Advanced Methods for Evolutionary Optimisation

Abstract In this paper we present two advanced methods for evolutionary optimisation. One method is based on Parallel Genetic Algorithms. It is called Cooperating Populations with Different Evolution Behaviours (CoPDEB), and allows each population to exhibit a different evolution behaviour. Results from two problems show the advantage of using different evolution behaviour on each population. The other method concerns application of GAs on constrained optimisation problems. It is called the Varying Fitness Function (VFF) method and implements a fitness function with varying penalty tenns, added to the objective function for penalising infeasible solutions, in order to assist the GA to easily locate the area of the global optimum. Simulation results on two real world problems show that the VFF method outperfonns the classic static fitness function implementations.

[1]  Heinz Mühlenbein,et al.  The parallel genetic algorithm as function optimizer , 1991, Parallel Comput..

[2]  Lawrence Davis,et al.  Using a genetic algorithm to optimize problems with feasibility constraints , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[3]  Lawrence. Davis,et al.  Handbook Of Genetic Algorithms , 1990 .

[4]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[5]  Christopher R. Houck,et al.  On the use of non-stationary penalty functions to solve nonlinear constrained optimization problems with GA's , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[6]  Jack Sklansky,et al.  Constrained Genetic Optimization via Dynamic Reward-penalty Balancing and its Use in Pattern Recognition , 1993, Handbook of Pattern Recognition and Computer Vision.

[7]  Vassilios Petridis,et al.  Co-operating Populations with Different Evolution Behaviours , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[8]  Vassilios Petridis,et al.  Varying fitness functions in genetic algorithm constrained optimization: the cutting stock and unit commitment problems , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[9]  Allen J. Wood,et al.  Power Generation, Operation, and Control , 1984 .

[10]  V. Petridis,et al.  Recurrent neural networks as pattern generators , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[11]  Theodore C. Belding,et al.  The Distributed Genetic Algorithm Revisited , 1995, ICGA.

[12]  A. Papaikonomou,et al.  A genetic algorithm for training recurrent neural networks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[13]  Vassilios Petridis,et al.  Varying quality function in genetic algorithms and the cutting problem , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[14]  Z. Michalewicz,et al.  Genocop III: a co-evolutionary algorithm for numerical optimization problems with nonlinear constraints , 1995, Proceedings of 1995 IEEE International Conference on Evolutionary Computation.

[15]  Anastasios G. Bakirtzis,et al.  Genetic algorithm solution to the economic dispatch problem , 1994 .

[16]  Alice E. Smith,et al.  Genetic Optimization Using A Penalty Function , 1993, ICGA.

[17]  Ron Shonkwiler,et al.  Parallel Genetic Algorithms , 1993, ICGA.

[18]  Joachim Stender,et al.  Parallel Genetic Algorithms: Introduction and Overview of Current Research , 1993 .

[19]  Schloss Birlinghoven.  Evolution in Time and Space -the Parallel Genetic Algorithm , 1991 .