On learning assistance systems for numerical simulation

The work we present deals with the problem to provide learning assistance systems in the context of simulation and modelling. We develop a classification scheme for learning assistance systems and their use cases. Beyond this, we discuss how learning from simulation data differs from traditional knowledge discovery from data bases. The discussion contains a classification and review of existing approaches followed by an enclosing case study of an assistance system for load balancing purpose in FEM simulation. The presented application case uses a two-stage architecture to minimize additional computational costs. The approach does not require labeled data in the sense of a quality rating for a load distribution nor a teacher for the initial setup and can improve itself unsupervised. For the FEM simulation on heterogeneous distributed systems we introduce a novel feature set and perform an evaluation for several problem sets.