QSR Data Mining System for Dynamic Route Selection in Multimedia Communication Networks

摘要

This paper presents a new data mining system for quality of service capable switch-router (QSR) called QSR data mining system. This QSR data mining system is used for dynamic route selection of multimedia communication networks (MCNs). The QSR data mining system dynamically chooses the routes for multi-traffic flow according to not only different performance requirements, but also the existent resource status of MCNs. In MCNs the principles of routers and transfer control protocol/internet protocol (TCP/IP) are used. The principles of data mining system, quality of service (QoS) integrated performance evaluation, route mechanism, back propagation neural network (BPNN) and so on are combined in the QSR data mining system. The real-time data experiments of the QSR data mining system for MCNs are used to test the effectiveness of the data Mining system.