The Fuzzified Grey Wolf: An improved grey wolf optimizer based on dynamic fuzzy system FGWO

Abstract

The Grey Wolf Optimizer (GWO) is a leading, powerful, and effective algorithm in swarm optimization techniques, showing competitive performance across various optimization problems. Yet, GWO is burdened by high tendencies toward exploitation and imprecise population diversity. This work introduces an improved GWO called the Fuzzified Grey Wolf Optimizer (FGWO) for solving global optimization problems. FGWO benefits from a dynamic fuzzy inference system (DFIS) to capture the optimal value of $\overrightarrow{a}$ throughout iterations. DFIS integrates two inputs: the diversity rate and iteration number, and by inferring the optimal value of $\overrightarrow{a}$, FGOW determines whether to exploit or explore. Moreover, DFIS employs an adaptive membership function to capture the precise value of population diversity throughout the course of iteration. This optimal $\overrightarrow{a}$ determination strategy can achieve a balanced exploitation–exploration ratio, mitigating premature convergence and enhancing diversity. FGWO is evaluated on CEC2017 benchmark functions, four engineering designs, and a breast cancer genes feature selection design. FGWO was compared with three other improved GWOs, and across all experiments, the outcomes demonstrate its superiority in terms of efficiency and applicability to real-world designed problems.