Introduction
In 2007, 30 countries were operating a total of 439 commercial nuclear power reactors which contributed about 16% of the world’s total electrical power. With concerns about global warming it is likely that more reactors will be built in the near future.
In this paper we will describe, in general terms, the operation of a commercial nuclear reactor and how this leads to a difficult problem in combinatorial optimisation. We then describe the principles of the Estimation of Distribution Algorithm (EDA) and how we have adapted it to solve a combinatorial problem, it is demonstrated using the travelling salesman problem. Next we explain how the method was modified to solve the nuclear fuel management problem and how heuristic information was incorporated. Finally we examine the performance of the EDA on three test problems for the CONSORT reactor, a small research reactor at Imperial College in London, and show how this compares to the performance of a Genetic Algorithm (GA), which is regarded as the best current optimisation algorithm for this problem[24].
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Avery, R.: Theory of coupled reactors. In: 2nd UN Conference on Peaceful Uses of Atomic Energy, Geneva (1958)
Baker, J.E.: Adaptive selection methods for genetic algorithms. In: Proceedings of the first International Conference on Genetic Algorithms and their Applications, pp. 101–111 (1985)
Baluja, S.: Population-based incremental learning: A method for integrating genetic search based function optimization and competitive learning. CMU-CS-94-163. Carnegie Mellon University, Ottawa (1994)
de Jong, K.A., Spears, W.M.: Using genetic algorithms to solve p-complete problems. In: Proc. of Third Int. Conf. Genetic Algorithms and their Applications, pp. 124–132. Morgan Kaufmann, San Francisco (1989)
Dorigo, M., Gambardella, L.M.: Ant colony system: A cooperative learning approach to traveling salesman problem. IEEE Trans on Evolutionary Computations 1(1), 53–66 (1997)
Erdogan, A., Geckinli, M.: A PWR reload optimisation code (XCORE) using artificial neural networks and genetic algorithms. Annals of Nuclear Energy 30, 35–53 (2003)
EVENT, http://amcg.ese.ic.ac.uk/index.php? title=EVENT Applied Modelling and Computation Group (AMCG), Imperial College
Fox, B.R., McMahon, M.B.: Genetic operators for sequencing problems. In: Foundations of Genetic Algorithms, pp. 284–300. Morgan Kaufmann, San Francisco (1990)
Franklin, S.J., Goddard, A.J.H., O’Connell, J.S.: Research reactor facilities and recent developments at Imperial College, London. In: Research Reactor Fuel Management 1998: European Nuclear Society (1998)
Franklin, S.J., Gardner, D., Mumford, J., Lea, R., Knight, J.: Business operations and decommissioning strategy for Imperial College London research reactor ‘CONSORT’ - a financial risk management approach. In: Research Reactor Fuel Management 2005, European Nuclear Society (2005)
Grefenstette, J., Gopal, R., Rosmaita, B., Van Gucht, D.: Genetic algorithms for the traveling salesman problem. In: Proceedings of the first International Conference on Genetic Algorithms and their Applications, p. 160 (1985)
Harik, G.R., Lobo, F.G., Goldberg, D.E.: The compact genetic algorithm. IEEE Transactions on Evolutionary Computation 3, 287–297 (1999)
Jiang, S.: Nuclear Fuel Management Optimisation Using Estimation of Distribution Algorithms. PhD thesis, Department of Earth Science and Engineering, Imperial College London (2009)
Muhlenbein, H., Paab, G.: From recombination of genes to the estimation of distributions i. In: Ebeling, W., Rechenberg, I., Voigt, H.-M., Schwefel, H.-P. (eds.) PPSN 1996. LNCS, vol. 1141, pp. 178–187. Springer, Heidelberg (1996)
Oliver, I.M., Smith, D.J., Holland, J.R.C.: A study of permutation crossover operators on the travelling salesman problem. In: Proceedings of the 2nd International Conference of Genetic Algorithms and Their Applications, pp. 224–230 (1987)
Poon, P.W.: The Genetic Algorithm Applied to PWR Reload Core Design. PhD thesis, Department of Engineering, University of Cambridge (1992)
Poon, P.W., Carter, J.N.: Genetic algorithm crossover operators for ordering applications. Computers and Operations Research 22(1), 135–147 (1995)
Poon, P.W., Parks, G.T.: Application of genetic algorithms to in-core nuclear fuel management optimization. In: Proc. Joint Int. Conf. Mathematical Methods and Super-computing in Nuclear Applications, vol. 2, pp. 777–786 (1993)
van Geemert, R., Quist, A.J., Hoogenboom, J.E., Gibcus, H.P.M.: Research reactor in-core fuel management optimisation by application of multiple cyclic interchange algorithms. Nuclear Engineering and Design 186, 369–377 (1998)
Whitley, D., Starkweather, T., Fuquay, D.: Scheduling problems and the traveling salesman: the genetic edge recombination operator. In: Proceedings of the Third International Conference on Genetic Algorithms, Arlington, VA, pp. 116–121 (1989)
Zhang, Q.: CC483 Evolutionary Computation: Lecture notes, Department of Computer Science. University of Essex (2003)
Zhang, Q., Sun, J., Tsang, E., Ford, J.: Hybrid estimation of distribution algorithm for global optimisation. Engineering Computations 21(1), 91–107 (2004)
Zhang, Q., Zhou, A., Jin, Y.: RM-MEDA: A regularity model based multiobjective estimation of distribution algorithm. IEEE Trans. on Evolutionary Computation 12(1), 41–63 (2008)
Ziver, A.K., Pain, C.C., Carter, J.N., et al.: Genetic algorithms and artificial neural networks for loading pattern optimisation of advanced gas-cooled reactors. Annals of Nuclear Energy 31, 431–457 (2004); ISSN: 0306-4549
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Jiang, S., Carter, J. (2011). Application of Estimation of Distribution Algorithms for Nuclear Fuel Management. In: Köppen, M., Schaefer, G., Abraham, A. (eds) Intelligent Computational Optimization in Engineering. Studies in Computational Intelligence, vol 366. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21705-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-21705-0_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21704-3
Online ISBN: 978-3-642-21705-0
eBook Packages: EngineeringEngineering (R0)