Evolutionary computation: practical issues

Evolutionary computation techniques, which are based on a powerful principle of evolution: survival of the fittest, constitute an interesting category of heuristic search. These stochastic algorithms whose search methods model some natural phenomena: genetic inheritance and Darwinian strife for survival, have been applied to a large number of hard, real-world problems from a variety of domains: social systems, machine learning, operations research, ecology, engineering, immune systems, economics, management, etc. Any evolutionary algorithm applied to a particular problem must address the issue of genetic representation of solutions to the problem and genetic operators that would alter the genetic composition of offspring during the reproduction process. Additional heuristics should be incorporated in the algorithm as well; some of these heuristic rules provide guidelines for initializing the population of potential solutions, for setting various parameters of the system (e.g., population size, probabilities of operators, etc.) and for evaluating individuals in the population. This paper discusses some practical issues connected with applications of evolutionary techniques