Condor-G: A Computation Management Agent for Multi-Institutional Grids
Cluster Computing
Adaptive Computing on the Grid Using AppLeS
IEEE Transactions on Parallel and Distributed Systems
A framework for adaptive execution in grids
Software—Practice & Experience
Hi-index | 0.00 |
In this paper, we consider the resource management problem in geographically-distributed computer systems. Decentralized scheduling algorithms are proposed: locally optimal algorithm (LOS), algorithm with the job replication (RS), algorithm with the job migration (MS) and algorithm based on the combined approach (MRS). The algorithms were investigated on the multicluster computer system. We also compare efficiency of decentralized scheduler GBroker with centralized scheduler GridWay.