Page 240 - Big data - Concept and application for telecommunications

5 Big data - Concept and application for telecommunications

Figure 6-4 – Big-data-driven quality of service anomaly detection and root cause tracking

Network performance anomalies are network data, e.g., network traffic data, syslog data and management
data. QoS anomaly network data are from network anomaly events, e.g., network attacks, protocol bugs and
link up/down. Based on the analysis of multi-layer dependence and spatiotemporal dependence of network
data and network events, bDDN can reversely track the root causes of network anomalies. The bDDN can
clarify the positive correlations and reverse tracking mechanisms of network 'anomaly events – anomaly data
– Network anomalies'. See Figure 6-5.

Figure 6-5 – Training of quality of service anomaly detector

232 Network and infrastructure