QPSO with avoidance behaviour to solve electromagnetic optimization problems

Article type: Research Article

Authors: Duca, Anton^{a; b;} | Duca, Laurentiu^b | Ciuprina, Gabriela^a

Affiliations: [a] Faculty of Electrical Engineering, Politehnica University of Bucharest, Bucharest, Romania | [b] Faculty of Computer Science, Politehnica University of Bucharest, Bucharest, Romania

Correspondence: [*] Corresponding author: Anton Duca, Faculty of Electrical Engineering, Politehnica University of Bucharest, 313 Splaiul Independentei 060042, Bucharest, Romania. E-mail: anton.duca@upb.ro

Abstract: The paper proposes a new set of improved Quantum-behaved Particle Swarm Optimization (QPSO) algorithms by using the avoidance from the worst behaviour. The avoidance behaviour, which consist in introducing personal/local or global worst terms, are applied to the attractor’s formula. The enhanced QPSO algorithms are targeted towards benchmark electromagnetic optimization problems, and their efficiency is tested and tuned on Loney’s solenoid.

Keywords: PSO, QPSO, avoidance behaviour, optimization, electromagnetic field

DOI: 10.3233/JAE-171170

Journal: International Journal of Applied Electromagnetics and Mechanics, vol. 59, no. 1, pp. 63-69, 2019