Clonal Selection Approach with Mutations Based on Symmetric alpha -Stable Distributions for Non-stationary Optimization Tasks

Efficiency of two mutation operators applied in a clonalselection based optimization algorithm AIIA for non-stationarytasks is investigated. In both operators traditional Gaussianrandom number generator was exchanged by α-stablerandom number generator and thus αbecame one of theparameters of the algorithm. Obtained results showed thatappropriate tuning of the αparameter allows tooutperform the results of algorithms with the traditionaloperators.

[1]  R.W. Morrison,et al.  A test problem generator for non-stationary environments , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[2]  L.N. de Castro,et al.  An artificial immune network for multimodal function optimization , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[3]  S. Wierzchon.  FUNCTION OPTIMIZATION BY THE IMMUNE METAPHOR , 2002 .

[4]  Jürgen Branke,et al.  Memory enhanced evolutionary algorithms for changing optimization problems , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[5]  Krzysztof Trojanowski,et al.  Clonal selection principle based approach to non-stationary optimization tasks , 2006 .

[6]  Xin Yao,et al.  Evolutionary programming using mutations based on the Levy probability distribution , 2004, IEEE Transactions on Evolutionary Computation.

[7]  Krzysztof Trojanowski,et al.  Studying Properties of Multipopulation Heuristic Approach to Non-Stationary Optimisation Tasks , 2003, IIS.

[8]  Zbigniew Michalewicz,et al.  Searching for optima in non-stationary environments , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[9]  Andrzej Obuchowicz,et al.  Phenotypic evolution with a mutation based on symmetric α-stable distributions , 2004 .