Novel dynamic delay allocation adjustment for improving bandwidth efficiency

Abstract

End-to-end delay guarantees are critical to many delay-sensitive applications. To ensure such a guarantee on a flow path, the existing approaches usually statically divide its end-to-end delay requirement into per-hop delay requirements. However, such static path-level resource allocations often cause unbalanced resource reservations and bottlenecks in a network as shown in this paper, limit the total number of sessions accommodated in the network, and result in low network utilization. To address this issue, we propose a Dynamic Allocation Adjustment (DAA) approach to improve bandwidth efficiency by spreading loads over a flow path and other related links not on the path. Our simulation results show that DAA is able to significantly increase the total number of flows admitted into a network by 30% or more, compared with the best existing solution. Furthermore, it efficiently utilizes bandwidth by greatly reducing the average flow reservation at a link and the total resources reserved for a flow on its entire path.