Sardine Fish Optimization Algorithm

Swarm intelligence optimization algorithms, by simulating the collective behavior of organisms in nature, exhibit excellent global search and local exploitation capabilities in complex optimization problems. This paper proposes an optimization algorithm based on the swarm behavior of anchovies—the Sardine Fish Optimization Algorithm (SFOA). This algorithm achieves efficient solutions to complex optimization problems by simulating the predation behavior, escape behavior, group cooperation mechanisms, and historical memory utilization of anchovies. The algorithm maintains a balance between global search and local exploitation, while introducing adaptive step size and multi-scale random perturbation mechanisms to improve convergence accuracy and search efficiency. Theoretical analysis shows that SFOA possesses strong convergence and swarm intelligence characteristics, effectively avoiding getting trapped in local optima in high-dimensional complex problems. SFOA can be widely applied in continuous optimization, combinatorial optimization, multi-objective optimization, and engineering optimization.