Fuzzy adaptive connection admission control for real-time applications in ATM-based heterogenous networks

In this paper, we study connection-oriented service in heterogeneous network for real-time applications. Many existing distributed mission-critical systems are deployed over heterogeneous networks. Hence, it is necessary to extend the real-time communication technology to encompass heterogeneous networks. A connection can be considered as a contract between an application and the network: the application specifies the characteristics of the traffic which it may generate and the network agrees to provide the requested quality of service (QoS) to the application. For real-time applications, the most crucial QoS is to meet deadline requirements. We propose a fuzzy intelligent system for connection admission control (CAC). Upon a request of connection establishment, the CAC determines if the worst case delays of the requesting and existing connections can be satisfied given the available network resources. If so, the CAC allocates appropriate network resources to the requesting connection. Our system uses fuzzy logic to capture the knowledge for adapting its strategy to dynamic system status. The parameters in fuzzy logic rule can be identified using genetic algorithms. Our approach is compatible with current network standards and hence can be readily used in practical systems.