f-MOPSO/Div: an improved extreme-point-based multi-objective PSO algorithm applied to a socio-economic-environmental...

Area of Science:

• Computational Intelligence
• Optimization Algorithms
• Environmental Management

Background:

• Particle swarm optimization (PSO) is a metaheuristic optimization algorithm inspired by social-behavior patterns.
• Multi-objective optimization problems involve optimizing several conflicting objectives simultaneously.
• Existing fuzzy multi-objective particle swarm optimization (f-MOPSO) algorithms can be improved for better performance.

Purpose of the Study:

• To propose a novel Diversity-enhanced fuzzy multi-objective particle swarm optimization (f-MOPSO/Div) algorithm.
• To enhance the guidance mechanism for particles in the search space by evaluating particle "extremity."
• To address shortcomings of previous f-MOPSO versions, including local optima entrapment and pre-optimization requirements.

Main Methods:

• The f-MOPSO/Div algorithm incorporates three key improvements: diversity-based global best selection, dynamic probability-based mutation to avoid local optima, and removal of the pre-optimization process.
• Particle guidance is enhanced by evaluating both Pareto dominance and a new
• extremity
• characteristic in the objective space.
• The algorithm's performance was validated against other multi-objective algorithms on 14 standard test problem suites.

Main Results:

• Comparative analysis demonstrated the superior performance of f-MOPSO/Div over existing popular multi-objective algorithms.
• Application to an optimal conjunctive water use management problem in a semi-arid region showed significant reduction in groundwater level drawdown.
• The algorithm successfully maximized aquifer sustainability (environmental goal) while maintaining desirable crop yields (socio-economic goal).

Conclusions:

• The proposed f-MOPSO/Div algorithm offers significant improvements in multi-objective optimization.
• It effectively balances environmental and socio-economic objectives in complex water resource management scenarios.
• f-MOPSO/Div proves superior for solving large-scale, real-world optimization problems, particularly in sustainable resource management.