Akademik Veri Yönetim Sistemi
EURO-PAR 2004 PARALLEL PROCESSING, PROCEEDINGS, cilt.3149, ss.468-475, 2004 (SCI-Expanded)
Efficient data scheduling in Grid environments is becoming a seemingly important issue for distributed real-time applications that produce and process huge datasets. Thus, in this paper, we consider the data scheduling problem so as to provide reliable dissemination of large-scale datasets for the distributed real-time applications. We propose a new path selection-based algorithm for optimizing a criterion that reflects the general satisfiability of the system. The algorithm adopts a blocking-time analysis method combined with a simple heuristic (LCSP or SLCP). The simulation results show that our algorithm outperforms the algorithms existing in the literature.