Probabilistic Fault Diagnosis In The Magneto Autonomic Control Loop

Management of outer edge domains is a big challenge for service providers due to the diversity, heterogeneity and large amount of such networks, together with limited visibility on their status. This paper focuses on the probabilistic fault diagnosis functionality developed in the MAGNETO project, which enables finding the most probable cause of service problems and thus triggering appropriate repair actions. Moreover, its self-learning capabilities allow continuously enhancing the accuracy of the diagnostic process.