A Fitness Landscape View on the Tuning of an Asynchronous Master-Worker EA for Nuclear Reactor Design

  • Mathieu Muniglia
  • Sébastien Verel
  • Jean-Charles Le Pallec
  • Jean-Michel Do
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10764)

Abstract

In the context of the introduction of intermittent renewable energies, we propose to optimize the main variables of the control rods of a nuclear power plant to improve its capability to load-follow. The design problem is a black-box combinatorial optimization problem with expensive evaluation based on a multi-physics simulator. Therefore, we use a parallel asynchronous master-worker Evolutionary Algorithm scaling up to thousand computing units. One main issue is the tuning of the algorithm parameters. A fitness landscape analysis is conducted on this expensive real-world problem to show that it would be possible to tune the mutation parameters according to the low-cost estimation of the fitness landscape features.

References

  1. 1.
    Alba, E., Tomassini, M.: Parallelism and evolutionary algorithms. IEEE Trans. Evol. Comput. 6(5), 443–462 (2002)CrossRefGoogle Scholar
  2. 2.
    Arnaud, G., Do, J.-M., Lautard, J.-J., Baudron, A.-M., Douce, S.: Selection combinatory algorithm for loading pattern design of light water reactor with two levels of heterogeneity. In: Proceedings of ICAPP (2011)Google Scholar
  3. 3.
    Daolio, F., Liefooghe, A., Verel, S., Aguirre, H., Tanaka, K.: Problem features vs. algorithm performance on rugged multi-objective combinatorial fitness landscapes. Evolutionary Computation (2016)Google Scholar
  4. 4.
    de Moura Meneses, A.A., Gambardella, L.M., Schirru, R.: A new approach for heuristics-guided search in the in-core fuel management optimization. Prog. Nucl. Energy 52, 339–351 (2010)CrossRefGoogle Scholar
  5. 5.
    Dubreuil, M., Gagne, C., Parizeau, M.: Analysis of a master-slave architecture for distributed evolutionary computations. IEEE Trans. Syst. Man Cybern. Part B 36, 229–235 (2006)CrossRefMATHGoogle Scholar
  6. 6.
    Dumont, O.: Ademe energie 2030: production d’énergies renouvelables. Technical report, Ademe (2012)Google Scholar
  7. 7.
    Eiben, A.E., Michalewicz, Z., Schoenauer, M., Smith, J.E.: Parameter control in evolutionary algorithms. In: Lobo, F.G., Lima, C.F., Michalewicz, Z. (eds.) Parameter Setting in Evolutionary Algorithms. SCI, vol. 54, pp. 19–46. Springer, Heidelberg (2007).  https://doi.org/10.1007/978-3-540-69432-8_2 CrossRefGoogle Scholar
  8. 8.
    Grard, H.: Physique, fonctionnement et sûreté des REP. EDP Sciences (2014)Google Scholar
  9. 9.
    Hordijk, W.: A measure of landscapes. Evol. Comput. 4(4), 335–360 (1996)CrossRefGoogle Scholar
  10. 10.
    Kim, J.H., Park, S.H., Na, M.G.: Design of a model predictive load-following controller by discrete optimization of control rod speed for PWRs. Ann. Nucl. Energy 71, 343–351 (2014)CrossRefGoogle Scholar
  11. 11.
    Liefooghe, A., Derbel, B., Verel, S., Aguirre, H., Tanaka, K.: Towards landscape-aware automatic algorithm configuration: preliminary experiments on neutral and rugged landscapes. In: Hu, B., López-Ibáñez, M. (eds.) EvoCOP 2017. LNCS, vol. 10197, pp. 215–232. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-55453-2_15 CrossRefGoogle Scholar
  12. 12.
    Lokhov, A.: Technical and economic aspect of load following with nuclear power plants. In: Nuclear Energy Agency. OECD, June 2011Google Scholar
  13. 13.
    López-Ibáñez, M., Dubois-Lacoste, J., Stützle, T., Birattari, M.: The Rpackageirace package, iterated race for automatic algorithm configuration. Technical Report TR/IRIDIA/2011-004, IRIDIA, Université Libre de Bruxelles (2011)Google Scholar
  14. 14.
    Muniglia, M., Do, J.-M., Le Pallec, J.-C., Grard, H., Verel, S.V., David, S.: A multi-physics PWR model for the load following. In: ICAPP (2016)Google Scholar
  15. 15.
    Na, M.G., Hwang, I.J., Lee, Y.J.: Design of a fuzzy model predictive power controller for pressurized water reactors. IEEE Trans. Nucl. Sci. 53(3), 1504–1514 (2006)CrossRefGoogle Scholar
  16. 16.
    Pereira, C.M., Lapa, C.M.: Coarse-grained parallel genetic algorithm applied to a nuclear reactor core design optimization problem. Ann. Nucl. Energy 30, 555–565 (2003)CrossRefGoogle Scholar
  17. 17.
    Rice, J.R.: The algorithm selection problem. Adv. Comput. 15, 65–118 (1976)CrossRefGoogle Scholar
  18. 18.
    Sacco, W.F., De Oliveira, C.R., Pereira, C.M.: Two stochastic optimization algorithms applied to nuclear reactor core design. Prog. Nucl. Energy 48, 525–539 (2006)CrossRefGoogle Scholar
  19. 19.
    Sacco, W.F., Lapa, C.M., Pereira, C.M., Filho, H.A.: A metropolis algorithm applied to a nuclear power plant auxiliary feedwater system surveillance tests policy optimization. Prog. Nucl. Energy 50, 15–21 (2008)CrossRefGoogle Scholar
  20. 20.
    Schneider, D., Dolci, F., Gabriel, F., Palau, J.-M.: Apollo3\(^{\textregistered }\): CEA/DEN deterministic multi-purpose code for reactor physics analysis. In: PHYSOR (2016)Google Scholar
  21. 21.
    Stadler, P.F.: Fitness landscapes. In: Lässig, M., Valleriani, A. (eds.) Biological Evolution and Statistical Physics. LNP, vol. 585, pp. 183–204. Springer, Heidelberg (2002).  https://doi.org/10.1007/3-540-45692-9_10 CrossRefGoogle Scholar
  22. 22.
    Vanneschi, L., Tomassini, M., Collard, P., Vérel, S., Pirola, Y., Mauri, G.: A comprehensive view of fitness landscapes with neutrality and fitness clouds. In: Ebner, M., O’Neill, M., Ekárt, A., Vanneschi, L., Esparcia-Alcázar, A.I. (eds.) EuroGP 2007. LNCS, vol. 4445, pp. 241–250. Springer, Heidelberg (2007).  https://doi.org/10.1007/978-3-540-71605-1_22 CrossRefGoogle Scholar
  23. 23.
    Weinberger, E.D.: Local properties of Kauffman’s NK model, a tuneably rugged energy landscape. Phys. Rev. A 44, 6399–6413 (1991)CrossRefGoogle Scholar
  24. 24.
    Wessing, S., Rudolph, G., Menges, D.A.: Comparing asynchronous and synchronous parallelization of the SMS-EMOA. In: Handl, J., Hart, E., Lewis, P.R., López-Ibáñez, M., Ochoa, G., Paechter, B. (eds.) PPSN 2016. LNCS, vol. 9921, pp. 558–567. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-45823-6_52 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Mathieu Muniglia
    • 1
  • Sébastien Verel
    • 2
  • Jean-Charles Le Pallec
    • 1
  • Jean-Michel Do
    • 1
  1. 1.CEA (french Commissariat à l’Energie Atomique)Gif-sur-YvetteFrance
  2. 2.Université du Littoral Côte d’Opale, LISICCalaisFrance

Personalised recommendations