Analysis and reduction of data spikes in thin client computing

摘要: While various optimization techniques have been used in existing thin client systems to reduce network traffic, the screen updates triggered by many user operations will still result long interactive latencies contemporary environments. Long an unfavorable effect on users' perception of graphical interfaces and visual contents. The arise when data spikes need be transferred over a while available bandwidth is limited. These are composed large amount update produced very short time. In this paper, we propose model analyze packet-level redundancy streams caused repainting objects. Using analyzed streams. Based analysis designed hybrid cache-compression scheme. This scheme caches both server sides, uses cached as history better compress recurrent possible spikes. We empirically studied effectiveness our cache some generated one most bandwidth-efficient system, Microsoft Terminal Service. experiment results showed that with 2M bytes can 26.7%-42.2% spike count 9.9%-21.2% traffic for tested data, 25.8%-38.5% noticeable different types applications. costs only little additional computation time size negotiated between server.