Data Mining for Managing Intrinsic Quality of Service in MPLS

Quality of Service (QoS) is more and more becoming a necessity for emerging applications carried by IP networks. Thus, dynamic admission control is a very important mechanism that aims, not only to ensure resources availability, but also to verify QoS constraints satisfaction. Nowadays traffic engineering is an essential ingredient for guaranteeing QoS and for efficient or cost effective resource utilization, design and operation of IP networks. MPLS (Multiprotocol Label Switching) is a standards-based technology that can improve network performance and QoS for select traffic. MPLS offers multiple classes of service, each associated with different locally significant labels in the packet header and the packets are forwarded by network nodes via label swapping types of traffic. MPLS uses short, fixed-length similar to layer 2 switching.