Planning Heuristics for Efficient Data Movement on the Grid

Computationally challenging experiments such as the STAR at RHIC (Relativistic Heavy Ion Collider [1]) located at the Brookhaven National Laboratory (USA), have developed a distributed computing approach (Grid) to face their massive computational and storage requirements. Since the peta-bytes of data produced by STAR are geographically spread, it is necessary to face the question of efficient data transfers and placements in order to bring requested dataset to a particular site for further analyses. Our aim is to create a plan how to transfer data from data-warehouses to the requested site in the shortest time. The presented approach is based on Constraint Programming with initial modeling idea from [2] further extended in [3]. This paper brings a new search heuristic used during the selection of routes.