This book is primarily intended for undergraduate and postgraduate students of Science, Electrical Engineering, or Computational Mathematics. Metaheuristic search methods are so numerous and varied in terms of design and potential applications; however, for such an abundant family of optimization techniques, there seems to be a question which needs to be answered: Which part of the design in a metaheuristic algorithm contributes more to its better performance? Several works that compare the performance among metaheuristic approaches have been reported in the literature. Nevertheless, they suffer from one of the following limitations: (A)Their conclusions are based on the performance of popular evolutionary approaches over a set of synthetic functions with exact solutions and well-known behaviors, without considering the application context or including recent developments. (B) Their conclusions consider only the comparison of their final results which cannot evaluate the nature of a good or bad balance between exploration and exploitation. The objective of this book is to compare the performance of various metaheuristic techniques when they are faced with complex optimization problems extracted from different engineering domains. The material has been compiled from a teaching perspective.
Author(s): Erik Cuevas, Primitivo Diaz, Octavio Camarena
Series: Intelligent Systems Reference Library, 195
Publisher: Springer
Year: 2020
Language: English
Pages: 269
City: Cham
Preface
Contents
1 Introductory Concepts of Metaheuristic Computation
1.1 Formulation of an Optimization Problem
1.2 Classical Optimization Methods
1.3 Metaheuristic Computation Schemes
1.3.1 Generic Structure of a Metaheuristic Method
References
2 An Enhanced Swarm Method Based on the Locust Search Algorithm
2.1 Introduction
2.2 The Locust Search Algorithm
2.2.1 LS Solitary Phase
2.2.2 LS Social Phase
2.3 The LS-II Algorithm
2.3.1 Selecting Between Solitary and Social Phases
2.3.2 Modified Social Phase Operator
2.4 Experiments and Results
2.4.1 Benchmark Test Functions
2.4.2 Engineering Optimization Problems
2.5 Conclusions
Appendix A
Appendix B
B2.1 Pressure Vessel Design Problem
B2.2 Gear Train Design Problem
B2.3 Tension/Compression Spring Design Problem
B2.4 Three-Bar Truss Design Problem
B2.5 Welded Beam Design Problem
B2.6. Parameter Estimation for FM Synthesizers
B2.7 Optimal Capacitor Placement for the IEEE’s 69-Bus Radial Distribution Networks
References
3 A Metaheuristic Methodology Based on Fuzzy Logic Principles
3.1 Introduction
3.2 Fuzzy Logic and Reasoning Models
3.2.1 Fuzzy Logic Concepts
3.2.2 The Takagi-Sugeno (TS) Fuzzy Model
3.3 The Proposed Methodology
3.3.1 Optimization Strategy
3.3.2 Computational Procedure
3.4 Discussion About the Proposed Methodology
3.4.1 Optimization Algorithm
3.4.2 Modeling Characteristics
3.5 Experimental Study
3.5.1 Performance Evaluation with Regard to Its Own Tuning Parameters
3.5.2 Comparison with Other Optimization Approaches
3.6 Conclusions
Appendix A. List of Benchmark Functions
References
4 A Metaheuristic Computation Scheme to Solve Energy Problems
4.1 Introduction
4.2 Crow Search Algorithm (CSA)
4.3 The Proposed Improved Crow Search Algorithm (ICSA)
4.3.1 Dynamic Awareness Probability (DAP)
4.3.2 Random Movement—Lévy Flight
4.4 Motor Parameter Estimation Formulation
4.4.1 Approximate Circuit Model
4.4.2 Exact Circuit Model
4.5 Capacitor Allocation Problem Formulation
4.5.1 Load Flow Analysis
4.5.2 Mathematical Approach
4.5.3 Sensitivity Analysis and Loss Sensitivity Factor
4.6 Experiments
4.6.1 Motor Parameter Estimation Test
4.6.2 Capacitor Allocation Test
4.7 Conclusions
Appendix A: Systems Data
References
5 ANFIS-Hammerstein Model for Nonlinear Systems Identification Using GSA
5.1 Introduction
5.2 Background
5.2.1 Hybrid ANFIS Models
5.2.2 Adaptive Neuro-Fuzzy Inference System (ANFIS)
5.2.3 Gravitational Search Algorithm (GSA)
5.3 Hammerstein Model Identification by Using GSA
5.4 Experimental Study
5.4.1 Experiment I
5.4.2 Experiment II
5.4.3 Experiment III
5.4.4 Experiment IV
5.4.5 Experiment V
5.4.6 Experiment VI
5.4.7 Experiment VII
5.4.8 Statistical Analysis
5.5 Conclusions and Further Research
References
6 A States of Matter Search-Based Scheme to Solve the Problem of Power Allocation in Plug-in Electric Cars
6.1 Introduction
6.2 Problem Formulation
6.3 The States of Matter Search (SMS) Algorithm
6.3.1 States of Matter Transition
6.3.2 Molecule Movement Operators
6.4 SMS-Based Smart Power Allocation for PHEVs
6.5 Experimental Results
6.6 Conclusions
References
7 Locus Search Method for Power Loss Reduction on Distribution Networks
7.1 Introduction
7.2 Capacitor Allocation Problem Formulation
7.2.1 Power Loss Calculation
7.2.2 Voltage Constrains
7.3 The Locust Search Algorithm
7.3.1 LS Solitary Phase
7.3.2 LS Social Phase
7.4 Optimal Capacitor Allocation Based on LS-Algorithm
7.5 Experimental Results
7.5.1 Statistical Results of Test Cases
7.5.2 Comparative Results for IEEE’s 10-Bus Distribution System
7.5.3 Comparative Results for IEEE’s 33-Bus Distribution System
7.5.4 Comparative Results for IEEE’s 69-Bus Distribution System
7.6 Conclusions
Appendix
References
8 Blood Vessel and Optic Disc Segmentation Based on a Metaheuristic Method
8.1 Introduction
8.2 Preliminary Concepts
8.2.1 Lateral Inhibition
8.2.2 Cross Entropy
8.2.3 Differential Evolution Algorithm
8.3 Methodology
8.3.1 Pre-processing
8.3.2 Processing
8.3.3 Post-processing
8.4 Experimental Results
8.5 Conclusions
References
9 Detection of White Blood Cells with Metaheuristic Computation
9.1 Introduction
9.2 Differential Evolution
9.3 Ellipse Detection Under an Optimization Perspective
9.4 Ellipse Detector Process
9.5 Experimental Results
9.6 Conclusions
References
10 Experimental Analysis Between Exploration and Exploitation
10.1 Introduction
10.2 Exploration and Exploitation
10.3 Exploration-Exploitation Evaluation
10.4 Experimental Results
10.5 Discussion
10.6 Conclusion
References
