An enhanced workflow management for Utility Management Systems

The emerging computational grid infrastructure consists of widely distributed heterogeneous resources, which makes mapping of increasingly complex applications a very challenging task. Utility Management Systems (UMS) manage large number of workflows with high resource requirements and thereby optimization of resource utilization has to be adapted. In this work we propose the architecture that implements a novel concept for dynamical execution of a scheduling algorithm using near real-time feedback from the execution monitoring process. An Artificial Neural Network (ANN) was trained for workflow scheduling. In the case study, we first perform experiments with same number of workflows and then introduce two additional in the system observing its´ behavior with and without proposed improvements. Performance tests show that significant improvements of overall execution time can be achieved by introducing adaptive Artificial Neural Network.