发明名称 |
System and Method for a Multi View Learning Approach to Anomaly Detection and Root Cause Analysis |
摘要 |
A system and method for detecting anomalies in a communication network includes detecting first outliers in a first set of quality indicators for a cellular group, detecting second outliers in a second set of performance indicators for the cellular group, correlating the first outliers and the second outliers to produce an anomaly candidate, determining a confidence threshold for the anomaly candidate, and indicating a network anomaly in response to the confidence threshold exceeding a predetermined threshold. |
申请公布号 |
US2017094537(A1) |
申请公布日期 |
2017.03.30 |
申请号 |
US201514864360 |
申请日期 |
2015.09.24 |
申请人 |
Futurewei Technologies, Inc. |
发明人 |
Yang Kai;Liu Ruilin;Sun Yanjia |
分类号 |
H04W24/04 |
主分类号 |
H04W24/04 |
代理机构 |
|
代理人 |
|
主权项 |
1. A method for detecting anomalies in a communication network, the method comprising:
detecting key quality indicator (KQI) outliers in a set of KQIs for a cellular group; detecting key performance indicator (KPI) outliers in a set of KPIs for the cellular group; correlating, by a first network device, the KQI outliers for the cellular group with the KPI outliers for the cellular group to identify an anomaly candidate for the cellular group; determining a confidence threshold for the anomaly candidate; and detecting, by the first network device, a root cause for the anomaly candidate and sending a signal that identifies the root cause to a second network device when the confidence threshold for the anomaly candidate exceeds a predetermined threshold. |
地址 |
Plano TX US |