First person shooters: can a smarter network save bandwidth without annoying the players?

Saldaña, José; Fernández-Navajas, Julián; Ruíz-Mas, José; Aznar, Jose I.; Viruete, Eduardo; Casadesus, Luis

doi:10.1109/mcom.2011.6069728

Cited by 14 publications

(16 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typically 'acceptable' [17] game latencies range from 100ms for first person shooter (FPS) and racing games, 500ms for sports and role playing games (RPG), and 1000ms for real-time strategy games (RTS). Active QoS measurement approaches include active ping latency measurement for cloud-hosted FPS and RTS [14] games, Passive QoS measurement approaches use sampling latency and packet loss from tcpdump traffic data [39] for Massively Multiplayer Online Role-Playing Games (MMORPG's) like World of Warcraft and, interpacket arrival times [12] for FPS's like Quake3 and Halo2.…”

Section: Related Workmentioning

confidence: 99%

Scalable classification of QoS for real-time interactive applications from IP traffic measurements

Middleton

Modafferi

2016

Computer Networks

View full text Add to dashboard Cite

Measurement of network Quality of Service (QoS) has attracted considerable research effort over the last two decades. The recent trend towards Internet Service Providers (ISP's) offering application-specific QoS is creating possibilities for more sophisticated QoS metrics to be offered by ISP's in service level agreements. This in turn could be used for the purposes of improved network optimization and billing according to application specific QoS guarantees. We report a scalable near real-time approach using passively logging IP traffic data for classification of application latency and packet loss across a range of real-time interactive applications. We run six experiments involving Minecraft, Quake 3 Urban Terror, VLC video streaming and the commercial Wirofon VOIP application. We use a mixture of laboratory and realworld deployments, with run times ranging from hours to days, and observe a combination of real and simulated ISP latency and packet loss events. Our binary classification (i.e. classes 'OK' or 'lag') 10-fold cross validation F1 scores are between 0.80 and 0.93 depending on application type. Our multi-class classification (i.e. classes representing discrete packet loss or latency ranges) 10-fold cross validation F1 scores for Minecraft are 0.89 for latency and 0.90 for packet loss. With new business models between ISP's and application developers being actively considered this work represents a significant contribution to the debate by providing scientific evidence relating to a novel approach to scalable QoS measurement

show abstract

Section: Related Workmentioning

confidence: 99%

Scalable classification of QoS for real-time interactive applications from IP traffic measurements

Middleton

Modafferi

2016

Computer Networks

View full text Add to dashboard Cite

show abstract

“…In [10] the expected savings when optimizing eight different UDP-based FPS games were calculated, showing that a bandwidth reduction of 30 or 35 % can be obtained for client-to-server flows. If IPv6 is used, these figures may rise up to 55 %.…”

Section: First Person Shooter Games Traffic Optimizationmentioning

confidence: 99%

“…4). This sets an upper bound for the additional multiplexing delay [10], which average value will be PE/2. In [14] different studies were conducted with the aim of studying the effect of this additional delay, showing the conditions in which subjective quality can be maintained.…”

Section: First Person Shooter Games Traffic Optimizationmentioning

confidence: 99%

“…A Quality of Experience (QoE) estimator deployed for a game was used [15]. A clear conclusion was devised: when the number of flows to multiplex is high enough, the added delay can be really tiny: as an example, if 20 flows are being multiplexed, bandwidth savings above 30 % are achievable even using a period of 10 ms [10]. In the same situation, the amount of packets per second may pass from 500 to 100.…”

Section: First Person Shooter Games Traffic Optimizationmentioning

confidence: 99%

“…An L2TPv3 (Layer 2 Tunneling Protocol version 3) tunnel was included in order to permit the end-to-end sending of packets. An adaptation of this method for UDP (not RTP/UDP) has been proposed [9], [10]. In [13] a mechanism for selecting the packets to be multiplexed, using a predefined period, was proposed and compared, in terms of delay and jitter, with another one based on a timeout.…”

Section: Traffic Optimization By Means Of Header Compressionmentioning

confidence: 99%

See 2 more Smart Citations

On the effectiveness of an optimization method for the traffic of TCP-based multiplayer online games

Saldaña

2015

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

This paper studies the feasibility of using an optimization method, based on multiplexing and header compression, for the traffic of Massively Multiplayer Online Role Playing Games (MMORPGs) using TCP at the Transport Layer. Different scenarios where a number of flows share a common network path are identified. The adaptation of the multiplexing method is explained, and a formula of the savings is devised. The header compression ratio is obtained using real traces of a popular game and a statistical model of its traffic is used to obtain the bandwidth saving as a function of the number of players and the multiplexing period. The obtained savings can be up to 60 % for IPv4 and 70 % for IPv6. A Mean Opinion Score model from the literature is employed to calculate the limits of the multiplexing period that can be used without harming the user experience.The interactions between multiplexed and non-multiplexed flows, sharing a bottleneck with different kinds of background traffic, are studied through simulations. As a result of the tests, some limits for the multiplexing period are recommended: the unfairness between players can be low if the value of the multiplexing period is kept under 10 or 20 ms. TCP background flows using SACK (Selective Acknowledgment) and Reno yield better results, in terms of fairness, than Tahoe and New Reno. When UDP is used for background traffic, high values of the multiplexing period may stress the unfairness between flows if network congestion is severe.

show abstract

Online FPS games: effect of router buffer and multiplexing techniques on subjective quality estimators

Saldaña

Fernández-Navajas

Ruíz-Mas

et al. 2012

Multimed Tools Appl

View full text Add to dashboard Cite

First person shooters: can a smarter network save bandwidth without annoying the players?

Cited by 14 publications

References 10 publications

Scalable classification of QoS for real-time interactive applications from IP traffic measurements

Scalable classification of QoS for real-time interactive applications from IP traffic measurements

On the effectiveness of an optimization method for the traffic of TCP-based multiplayer online games

Online FPS games: effect of router buffer and multiplexing techniques on subjective quality estimators

Contact Info

Product

Resources

About