Comprehensive learning gravitational search algorithm for global optimization of multimodal functions

• Published in: Neural computing & applications 2020-06, Vol.32 (11), p.7347-7382
• Main Authors: Bala, Indu, Yadav, Anupam
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Global optimization; Gravitation; Image Processing and Computer Vision; Machine learning; Optimization; Original Article; Probability and Statistics in Computer Science; Search algorithms
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-019-04250-5

In this paper, a new comprehensive learning gravitational search algorithm (CLGSA) is proposed to enhance the performance of basic GSA. The proposed algorithm is a new kind of intelligent optimization algorithm which has better ability to choose good elements. An intensive comprehensive learning methodology is proposed to enrich the optimization ability of the GSA. The efficiency of the proposed algorithm was evaluated by 28 benchmark functions which have been proposed in IEEE-CEC 2013 sessions. The results are compared with eight state-of-the-art algorithms IPOP, BIPOP, NIPOP, NBIPOP, DE/rand, SPSRDEMMS, SPSO-2011 and GSA. A variety of ways are considered to examine the ability of the proposed technique in terms of convergence ability, success rate and statistical behavior of algorithm over dimensions 10, 30 and 50. Apart from experimental studies, theoretical stability of the proposed CLGSA is also proved. It was concluded that the proposed algorithm performed efficiently with good results.