Network-Aware State Update For Large Scale Mobile Games

Abstract

In large scale mobile gaming environments, efficient mechanisms for state update is crucial to allow graceful real-time interaction of a large number of players, under limited wireless network bandwidth. By using the state updating threshold as a key parameter that bridges the resulting state inconsistency (or distortion) and the network traffic, we are able to model the fundamental traffic-distortion tradeoffs. Given the tradeoffs for all users, an optimal bandwidth allocation can be derived using well-known convex programming techniques. By exploring the temporal locality of gaming behavior, we also propose a prediction method to realize on-line bandwidth adaptation. Using real data trace from a multi-player driving game, the proposed network aware bandwidth allocation method, NABA, is able to achieve significant reduction in state distortion compared to two baselines: Uniform and Proportional policies. NABA is also adaptable to variations in system parameters, including bandwidth constraint and network delay.