Potential benefit of flow‐based routing in multihomed environments

Abstract

SUMMARYThe data rates provisioned by broadband Internet access connections continue to fall short of the requirements posed by emerging applications. However, the potential of statistical multiplexing of the last mile broadband connections remains unexploited even as the average utilisation of these connections remains low. Despite recent work in this area, two key questions remain unanswered: (a) what is the attainable benefit of broadband access sharing? and (b) how much of this benefit is realisable given real-world constraints? In this work we quantify the attainable benefit of a multihomed broadband access environment by proposing and evaluating several flow-based access sharing policies using a custom flow-based simulator. We then analyse how much of the performance benefit is lost due to real-world constraints by migrating from simulations to a test-lab environment employing a wireless network. Our results show that in today's broadband Internet access scenarios, a significant reduction in download times (up to a factor of 3) is achievable.

A utility minimization approach for energy‐aware cooperative content distribution with fairness constraints

“…In [13], an optimization framework for cooperative relay node selection in heterogeneous wireless communication networks is presented, and a suboptimal cooperative relay node selection algorithm is proposed. The benefits of collaboration for content distribution have been even investigated in wired networks, for example, in [22], where broadband access sharing is studied. In [21], data substream distribution and energy consumption are studied in an optimised way using integer linear programming.…”

Optimization of Internet interconnection policy in the top percentile pricing framework

“…Some variants of this problem have been studied, focusing on the quality of service (Akella et al 2003(Akella et al , 2008Guo et al 2004;Manilici et al 2009) and/or the cost of allocation policies (Goldenberg et al 2004;Chardy 2004 …”

On channel assignment, distributed antennas and network load distribution in dense IEEE 802.11 infrastructure networks

“…To distribute the network load equally Haidar et al [6] proposed a solution where the load on the most heavily loaded AP is minimized. According to the solution described in [5] multiple data flows of a single client are distributed among multiple APs and their DSL connections in a two-hop fashion. Therefore the utilization of the backbone is constantly monitored.…”