Fault and performance management systems, in the traditional carrier networks, are based on rule-based diagnostics that correlates alarms and other markers to detect and localize faults and performance issues. As carriers move to Virtual Network Services, based on Network Function Virtualization and multi-cloud, the traditional methods fail to deliver because of the impalpability of the constituent Virtual Network Functions and increased complexity of the resulting architecture. In this paper, we propose a framework, called HYPER-VINES, that interfaces with various management platforms involved, to process markers, through a system of shallow and deep machine learning models, to detect and localize manifested and impending fault and performance issues. Our experiments validate the functionality and feasibility of the framework in terms of accurate detection and localization of such issues and unambiguous prediction of impending issues. Simulations with real network fault datasets show effectiveness of its architecture in large networks.
Complete paper in Adobe Acrobat format.