Self-aware Services of NGSDP: Using Bayesian Networks for Measuring Quality of Convergent Services

We propose a general architecture and implementation for the autonomous assessment of quality of arbitrary service elements in the convergent service environments. We describe a quality engine, which is the central component of our proposed architecture of self-aware convergent services of NGSDP. The quality engine combines domain independent statistical analysis and probabilistic reasoning technology (Bayesian networks) with domain dependent measurement collection and evaluation methods. The resultant probabilistic assessment can be transported via network protocols in the convergent services and it enables non-hierarchical communications about the quality of service elements. We demonstrate the validity of our approach using Multimedia Messaging Service (MMS) Relay/Server and detecting anomalies: storage overflow and message expiration.