PEER RISK BENCHMARKING USING GENERATIVE ADVERSARIAL NETWORKS

    公开(公告)号:US20230118857A1

    公开(公告)日:2023-04-20

    申请号:US18067068

    申请日:2022-12-16

    Abstract: A method, computer system, and computer program product are provided for peer risk benchmarking. Customer data for a first network is obtained, wherein the customer data comprises a role of one or more network devices in the first network and a plurality of risk reports corresponding to the one or more network devices, and wherein each risk report is associated with a particular dimension of a plurality of dimensions of risk for the one or more network devices. A network profile image is generated by processing the plurality of risk reports. A generative adversarial network generates a synthetic network profile image from the network profile image, wherein the synthetic network profile image does not include the customer data. A second network is evaluated using the synthetic network profile image to identify differences between the first network and the second network.

    Management of a computing system with multiple domains

    公开(公告)号:US11606262B2

    公开(公告)日:2023-03-14

    申请号:US16678289

    申请日:2019-11-08

    Abstract: A method, computer program product, and system are provided to identify a target computing system configured to operate in a plurality of service domains. The method, computer program product, and system also, for each service domain of the plurality of service domains: collect current values of: (i) a metric indicating success of the service domain, and (ii) one or more other collection metrics of the service domain; determine one or more predominant metrics from the one or more other collection metrics, based, at least in part, on a statistical regression between the current values of the metric indicating success and the one or more other collection metrics, the one or more predominant metrics being predominant in affecting the metric indicating success; and output an indication of the current values of the metric indicating success and the one or more predominant metrics.

    Peer risk benchmarking using generative adversarial networks

    公开(公告)号:US11533241B2

    公开(公告)日:2022-12-20

    申请号:US17704449

    申请日:2022-03-25

    Abstract: A method, computer system, and computer program product are provided for peer risk benchmarking. Customer data for a first network is obtained, wherein the customer data comprises a role of one or more network devices in the first network and a plurality of risk reports corresponding to the one or more network devices, and wherein each risk report is associated with a particular dimension of a plurality of dimensions of risk for the one or more network devices. A network profile image is generated by processing the plurality of risk reports. A generative adversarial network generates a synthetic network profile image from the network profile image, wherein the synthetic network profile image does not include the customer data. A second network is evaluated using the synthetic network profile image to identify differences between the first network and the second network.

    RELIABILITY ESTIMATION SYSTEM AND RELIABILITY ESTIMATION METHOD

    公开(公告)号:US20220321447A1

    公开(公告)日:2022-10-06

    申请号:US17596212

    申请日:2019-06-26

    Abstract: Provided are a reliability estimation system and a reliability estimation method capable of reducing a calculation amount of a reliability of a plurality of networks between terminals in communication between the terminals over the plurality of networks. The reliability estimation system according to the present invention calculates, for each network, a contraction reliability Rx, a contraction reliability Rx′ when nodes are contracted, and a contraction reliability RB′ between the networks including the terminals, and a true value of the reliability between the terminals over the plurality of networks is between a product P1 (=RB′ Rx) and a product P2 (=RB′ Rx′). Instead of calculating the true value of the reliability, only an upper limit and a lower limit are calculated, and thus, it is possible to significantly low additional remark the calculation amount.

    Selectively monitoring a network of network function chains based on probability of service level agreement violation

    公开(公告)号:US11425049B2

    公开(公告)日:2022-08-23

    申请号:US16685877

    申请日:2019-11-15

    Abstract: In some implementations, a method includes conducting, by a network device, a query associated with a network function chain comprising a plurality of switches and middleboxes to verify whether a service performed by the network function chain complies with a Service Level Agreement (SLA); computing, by the network device, based on a result of the query, a difference in metric value between an actual performance metric of a packet passing through a path in the network function chain and an expected performance metric of the packet passing through the path; deriving, by the network device, a probability of SLA violation associated with the path based on the difference in metric value; and selectively monitoring, by the network device, a network of network function chains by monitoring the path for passive performance measurements based on the probability of SLA violation.

Patent Agency Ranking