A Discrete Optimization Method for Nuclear Fuel Management

Abstract

Nuclear fuel management can be seen as a large discrete optimization problem under constraints. and optimization methods on such problems are numerically costly. After an introduction of the main aspects of nuclear fuel management, this paper presents a new way to treat the combinatiorial problem by using information included in the gradient of optimized cost function. New search process ideas is to choose, by direct observation of the gradient, the more interesting changes in fuel loading patterns. An example is then developed to illustrate an operating mode of the method. Finally, connections with classical simulated annealing and genetic algorithms are described as an attempt to improve search processes.