A strategy in evolutionary algorithms where the best one or more solutions, called the elites, in each generation, are inserted into the next, without undergoing any change. This strategy usually speeds up the convergence of the algorithm. In a multi-objective framework, any non-dominated solution can be considered to be an elite
Published in Chapter:
Multi-Objective Evolutionary Algorithms
Sanjoy Das (Kansas State University, USA) and Bijaya K. Panigrahi (Indian Institute of Technology, India)
Copyright: © 2009
|Pages: 7
DOI: 10.4018/978-1-59904-849-9.ch167
Abstract
Real world optimization problems are often too complex to be solved through analytical means. Evolutionary algorithms, a class of algorithms that borrow paradigms from nature, are particularly well suited to address such problems. These algorithms are stochastic methods of optimization that have become immensely popular recently, because they are derivative-free methods, are not as prone to getting trapped in local minima (as they are population based), and are shown to work well for many complex optimization problems. Although evolutionary algorithms have conventionally focussed on optimizing single objective functions, most practical problems in engineering are inherently multi-objective in nature. Multi-objective evolutionary optimization is a relatively new, and rapidly expanding area of research in evolutionary computation that looks at ways to address these problems. In this chapter, we provide an overview of some of the most significant issues in multi-objective optimization (Deb, 2001).