A learning approach to quality-of-service routing for supporting multimedia applications

Multimedia applications such as digital video and audio often have stringent quality-of-service (QoS) requirements. In recent years, several new architectures have been developed for supporting such applications. One important element that is still missing from these architectures is QoS routing, namely routing based on QoS requirements. In traditional data networks, routing has been primarily concerned with connectivity. Routing Protocols usually characterize the network with a single metric such as hop-count or delay. However to support a wide range of QoS requirements, there is a need to consider multiple metrics such as bandwidth, delay and loss probability while making routing decisions. The problem of determining a path that satisfies multiple constraints is computationally very demanding and in most cases, such problems have been shown to be NP complete. In this' paper, we first examine-the basic problem of QoS routing and then propose a new, efficient learning algorithm for selection of the optimum path. This algorithm is subsequently utilized to make routing decisions in various routing architectures.