Research of Improved Artificial Fish Swarm Algorithm Based on Simulated Annealing Algorithm

This paper proposed an improved artificial fish-swarm algorithm,which was aimed at some defects of AFSA,such as low optimization precision and long running time.The new algorithm used the metropolis criterion of the simulated annealing algorithm for reference in order to improve the artificial fish feeding behavior.This algorithm not only can find the global optimal result,but also can make the result more accurate.The new algorithm is as simple as AFSA in implementing,and can greatly improve the ability of seeking global excellent result,and the convergence property and the accuracy.The feasibility and effectiveness of the new approach was verified through testing by function and practical problem.The experimental results show that the proposed algorithm is significantly superior to original AFSA.