Routing and Scheduling for Variable Bandwidth Advance Reservation

Abstract

Emerging elastic applications generate voluminous datasets, which are often required to be transferred across the network irrespective of flow level bandwidth guarantees. The primary concern in efficient transfers of such bulk data is to minimize the net transfer time. Variable bandwidth advance reservation (VBAR) can efficiently support such applications by reserving time variant bandwidth over the duration of a connection in advance. In this work, we address the routing and bandwidth scheduling problem in VBAR with the objective of minimizing the data transfer time. We propose three heuristic algorithms, and evaluate their performance for a single request under a given network state. We also evaluate the performance of the heuristics in a network under a dynamic traffic scenario. We demonstrate that VBAR outperforms conventional standard advance reservation and immediate reservation approaches in terms of delay, blocking probability, and network throughput. Furthermore, the performance of the proposed heuristic outperforms existing solutions in the dynamic traffic scenario with significantly lower time and storage complexities.