Bandwidth Scheduling Algorith for Multiple Data Transfers in High Performance Networks (HPNS)

Abstract

The significance of high-performance dedicated networks has well recognized due to the rapidly increasing number of large-scale applications that require high-speed data transfer. Efficient algorithms are needed for path computation and bandwidth scheduling in dedicated networks to improve the utilization of network resources and meet diverse user request. We consider three periodic bandwidth scheduling problems: multiple data transfer allocation (MDTA), multiple data transfer allocation with shortest job first (MDTA/SJF) and multiple fixed-slot bandwidth reservation (MFBR), all of which schedule a number a number of user requests accumulated in a certain period. MDTA is to assign multiple data transfer requests on several pre-specified network paths to minimize the total data transfer end time, while MDTA/SJF is to minimize the total transfer end time by sorting the user requests in increasing order, while MFBR is to satisfy multiple bandwidth reservation requests, each of which specifies a bandwidth and a time slot. For MDTA, and MDTA/SJF we design an optimal algorithm and provide its corresponding proof. For MFBR we prove an algorithm and purpose of the algorithm, Minimal Bandwidth and Distance Product Algorithm (MBDPA). Extensively simulation results illustrate the performance of superiority of the proposed MDBPA algorithm over a greedy approach and provide valuable insight into the advantage of periodic bandwidth scheduling over instant bandwidth scheduling.