Evolutionary computation and grid computing to optimise nuclear fusion devices

Abstract

Nuclear fusion is the next generation of energy, but many problems are still present in current nuclear fusion devices. Some of these problems can be solved by means of modeling tools. These tools usually require a large time to finish their computations and they also use a large number of parameters to represent the behaviour of nuclear fusion devices. Here, the possibility to introduce evolutionary algorithms (EAs) like genetic algorithms (GAs) or Scatter Search (SS) to look for optimised configurations offers a great solution for some of these problems. Since these applications require a high computational cost to perform their operations, the use of the grid arises as an ideal environment to carry out these tests. Because of the high complexity of the problems we are trying to optimise, the distributed paradigm as well as the number of computational resources of the grid represents an excellent alternative to carry out experiments to modelize and improve nuclear fusion devices by executing these tools. The results obtained clearly improve the configuration of existing devices.