User preference driven multiobjective resource management in grid environments

Scientific and other grand challenge applications are a driving force for developing the computing infrastructure of the future. Their constantly increasing computational power requirements often cannot be met by available systems (F. Gagliardi, 2000). Such a situation has led to the emergence of new platform called "Computational Grid" (I. Foster and C. Kesselman, 1999). It seems very important to identify common and reusable components that are needed and can be used in a computational grid by different applications. Such components could be the Grid information services, security mechanisms, resource management, large data set management, etc. The paper sketches the issues of one of the most important components of the grid: the resource management and scheduling component. We present our work on a multiobjective resource management system. The novelty of the approach lies in its multiobjective nature. We present the Multi-Criteria Resource Broker (MC-Broker), whose scheduling mechanisms are driven by user preferences regarding various scheduling criteria, such as computation time and cost, communication time between distributed processes, level of load balancing and others.