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

Biao Chen, Yingbi Zhang, John Yen, Wei Zhao

Research output: Contribution to journalArticlepeer-review

10 Scopus citations


In this paper, we study connection-oriented communication 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 requirement. 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. Our performance study demonstrates that system performance can be improved significantly and consistently with our fuzzy adaptive connection admission control. Our approach is compatible with current network standards and hence can be readily used in practical systems.

Original languageEnglish (US)
Pages (from-to)125-135
Number of pages11
JournalJournal of Intelligent and Fuzzy Systems
Issue number2
StatePublished - 1999

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • General Engineering
  • Artificial Intelligence


Dive into the research topics of 'Fuzzy adaptive connection admission control for real-time applications in ATM-based heterogeneous networks'. Together they form a unique fingerprint.

Cite this