Bat algorithm based on simulated annealing and Gaussian perturbations

• Published in: Neural computing & applications Vol. 25; no. 2; pp. 459 - 468
• Main Authors: He, Xing-shi, Ding, Wen-Jing, Yang, Xin-She
• Format: Journal Article
• Language: English
• Published: London Springer London 01.08.2014; Springer
• Subjects: Algorithmics. Computability. Computer arithmetics; Applied sciences; Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Computer science; control theory; systems; Data Mining and Knowledge Discovery; Exact sciences and technology; Image Processing and Computer Vision; Original Article; Probability and Statistics in Computer Science; Theoretical computing; Swarm intelligence; Bat algorithm; Algorithm; Optimization; Simulated annealing; Capability index; Global optimum; Particle swarm optimization; Stochastic programming; Vertebrata; Mammalia; Gaussian process; Efficiency; Heuristic method; Convergence rate; Artificial intelligence; Chiroptera; Numerical convergence
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-013-1518-4

Bat algorithm (BA) is a new stochastic optimization technique for global optimization. In the paper, we introduce both simulated annealing and Gaussian perturbations into the standard bat algorithm so as to enhance its search performance. As a result, we propose a simulated annealing Gaussian bat algorithm (SAGBA) for global optimization. Our proposed algorithm not only inherits the simplicity and efficiency of the standard BA with a capability of searching for global optimality, but also speeds up the global convergence rate. We have used BA, simulated annealing particle swarm optimization and SAGBA to carry out numerical experiments for 20 test benchmarks. Our simulation results show that the proposed SAGBA can indeed improve the global convergence. In addition, SAGBA is superior to the other two algorithms in terms of convergence and accuracy.