0137 a 397 0105 a 167 a 163 a 159 0149 0113 a 171 A

| This paper deals with the application of evolutionary algorithms to 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 nd promising solutions. Due of 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 the experience of years. It is outlined in the paper, how problem speciic operators can be developed which make the search process more eecient by reducing the number of possible conngurations in the search space. Based on investigations regarding the performance of symmetric solutions, the concept of symmetry preserving operators is presented in the paper. As far as we know reactor refueling is one of the economically 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 of saving several percent of the costs.