Tuna Swarm Optimization: A Novel Swarm-Based Metaheuristic Algorithm for Global Optimization

Area of Science:

• Computational Intelligence
• Swarm Intelligence
• Optimization Algorithms

Background:

• Metaheuristic algorithms are crucial for solving complex optimization problems.
• Existing algorithms often lack efficiency in exploring and exploiting search spaces.
• Understanding natural swarm behaviors can inspire novel computational approaches.

Purpose of the Study:

• To propose a novel swarm-based metaheuristic algorithm named Tuna Swarm Optimization (TSO).
• To leverage the cooperative foraging strategies of tuna swarms for optimization.
• To evaluate the efficacy of TSO against established algorithms.

Main Methods:

• Developed TSO algorithm inspired by tuna's spiral and parabolic foraging behaviors.
• Tested TSO on standard benchmark functions and real-world engineering problems.
• Performed sensitivity, scalability, robustness, and convergence analyses using statistical tests (Wilcoxon, Friedman).

Main Results:

• TSO exhibited competitive or superior performance compared to other metaheuristic algorithms.
• Statistical analyses confirmed the significant advantages of TSO.
• The algorithm demonstrated robustness and scalability across diverse problem sets.

Conclusions:

• TSO is an effective and efficient metaheuristic algorithm for optimization tasks.
• The foraging behaviors of tuna swarms provide a strong foundation for novel optimization strategies.
• TSO offers a promising alternative for complex problem-solving in engineering and computational intelligence.