Qing / Lee Differential Evolution in Electromagnetics

2010
ISBN: 978-3-642-12869-1
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 4, 195 Seiten

Reihe: Adaptation, Learning, and Optimization

Differential evolution has proven itself a very simple while very powerful stochastic global optimizer. It has been applied to solve problems in many scientific and engineering fields. This book focuses on applications of differential evolution in electromagnetics to showcase its achievement and capability in solving synthesis and design problems in electromagnetics.Topics covered in this book include:•A comprehensive up-to-date literature survey on differential evolution•A systematic description of differential evolution•A topical review on applications of differential evolution in electromagnetics•Five new application examplesThis book is ideal for electromagnetic researchers and people in differential evolution community. It is also a valuable reference book for researchers and students in the optimization or electrical and electronic engineering field. In addition, managers and engineers in relevant fields will find it a helpful introductory guide.

Autoren/Hrsg.

Qing, Anyong

Lee, Ching Kwang

Inhaltsverzeichnis

1;Title Page ;2
2;Preface;6
3;Acknowledgement;10
4;Contents;11
5;A Literature Survey on Differential Evolution;18
5.1;Motivations;18
5.1.1;Eliminating Inconsistencies;18
5.1.2;Crediting Original Contributions;18
5.1.3;Knowing the State of the Art;18
5.1.4;Gaining Insight;19
5.2;Platforms;19
5.2.1;Starting Point;19
5.2.2;Databases;20
5.2.3;Informal Online Resources and Tools;21
5.3;Result Refining;22
5.3.1;Books;22
5.3.2;Book Chapters;23
5.3.3;Other Formal Publications;23
5.3.4;Informal Notes;24
5.4;Result Analysis;24
5.4.1;Theory of Differential Evolution;24
5.4.2;Fundamentals of Differential Evolution;25
5.4.3;Intrinsic Control Parameters;26
5.4.4;Evaluation of Differential Evolution;26
5.4.5;Applications of Differential Evolution;26
5.4.6;Hybridization;26
5.5;Future Actions;27
5.5.1;Open Access;27
5.5.2;Future Update;27
5.6;Misconceptions and Misconducts on Differential Evolution;27
5.7;References;27
6;Basics of Differential Evolution;35
6.1;A Short History;35
6.1.1;Inception;35
6.1.2;Early Years;36
6.1.3;Key Milestones in and after 1998;38
6.2;The Foundational Differential Evolution Strategies;39
6.2.1;Notations;39
6.2.2;Strategy Framework;40
6.2.3;Intrinsic Control Parameters;43
6.3;Classic Differential Evolution;44
6.3.1;Initialization;44
6.3.2;Differential Mutation;44
6.3.3;Crossover;46
6.4;Dynamic Differential Evolution;52
6.5;State of the Art of Differential Evolution;52
6.6;Essential Features of Differential Evolution;53
6.6.1;Advantages;53
6.6.2;Disadvantages;54
6.7;References;54
7;A Retrospective of Differential Evolution in Electromagnetics;59
7.1;Introduction;59
7.1.1;Coverage;59
7.1.2;Pioneering Works;60
7.1.3;An Overview of Applications of Differential Evolution in Electromagnetics;60
7.2;Electromagnetic Inverse Problems;61
7.2.1;A Bird’s Eye View;61
7.2.2;Further Classification;61
7.3;Antenna Arrays;64
7.3.1;Conventional Antenna Arrays;64
7.3.2;Time-Modulated Antenna Arrays;65
7.3.3;Moving Phase Center Antenna Arrays;66
7.4;Microwave and RF Engineering;66
7.4.1;Design of Microwave and RF Devices;66
7.4.2;Characterization of Microwave and RF Devices;67
7.5;Antennas;68
7.5.1;Design of Antennas;68
7.5.2;Measurement of Antennas;69
7.6;Electromagnetic Structures;69
7.6.1;Plain Electromagnetic Structures;70
7.6.2;Frequency Selective Surfaces;71
7.7;Electromagnetic Composite Materials;72
7.7.1;Modeling of Electromagnetic Composite Materials;72
7.7.2;Retrieval of Effective Permittivity Tensor;72
7.8;Frequency Planning;73
7.9;Radio Network Design;74
7.10;MIMO;74
7.11;Radar;75
7.12;Computational Electromagnetics;75
7.13;Electromagnetic Compatibility;76
7.14;Miscellaneous Applications;76
7.15;An Outlook to Future Applications of Differential Evolution in Electromagnetics;76
7.16;References;77
8;Application of Differential Evolution to a Two-Dimensional Inverse Scattering Problem;88
8.1;Introduction;88
8.2;General Description of the Problem;89
8.2.1;Experimental Setup;89
8.2.2;The Optimization Problem;91
8.3;Mathematical Nature of the Optimization Problem and Differential Evolution;91
8.4;Initial Guess;92
8.4.1;Foldy-Lax Model of Scattering;93
8.4.2;Multiple Signal Classification for Estimating the Scatterer Support;94
8.4.3;Least Square Based Method for Generating Initial Guess for the Relative Permittivity;95
8.5;Numerical Results;96
8.5.1;Measurement Setup;96
8.5.2;Control Parameters;96
8.5.3;Numerical Example 1: A Single Cylinder;97
8.5.4;Numerical Example 2: Two Identical Cylinders;102
8.5.5;Numerical Example 3: Two Different Cylinders;105
8.5.6;Numerical Example 4: Two Closely Located Identical Cylinders;109
8.5.7;Numerical Example 5: Kite Cross-Section Cylinder;112
8.6;Conclusions;116
8.7;References;117
9;The Use of Differential Evolution for the Solution of Electromagnetic Inverse Scattering Problems;121
9.1;Introduction;121
9.2;Problem Formulation;122
9.2.1;The Inverse Scattering Formulation;122
9.2.2;Discrete Setting;123
9.2.3;The Inverse Scattering Problem as an Optimization Problem;124
9.3;The Iterative Multiscaling Approach;124
9.4;Numerical Results;126
9.4.1;Off-Centered Dielectric Cylinder;126
9.4.2;Off-Centered Dielectric Hollow Cylinder;131
9.4.3;Centered Stratified Dielectric Square Cylinder;135
9.4.4;Centered E-Shape Dielectric Cylinder;140
9.5;Conclusions;143
9.6;References;143
10;Modeling of Electrically Large Equipment with Distributed Dipoles Using Metaheuristic Methods;146
10.1;Introduction;146
10.1.1;Near-Field to Far-Field Transformation;146
10.1.2;Radiating Equipment Modeling with Prefixed Position Dipoles;147
10.1.3;Present Work;148
10.2;Electromagnetic Modeling of a Radiating Equipment with Distributed Infinitesimal Dipoles;149
10.2.1;Integral Equations for the Radiation of Electronic Equipment;149
10.2.2;Point-Matching Method with Dirac Delta Basis Functions;150
10.2.3;Ground Plane in Semi-anechoic Chambers;150
10.3;Proposed Method for Near-Field to Far-Field Transformation;151
10.3.1;Description of the Method;151
10.3.2;Optimization Problem;153
10.3.3;Source Identification;153
10.4;Electromagnetic Optimization by Genetic Algorithms;153
10.4.1;EMOGA v1.0: Genetic Algorithm;154
10.4.2;EMOGA v2.0: Metaheuristic Method;155
10.5;Numerical Results;157
10.5.1;Measurement Systems;157
10.5.2;Near-Field Results;160
10.5.3;Far-Field Prediction;162
10.6;Conclusions;163
10.7;References;164
11;Application of Differential Evolution to a Multi-Objective Real-World Frequency Assignment Problem;168
11.1;Introduction;168
11.2;Multi-objective FAP in a GSM Network;169
11.2.1;GSM Components and Frequency Planning;169
11.2.2;Interference Cost;170
11.2.3;Separation Cost;171
11.3;Multi-objective Differential Evolution with Pareto Tournaments;172
11.3.1;Algorithm Structure;172
11.3.2;Pareto Tournament;172
11.3.3;Problem Domain Knowledge;173
11.4;Multi-objective Variable Neighborhood Search;173
11.4.1;Variable Neighborhood Search;173
11.4.2;Multi-objective Variable Neighborhood Search;174
11.4.3;Greedy Mutation;175
11.4.4;Multi-objective Skewed Variable Neighborhood Search;175
11.5;Experiments and Results;176
11.5.1;Experimental Setup;176
11.5.2;Methodology and Metrics;179
11.5.3;Tuning of the DEPT Parameters;179
11.5.4;Empirical Results;186
11.6;Conclusions;188
11.7;References;188
12;RNN Based MIMO Channel Prediction;190
12.1;Introduction;190
12.2;Received Signal Model;191
12.2.1;Received Signal Model;191
12.2.2;Optimization Problem;192
12.3;Hybrid PSO-ES-DEPSO Training Algorithm;192
12.4;MIMO Channel/Beam-Forming Models;193
12.4.1;Channel Model;193
12.4.2;Channel Estimation Model;195
12.4.3;MIMO Beam-Forming;195
12.5;Recurrent Neural Network for Channel Prediction;197
12.6;Training Procedure;198
12.7;Numerical Results;200
12.7.1;Algorithm Comparison;200
12.7.2;Robustness of PSO-ES-DEPSO Algorithm;201
12.7.3;Linear and Nonlinear Predictors with PSO-EA-DEPSO Algorithm;204
12.7.4;Non-convexity of the Solution Space;205
12.8;Performance Measures of RNN Predictors;206
12.9;Conclusions;216
12.10;References;217
13;Index;220

Leseproben

"Chapter 1 A Literature Survey on Differential Evolution (p. 1-2)

Anyong Qing

1.1 Motivations

1.1.1 Eliminating Inconsistencies

It has been observed since 2004 that there are many inconsistent or even false claims prevailing in the community of differential evolution [1]. Two measures have been taken to clarify them. The first is a system level parametric study on differential evolution [1]-[4]. The second is the large scale literature survey mentioned here. It is one of the foundation stones of this book.

1.1.2 Crediting Original Contributions

The academic society nowadays has become more and more utilitarian and impetuous. Many researchers dream a shortcut to their academic success. They tend to accept established view points especially those from topical review articles by leading researchers. Original publications are neglected that insufficient credits are given to originality. In some cases, they may not be aware that the original contributions are cited incorrectly [1]. Academic misconducts such as multiple submissions, exaggerated claims, or even plagiarism are not rare. It is one of the objectives of this survey to promote good academic conducts by locating and appropriately crediting original contributions.

1.1.3 Knowing the State of the Art

It has been more than ten years since the inception of differential evolution. However, as far as we know, nobody else has done any comprehensive literature survey on differential evolution. The state of the art of differential evolution is therefore not precisely known to interested researchers. This literature survey aims to fill this gap. It also serves to reveal the popularity of differential evolution.

1.1.4 Gaining Insight

The literature survey involves not only literature collection but also literature analysis among which the latter is more important. Through the analysis, the following questions will be answered
(a) What is differential evolution?
(b) When is differential evolution used and why is it useful?
(c) When will differential evolution fail and why does it fail?"