE values across all tested PEMFC stacks, demonstrating superior accuracy.
• PO exhibited the fastest runtime (RT) among all algorithms, significantly improving computational efficiency.
• Simulation results for I-V and V-P characteristics closely matched experimental data under various conditions, validating PO's practical applicability.

Conclusions:

• The Parrot Optimizer (PO) is a highly effective and efficient algorithm for optimizing proton exchange membrane fuel cell design variables.
• PO offers improved accuracy and speed compared to existing metaheuristic algorithms, enhancing PEMFC performance and reliability.
• PO shows significant potential for real-world applications in improving PEMFC design and control systems.