An Improvised Grey Wolf Optimizer for Global Optimization Problems

The Grey Wolf Optimization algorithm (GWO) is one of the popular meta-heuristic algorithms in Evolutionary Computation. However, the GWO algorithm is having many drawbacks such as less accurateness, incapable of local searching competence, and low convergence speed. Therefore, in this paper an Improvised Grey Wolf Optimization algorithm called IGWO is being introduced to compensate these drawbacks of the GWO method by altering the surrounding behaviour along with the new position updating formula. Several well-known benchmark functions are considered to examine the accurateness and convergence of the modified version. The outcomes are matched to the well-known algorithms like Particle Swarm Optimisation algorithm, Grey Wolf Optimisation algorithm, Mean Grey Wolf Optimization algorithm, FEP and GSA. The experimental results showed that the newly modified form called as IGWO can produce extremely superior results in terms of optimum objective functions and convergence speediness