THRESHOLD SELECTION FOR KPI CANDIDACY IN ROOT CAUSE ANALYSIS OF NETWORK ISSUES

    公开(公告)号:US20220231903A1

    公开(公告)日:2022-07-21

    申请号:US17716913

    申请日:2022-04-08

    Abstract: In one embodiment, a network assurance service that monitors a network maps time series of values of key performance indicator (KPIs) measured from the network to lists of unique values from the time series. The service sets a target alarm rate for anomaly detection alarms raised by the network assurance service. The service uses an optimization function to identify a set of thresholds for the KPIs. The optimization function is based on: a comparison between the target alarm rate and a fraction of network issues flagged by the service as outliers, KPI thresholds selected based on the lists of unique values from the time series, and a number of thresholds that the KPIs must cross for the service to raise an alarm. The service raises an anomaly detection alarm for the monitored network based on the identified set of thresholds for the KPIs.

    BSS color assignment in infrastructure WLANS

    公开(公告)号:US10863379B2

    公开(公告)日:2020-12-08

    申请号:US16505105

    申请日:2019-07-08

    Abstract: In one embodiment, a basic service set (BSS) color assignment apparatus includes a processor, and a memory to store data used by the processor, wherein the processor is operative to calculate, for each one BSS color of a plurality of BSS colors, a BSS color assignment metric at least based on use of the one BSS color in at least one neighboring BSS neighboring a BSS of an access point in an infrastructure wireless local area network (WLAN), yielding a plurality of BSS color assignment metrics for the BSS of the access point, select one of the plurality of BSS color assignment metrics associated with an optimal choice BSS color of the plurality of BSS colors for the BSS of the access point and assign the optimal choice BSS color to the BSS of the access point.

    Characterizing movement behaviors of wireless nodes in a network

    公开(公告)号:US10542517B1

    公开(公告)日:2020-01-21

    申请号:US16539359

    申请日:2019-08-13

    Abstract: In one embodiment, a device receives location estimates for a wireless node in a network, each location estimate having an associated timestamp. The device applies hierarchical clustering to the received location estimates and their associated timestamps, to identify locations and points in time in which the wireless node was stationary. The device performs sequence modeling on the identified locations and points in time in which the wireless node was stationary, to form a sequence of locations and associated time periods in which the wireless node was stationary. The device associates the wireless node with a behavioral profile based on the sequence of locations and associated time periods in which the wireless node. The device generates, based in part on the behavioral profile for the wireless node, a predictive model that predicts a location of the wireless node at a particular point in time.

    Resource allocation for OFDMA with preservation of wireless location accuracy

    公开(公告)号:US10524272B2

    公开(公告)日:2019-12-31

    申请号:US15865877

    申请日:2018-01-09

    Abstract: In one embodiment, a control device associated with a wireless network of a given location determines a reference quality of location readings between access points and client devices based on using substantially all of an available wireless communication bandwidth. The control device may then determine channel state information (CSI) between the client devices and access points for each orthogonal frequency-division multiple access (OFDMA) resource unit (RU), and selects a subset of RUs for allocation to each respective client device, based on the subset of RUs allocated to each respective client device i) surpassing a determined threshold of certain parameters of the CSI, while also ii) providing a minimum quality of a location reading based on using only the subset of RUs as compared to the reference quality of location readings. The control device may then allocate the selected subset of RUs to each respective client device for location-preserving OFDMA-signaling-based communication.

    DETECTING TRANSIENT VS. PERPETUAL NETWORK BEHAVIORAL PATTERNS USING MACHINE LEARNING

    公开(公告)号:US20190238421A1

    公开(公告)日:2019-08-01

    申请号:US15880600

    申请日:2018-01-26

    Abstract: In one embodiment, a network assurance service that monitors a network detects a pattern of network measurements from the network that are associated with a particular network problem. The network assurance service tracks characteristics of the detected pattern over time. The network assurance service uses the tracked characteristics of the detected pattern over time as input to a machine learning-based pattern analyzer. The pattern analyzer is configured to determine whether the detected pattern is a perpetual or transient pattern in the network, and the pattern analyzer is further configured to detect anomalies in the characteristics of the pattern. The network assurance service initiates a change to the network based on an output of the machine learning-based pattern analyzer.

    DETECTING INCORRECTLY PLACED ACCESS POINTS
    8.
    发明申请
    DETECTING INCORRECTLY PLACED ACCESS POINTS 有权
    检测不正确的接入点

    公开(公告)号:US20150126215A1

    公开(公告)日:2015-05-07

    申请号:US14072851

    申请日:2013-11-06

    CPC classification number: G01S5/0252 G01S5/021 G01S5/0242 H04W64/003

    Abstract: Embodiments provide techniques for detecting access points on a position map, particularly incorrectly placed access points. For each access point in a plurality of access points, a subset of the plurality of access points that neighbor the access point are identified. Embodiments estimate a location of the access point, based on a respective indication of signal strength from each neighboring access point in the subset of access points and a respective position of each of the neighboring access points in position map. A difference between a recorded position of the access point in the position map and the estimated location of the access point is calculated. Embodiments then determine that the position within the position map for a first one of the plurality of access points is incorrect, based on the determined difference for the first access point.

    Abstract translation: 实施例提供了用于检测位置图上的接入点的技术,特别是不正确放置的接入点。 对于多个接入点中的每个接入点,识别与接入点相邻的多个接入点的子集。 实施例基于来自接入点子集中的每个相邻接入点的信号强度的相应指示和位置图中的每个相邻接入点的相应位置估计接入点的位置。 计算位置图中的接入点的记录位置与接入点的估计位置之间的差异。 然后,实施例基于所确定的第一接入点的差异,确定位置图中位于多个接入点中的第一接入点的位置是不正确的。

Patent Agency Ranking