The "molecular" traveling salesman

Abstract

We consider a method for optimization of NP-problems motivated by natural evolution. The basic entity is a population of individuals searching in state space defined by the problem. A message exchange mechanism between individuals enables the system to proceed fast and to avoid local optima. We introduce the concept of isolated evolution to maintain a certain degree of variance in the population. The global optimum can be approached to an arbitrary degree. The method is applied to the TSP and its behavior is shown in a couple of simulations. © 1990 Springer-Verlag.