LGWO: An Improved Grey Wolf Optimization for Function Optimization
Grey wolf optimization (GWO) algorithm is a novel nature-inspired heuristic paradigm. GWO was inspired by grey wolves, which mimics the leadership hierarchy and hunting mechanism of grey wolves in nature. It has exhibited promising performance in many fields. However, GWO algorithm has the drawback of slow convergence and low precision. In order to overcome this drawback, we propose an improved version of GWO enhanced by the Lévy-flight strategy, termed as LGWO. Lévy-flight strategy was introduced into the GWO to find better solutions when the grey wolves fall into the local optimums. The effectiveness of LGWO has been rigorously evaluated against ten benchmark functions. The experimental results demonstrate that the proposed approach outperforms the other three counterparts.
KeywordsGrey wolf optimization Function optimization Lévy-flight
This research is supported by the National Natural Science Foundation of China (NSFC) (61303113, 61402337). This research is also funded by the Zhejiang Provincial Natural Science Foundation of China (LY17F020012, LQ13G010007, LQ13F020011 and LY14F020035), the Science and Technology Plan Project of Wenzhou, China (G20140048, H20110003).
- 3.Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of the 1995 IEEE International Conference on Neural Networks. IEEE, vol. 4, pp. 1942–1948. IEEE Press, Piscataway (1995)Google Scholar
- 6.Li, Q., Chen, H., Huang, H., Zhao, X., Cai, Z., Tong, C., Liu, W., Tian, X.: An enhanced grey wolf optimization based feature selection wrapped kernel extreme learning machine for medical diagnosis. Comput. Math. Methods Med. 2017 (2017)Google Scholar