Beaver behavior optimizer: A novel metaheuristic algorithm for solar PV parameter identification and engineering...

Area of Science:

• Computational Intelligence
• Swarm Intelligence Algorithms
• Bio-inspired Computing

Background:

• Numerical optimization is crucial for solar photovoltaic (PV) systems and engineering, but traditional methods face challenges with complex, high-dimensional problems.
• Existing optimization techniques struggle to efficiently find solutions in non-linear landscapes, hindering advancements in fields like solar energy.

Purpose of the Study:

• Introduce the novel Beaver Behavior Optimizer (BBO), a swarm intelligence algorithm inspired by beaver dam-building behaviors.
• Validate the BBO's effectiveness on benchmark test functions and real-world engineering problems, with a focus on solar PV parameter optimization.

Main Methods:

• Modeled BBO based on beaver behaviors, incorporating distinct exploration and exploitation phases.
• Tested BBO on CEC 2017 and CEC 2022 benchmark functions across various dimensions (10 to 100).
• Applied BBO to three solar PV parameter identification problems and four engineering design problems, comparing against 11 other algorithms.

Main Results:

• BBO demonstrated superior performance on all benchmark functions and ranked first in solar PV and engineering optimization tasks.
• The algorithm outperformed state-of-the-art methods in most scenarios, showing robust convergence and minimal result variance.
• Statistical tests confirmed the significance of BBO's performance improvements.

Conclusions:

• The Beaver Behavior Optimizer (BBO) is validated as a powerful tool for complex optimization, especially in solar PV and engineering design.
• BBO's bio-inspired approach effectively balances exploration and exploitation, offering a competitive advantage.
• The study highlights BBO's potential for efficient and accurate solutions in demanding optimization challenges.