W. Süss, W. Jakob, A. Quinte, and K.-U. Stucky (Germany)
Grid Computing, Resource Broker, Evolutionary Algorithms, Optimisation.
The subject of this paper is the resource management for a grid system that is primarily intended to support computationally expensive tasks like simulations and optimisations on a grid. Applications are represented as workflows that can be decomposed into single grid jobs. These jobs require resources from the grid that are described as accurately as necessary. The main task of the resource management is resource brokering to optimise a global schedule for all requesting grid jobs and all requested resources. Consequently, a global optimising resource broker (GORBA) is proposed that deploys Evolutionary Algorithms (EA). The paper focuses on the architecture of GORBA, its embedding in the application and resource management system, and on important implementation decisions. The performance of the optimisation method is demonstrated by an example from related fields.
Important Links:
Go Back
