Gazelle optimization algorithm: a novel nature-inspired metaheuristic optimizer

• Published in: Neural computing & applications Vol. 35; no. 5; pp. 4099 - 4131
• Main Authors: Agushaka, Jeffrey O., Ezugwu, Absalom E., Abualigah, Laith
• Format: Journal Article
• Language: English
• Published: London Springer London 01.02.2023; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Design engineering; Heuristic methods; Image Processing and Computer Vision; Mechanical engineering; Mechanical engineering design; Optimization; Optimization algorithms; Original Article; Predators; Probability and Statistics in Computer Science; State of the art; Statistical analysis; Survival; Population-based; Gazelle optimization algorithm; Metaheuristics; Gazelle; GOA; Industrial engineering design problems; Optimization problems; Nature-inspired
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-022-07854-6

This study proposes a novel population-based metaheuristic algorithm called the Gazelle Optimization Algorithm (GOA), inspired by the gazelles’ survival ability in their predator-dominated environment. Every day, the gazelle knows that if it does not outrun and outmaneuver its predators, it becomes meat for the day, and to survive, the gazelles have to escape from their predators consistently. This information is vital to proposing a new metaheuristic algorithm that uses the gazelle’s survival abilities to solve real-world optimization problems. The exploitation phase of the algorithm simulates the gazelles grazing peacefully in the absence of the predator or while the predator is stalking it. The GOA goes into the exploration phase once a predator is spotted. The exploration phase consists of the gazelle outrunning and outmaneuvering the predator to a safe haven. These two phases are iteratively repeated, subject to the termination criteria, and finding optimal solutions to the optimization problems. The robustness and efficiency of the developed algorithm as an optimization tool were tested using benchmark optimization test functions and selected engineering design problems (fifteen classical, ten composited functions, and four mechanical engineering design problems). The results of the GOA are compared with nine other state-of-the-art algorithms. The simulation results obtained confirm the superiority and competitiveness of the GOA algorithm over nine state-of-the-art algorithms available in the literature. Also, the standard statistical analysis test carried out on the results further confirmed the ability of GOA to find solutions to the selected optimization problems. It also showed that GOA performed better or, in some cases, was very competitive with some state-of-the-art algorithms. Also, the results show that GOA is a potent tool for optimization that can be adapted to solve problems in different optimization domains.