Deals with the application of evolutionary algorithms to the refueling of pressurized water reactors. We describe the optimization problem in detail and derive an appropriate goal function for the problem. After characterizing how the designers tackle this problem today, we apply an evolutionary algorithm to find promising solutions. Due to the discrete nature of the problem, a special evolutionary algorithm was implemented. This algorithm produces good results, which are already able to compete well with solutions generated by experts based on years of experience. We outline how problem-specific operators can be developed which make the search process more efficient by reducing the number of possible configurations in the search space. Based on investigations regarding the performance of symmetric solutions, the concept of symmetry-preserving operators is presented. Reactor refueling is economically one of the most ambitious problems ever tackled by evolutionary algorithms, since the refueling material of a single power station costs about 100 million US$ per year, and there is a potential for saving several percent of the costs.
[1]
David E. Goldberg,et al.
Genetic Algorithms in Search Optimization and Machine Learning
,
1988
.
[2]
L. Darrell Whitley,et al.
The GENITOR Algorithm and Selection Pressure: Why Rank-Based Allocation of Reproductive Trials is Best
,
1989,
ICGA.
[3]
Thomas Bäck,et al.
A Survey of Evolution Strategies
,
1991,
ICGA.
[4]
Jack Dongarra,et al.
PVM: Parallel virtual machine: a users' guide and tutorial for networked parallel computing
,
1995
.