A Streaming Data Anomaly Detection Analytic Engine for Mobile Network Management
Mingxue Wang, Sidath B. Handurukande · 2016
With emerging Network Functions Virtualization (NFV), Software Defined Networking (SDN) paradigms in Network Management (NM), new network devices, features can immediately become available. Available network resources, services can be altered, optimized in real time to gain the maximum benefit. However, this requires real time analytics information sent to SDN controllers rather than traditional manual offline or batch analytics which deliver outputs in hourly or monthly in NM Systems. As a result, real time analytic is becoming a critical element for NM. In this paper, we describe a configuration free (i.e., non-parametric) streaming data anomaly detection analytic engine for automatic NM system development. We describe the design principles, innovative algorithm design, architecture, implementation of the engine in relation to streaming data, mobile NM. Finally, we present use cases, evaluation results.