A review on soft computing optimization techniques for electromagnetics

Prashansa and B Singh and N Kushwaha, FREQUENZ, 79, 451-478 (2025).

DOI: 10.1515/freq-2024-0307

This study delves various nature inspired soft computing optimization and their applications for solving complex electromagnetics optimization problems. As the discipline advances, the integration of soft computing and electromagnetics is expected to drive innovation and broaden the scope of various engineering fields. In the past, there have been efforts to exploit various nature based optimization techniques like Genetic Algorithm (GA), Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), Differential Evolution (DE), Evolutionary Strategy, Simulated Annealing (SA), Memetic Algorithm (MA), Bacteria Foraging Optimization (BFO), Comprehensive Learning Particle Swarm Optimization (CLPSO), Wind Driven Optimization (WDO) Technique and many more, for solving multi-modal and multi-dimension in area of electromagnetcis, communications, system identifications, power flow optimization, pattern recognition, biomedical, health-care and marketing management etc. Incorporating soft computing techniques - such as Neural Networks (NN), Wind Driven Optimization (WDO), and Genetic Algorithms (GA) etc. - into electromagnetics has demonstrated significant potential in overcoming complex challenges where traditional methods fall short. These methods enhance resilience against the inherent uncertainties and nonlinear characteristics of electromagnetic systems, leading to notable progress in design optimization, antenna pattern synthesis, and mitigating electromagnetic interference.

Return to Publications page