Natural Computing For Simulation Based Optimization And Beyond

This SpringerBrief bridges the gap between the areas of simulation studies on the one hand, and optimization with natural computing on the other. Since natural computing methods have been applied with great success in several application areas, a review concerning potential benefits and pitfalls for simulation studies is merited. The brief presents such an overview and combines it with an introduction to natural computing and selected major approaches, as well as with a concise treatment of general simulation-based optimization. As such, it is the first review which covers both the methodological background and recent application cases. The brief is intended to serve two purposes: First, it can be used to gain more information concerning natural computing, its major dialects, and their usage for simulation studies. It also covers the areas of multi-objective optimization and neuroevolution. While the latter is only seldom mentioned in connection with simulation studies, it is a powerful potential technique. Second, the reader is provided with an overview of several areas of simulation-based optimization which range from logistic problems to engineering tasks. Additionally, the brief focuses on the usage of surrogate and meta-models. The brief presents recent application examples.

This book presents the state of the art in designing high-performance algorithms that combine simulation and optimization in order to solve complex optimization problems in science and industry, problems that involve time-consuming simulations and expensive multi-objective function evaluations. As traditional optimization approaches are not applicable per se, combinations of computational intelligence, machine learning, and high-performance computing methods are popular solutions. But finding a suitable method is a challenging task, because numerous approaches have been proposed in this highly dynamic field of research. That’s where this book comes in: It covers both theory and practice, drawing on the real-world insights gained by the contributing authors, all of whom are leading researchers. Given its scope, if offers a comprehensive reference guide for researchers, practitioners, and advanced-level students interested in using computational intelligence and machine learning to solve expensive optimization problems.

Simulation-Based Optimization: Parametric Optimization Techniques and Reinforcement Learning introduce the evolving area of static and dynamic simulation-based optimization. Covered in detail are model-free optimization techniques – especially designed for those discrete-event, stochastic systems which can be simulated but whose analytical models are difficult to find in closed mathematical forms. Key features of this revised and improved Second Edition include: · Extensive coverage, via step-by-step recipes, of powerful new algorithms for static simulation optimization, including simultaneous perturbation, backtracking adaptive search and nested partitions, in addition to traditional methods, such as response surfaces, Nelder-Mead search and meta-heuristics (simulated annealing, tabu search, and genetic algorithms) · Detailed coverage of the Bellman equation framework for Markov Decision Processes (MDPs), along with dynamic programming (value and policy iteration) for discounted, average, and total reward performance metrics · An in-depth consideration of dynamic simulation optimization via temporal differences and Reinforcement Learning: Q-Learning, SARSA, and R-SMART algorithms, and policy search, via API, Q-P-Learning, actor-critics, and learning automata · A special examination of neural-network-based function approximation for Reinforcement Learning, semi-Markov decision processes (SMDPs), finite-horizon problems, two time scales, case studies for industrial tasks, computer codes (placed online) and convergence proofs, via Banach fixed point theory and Ordinary Differential Equations Themed around three areas in separate sets of chapters – Static Simulation Optimization, Reinforcement Learning and Convergence Analysis – this book is written for researchers and students in the fields of engineering (industrial, systems, electrical and computer), operations research, computer science and applied mathematics.

The book provides readers with a snapshot of the state of the art in the field of nature-inspired computing and its application in optimization. The approach is mainly practice-oriented: each bio-inspired technique or algorithm is introduced together with one of its possible applications. Applications cover a wide range of real-world optimization problems: from feature selection and image enhancement to scheduling and dynamic resource management, from wireless sensor networks and wiring network diagnosis to sports training planning and gene expression, from topology control and morphological filters to nutritional meal design and antenna array design. There are a few theoretical chapters comparing different existing techniques, exploring the advantages of nature-inspired computing over other methods, and investigating the mixing time of genetic algorithms. The book also introduces a wide range of algorithms, including the ant colony optimization, the bat algorithm, genetic algorithms, the collision-based optimization algorithm, the flower pollination algorithm, multi-agent systems and particle swarm optimization. This timely book is intended as a practice-oriented reference guide for students, researchers and professionals.

This book presents a cutting-edge research procedure in the Nature-Inspired Computing (NIC) domain and its connections with computational intelligence areas in real-world engineering applications. It introduces readers to a broad range of algorithms, such as genetic algorithms, particle swarm optimization, the firefly algorithm, flower pollination algorithm, collision-based optimization algorithm, bat algorithm, ant colony optimization, and multi-agent systems. In turn, it provides an overview of meta-heuristic algorithms, comparing the advantages and disadvantages of each. Moreover, the book provides a brief outline of the integration of nature-inspired computing techniques and various computational intelligence paradigms, and highlights nature-inspired computing techniques in a range of applications, including: evolutionary robotics, sports training planning, assessment of water distribution systems, flood simulation and forecasting, traffic control, gene expression analysis, antenna array design, and scheduling/dynamic resource management.

Nature has long provided the inspiration for a variety of scientific discoveries in engineering, biomedicine, and computing, though only recently have these elements of nature been used directly in computational systems. Natural Computing for Simulation and Knowledge Discovery investigates the latest developments in nature-influenced technologies. Within its pages, readers will find an in-depth analysis of such advances as cryptographic solutions based on cell division, the creation and manipulation of biological computers, and particle swarm optimization techniques. Scientists, practitioners, and students in fields such as computing, mathematics, and molecular science will make use of this essential reference to explore current trends in natural computation and advance nature-inspired technologies to the next generation.

This textbook provides a comprehensive introduction to nature-inspired metaheuristic methods for search and optimization, including the latest trends in evolutionary algorithms and other forms of natural computing. Over 100 different types of these methods are discussed in detail. The authors emphasize non-standard optimization problems and utilize a natural approach to the topic, moving from basic notions to more complex ones. An introductory chapter covers the necessary biological and mathematical backgrounds for understanding the main material. Subsequent chapters then explore almost all of the major metaheuristics for search and optimization created based on natural phenomena, including simulated annealing, recurrent neural networks, genetic algorithms and genetic programming, differential evolution, memetic algorithms, particle swarm optimization, artificial immune systems, ant colony optimization, tabu search and scatter search, bee and bacteria foraging algorithms, harmony search, biomolecular computing, quantum computing, and many others. General topics on dynamic, multimodal, constrained, and multiobjective optimizations are also described. Each chapter includes detailed flowcharts that illustrate specific algorithms and exercises that reinforce important topics. Introduced in the appendix are some benchmarks for the evaluation of metaheuristics. Search and Optimization by Metaheuristics is intended primarily as a textbook for graduate and advanced undergraduate students specializing in engineering and computer science. It will also serve as a valuable resource for scientists and researchers working in these areas, as well as those who are interested in search and optimization methods.

Simulation-Based Optimization: Parametric Optimization Techniques and Reinforcement Learning introduces the evolving area of simulation-based optimization. The book's objective is two-fold: (1) It examines the mathematical governing principles of simulation-based optimization, thereby providing the reader with the ability to model relevant real-life problems using these techniques. (2) It outlines the computational technology underlying these methods. Taken together these two aspects demonstrate that the mathematical and computational methods discussed in this book do work. Broadly speaking, the book has two parts: (1) parametric (static) optimization and (2) control (dynamic) optimization. Some of the book's special features are: *An accessible introduction to reinforcement learning and parametric-optimization techniques. *A step-by-step description of several algorithms of simulation-based optimization. *A clear and simple introduction to the methodology of neural networks. *A gentle introduction to convergence analysis of some of the methods enumerated above. *Computer programs for many algorithms of simulation-based optimization.