Data redistribution in parallel is an often-addressed issue in modern computer networks. In this context, westudy the case of data redistribution over a switching network. Data from the source stations need to betransferred to the destination stations in the minimum time possible. Unfortunately the time required tocomplete the transfer is burdened by each switching and thus producing an optimal schedule is proven tobe computationally intractable. For the purposes of this paper we consider two algorithms, which havebeen proved to be very efficient in the past. To get improved results in comparison to previous approaches,we propose splitting the data in two clusters depending on the size of the data to be transferred. To provethe efficiency of our approach we ran experiments on all three algorithms, comparing the time span of theschedules produced as well as the running times to produce those schedules. The test cases we ranindicate that not only our newly proposed algorithm yields better results in terms of the schedule producedbut runs faster as well.
展开▼
