Evolutionary Computation in Dynamic and Uncertain Environments

Evolutionary computation is a class of problem optimization methodology with the inspiration from the natural evolution of species. In nature, the population of a species evolves by means of selection and variation. These two principles of natural evolution form the fundamental of evolutionary - gorithms (EAs). During the past several decades, EAs have been extensively studied by the computer science and arti?cial intelligence communities. As a classofstochasticoptimizationtechniques,EAscanoftenoutperformclassical optimization techniques for di?cult real world problems. Due to the ease of use and robustness, EAs have been applied to a wide variety of optimization problems. Most of these optimization problems ta- led are stationary and deterministic. However, many real-world optimization problems are subjected to dynamic and uncertain environments that are often impossible to avoid in practice. For example, the ?tness function is uncertain or noisy as a result of simulation errors, measurement errors or approximation errors. In addition, the design variables or environmental conditions may also perturb or change over time. For these dynamic and uncertain optimization problems, the objective of the EA is no longer to simply locate the global optimum solution, but to continuously track the optimum in dynamic en- ronments, or to ?nd a robust solution that operates optimally in the presence of uncertainties. This poses serious challenges to classical optimization te- niques and conventional EAs as well. However, conventional EAs with proper enhancements are still good tools of choice for optimization problems in - namic and uncertain environments.

Evolutionary computation is a class of problem optimization methodology with the inspiration from the natural evolution of species. In nature, the population of a species evolves by means of selection and variation. These two principles of natural evolution form the fundamental of evolutionary - gorithms (EAs). During the past several decades, EAs have been extensively studied by the computer science and arti?cial intelligence communities. As a classofstochasticoptimizationtechniques,EAscanoftenoutperformclassical optimization techniques for di?cult real world problems. Due to the ease of use and robustness, EAs have been applied to a wide variety of optimization problems. Most of these optimization problems ta- led are stationary and deterministic. However, many real-world optimization problems are subjected to dynamic and uncertain environments that are often impossible to avoid in practice. For example, the ?tness function is uncertain or noisy as a result of simulation errors, measurement errors or approximation errors. In addition, the design variables or environmental conditions may also perturb or change over time. For these dynamic and uncertain optimization problems, the objective of the EA is no longer to simply locate the global optimum solution, but to continuously track the optimum in dynamic en- ronments, or to ?nd a robust solution that operates optimally in the presence of uncertainties. This poses serious challenges to classical optimization te- niques and conventional EAs as well. However, conventional EAs with proper enhancements are still good tools of choice for optimization problems in - namic and uncertain environments.

This book compiles recent advances of evolutionary algorithms in dynamic and uncertain environments within a unified framework. The book is motivated by the fact that some degree of uncertainty is inevitable in characterizing any realistic engineering systems. Discussion includes representative methods for addressing major sources of uncertainties in evolutionary computation, including handle of noisy fitness functions, use of approximate fitness functions, search for robust solutions, and tracking moving optimums.

Optimum Tracking in Dynamic Environments.- Explicit Memory Schemes for Evolutionary Algorithms in Dynamic Environments.- Particle Swarm Optimization in Dynamic Environments.- Evolution Strategies in Dynamic Environments.- Orthogonal Dynamic Hill Climbing Algorithm: ODHC.- Genetic Algorithms with Self-Organizing Behaviour in Dynamic Environments.- Learning and Anticipation in Online Dynamic Optimization.- Evolutionary Online Data Mining: An Investigation in a Dynamic Environment.- Adaptive Business Intelligence: Three Case Studies.- Evolutionary Algorithms for Combinatorial Problems in the Uncertain Environment of the Wireless Sensor Networks.- Approximation of Fitness Functions.- Individual-based Management of Meta-models for Evolutionary Optimization with Application to Three-Dimensional Blade Optimization.- Evolutionary Shape Optimization Using Gaussian Processes.- A Study of Techniques to Improve the Efficiency of a Multi-Objective Particle Swarm Optimizer.- An Evolutionary Multi-objective Adaptive Meta-modeling Procedure Using Artificial Neural Networks.- Surrogate Model-Based Optimization Framework: A Case Study in Aerospace Design.- Handling Noisy Fitness Functions.- Hierarchical Evolutionary Algorithms and Noise Compensation via Adaptation.- Evolving Multi Rover Systems in Dynamic and Noisy Environments.- A Memetic Algorithm Using a Trust-Region Derivative-Free Optimization with Quadratic Modelling for Optimization of Expensive and Noisy Black-box Functions.- Genetic Algorithm to Optimize Fitness Function with Sampling Error and its Application to Financial Optimization Problem.- Search for Robust Solutions.- Single/Multi-objective Inverse Robust Evolutionary Design Methodology in the Presence of Uncertainty.- Evolving the Tradeoffs between Pareto-Optimality and Robustness in Multi-Objective Evolutionary Algorithms.- Evolutionary Robust Design of Analog Filters Using Genetic Programming.- Robust Salting Route Optimization Using Evolutionary Algorithms.- An Evolutionary Approach For Robust Layout Synthesis of MEMS.- A Hybrid Approach Based on Evolutionary Strategies and Interval Arithmetic to Perform Robust Designs.- An Evolutionary Approach for Assessing the Degree of Robustness of Solutions to Multi-Objective Models.- Deterministic Robust Optimal Design Based on Standard Crowding Genetic Algorithm.