International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 06 | Jun 2023
p-ISSN: 2395-0072
www.irjet.net
Enhancing Mountain Gazelle Optimizer (MGO) with an Improved FParameter for Global Optimization Toufic Seini1, Abdul-Fatawu Seini Yussif2, Iddrisu Mohammed Katali3 1,3Department of Physical Sciences, University for Development Studies, Ghana
2Department of Electrical and Electronic Engineering, Kwame Nkrumah University of Science and Technology,
Kumasi, Ghana ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - In this paper, a simplified alternative approach
dimensional problems, the algorithm’s ability to efficiently explore the search space and locate global optimal solutions is enhanced.
to determining the value of parameter F in Mountain Gazelle Optimizer (MGO) is proposed to enhance the algorithm’s global performance on high-dimensional problems. The proposed improved MGO called Improved F-parameter Mountain Gazelle Optimizer (IFMGO), was tested on 13 standard high-dimensional benchmark functions while varying the problem dimensions. Further simulation test was run on other 10 fixed-dimensional benchmark functions. The MATLAB simulation results were compared to those of the original MGO and Particle Swarm Optimization (PSO) algorithms reported in the literature. The proposed IFMGO performed exceptionally better than the original MGO and PSO in solving high-dimensional optimization benchmark functions, as well as maintained excellent performance on fixed-dimensional optimization benchmark functions. The IFMGO also exhibited robustness, good convergence characteristics, and stability relative to the other algorithms.
The primary objective of this research is to investigate the impact of the proposed F-parameter modification on the performance of the MGO algorithm when applied to a set of widely recognized high-dimensional benchmark functions. These benchmark functions have been extensively used in the literature to evaluate and compare the performance of various optimization algorithms [4][6][7]. By conducting a comprehensive experimental study, the aim is to assess the effectiveness of the proposed modification and provide empirical evidence of its benefits. The remainder of this paper is organized as follows: Section 2 presents a detailed description of the MGO algorithm and its key components. Section 3 outlines the proposed modification to the F-parameter and explains its rationale. Section 4 describes the experimental setup and implementation to evaluate the performance. Section 5 presents the test results and discussions drawn from the test simulation. Finally, Section 6 concludes and outlines possible directions for future research.
Key Words: optimization, mountain gazelle optimizer, benchmark functions, particle swarm optimization, improved F-parameter mountain gazelle optimizer.
1. INTRODUCTION
2. ORIGINAL MGO ALGORITHM 2.1 Background
In recent years, nature-inspired optimization algorithms have gained significant attention for their ability to tackle complex optimization problems [1][2][3]. One such algorithm is the Mountain Gazelle Optimizer (MGO), inspired by the intelligence behind the wildlife of mountain gazelle species in their natural habitat [4]. While MGO has shown promising results in various optimization tasks, its performance in solving high-dimensional problems can be further enhanced to address the challenges presented by real-world problems characterized by a large number of variables [5].
The mountain gazelle is a species of gazelle that naturally live in the Arabian Peninsula and the surrounding regions [4]. Despite having a wide distribution, the gazelle population density is relatively low. This species is closely linked to the habitat of the Robinia tree species. Mountain gazelles exhibit strong territorial behavior, establishing their territories at significant distances from each other. They form three distinct types of groups, which include herds consisting of mothers and offspring, herds of young males, and solitary males within their territories. Male gazelles engage in frequent battles, where the competition for resources is more intense than the competition for females. In these battles, immature males utilize their horns more frequently compared to adults or territorial males. Mountain gazelles undertake migrations of over 120km in search of food. They possess remarkable speed, being able to run 100 meters at a speed of 80km/h on average [4][5].
In this paper, a new modification to the MGO is proposed by improving the F-parameter calculation to improve the algorithm’s performance in handling high-dimensional optimization problems. The F-parameter plays a crucial role in controlling the exploration and exploitation trade-off during the search process, influencing the convergence speed and stability to escape local optima [5]. By modifying the F-parameter to the specific requirements of high-
© 2023, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 921