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

Saldana, J. (Universidad de Zaragoza)

Resumen: 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.

Idioma: Inglés

DOI: 10.1007/s11042-015-3001-y

Año: 2015

Publicado en: MULTIMEDIA TOOLS AND APPLICATIONS (2015), [42 pp]
ISSN: 1380-7501

Factor impacto JCR: 1.331 (2015)

Categ. JCR: COMPUTER SCIENCE, INFORMATION SYSTEMS rank: 62 / 143 = 0.434 (2015) - Q2 - T2
Categ. JCR: ENGINEERING, ELECTRICAL & ELECTRONIC rank: 121 / 257 = 0.471 (2015) - Q2 - T2
Categ. JCR: COMPUTER SCIENCE, THEORY & METHODS rank: 37 / 105 = 0.352 (2015) - Q2 - T2
Categ. JCR: COMPUTER SCIENCE, SOFTWARE ENGINEERING rank: 31 / 106 = 0.292 (2015) - Q2 - T1

Factor impacto SCIMAGO: 0.345 - Media Technology (Q1) - Computer Networks and Communications (Q2) - Hardware and Architecture (Q2) - Software (Q3)

Tipo y forma: Article (PostPrint)

Área (Departamento): Área Ingeniería Telemática (Dpto. Ingeniería Electrón.Com.)