白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Anomaly detection in a network based on a key performance indicator prediction model

專利號(hào)
US11616707B2
公開日期
2023-03-28
申請(qǐng)人
VIAVI Solutions Inc.(US AZ Chandler)
發(fā)明人
Dave Padfield; Yannis Petalas; Oliver Parry-Evans
IPC分類
H04L43/0823; H04L43/04; H04L43/16
技術(shù)領(lǐng)域
kpi,prediction,network,anomaly,platform,or,monitoring,value,may,threshold
地域: CA CA San Jose

摘要

A network monitoring platform may obtain a measurement of a particular value of a key performance indicator (KPI) and one or more parameters of the particular value of the KPI. The network monitoring platform may determine a prediction of the particular value of the KPI. The network monitoring platform may determine an amount of error in the prediction of the particular value of the KPI, wherein the amount of error in the prediction of the particular value of the KPI is based on a difference between the prediction of the particular value of the KPI and the measurement of the particular value of the KPI. The network monitoring platform may perform, based on the amount of error in the prediction of the particular value of the KPI, one or more actions.

說(shuō)明書

As a second step, the network monitoring platform may determine classifier chains, whereby labels of target variables may be correlated (e.g., in this example, labels may be parameters and correlation may refer to a common characteristic of the parameters in similarly increased, decreased, or unaffected historical values of the KPI). In this case, the network monitoring platform may use an output of a first label as an input for a second label (as well as one or more input features, which may be other data relating to the particular value of the KPI), and may determine a likelihood that particular parameter that includes a set of characteristic (some of which associated with a historical values of the KPI that were increased (relative to one or more recent values of the KPI), some of which associated with historical values of the KPI that were decreased, and some of which associated with historical values of the KPI that were unaffected) are associated with based on a similarity to other parameters that include similar characteristics. In this way, the network monitoring platform transforms classification from a multilabel-classification problem to multiple single-classification problems, thereby reducing processing utilization. As a third step, the network monitoring platform may determine a Hamming Loss Metric relating to an accuracy of a label in performing a classification by using the validation set of the data. For example, an accuracy with which a weighting applied to each parameter and whether each parameter is associated with increasing, decreasing, or not affecting the value of the prediction, results in a correct prediction of an expected value of the KPI, thereby accounting for differing amounts to which association of any one parameter influences the value of the prediction. As a fourth step, the network monitoring platform may finalize the KPI prediction model based on labels that satisfy a threshold accuracy associated with the Hamming Loss Metric and may use the KPI prediction model for subsequent prediction of whether parameters of a particular value of the KPI are to result in an increased, decreased, or unaffected value of the prediction.

權(quán)利要求

1
微信群二維碼
意見(jiàn)反饋