HYBRID PARTICLE SWARM OPTIMIZATION: FROM COOPERATIVE MECHANISMS TO LÉVY FLIGHT DYNAMICS
HYBRID PARTICLE SWARM OPTIMIZATION: FROM COOPERATIVE MECHANISMS TO LÉVY FLIGHT DYNAMICS
Desheng Li
School of AI Engineering
Guangzhou College of Technology and Business
Copyright © 2026 by Cayley Nielson Press, Inc.
ISBN: 978-1-957274-27-0
Cayley Nielson Press Scholarly Monograph Series Book Code No.: 216-3-1
US$168.50
Preface
In recent years, Particle Swarm Optimization (PSO) has emerged as a cornerstone of optimization heuristics due to its robust search capabilities and rapid convergence. Among its variants, the Cooperative Particle Swarm Optimizer (CPSO) - originally proposed by Frans Van den Bergh - stands out as a highly effective paradigm. CPSO operates by partitioning the particle dimensions into multiple sub-swarms that evolve independently, after which their individual contributions are integrated to evaluate global fitness and update system parameters.
This monograph introduces a series of novel PSO algorithms enhanced by innovative computational techniques. Specifically, we present the Dynamic Varying Search Area (DVSA) method, which effectively regulates the activity range of particles to balance exploration and exploitation. Furthermore, we leverage a Cooperative Strategy that decomposes complex candidate solution vectors into specialized sub-swarms for enhanced efficiency. To mitigate the risk of premature convergence and stagnation, a stochastic disturbance mechanism based on Lévy Flights is employed, introducing strategic random movements to re-energize stagnant sub-swarms. Finally, the monograph explores various practical applications, demonstrating the efficacy of these proposed algorithms in solving complex, real-world optimization problems.
The content is supported partly by the 2025 Guangdong Provincial Ordinary University Characteristic Innovation Project, Natural Science Category (Project No. 2025KTSCX205), and the 2024 Foshan Self-Funded Science and Technology Innovation (Project No. 2420001004401), the Natural Science Foundation of Anhui Province (Project No. 1708085MF161), KeyProject of Supporting Program for Outstanding Young Talents in Universities of 2016 (Project No. Gxyqzd2016214).
Desheng Li
School of AI Engineering
Guangzhou College of Technology and Business
Foshan, Guangdong, China
January, 2026
Contents
Preface I
Authors Biography III
Chapter 1 Introduction 1
1.1 PSO Algorithms 1
1.2 Several Variants of PSO Algorithms 2
1.3 Proposed CQPSO-DVSA-LFD 8
1.4 Dynamic Varying Search Area (DVSA) 10
1.5 Lévy Flights and Disturbance 16
1.6 Experimental Studies 22
1.7 Conclusions 27
Chapter 2 Cooperative Multi-Swarm Particle Swarm Optimization with Electoral Mechanism 29
2.1 Hybrid Flow Shop Scheduling Problem 29
2.2 Mathematical Formulation of HFS 30
2.3 The Proposed PSO Algorithm 31
2.4 Experiments on Carlier and Néron’s benchmark 38
2.5 Conclusions 43
Chapter 3 Flame Combustion Diagnosis of Pulverized Coal Furnace in Thermal Power Station using Artificial Neural Network Ensembles 44
3.1 Introduction 44
3.2 Neural Network Ensemble Based on ECPSO and Bootstrap 45
3.3 Experiments and Computational Results 51
3.4 Conclusion 52
Chapter 4 Optimization of Neural Network Model Design with Electoral Cooperative Particle Swarm Optimization 54
4.1 Introduction 54
4.2 PSO Algorithms 55
4.3 Artificial Neural Network Model Design with ECPSO 56
4.4 Computational Results on NN for Classification 62
4.5 Conclusion 65
Chapter 5 Optimization and Symmetry Property of Lennard-Jones Atomic Clusters using Cooperative Quantum Particle Swarm Algorithm with Lévy Flights 66
5.1 Introduction 66
5.2 Lennard-Jones Potential Problem 67
5.4 Proposed Algorithms 68
5.5 Experimental Studies 71
5.6 Results on Symmetry Research 74
5.7 Conclusions and Future Work 90
Chapter 6 Velocity Control of Longitudinal Vibration Ultrasonic Motor Using Improved Elman Neural Network Trained By CQPSO with Lévy Flights 92
6.1 Introduction 92
6.2 Longitudinal Vibration Ultrasonic Motor (LV-USM) 93
6.3 Elman Neural Network Based on CQPSO with Lévy Flights 97
6.4 Velocity Control of Longitudinally Vibration Ultrasonic Motor 106
6.5 Conclusions 117
Appendix A. 119
References 121
Readership
This book should be useful for students, scientists, engineers and professionals working in the areas of optoelectronic packaging, photonic devices, semiconductor technology, materials science, polymer science, electrical and electronics engineering. This book could be used for one semester course on adhesives for photonics packaging designed for both undergraduate and graduate engineering students.
