In the context of next generation networks (NGN), there is a critical need to address the challenges facing the network management functions, to administer the converged infrastructure and services. One of the challenges is to model the unknown and probabilistic dependency relationships among the diverse network elements and adapt this model to capture the real-time network behavior. This paper proposes BARD (BAyesian Reasoner and Decision-maker), a proactive system to enhance the network performance management functions by use of machine learning technique called Bayesian Belief Networks (BBN). It exploits the predictive and diagnostic reasoning features of BBN to make accurate decisions for effective management. A case study is presented to demonstrate the application of this technique to the problem of Call Admission Control in a typical communication network. The simulation results provide the proof that BARD is an effective and feasible solution when applied for network management tasks, especially Quality-of-Service (QoS) management.
|Title of host publication||Proceedings of the 10th PostGraduate Symposium on the Convergence of Telecommunications, Networking and Broadcasting|
|Publication status||Published - Jun 2009|
- Network Management
- Next Generation Networks (NGN)
- Bayesian Belief Networks (BBN)
- Machine Learning