Journal of shanghai Jiaotong University (Science) ›› 2015, Vol. 20 ›› Issue (1): 38-43.doi: 10.1007/s12204-015-1585-z

Previous Articles     Next Articles

Simplified Group Search Optimizer Algorithm for Large Scale Global Optimization

Simplified Group Search Optimizer Algorithm for Large Scale Global Optimization

ZHANG Wen-fen (张雯雰)   

  1. (Department of Computer Science, Xiangnan University, Chenzhou 423000, Hunan, China)
  2. (Department of Computer Science, Xiangnan University, Chenzhou 423000, Hunan, China)
  • Online:2015-02-28 Published:2015-03-10
  • Contact: ZHANG Wen-fen (张雯雰) E-mail:yydzhwf@163.com

Abstract: A simplified group search optimizer algorithm denoted as “SGSO” for large scale global optimization is presented in this paper to obtain a simple algorithm with superior performance on high-dimensional problems. The SGSO adopts an improved sharing strategy which shares information of not only the best member but also the other good members, and uses a simpler search method instead of searching by the head angle. Furthermore, the SGSO increases the percentage of scroungers to accelerate convergence speed. Compared with genetic algorithm (GA), particle swarm optimizer (PSO) and group search optimizer (GSO), SGSO is tested on seven benchmark functions with dimensions 30, 100, 500 and 1 000. It can be concluded that the SGSO has a remarkably superior performance to GA, PSO and GSO for large scale global optimization.

Key words: evolutionary algorithms| swarm intelli-gence| group search optimizer (PSO)| large scale global optimization| function optimization

摘要: A simplified group search optimizer algorithm denoted as “SGSO” for large scale global optimization is presented in this paper to obtain a simple algorithm with superior performance on high-dimensional problems. The SGSO adopts an improved sharing strategy which shares information of not only the best member but also the other good members, and uses a simpler search method instead of searching by the head angle. Furthermore, the SGSO increases the percentage of scroungers to accelerate convergence speed. Compared with genetic algorithm (GA), particle swarm optimizer (PSO) and group search optimizer (GSO), SGSO is tested on seven benchmark functions with dimensions 30, 100, 500 and 1 000. It can be concluded that the SGSO has a remarkably superior performance to GA, PSO and GSO for large scale global optimization.

关键词: evolutionary algorithms| swarm intelli-gence| group search optimizer (PSO)| large scale global optimization| function optimization

CLC Number: