Two New Improved Variants of Grey Wolf Optimizer for Unconstrained Optimization

Abstract

Grey wolf optimization (GWO) algorithm is a relatively recent and novel optimization approach. GWO showed performance improvement over all competing algorithms. However, the relevant literature identified that the primary GWO due to its position update equation shows superiority in exploitation, but is inefficient in exploration. It shows slow convergence and low precision, too. Motivated by the outlined issues in the primary GWO, this work presents two new and improved GWO algorithms. The first proposed variant modifies all the three models, encircling model of prey, position update equation and the hunting equation of canonical GWO. Further, a new parameter is introduced to scale the encircling and position update equations. As a result, the exploration issue of the algorithm is tackled. Unlike the first variant, the second proposed variant does not modify the position update models, but it incorporates Minkowski's information into GWO. To the best of our knowledge, no such modifications to GWO have been done before. The proposed modified versions of GWO are tested on a well-known test functions suit and then compared with different population-based algorithms, including fast evolutionary programming and particle swarm optimization. It was identified from the simulation results that proposed algorithms outperform different algorithms in comparison on majority of problems. The sensitivity study of the proposed algorithms to their various parameters is also provided. INDEX TERMS Population-based search approaches, evolutionary computation, unconstrained optimization, grey wolf optimization, global search, Minkowski's formula. The associate editor coordinating the review of this manuscript and approving it for publication was Huaqing Li.

Evolving CNN-LSTM Models for Time Series Prediction Using Enhanced Grey Wolf Optimizer

“…This arrangement remains static over the whole iteration course, regardless of the difference of the fitness scores of the wolf leaders. This lack of prioritizing operators among the dominant wolf leaders results in a slow convergence rate, therefore compromising search efficiency [34,75]. Motivated by many diverse strategies proposed to establish dynamic and strict social leadership hierarchies in GWO, e.g.…”

ACanis lupusinspired upgraded Harris hawks optimizer for nonlinear, constrained, continuous, and discrete engineering design problem

“…Khanum et al implemented two novel improved variants of GWO to solve the problem associated with unconstrained optimization. The two variant consisted of different population‐based algorithms including PSO and fast evolutionary programming 89 . Mittal et al designed modified GWO (mGWO) to solve the global optimization problem in the area of optical engineering and real mechanical multidisciplinary engineering design problems.…”

A Modified Grey Wolf Optimizer for Optimum Parameters of Multilayer Type-2 Asymmetric Fuzzy Controller

“…The grey wolf optimizer (GWO) was first introduced by Mirjalili in 2014, which is a type of meta-heuristic algorithm based on the grey wolf community hierarchy and hunting mechanisms [32]. Recently, some notable studies on different GWO variants have been presented to better respond to the complex search space of optimization problems [33][34][35][36][37][38][39][40][41]. In 2018, Abdo et al presented a developed GWO for solving non-smooth optimal power flow problems [33].…”

“…In 2018, Abdo et al presented a developed GWO for solving non-smooth optimal power flow problems [33]. In 2019, Khanum et al proposed two new improved variants of GWO for unconstrained optimization [35]. In 2020, Gupta and Deep presented a memory-based GWO for global optimization tasks [40].…”