Bandwidth Allocation for Iterative Data-Dependent E-science Applications

Abstract

We develop a novel framework for supporting e-Science applications that require streaming of information between sites. Using a Synchronous Dataflow (SDF) model, our framework incorporates the communication times inherent in large scale distributed applications, and can be used to formulate the bandwidth allocation problem with throughput constraints as a multi-commodity linear programming problem. Our algorithms determine how much bandwidth is allocated to each edge while satisfying temporal constraints on collaborative tasks. Simulation results show that the bandwidth allocation by the formulated linear programming outperforms the bandwidth allocation by simple heuristics.