An Intelligent Media Delivery Prototype System with Low Response Time

Streaming media has been increasing in the Internet as a popular form of content. However, the streaming media delivery between server and client browser still has problems to be solved, such as the poor processing efficiency in dealing with large concurrent access and the high usage of bandwidth. In particular, large scale video site usually has a large number of distributed server nodes. It is of great importance for the system to respond to users’ request rapidly by choosing the proper video source for users and handling resource cache problem properly. To solve the above problems in streaming media delivery, this paper proposes a content delivery solution. The system consists of several nodes that differ in role function, and streaming media content is stored in these nodes. Users will get an optimized response, and the system selects the nearest node that has the requested video according to logical distance intellectually. The selected node will provide video stream for users. In addition, the system is equipped with a high performance content indexing and searching mechanism. The index is able to retrieve users’ requested resource rapidly and therefore guarantees a good performance in selecting nodes.