Datacenter Traffic Shaping for Delay Reduction in Cloud Gaming

Cloud Gaming enables users to play games using a thin-client, regardless of their location or what platform they use (PCs, laptops, tablets, smartphones). Since the major computational parts of game processing are performed in datacenters, effectively assigning the resources (e.g. memory, bandwidth) to gaming sessions plays a key role in providing a high quality gaming experience to end-users. In this paper, we propose a traffic policing and shaping method using the Software Defined Networking (SDN) paradigm to solve the bandwidth allocation problem in cloud gaming datacenter networks. Our proposed method considers the current status of the datacenter paths in terms of remaining bandwidth and delay to achieve fair bandwidth allocation. The proposed scheme optimizes bandwidth utilization while ensuring compliance with the threshold of tolerable delay in cloud gaming systems. Our experimental results show that the proposed method improves bandwidth utilization and reduces end-to-end delay and delay variation (jitter) by almost 12% and 9%, respectively, without engendering additional packet loss compared to a representative conventional method: Equal Cost Multi-path (ECMP). These reductions lead to improvements in players' gaming experience.

[1]  Yan Lu,et al.  Introduction to the Special Section on Visual Computing in the Cloud: Cloud Gaming and Virtualization , 2015, IEEE Trans. Circuits Syst. Video Technol..

[2]  Mark Claypool,et al.  Network analysis of Counter-strike and Starcraft , 2003, Conference Proceedings of the 2003 IEEE International Performance, Computing, and Communications Conference, 2003..

[3]  Albert G. Greenberg,et al.  The nature of data center traffic: measurements & analysis , 2009, IMC '09.

[4]  José Alberto Hernández,et al.  Dissecting the protocol and network traffic of the OnLive cloud gaming platform , 2014, Multimedia Systems.

[5]  Qing Yang,et al.  Cascading impact of lag on Quality of Experience in cooperative multiplayer games , 2014, 2014 13th Annual Workshop on Network and Systems Support for Games.

[6]  Arthur M. Geoffrion,et al.  Lagrangian Relaxation for Integer Programming , 2010, 50 Years of Integer Programming.

[7]  Hussein Al Osman,et al.  SDN-based game-aware network management for cloud gaming , 2015, 2015 International Workshop on Network and Systems Support for Games (NetGames).

[8]  Hua-Jun Hong,et al.  Placing Virtual Machines to Optimize Cloud Gaming Experience , 2015, IEEE Transactions on Cloud Computing.

[9]  Wu-chi Feng,et al.  A traffic characterization of popular on-line games , 2005, IEEE/ACM Transactions on Networking.

[10]  Gwendal Simon,et al.  The brewing storm in cloud gaming: A measurement study on cloud to end-user latency , 2012, 2012 11th Annual Workshop on Network and Systems Support for Games (NetGames).

[11]  Gwendal Simon,et al.  A hybrid edge-cloud architecture for reducing on-demand gaming latency , 2014, Multimedia Systems.

[12]  Seungjoon Lee,et al.  SMOG: A cloud platform for seamless wide area migration of online games , 2012, 2012 11th Annual Workshop on Network and Systems Support for Games (NetGames).

[13]  Amin Vahdat,et al.  A scalable, commodity data center network architecture , 2008, SIGCOMM '08.

[14]  Hussein Al Osman,et al.  An SDN Controller for Delay and Jitter Reduction in Cloud Gaming , 2015, ACM Multimedia.

[15]  Paul B. Beskow,et al.  Latency Reduction in Massively Multi-player Online Games by Partial Migration of Game State , 2007 .

[16]  Mark Claypool,et al.  Traffic analysis of avatars in Second Life , 2008, NOSSDAV.

[17]  Panos M. Pardalos,et al.  Encyclopedia of Optimization , 2006 .

[18]  Hussein Al Osman,et al.  Toward Delay-Efficient Game-Aware Data Centers for Cloud Gaming , 2016, ACM Trans. Multim. Comput. Commun. Appl..