Sarker / Ray Agent-Based Evolutionary Search

1. Auflage 2010
ISBN: 978-3-642-13425-8
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 5, 293 Seiten

Reihe: Adaptation, Learning, and Optimization

Agent based evolutionary search is an emerging paradigm in computational int- ligence offering the potential to conceptualize and solve a variety of complex problems such as currency trading, production planning, disaster response m- agement, business process management etc. There has been a significant growth in the number of publications related to the development and applications of agent based systems in recent years which has prompted special issues of journals and dedicated sessions in premier conferences. The notion of an agent with its ability to sense, learn and act autonomously - lows the development of a plethora of efficient algorithms to deal with complex problems. This notion of an agent differs significantly from a restrictive definition of a solution in an evolutionary algorithm and opens up the possibility to model and capture emergent behavior of complex systems through a natural age- oriented decomposition of the problem space. While this flexibility of represen- tion offered by agent based systems is widely acknowledged, they need to be - signed for specific purposes capturing the right level of details and description. This edited volume is aimed to provide the readers with a brief background of agent based evolutionary search, recent developments and studies dealing with various levels of information abstraction and applications of agent based evo- tionary systems. There are 12 peer reviewed chapters in this book authored by d- tinguished researchers who have shared their experience and findings spanning across a wide range of applications.

Autoren/Hrsg.

Ray, Tapabrata

Sarker, Ruhul A.

Inhaltsverzeichnis

1;Title;2
2;Preface;6
3;Contents;7
4;List of Contributors;9
5;Agent Based Evolutionary Approach: An Introduction;12
5.1;Introduction;12
5.2;Evolutionary Algorithms;14
5.3;Agent and Multi-Agent System;14
5.4;Integration of MAS and EAs;17
5.5;Agent-Based Evolutionary Algorithms;18
5.6;A Brief Description on the Content of This Book;19
5.7;References;20
6;Multi-Agent Evolutionary Model for Global Numerical Optimization;23
6.1;Introduction;24
6.2;Multi-Agent Genetic Algorithm;25
6.3;Multi-Agent Evolutionary Model for Decomposable Function Optimization;44
6.4;Hierarchy Multi-Agent Genetic Algorithm;48
6.5;Conclusions;56
6.6;References;57
7;An Agent Based Evolutionary Approach for Nonlinear Optimization with Equality Constraints;59
7.1;Introduction;59
7.2;Agent-Based Evolutionary Algorithms;62
7.2.1;Environment of Agents;62
7.2.2;Behavior of Agents;63
7.2.3;Learning of Agents;63
7.2.4;Reasoning Capability of Agents;63
7.3;Agent-Based Memetic Algorithms;64
7.3.1;Crossover;65
7.3.2;Life Span Learning Process;65
7.3.2.1;New Learning Process for Handling Equality Constraints;65
7.3.2.2;Pseudo Code of the Other LSLPs;68
7.3.3;The Algorithm;70
7.3.4;Constraint Handling;70
7.4;Experimental Studies;70
7.4.1;Initial Design Experience;70
7.4.2;Experimental Results and Discussion;71
7.4.3;Comparison with Other Algorithms;73
7.4.4;Effect of the New LSLP;76
7.4.5;Effect of Probability of Using LSLP;77
7.5;Conclusions;80
7.6;Appendix;81
7.6.1;$g$03;81
7.6.2;$g$05;81
7.6.3;$g$11;81
7.6.4;$g$13;82
7.6.5;B01;82
7.6.6;B02;82
7.7;References;83
8;Multiagent-Based Approach for Risk Analysis in Mission Capability Planning;87
8.1;Introduction;88
8.2;Background;89
8.2.1;Project Scheduling Problems;89
8.2.1.1;Overview;89
8.2.1.2;Resource Investment Problems;90
8.3;Mission Capability Planning;91
8.3.1;Overview of Capability Planning Process;91
8.3.2;Mission Capability Planning Problem;93
8.3.3;Mathematical Formulation of MCPP;94
8.4;A Multiagent-Based Framework;94
8.4.1;General Framework;95
8.4.2;Options Production Layer — OPL;95
8.4.3;Risk Tolerance Layer —RTL;96
8.4.4;Risk Simulation;96
8.4.5;Feedback from Agents to the Solutions;97
8.5;Case Study;98
8.5.1;Test Scenarios;98
8.5.2;Parameter Settings;98
8.5.3;Results and Discussion;99
8.5.4;The Effect of Feedback Mechanism: A Pilot Study;102
8.6;Conclusion;103
8.7;References;104
9;Agent Based Evolutionary Dynamic Optimization;107
9.1;Introduction;107
9.2;Proposed Agent Based Evolutionary Search Algorithm;108
9.2.1;The Framework of AES;108
9.2.2;Behaviors of Agents;111
9.2.2.1;Competitive Behavior;111
9.2.2.2;Statistics Based Learning Behavior;112
9.2.3;Two Diversity Maintaining Schemes on AES;113
9.2.3.1;Random Immigrants Method (RI);114
9.2.3.2;Adaptive Dual Mapping Method(ADM);114
9.3;The Dynamic Testing Suite;114
9.3.1;Stationary Test Problems;114
9.3.1.1;One-Max Function;115
9.3.1.2;Royal Road Function;115
9.3.1.3;Deceptive Function;116
9.3.1.4;Double Deceptive Function;116
9.3.2;Generating Dynamic Test Problems;116
9.4;Experimental Study;117
9.4.1;Experimental Setting;117
9.4.2;Experimental Results on DOPs;118
9.5;Conclusions;123
9.6;References;124
10;Divide and Conquer in Coevolution: A Difficult Balancing Act;127
10.1;Introduction;127
10.2;Background;129
10.2.1;Basic CCEA;129
10.2.2;Why Are CCEAs Attractive?;130
10.2.3;Shortcomings of Basic CCEA;132
10.3;Proposed CCEA with Adaptive Variable Partitioning Based on Correlation;134
10.4;Numerical Experiments;137
10.4.1;Results on 50D Test Problems;137
10.4.2;Results for 100D Problems;141
10.4.3;Variation in Performance of CCEA-AVP with Different Values of Correlation Threshold;144
10.5;Conclusions and Further Studies;145
10.6;References;147
11;Complex Emergent Behaviour from Evolutionary Spatial Animat Agents;149
11.1;Introduction;149
11.2;A Review of Animat Models;151
11.3;The Animat Model;153
11.3.1;Model Basics;153
11.3.2;Changes to the Model;156
11.3.3;Fine Tuning;156
11.4;Animat Model Observations;159
11.5;Evolution Algorithms;160
11.6;Evolution Experiments;161
11.6.1;Simulation 1 – The Control;162
11.6.2;Simulation 2 – Evolution by Crossover Only;162
11.6.3;Simulation 3 – Evolution by Crossover and Mutation;164
11.6.4;Simulation 4 – Evolution with Scarce Resorces;165
11.7;Discussion and Conclusions;166
11.8;References;168
12;An Agent-Based Parallel Ant Algorithm with an Adaptive Migration Controller;170
12.1;Introduction;170
12.2;A Brief Introduction to a Continuous Ant Algorithm;172
12.2.1;Initialization;172
12.2.2;Selection;172
12.2.3;Dump Operation and Pheromones Update;173
12.2.4;Random Search;173
12.3;Implementation of the Agent-Based Parallel Ant Algorithm (APAA);174
12.3.1;Division of the Solution Vector;175
12.3.2;Stagnation-Based Asynchronous Migration Controller (SAMC);176
12.4;Experiments and Discussions;178
12.4.1;Parameter Settings;179
12.4.2;Comparison of Solution Quality;180
12.4.3;Comparison of Convergence Speed;182
12.5;Conclusions;185
12.6;References;185
13;An Attempt to Stochastic Modeling of Memetic Systems;187
13.1;Motivation;187
13.2;EMAS Definition;190
13.2.1;EMAS Structure;190
13.2.2;EMAS State;191
13.2.3;EMAS Behavior;192
13.2.4;EMAS Actions;193
13.2.5;EMAS Dynamics;197
13.3;iEMAS Extension;198
13.3.1;iEMAS Structure;198
13.3.2;iEMAS State;199
13.3.3;iEMAS Behavior;199
13.3.4;iEMAS Actions;200
13.3.5;iEMAS Dynamics;205
13.4;Experimental Results;206
13.5;Conclusions;208
13.6;References;209
14;Searching for the Effective Bidding Strategy Using Parameter Tuning in Genetic Algorithm;211
14.1;Introduction;211
14.2;Genetic Algorithms;212
14.3;Related Work;214
14.4;Bidding Strategy Framework;215
14.5;Algorithm;220
14.6;Experimental Setting;221
14.7;Experimental Evaluation;224
14.8;Results and Discussion;224
14.9;Conclusion;233
14.10;References;233
15;$PSO$ (Particle Swarm Optimization): One Method, Many Possible Applications;237
15.1;$PSO$ and Evolutionary Search;237
15.2;$PSO$: Algorithms Inspired by Nature Twice;239
15.2.1;Definitions;240
15.2.2;$PSO$ and Multiobjective Optimization Problems;241
15.2.3;$PSO$: A Population-Based Technique;245
15.3;Case Studies;249
15.3.1;Looking for Resources;249
15.3.2;Microeconomy: General Equilibirum Theory;252
15.3.3;Tactical vs. Strategic Behavior;257
15.4;Conclusions;259
15.5;References;261
16;$VISPLORE$: Exploring Particle Swarms by Visual Inspection;263
16.1;Related Work;265
16.2;Particle Swarm Optimization;267
16.3;The $VISPLORE$ Toolkit;267
16.3.1;Visualization of a Particle;267
16.3.2;Visualization of a Population as a Collection of Particles;271
16.3.3;Visualization of an Experiment as a Collection of Populations;276
16.3.4;Visualization of Experiments as a Collection of Experiments;278
16.4;Searching in $VISPLORE$;279
16.5;Different Views in $VISPLORE$;281
16.6;Customizing Plots in $VISPLORE$;282
16.7;$VISPLORE$ on the Foxholes Function;284
16.8;An Application Example: Soccer Kick Simulation;286
16.9;Conclusion;289
16.10;References;291
17;Index;1