Numerical Simulations for Hybrid Electromagnetism-Like Mechanism Optimization Algorithms with Descent Methods

Electromagnetism-like Mechanism (EM) method is known as one of metaheuristics. The basic idea is that the position of a charged particle represents a solution for the optimization problem, and the charge amount of the particle corresponds to the evaluation value of the solution. Starting with a population of particles whose positions are randomly initialized, the population converges to a neighborhood of the optimal or semi-optimal solution. Like other metaheuristics, one of its drawbacks is that it takes too much time to converge to a solution. In this paper, we will perform numerical simulations to investigate how to use and combine EM and steepest descent methods. Further, we will show that hybrid EM methods are superior in accuracy to conventional methods.