Date Added: Sep 2012
In this paper, the authors present the design and implementation of an application-layer data throughput prediction and optimization service for many-task computing in widely distributed environments using Operation research. This service uses multiple parallel TCP streams which are used to find maximum data distribution stream through assignment model which is to improve the end-to-end throughput of data transfers in the network. A novel mathematical model (optimization model) is developed to determine the number of parallel streams, required to achieve the best network performance. This model can predict the optimal number of parallel streams with as few as three prediction points (i.e. three Switching points).