An Optimization Framework of Multiobjective Artificial Bee Colony Algorithm Based on the MOEA Framework

Area of Science:

• Computational Intelligence
• Optimization Algorithms
• Artificial Intelligence

Background:

• The artificial bee colony (ABC) algorithm is a popular optimization metaheuristic.
• Existing multiobjective artificial bee colony (MOABC) algorithms lack integration into common optimization frameworks.
• This limits understanding, reuse, implementation, and comparison of MOABC algorithms.

Purpose of the Study:

• To present a unified, flexible, and user-friendly framework for MOABC algorithms.
• To integrate a specific MOABC algorithm (RMOABC) into the multiobjective evolution algorithms (MOEA) framework.
• To facilitate the development, experimentation, and study of metaheuristics for multiobjective optimization.

Main Methods:

• Developed a unified framework combining RMOABC with the MOEA framework.
• Tested the framework on the Walking Fish Group test suite.
• Applied the framework to a many-objective water resource planning problem for verification.

Main Results:

• The framework effectively and flexibly handles practical multiobjective optimization problems.
• It provides comprehensive and reliable parameter sets for optimization.
• It enables reference, comparison, and analysis tasks among multiple optimization algorithms.

Conclusions:

• The presented framework enhances the usability and applicability of MOABC algorithms.
• It serves as a valuable tool for research and practical applications in multiobjective optimization.
• The framework supports effective analysis and comparison of various optimization algorithms.