Fine Tuning of a Distributed VoD System

In a distributed Video-on-Demand system, customers are in charge of storing the video catalog, and they actively participate in serving video requests generated by other customers. The design of such systems is driven by key constraints like customer upload and storage capacities, video popularity distribution, and so on. In this paper, we analyze by simulations the impact of: i) the video allocation technique (used for distributed storage) ii) the use of a cache that allows nodes to redistribute the video they are using iii) the use of static/dynamic algorithms for video distribution. Based on these results, we provide some guidelines for setting the system parameters: the use of cache strongly improves system performance; popularity based allocation techniques can be sensitive and bring little improvement; dynamic distribution algorithms are needed only in extreme scenarios while static ones are generally sufficient.