Grid computing could be the future computing paradigm for enterprise applications, one of its benefits being that it

can be used for executing large scale applications. Utility Management Systems execute very large numbers of

workflows with very high resource requirements. This paper proposes architecture for a new scheduling mechanism

that dynamically executes a scheduling algorithm using feedback about the current status Grid nodes. Two

Artificial Neural Networks were created in order to solve the scheduling problem. A case study is created for the

Meter Data Management system with measurements from the Smart Metering system for the city of Novi Sad,

Serbia. Performance tests show that significant improvement of overall execution time can be achieved by

Hierarchical Artificial Neural Networks.