| | |
Summary: 1
Niching Evolution Strategy with Cluster Algorithms
O. Aichholzer, F. Aurenhammer, B. Brandstšatter, T. Ebner, H. Krasser, Ch. Magele
Abstract--- In most real world optimization problems one
tries to determine the global among some or even numer
ous local solutions within the feasible region of parameters.
One the other hand, it could be worth to investigate some
of the local solutions as well. Therefore, a most desirable
behaviour would be, if the optimization strategy behaves
globally and yields additional information about local min
ima detected on the way to the global solution. In this paper
a clustering algorithm has been implemented into an Higher
Order Evolution Strategy in order to achieve these goals.
Keywords---Stochastic Optimization, Evolution Strategies,
Clustering Methods
I. Introduction
Stochastic optimization methods can be successfully ap
plied to problems, where there is no or very little knowl
edge about the behaviour of the objective function, about
the presence of local minima or the distribution of feasi
|
