COOPERATIVE PARTICLE SWARM OPTIMIZATION ALGORITHMS AND APPLICATIONS
Desheng Li
Anhui Science and Technology University
Copyright © 2017 by Cayley Nielson Press, Inc.
ISBN: 978-0-9992443-3-3
Cayley Nielson Press Scholarly Monograph Series Book Code No.: 140-1-5
US$148.60
Preface
In recent years, with the search ability, fast convergence speed and other characteristics, particle swarm optimization has been becoming the in-fact standard optimization algorithm. One most common and effective type is the cooperative particle swarm algorithm (Cooperarive PSO, CPSO) proposed by Fans Van den Bergh, which starts at the partition on the dimension of the particles of standard particle swarm optimization, and lets the multiple groups optimize respectively, and then calculates the fitness totally and updates by rules.
In this monograph, the author proposes some novel particle swarm algorithms with techniques, such as Dynamic Varying Search Area (DVSA), which takes charge of limiting the ranges of particles’ activity; the other is cooperative strategy, which divides the candidate solution vector into small sub-swarms. Even more, to avoid this kind of stagnation, we employ a stochastic disturbance method, i.e., Lévy flights disturbance, to generate a random movement of the stagnant sub-swarms. And then, some applications solved by the algorithms are also discussed in the chapters.
The author is supported financially by Natural Science Foundation of Anhui Province (1708085MF161), KeyProject of Supporting Program for Outstanding Young Talents in Universities of 2016 (Gxyqzd2016214), Key Project of Natural Science Research of Universities in Anhui (KJ2015A236), the Natural Science Foundation of Anhui Province (No. 1308085QF103), the Natural Science Foundation of Educational Government of Anhui Province (No. KJ2013B073), the Science and Technology Plan Project of Chuzhou City (No. 201236), and the Talent Introduction Special Fund of Anhui Science and Technology University (No. ZRC2011304), and was partially supported by grants of Natural Science Foundation of Anhui province (No. 1508085MC55), Key Project from Education Department of Anhui Province (No. KJ2013A076).
Desheng Li
Dr. Associate Professor
College of Information & Networking Engineering
Anhui Science and Technology University
Fengyang, Anhui, China
April 18, 2017
Contents
Preface............................................................................................................................................ I
1 Cooperative Quantum-Behaved Particle Swarm Optimization with Dynamic Varying Search Areas and Lévy Flight Disturbance.... 1
1.1 Introduction....................................................................................................................... 1
1.2 Review on related PSO algorithms........................................................................ 2
1.2.1 PSO........................................................................................................................................... 2
1.2.2 CPSO......................................................................................................................................... 3
1.2.3 QPSO........................................................................................................................................ 5
1.2.4 CQPSO...................................................................................................................................... 6
1.3 Proposed algorithm: CQPSO-DVSA-LFD.................................................................... 9
1.4 Dynamic Varying Search Area (DVSA).................................................................... 11
1.4.1 Rationale of Dynamic Varying Search Area (DVSA).................................. 11
1.4.2 Condition of DVSA........................................................................................................ 13
1.4.3 Policy of population scale adjustment......................................................... 14
1.4.4 Theoretical analysis................................................................................................. 15
1.5 Lévy flights disturbance........................................................................................... 17
1.6 Experimental studies................................................................................................... 23
1.6.1 Experiments on continuous optimization benchmarks........................ 23
1.6.2 Experiments on combinatorial optimization problem........................ 28
1.7 Conclusions and future work................................................................................. 29
2 Cooperative Multi-Swarm PSO with Electoral Mechanism to Solve Hybrid Flow Shop Scheduling Problem.............. 32
2.1 Introduction..................................................................................................................... 32
2.2 Mathematical formulation of HFS...................................................................... 33
2.3 The proposed algorithm............................................................................................ 34
2.3.1 Cooperative multi-swarm PSO (CMPSO)............................................................ 34
2.3.2 Cooperative multi-swarm PSO using electoral mechanism (CMPSO-EM) 36
2.3.3 Solution representation....................................................................................... 38
2.3.4 Fitness calculation.................................................................................................... 38
2.3.5 Disturbance approach.............................................................................................. 39
2.3.6 Main procedure............................................................................................................ 40
2.4 Experiments on Carlier and Néron’s benchmark........................................ 42
2.4.1 Design of experiments.............................................................................................. 42
2.4.2 Experiment results.................................................................................................... 43
2.5 Conclusions........................................................................................................................ 46
3 Cooperative Particle Swarm Optimizer in Permutation Flow Shop Scheduling Problem 47
3.1 Introduction..................................................................................................................... 47
3.2 The Proposed Cooperative Particle Swarm Optimizer with PFSSP..... 50
3.2.1 Electoral Cooperative Mechanism.................................................................. 50
3.2.2 Main Procedure of ECPSO......................................................................................... 52
3.2.3 Formulation of PFSSP................................................................................................ 55
3.2.4 Fitness Evaluation..................................................................................................... 58
3.3 Experimental results.................................................................................................. 59
3.3.1 Performance on Test Function Optimization............................................ 59
3.3.2 Taillard's Benchmark Suite for Makespan Criterion............................ 67
3.4 Conclusions........................................................................................................................ 68
4 Flame Combustion Diagnosis of Pulverized Coal Furnace in Thermal Power Station using Artifical Neural Network Ensembles.. 70
4.1 Introduction..................................................................................................................... 70
4.2 Neural network ensemble based on ECPSO and Bootstrap.................. 71
4.3 Experiments and Computational results........................................................ 77
4.4 Conclusion.......................................................................................................................... 79
5 Optimization of Neural Network Model Design with Electoral Cooperative Particle Swarm Optimization........... 81
5.1 Introduction..................................................................................................................... 81
5.2 PSO Algorithms................................................................................................................. 82
5.2.1 Electoral Cooperative Particle Swarm Optimization (ECPSO)......... 82
5.3 Artificial neural network model design with ECPSO.............................. 83
5.3.1 Population division and representative individual selection....... 83
5.3.2 Decision variable encoding................................................................................... 85
5.3.3 Fitness function........................................................................................................... 86
5.3.4 Algorithms...................................................................................................................... 87
5.4 Computational results on NN for classification........................................ 90
5.4.1 Experiment 1: Bi-spire problem............................................................................ 90
5.4.2 Experiment 2: Iris, Ionosphere, and Breast Cancer.................................. 91
5.5 Conclusion.......................................................................................................................... 93
6 Formal Modeling and Implementation of Particle Swarm Optimizer for QoS-aware Service Selection with an Extended Pi Calculus.................................................................................................... 94
6.1 Introduction..................................................................................................................... 94
6.2 The Pi-Beam-Cost Calculus.......................................................................................... 96
6.2.1 Language........................................................................................................................... 96
6.2.2 Meta-control Procedure of PSO........................................................................ 98
6.3 The Modeling of QoS-aware Web Service Selection................................ 101
6.3.1 Preliminary Modeling of QoS-aware Web Service Selection with Pi-beam-cost 101
6.3.2 Modeling in PSO Scheme......................................................................................... 107
6.4 Simulation Platform and Experiment............................................................. 111
6.4.1 System Architecture............................................................................................... 111
6.4.2 Experimental Results............................................................................................. 115
6.5 Conclusions...................................................................................................................... 117
7 Optimization and Symmetry Property of Lennard-Jones Atomic Clusters using Cooperative Quantum Particle Swarm Algorithm with Lévy Flights............. 118
7.1 Introduction.................................................................................................................. 118
7.2 Lennard-Jones potential problem.................................................................... 119
7.3 Review on PSO family algorithms....................................................................... 121
7.3.1 PSO...................................................................................................................................... 121
7.3.2 CPSO.................................................................................................................................... 122
7.3.3 QPSO................................................................................................................................... 123
7.3.4 CQPSO................................................................................................................................. 124
7.4 Proposed algorithms................................................................................................. 126
7.4.1 Lévy flights disturbance...................................................................................... 126
7.4.2 Flow of Algorithm................................................................................................... 133
7.5 Experimental studies................................................................................................. 136
7.5.1 Experiments on continuous optimization benchmarks for CQPSO-LF 136
7.5.2 Optimum structures of LJ cluster found by CQPSO-LF-DLS.................. 139
7.6 Results on Symmetry research............................................................................ 142
7.6.1 PPP of decahedron................................................................................................... 143
7.6.2 HPP of icosahedron.................................................................................................. 146
7.6.3 Freedom geometrical morphology PP......................................................... 150
7.7 Conclusions and future work.............................................................................. 158
8 Numerical Simulation of Chemical Pollutant Transportation and Dispersion Using Convection-Diffusion Analysis Method........ 160
8.1 Introduction.................................................................................................................. 160
8.2 Mathematical formulation.................................................................................. 163
8.2.1 Dispersion of the Pollutant.............................................................................. 163
8.2.2 Determining the diffusion coefficients by Lévy flights.................. 165
8.2.3 Velocity field of the water body.................................................................. 166
8.2.4 Variational form of equations........................................................................ 168
8.3 Solution by FEM............................................................................................................. 169
8.3.1 Discrete forms of FEM............................................................................................ 169
8.3.2 Solving stages............................................................................................................. 175
8.4 Experimental results and analysis................................................................... 176
8.4.1 Temporal and spatial distribution of pollutant concentration 176
8.4.2 Spatial distribution of pollutant concentration during the whole process 183
8.4.3 Temperature transport and heat flow of chemical pollutants 186
8.5 Conclusions...................................................................................................................... 193
9 Velocity control of longitudinal vibration ultrasonic motor using improved Elman neural network trained by CQPSO with Lévy flights.......................................................................... 195
9.1 Introduction.................................................................................................................. 195
9.2 Longitudinal vibration ultrasonic motor (LV-USM)............................... 196
9.3 Elman neural network based on CQPSO with Lévy flights................. 200
9.3.1 CQPSO with Lévy flights......................................................................................... 200
9.3.2 Elman neural network trained by CQPSO-LF............................................ 206
9.4 Velocity control of longitudinally vibration ultrasonic motor 211
9.4.1 Design of the speed control system and stability analysis........... 211
9.4.2 Stability analysis...................................................................................................... 213
9.4.3 Numerical experiments......................................................................................... 215
9.5 Conclusions...................................................................................................................... 223
Appendix A................................................................................................................................ 225
References.............................................................................................................................. 227
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.
