Abstract
This paper proposes a new meta-heuristic called Jumping Spider Optimization Algorithm (JSOA), inspired by Arachnida Salticidae hunting habits. The proposed algorithm mimics the behavior of spiders in nature and mathematically models its hunting strategies: search, persecution, and jumping skills to get the prey. These strategies provide a fine balance between exploitation and exploration over the solution search space and solve global optimization problems. JSOA is tested with 20 well-known testbench mathematical problems taken from the literature. Further studies include the tuning of a Proportional-Integral-Derivative (PID) controller, the Selective harmonic elimination problem, and a few real-world single objective bound-constrained numerical optimization problems taken from CEC 2020. Additionally, the JSOA’s performance is tested against several well-known bio-inspired algorithms taken from the literature. The statistical results show that the proposed algorithm outperforms recent literature algorithms and is capable to solve challenging real-world problems with unknown search space.
Highlights
Meta-heuristic algorithms are widely used as one of the main techniques to obtain an optimal solution in various complex problems in several engineering and scientific research areas
Metaheuristics are not perfect, one weakness is that the quality of the solution depends on the number of search agents and the stop condition of the algorithm, commonly determined by the number of iterations
In order to investigate the significant differences between the results of the proposed Jumping Spider Optimization Algorithm (JSOA) and the other algorithms, the Wilcoxon rank-sum non-parametric statistical test with a 5% degree of significance was carried out
Summary
Meta-heuristic algorithms are widely used as one of the main techniques to obtain an optimal solution (near to optimal) in various complex problems in several engineering and scientific research areas. It is possible to use them to solve any linear or non-linear optimization problem through one or several objective functions subject to several intrinsic restrictions. They are quite useful in solving very complex problems where deterministic algorithms get caught up in a local optimum. Meta-heuristics have become effective alternatives for solving NP-hard problems due to their versatility to find several local solutions, as in real-world applications, e.g., optimal design of structural engineering problems [1,2], logistics and industrial manufacture [3], renewable energy systems [4], Deep Neural Networks (DNNs) models optimization [5], among other applications. Metaheuristics generate several search agents, through stochastic processes within the solution space to find the optimal or close to the optimal value. Metaheuristics are not perfect, one weakness is that the quality of the solution depends on the number of search agents and the stop condition of the algorithm, commonly determined by the number of iterations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
