Textbook in PDF format

This book addresses and disseminates state-of-the-art research and development of differential evolution (DE) and its recent advances, such as the development of adaptive, self-adaptive and hybrid techniques. Differential evolution is a population-based meta-heuristic technique for global optimization capable of handling non-differentiable, non-linear and multi-modal objective functions. Many advances have been made recently in differential evolution, from theory to applications. This book comprises contributions which include theoretical developments in DE, performance comparisons of DE, hybrid DE approaches, parallel and distributed DE for multi-objective optimization, software implementations, and real-world applications. The book is useful for researchers, practitioners, and students in disciplines such as optimization, heuristics, operations research and natural computing.
We hope the chapters presented will inspire future research both from theoretical and practical viewpoints to spur further advances in the field. A brief introduction to each chapter is as follows.
Chapter “Analysis of Structural Bias in Differential Evolution Configurations” deals with structural bias which is a form of bias where artifacts in the algorithm lead to a preference to particular regions in the search space regardless of the objective function. In this chapter, authors systematically evaluate 10980 differential evolution configurations on structural bias, identify the configurations which causes bias, and analyze the results to make clear recommendations on which configurations to use.
Chapter “Spherical Model of Population Dynamics in Differential Evolution” discusses about the population dynamics models of differential evolution (DE). Selection in DE is challenging for analytical modeling due to its greedy character. Symmetries of the spherical function allow for approximating it utilizing a moment generating function of a minimum of two normally distributed random variables. This chapter describes the expected population diversity change in a complete iteration of DE.
Chapter “Reinforcement Learning-Based Differential Evolution for Global Optimization” proposes a reinforcement learning differential evolution where the reinforcement learning mechanism selects among the strategies incorporated from the original L-SHADE algorithm using the “DE/current-to-pbest/1/bin” mutation strategy toward the iL-SHADE to jSO using the “DE/current-to-pbest-w/1/bin” mutation strategies.
Chapter “Applications and Performance of Fuzzy Differential Evolution (DEFIS) in CFD Modeling of Heat and Mass Transfer” presents the artificial intelligence (AI) learning techniques for soft computing and data optimization generated by the computational fluid dynamics (CFD) approach for modeling fluid dynamic and heat transfer phenomenon. For this purpose, the applications and performance of a hybrid algorithm of differential evolution and fuzzy inference system (DEFIS) are explained