知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

22 records (took 0.019 seconds)

    Network traffic prediction using long short term memory neural networks
    3.
    发明授权
    Network traffic prediction using long short term memory neural networks 有权

    公开(公告)号：US10855550B2

    公开(公告)日：2020-12-01

    申请号：US15352938

    申请日：2016-11-16

    Applicant: Cisco Technology, Inc.

    Inventor： Mehdi Nikkhah ,  Preethi Natarajan

    IPC: H04L12/24 ,  H04L12/26 ,  G06N3/08 ,  G06N3/04

    Abstract: A server uses an LSTM neural network to predict a bandwidth value for a computer network element using past traffic data. The server receives a time series of bandwidth utilization of the computer network element. The time series includes bandwidth values associated with a respective time values. The LSTM neural network is trained with a training set selected from at least a portion of the time series. The server generates a predicted bandwidth value associated with a future time value based on the LSTM neural network. The provisioned bandwidth for the computer network element is adjusted based on the predicted bandwidth value.

    Multipath Provisioning of L4-L7 Traffic in a Network
    6.
    发明申请
    Multipath Provisioning of L4-L7 Traffic in a Network 审中-公开
    网络中L4-L7流量的多路径配置

    公开(公告)号：US20160119196A1

    公开(公告)日：2016-04-28

    申请号：US14612691

    申请日：2015-02-03

    Applicant: Cisco Technology, Inc.

    Inventor： Marc Portoles Comeras ,  Preethi Natarajan ,  Alberto Rodriguez Natal ,  Fabio Rodolfo Maino ,  Alberto Cabellos Aparicio ,  Vasileios Lakafosis ,  Lorand Jakab

    IPC: H04L12/24 ,  H04L12/707

    CPC classification number: H04L41/5054 ,  H04L45/24 ,  H04L47/125 ,  H04L47/193 ,  H04L69/14 ,  H04L69/16 ,  H04L69/161

    Abstract: Techniques are provided for a network mapping server device in a network to receive a connection upgrade message comprising information to establish a first data flow from a first endpoint that does not support multiple subflows for the first data flow according to a multipath protocol, where multiple subflows subdivide the first data flow across two or more network paths. The information in the connection upgrade message is analyzed in order to resolve network connectivity to determine potential network connections for at least two subflows of the first data flow to a second endpoint. A response message is sent comprising information configured to establish at least two subflows for the first data flow between the first endpoint and the second endpoint.

    Abstract translation: 为网络中的网络映射服务器设备提供技术，以接收包括信息的连接升级消息，以便根据多路径协议从不支持第一数据流的多个子流的第一端点建立第一数据流，其中多个子流 第一个数据流跨越两个或多个网络路径细分。 分析连接升级消息中的信息以便解析网络连接以确定到第二端点的至少两个子流的第一数据流的潜在网络连接。 发送响应消息，包括被配置为为第一端点和第二端点之间的第一数据流建立至少两个子流的信息。

    Estimating utilization of network resources using time series data
    7.
    发明授权
    Estimating utilization of network resources using time series data 有权

    公开(公告)号：US11281986B2

    公开(公告)日：2022-03-22

    申请号：US16913262

    申请日：2020-06-26

    Applicant: Cisco Technology, Inc.

    Inventor： Hao Hu ,  Preethi Natarajan ,  Nii Ako Ampa-Sowa ,  Stephen E. Jerman

    IPC: G06N7/00 ,  H04L41/14 ,  H04L43/0876 ,  G06F17/18

    Abstract: In one implementation, a method includes obtaining time series data. The time serious data includes a plurality of network utilization measurements. The plurality of network utilization measurements is indicative of a plurality of utilizations of one or more resources of a network resource at a plurality of times. The method also includes determining whether the time series data comprises a plurality of segments. Each segment of the plurality of segments is associated with a separate regression model and each segment includes a portion of the time series data. The method further includes identifying a current segment from the time series data when the time series data comprises the plurality of segments. The method further includes determining an estimated network utilization based on a current regression model associated with the current segment.

    ESTIMATING UTILIZATION OF NETWORK RESOURCES USING TIME SERIES DATA
    8.
    发明申请
    ESTIMATING UTILIZATION OF NETWORK RESOURCES USING TIME SERIES DATA 审中-公开

    公开(公告)号：US20200327436A1

    公开(公告)日：2020-10-15

    申请号：US16913262

    申请日：2020-06-26

    Applicant: Cisco Technology, Inc.

    Inventor： Hao Hu ,  Preethi Natarajan ,  Nii Ako Ampa-Sowa ,  Stephen E. Jerman

    IPC: G06N7/00 ,  H04L12/24 ,  H04L12/26 ,  G06F17/18

    Abstract: In one implementation, a method includes obtaining time series data. The time serious data includes a plurality of network utilization measurements. The plurality of network utilization measurements is indicative of a plurality of utilizations of one or more resources of a network resource at a plurality of times. The method also includes determining whether the time series data comprises a plurality of segments. Each segment of the plurality of segments is associated with a separate regression model and each segment includes a portion of the time series data. The method further includes identifying a current segment from the time series data when the time series data comprises the plurality of segments. The method further includes determining an estimated network utilization based on a current regression model associated with the current segment.

    ESTIMATING UTILIZATION OF NETWORK RESOURCES USING TIME SERIES DATA
    10.
    发明申请
    ESTIMATING UTILIZATION OF NETWORK RESOURCES USING TIME SERIES DATA 审中-公开
    使用时间序列数据估计网络资源的利用率

    公开(公告)号：US20160323158A1

    公开(公告)日：2016-11-03

    申请号：US14699961

    申请日：2015-04-29

    Applicant: Cisco Technology, Inc.

    Inventor： Hao Hu ,  Preethi Natarajan ,  Nii Ako Ampa-Sowa ,  Stephen E. Jerman

    IPC: H04L12/26 ,  G06N7/00

    CPC classification number: G06N7/005 ,  G06F17/18 ,  H04L41/145 ,  H04L43/0876

    Abstract: In one implementation, a method includes obtaining time series data. The time serious data includes a plurality of network utilization measurements. The plurality of network utilization measurements is indicative of a plurality of utilizations of one or more resources of a network resource at a plurality of times. The method also includes determining whether the time series data comprises a plurality of segments. Each segment of the plurality of segments is associated with a separate regression model and each segment includes a portion of the time series data. The method further includes identifying a current segment from the time series data when the time series data comprises the plurality of segments. The method further includes determining an estimated network utilization based on a current regression model associated with the current segment.

    Abstract translation: 在一个实现中，一种方法包括获得时间序列数据。 时间严重的数据包括多个网络利用率测量。 多个网络利用度测量指示多个时间网络资源的一个或多个资源的多个利用。 该方法还包括确定时间序列数据是否包括多个片段。 多个片段中的每个片段与单独的回归模型相关联，并且每个片段包括时间序列数据的一部分。 该方法还包括：当时间序列数据包括多个段时，从时间序列数据中识别当前段。 该方法还包括基于与当前段相关联的当前回归模型来确定估计的网络利用率。

Patent Agency Ranking