On synthetic workloads for multiplayer online games: a methodology for generating representative shooter game workloads

We present approaches to the generation of synthetic workloads for benchmarking multiplayer online gaming infrastructures. Existing techniques, such as mobility or traffic models, are often either too simple to be representative for this purpose or too specific for a particular network structure. Desirable properties of a workload are reproducibility, representativeness, and scalability to any number of players. We analyze different mobility models and AI-based workload generators. Real gaming sessions with human players using the prototype game Planet PI4 serve as a reference workload. Novel metrics are used to measure the similarity between real and synthetic traces with respect to neighborhood characteristics. We found that, although more complicated to handle, AI players reproduce real workload characteristics more accurately than mobility models.

[1]  Bettina Kemme,et al.  Peer-to-peer architectures for massively multiplayer online games: A Survey , 2013, CSUR.

[2]  Srinivasan Seshan,et al.  Donnybrook: enabling large-scale, high-speed, peer-to-peer games , 2008, SIGCOMM '08.

[3]  Wolfgang Effelsberg,et al.  Designing Benchmarks for P2P Systems , 2010, From Active Data Management to Event-Based Systems and More.

[4]  Srinivasan Seshan,et al.  Colyseus: A Distributed Architecture for Online Multiplayer Games , 2006, NSDI.

[5]  Kajal T. Claypool,et al.  Latency can kill: precision and deadline in online games , 2010, MMSys '10.

[6]  Markus Rupp,et al.  Traffic Analysis and Modeling for World of Warcraft , 2007, 2007 IEEE International Conference on Communications.

[7]  Mark Claypool,et al.  The effects of loss and latency on user performance in unreal tournament 2003® , 2004, NetGames '04.

[8]  Jussi Kangasharju,et al.  Explaining BubbleStorm: Resilient, Probabilistic, and Exhaustive PeertoPeer Search , 2007, SIGCOMM 2007.

[9]  Shun-Yun Hu,et al.  VON: a scalable peer-to-peer network for virtual environments , 2006, IEEE Network.

[10]  Son T. Vuong,et al.  MOPAR: a mobile peer-to-peer overlay architecture for interest management of massively multiplayer online games , 2005, NOSSDAV '05.

[11]  Grenville J. Armitage,et al.  A synthetic traffic model for Quake3 , 2004, ACE '04.

[12]  Alejandro P. Buchmann,et al.  pSense - Maintaining a Dynamic Localized Peer-to-Peer Structure for Position Based Multicast in Games , 2008, 2008 Eighth International Conference on Peer-to-Peer Computing.

[13]  Alejandro P. Buchmann,et al.  An online gaming testbed for peer-to-peer architectures , 2011, SIGCOMM.

[14]  Lars C. Wolf,et al.  On the suitability of dead reckoning schemes for games , 2002, NetGames '02.

[15]  Kajal T. Claypool,et al.  Latency and player actions in online games , 2006, CACM.

[16]  Jussi Kangasharju,et al.  Bubblestorm: resilient, probabilistic, and exhaustive peer-to-peer search , 2007, SIGCOMM '07.

[17]  Ralf Steinmetz,et al.  Towards a comparative performance evaluation of overlays for Networked Virtual Environments , 2011, 2011 IEEE International Conference on Peer-to-Peer Computing.

[18]  Wolfgang Effelsberg,et al.  Generation of synthetic workloads for multiplayer online gaming benchmarks , 2012, 2012 11th Annual Workshop on Network and Systems Support for Games (NetGames).

[19]  Philip W. Trinder,et al.  Design issues for Peer-to-Peer Massively Multiplayer Online Games , 2010, Int. J. Adv. Media Commun..