Evolutionary Multi-objective Ranking with Uncertainty and Noise
Real engineering optimisation problems are often subject to parameters whose values are uncertain or have noisy objective functions. Techniques such as adding small amounts of noise in order to identify robust solutions are also used. The process used in evolutionary algorithms to decide which solutions are better than others do not account for these uncertainties and rely on the inherent robustness of the evolutionary approach in order to find solutions. In this paper, the ranking process needed to provide probabilities of selection is re-formulated to begin to account for the uncertainties and noise present in the system being optimised. Both single and multi-objective systems are considered for rank-based evolutionary algorithms. The technique is shown to be effective in reducing the disturbances to the evolutionary algorithm caused by noise in the objective function, and provides a simple mathematical basis for describing the ranking and selection process of multi-objective and uncertain data.
KeywordsEvolutionary Algorithm Rank Position Multiobjective Evolutionary Algorithm Ranking Process Ranking Equation
Unable to display preview. Download preview PDF.
- 1.T. W. Then and Edwin K. Chong. Genetic algorithms in noisy environment. In IEEE International Symposium on Intelligent Control, pages 225–230, Columbus, Ohio, 16-18 August 1994.Google Scholar
- 2.Adrian Thompson. Evolutionary techniques for fault tolerance. In Control’ 96, UKACC International Conference on, volume 1, pages 693-698. IEE, 2-5 September 1996. Conf. Publ. No. 427.Google Scholar
- 3.T. Bäck and U. Hammel. Evolution strategies applied to perturbed objective functions. In IEEE World Congress on Computational Intelligence, volume 1, pages 40–45. IEEE, 1994.Google Scholar
- 4.Shigeyoshi Tsutsui and Ashish Ghosh. Genetic algorithms with a robust searching scheme. IEEE Transactions on Evolutionary Computation, 1(3): 201–8, September 1997.Google Scholar
- 5.Kumar Chellapilla and David B. Fogel. Anaconda defeats hoyle 6-0: A case study competing an evolved checkers program against commercially available software. In Congress on Evolution Computation-CEC2000, volume 1, pages 857–863, SanDiego, CA, 16-19 July 2000. IEEE.Google Scholar
- 6.Carlos A. Coello Coello. List of references on evolutionary multiobjective optimization. http://www.lania.mx/ ~ ccoello/EMOO/EMOObib.html. Last accessed 3 July 2000.
- 7.Anna L. Blumel, Evan J. Hughes, and Brian A. White. Fuzzy autopilot design using a multiobjective evolutionary algorithm. In Congress on Evolution Computation-CEC2000, volume 1, pages 54–61, San Diego, CA, 16-19 July 2000. IEEE.Google Scholar
- 8.Carlos M. Fonseca and Peter J. Flemming. Multiobjective genetic algorithms made easy: Selection, sharing and mating restriction. In GALESIA 95, pages 45–52, 12-14 September 1995. IEE Conf. Pub. No. 414.Google Scholar
- 10.David A. Van Veldhuizen and Gary B. Lamont. Multiobjective evolutionary algorithm research: A history and analysis. Technical Report TR–98–03, Air Force Institute of Technology, 1 Dec 1998.Google Scholar
- 11.William H. Press, Brian P. Flannery, Saul A. Teukolsky, and William T. Vetterling. NUMERICAL RECIPES in C. The Art Of Scientific Computing. Cambridge University Press, second edition, 1993.Google Scholar
- 12.Evan J. Hughes. Multi-objective probabilistic selection evolutionary algorithm. Technical Report DAPS/EJH/56/2000, Dept. Aerospace, Power, & Sensors, Cranfield University, RMCS, Shrivenham, UK, SN6 8LA, September 2000.Google Scholar
- 13.J. E. Baker. Adaptive selection methods for genetic algorithms. In Proc. 1st Int. conf. on Genetic Algorithms, pages 101–111, 1985.Google Scholar