Massive asynchronous master-worker EA for nuclear reactor optimization: a fitness landscape perspective - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Massive asynchronous master-worker EA for nuclear reactor optimization: a fitness landscape perspective

Résumé

In the global goal to increase the part of the intermittent renewable energies in the French energy mix, the production of nuclear energy has to be adapted to face the power variations. We propose to optimize the main parameters of the control rods of a nuclear power plant to improve its management, and increase the safety margins in case of a more heckled load-following schedule due to intermittent renewable energies. Using a multi-physics simulator, the criteria of interest can be computed in few minutes of computation, and we are thus facing a black-box combinatorial optimization problem with expensive evaluation. To solve it, we propose a parallel asynchronous master-worker (1+lambda)-evolutionary algorithm scaling up to thousand computing units. From a practical optimization point of view, one main difficulty is the tuning of algorithm parameters such as mutation. In this work, we perform a fitness landscape analysis on this expensive real-world problem, and show that it is possible to tune the mutation parameters according to the low-cost estimation of the fitness landscape structure. Surprisingly, we show that for a large scale computing environment, the mutation parameters associated to the most rugged landscape are relevant, contrary to a typical recommendation for sequential algorithms.
Fichier principal
Vignette du fichier
poster-gecco2017-hal2.pdf (689.16 Ko) Télécharger le fichier
Loading...

Dates et versions

hal-01496392 , version 1 (27-12-2017)

Identifiants

Citer

Mathieu Muniglia, Sébastien Verel, Le Pallec Jean-Charles, Jean-Michel Do. Massive asynchronous master-worker EA for nuclear reactor optimization: a fitness landscape perspective. Genetic and Evolutionary Computation Conference (GECCO 2017), Jul 2017, Berlin, Germany. pp.295-296, ⟨10.1145/3067695.3076061⟩. ⟨hal-01496392⟩
92 Consultations
102 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More