We are developing a distributed architecture for massivelymultiplayer games. In this paper, we focus on designing a low-latency event ordering protocol, called NEO, for this architecture. Previous event ordering protocols prevent several types of cheats at the expense of operating at the latency of the slowest player. We broaden the definition of cheating to include four common protocol level cheats and demonstrate how NEO prevents these cheats. At the same time, NEO has a playout latency independent of network conditions and adapts to network congestion to optimize performance.

No abstract

Understanding the distributions and behaviors of players within Massively Multiplayer Online Games (MMOGs) is essential for research in scalable architectures for these systems. We provide the first look into this problem through a measurement study on one of the most popular MMOGs, World of Warcraft [15]. Our goal is to answer four fundamental questions: how does the population of the virtual world change over time, how are players distributed in the virtual world, how much churn occurs with players, and how do they move in the virtual world. Through probing-based measurements, our preliminary results show that populations fluctuate according to a prime-time schedule, player distribution and churn appears to occur on a power-law distribution, and players move to only a small number of zones during each playing session. The ultimate goal of our research is to design an accurate player model for MMOGs so that future research can predict and simulate player behavior and population fluctuations over time.

No abstract