Joint Optimization on Bandwidth Allocation and Route Selection in QoE-Aware Traffic Engineering

Abstract

Wide area networks (WANs) are increasingly relying on software-defined networking to orchestrate data transmission. Google and Microsoft built B4 and SWAN, respectively, to interconnect their data centers in WANs, achieving higher network utilization and lower delay, where different priorities can be applied for bandwidth allocation and route selection in their centralized traffic engineering. However, simply relying on the priorities cannot accurately capture the complex properties of the quality of experience (QoE) function corresponding to the end users and always result in a suboptimal solution. We propose QTE, a novel traffic engineering in software-defined WANs, which proactively enforces forwarding policies by coordinating the traffic demand of each data center. The goal of QTE aims to maximize end-user QoE for client-trigger traffic and maximize network throughput for background traffic. We make several technical contributions in designing QTE. First, we formulate maximizing end-user QoE problem as two optimization programs and propose a heuristic algorithm to solve the problem. We further present a concrete design and implementation of the system based on the Floodlight controller. Extensive experiments use Openflow switches on Mininet and numerical simulations, which shows that QTE increases end-user experiences by 45.3% compared with prior work and can be readily implemented on the Floodlight controller. INDEX TERMS Computer networks, software defined networking.

Multi-Criteria Path Finding Using Multi-Queues Based Bidirectional Search for Multiple Target Nodes in Networks

“…In TE algorithms of B4 [14] and SWAN [15], k shortest path algorithm is used to compute paths form a data center to the other data centers in their wide area networks. Also, in other TE schemes [16]- [19], k shortest path algorithm is used to find paths for given source-destination pairs. These TE algorithms concern the network flows optimization without considering whether or not the paths can satisfy the SLA requirements of the services.…”

Joint Bandwidth Allocation and Path Selection in WANs with Path Cardinality Constraints

“…and I Y (y) as well as I X (x) are indicator functions defined in (5). The augmented Lagrangian function can be rewritten as…”

“…In [4], an approach called stacked congestion control is proposed to optimize multi-tenant multi-objective performance with a distributed host-based implementation. In [5], a traffic engineering approach in software-defined WANs is proposed to proactively enforce forwarding policies by coordinating the traffic demand of each data center instead of traditional passive control policies relying on given priorities. In [6], a centralized arbiter is used to decide when and at which path each packet should be sent.…”