Despite the greater bandwidth available for home Internet users, network problems continue to surface with regard to the mix of network applications being run. The ease in which Internet sharing can be configured, coupled with the increase in the number of computers present in consumer residences, increase the likelihood that concurrent network applications will have to compete for access to a limited bandwidth resource. The performance of applications such as network games and VoIP is heavily dependent on transmission delays and packet loss rates, which can be improved through priority queuing at the Internet Access device to minimise the impact of queuing delay. In this paper we compare the performance of both regular TCP traffic and network game traffic competing for Internet bandwidth on a DOCSIS Cable Modem link to quantify the performance gain and loss of both applications in an environment where priority queuing is enabled for game traffic. Our results show that the decrease in queuing delay and packet loss rate experienced by game flows is significant in the case of prioritised queuing while the un-prioritised TCP flows experience a slight drop in network performance.
[1]
Mark Claypool,et al.
The effects of loss and latency on user performance in unreal tournament 2003®
,
2004,
NetGames '04.
[2]
Lars C. Wolf,et al.
Analysis of factors affecting players' performance and perception in multiplayer games
,
2005,
NetGames '05.
[3]
Grenville J. Armitage,et al.
An experimental estimation of latency sensitivity in multiplayer Quake 3
,
2003,
The 11th IEEE International Conference on Networks, 2003. ICON2003..
[4]
Grenville Armitage,et al.
A synthetic traffic model for Half-Life
,
2003
.
[5]
Grenville J. Armitage,et al.
Passive TCP stream estimation of RTT and jitter parameters
,
2005,
The IEEE Conference on Local Computer Networks 30th Anniversary (LCN'05)l.
[6]
S. Zander,et al.
An Architecture for Automated Network Control of QoS over Consumer Broadband Links
,
2005,
TENCON 2005 - 2005 IEEE Region 10 Conference.
[7]
S. Zander,et al.
Empirically Measuring the QoS Sensitivity of Interactive Online Game Players
,
2004
.