Future Wei Technologies, Inc.

Huawei Technologies Co., Limited

Kai Yang

Yanjia Sun

Ruilin Liu

Jin Yang

Baoling S Sheen

Juan Roa

Tao Quan

Sijia Liu

Deti Liu

The disclosure relates to technology for identifying a root cause of anomalous behavior in a communications network. A key quality indicator (KQI) indicative of a performance level associated with a source is received in the communication network. The KQI includes a performance measurement value to identify a performance level of the source having the anomalous behavior. An improved KQI indicative of a level of degradation is calculated based on the anomalous behavior at the source by recovering the KQI to a historical value. Sources of the anomalous behavior are clustered into subsets according to the level of degradation based on the calculated KQI improvement. A global or partial degradation type of the root cause source in the subset having a severe level of degradation is determined using hypothesis testing, and a confidence value is provided for the accepted degradation type.

System and method for analyzing a root cause of anomalous behavior using hypothesis testing

The disclosure relates to technology for mining data in a database by recursively mining a conditional frequent pattern tree (FP-tree) for frequent items of each conditional pattern base for each node in an FP-tree to obtain frequent patterns. For each branch in the FP-tree, a single-item node table (NT) is generated for which a selected one of the frequent items appears in the node of the branch. The single-item NT including a list of all of the frequent items appearing in the FP-tree and a corresponding frequent item count. For each single-item NT of each branch generated for the selected one of the frequent items, the frequent item count of each frequent item is summed in the single-item NT formed for each branch to generate a combined single-item NT, and association rules based on the frequent patterns are generated for each of the frequent items and the combined single-item NT.

Distributed FP-growth with node table for large-scale association rule mining

Techniques are provided for monitoring the performance of a user device in a communication network. The techniques include detecting an anomaly in a performance measurement such as a key quality indicator (KQI) of the user device. The techniques include obtaining historical measurements of the KQI for user devices. The historical measurements are assigned to states to reflect whether the performance is good or bad, or somewhere in between. The states can be defined differently for different hours in the day so that the states represent the relative performance for that time of day. For each user device, a Markov model is provided indicating probabilities of transitions between the states. Additional measurements are obtained of the KQI for a selected user device, and the Markov model of the selected user device is used to detect an anomaly in the additional measurements.

User-level KQI anomaly detection using markov chain model

A processor implemented method of identifying a root cause of degraded network quality in a wireless network. The method includes accessing historical network performance data, the performance data including a time sequenced measure of performance indicators for the network. The method evaluates the historical performance data to determine regularly occurring associations between indicators to define a set of rules characterizing the associations of the wireless network, and stores the set of rules in a data structure. The wireless network is monitored by accessing analysis data reporting time sequenced performance indicator data. Next, anomalies are detected in a performance indicator in the analysis data and matched to at least one rule in the set of rules. The method outputs an indication of a cause of degradation in the wireless network resulting from the anomaly in the performance indicator.

Fingerprinting root cause analysis in cellular systems

The disclosure relates to technology for processing data sets to generate data rules for the data sets in a communications network. A first set of data including key quality indicators (KQIs) indicative of a quality of service and a second set of data including key performance indicators (KPIs) indicative of a performance level are received. The first data set and the second data set are categorized using a first value into a plurality of KQI groups and a second value into a plurality of KPI groups, respectively. Each of the KQI and KPI groups are identified with a label. Each of the KQI and KPI groups identified with a same label are processed by application of association rule learning to generate the data rules. The data rules model a relationship between the KQIs and the KPIs by calculating association frequencies.

Features selection and pattern mining for KQI prediction and cause analysis

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.

System and method for a multi view learning approach to anomaly detection and root cause analysis

A method includes performing, via a controller, adaptive filtering on a network quality indicator to predict future values of the network quality indicator, calculating, via the controller, residues between the predicted future values and measured values of the network quality indicator, analyzing, via the controller, the residues over at least one selected frequency band to determine if a threshold has been exceeded for the at least one selected frequency band, and detecting, via the controller, an anomaly event of the network in a frequency band in which a threshold has been exceeded using the residues and measured values of the network quality indicator.

Growing community of inventors

Bridgewater, NJ, United States of America

Kai Yang