Lawrence Stewart

An Architecture for Automated Network Control of QoS over Consumer Broadband Links

This paper proposes a novel architecture for meeting Quality of Service (QoS) requirements of real-time traffic across consumer broadband links. In our approach the responsibility of QoS signalling is moved away from the application to the network. Network servers automatically identify traffic that might benefit from QoS and then trigger the provisioning of QoS by signalling network elements such as access routers. This approach removes the need for the application to signal to the network its explicit QoS requirements, making applications easier to develop and more portable. It also enables QoS provision for legacy applications for which there is limited opportunity to include explicit end-host signalling protocols. The paper develops the architecture required to realize the approach and discusses the underlying techniques.

Some thoughts on emulating jitter for user experience trials

It is usually hard to control the network conditions affecting public online game servers when studying the impact of latency, loss and jitter on user experience. This leads to a natural desire for running user-experience trials under controlled network conditions, and hence a requirement for accurate (or at least predictable) emulation of IP level latency, loss and jitter on a localized network testbed. In this short paper we reflect on some experiences with running user-experience trials, and specifically evaluate the utility and limitations of using FreeBSDs kernel-resident dummynet module to introduce controlled jitter. We expect these insights will stimulate further user-experience trials built around low-cost, unix-based networking tools.

Outsourcing automated QoS control of home routers for a better online game experience

Consumer network access links can become bottlenecks when faced with heterogeneous network traffic where real-time traffic from network games finds itself competing with nongame traffic for access to bandwidth. We would like to prioritize network game traffic over these bandwidth restricted links. However, the limited resources of consumer access devices make this problematic. We propose a solution whereby the classification of flows is outsourced to an ISP-based system. The access device is then notified of flow classifications and can apply a simple flow prioritization rule. We have developed a prototype of this system and found it viable in terms of functionality, timeliness of classification, and scalability.

An independent H-TCP implementation under FreeBSD 7.0: description and observed behaviour

A key requirement for IETF recognition of new TCP algorithms is having an independent, interoperable implementation. This paper describes our BSD-licensed implementation of H-TCP within FreeBSD 7.0, publicly available as a dynamically loadable kernel module. Based on our implementation experience we provide a summary description of the H-TCP algorithm to assist other groups build further interoperable implementations. Using data from our live testbed we demonstrate that our version exhibits expected H-TCP behavior, and describe a number of implementation-specific issues that influence H-TCPs dynamic behavior. Finally, we illustrate the actual collateral impact on path latency of using H-TCP instead of NewReno. In particular we illustrate how, compared to NewReno, H-TCPs cwnd growth strategy can cause faster fluctuations in queue sizes at, yet lower median latency through, congestion points. We believe these insights will prove valuable predictors of H-TCPs potential impact if deployed in consumer end-hosts in addition to specialist, high-performance network environments.

Performance analysis of the ANGEL system for automated control of game traffic prioritisation

The Automated Network Games Enhancement Layer (ANGEL) [6] is a novel architecture for meeting Quality of Service (QoS) requirements of real-time network game traffic across consumer broadband links. ANGEL utilises detection of game traffic in the ISP network via the use of Machine Learning techniques and then uses this information to inform network routers - in particular the home access modem where bandwidth is limited - of these flows such that the traffic may be prioritised. In this paper we present the performance characteristics of the fully built ANGEL system. In particular we show that ANGEL is able to detect game traffic with better than 96% accuracy and effect prioritisation within a second of game flow detection. We also demonstrate the processing performance of key ANGEL components under typical hardware scenarios.

Automated network games enhancement layer: a proposed architecture

In this paper we present the design of the Automated Network Games Enhancement Layer (ANGEL), a novel architecture for meeting Quality of Service (QoS) requirements of real-time network game traffic across consumer broadband links. Consumer access links can become bottlenecks when faced with heterogeneous network traffic (e.g. simultaneous use of online games and peer-to-peer file sharing) and the online gaming experience can be significantly affected by bottleneck queuing. Implementing QoS on these links provides improvement by reducing latency and jitter. In our approach network servers automatically identify traffic that might benefit from QoS and then trigger provisioning of QoS by signaling network elements such as access routers. By placing intelligence within the network, QoS decisions can be transparently made for the game applications without imposing an additional processing cost at the access link router. Our system uniquely uses machine learning methods to perform traffic classification.