Ranking system
    11.
    发明授权

    公开(公告)号:US10305974B2

    公开(公告)日:2019-05-28

    申请号:US14757775

    申请日:2015-12-23

    Abstract: One embodiment provides an apparatus. The apparatus includes ranker logic. The ranker logic is to rank each of a plurality of compute nodes in a data center based, at least in part, on a respective node score. Each node score is determined based, at least in part, on a utilization (U), a saturation parameter (S) and a capacity factor (Ci). The capacity factor is determined based, at least in part, on a sold capacity (Cs) related to the compute node. The ranker logic is further to select one compute node with a highest node score for placement of a received workload.

    Ranking system
    14.
    发明申请
    Ranking system 审中-公开

    公开(公告)号:US20170187790A1

    公开(公告)日:2017-06-29

    申请号:US14757775

    申请日:2015-12-23

    CPC classification number: H04L67/1008 H04L41/5025

    Abstract: One embodiment provides an apparatus. The apparatus includes ranker logic. The ranker logic is to rank each of a plurality of compute nodes in a data center based, at least in part, on a respective node score. Each node score is determined based, at least in part, on a utilization (U), a saturation parameter (S) and a capacity factor (Ci). The capacity factor is determined based, at least in part, on a sold capacity (Cs) related to the compute node. The ranker logic is further to select one compute node with a highest node score for placement of a received workload.

    Telemetry Adaptation
    15.
    发明申请

    公开(公告)号:US20170187570A1

    公开(公告)日:2017-06-29

    申请号:US14998176

    申请日:2015-12-23

    Abstract: Methods, systems, and storage media for telemetry adaptation are disclosed herein. In an embodiment, a networking device may include a data collector agent module to receive measurement data from measurement sources according to an initial telemetry policy and to provide the measurement data to the one or more servers of the monitoring system. The networking device may include an anomaly detection module to receive measurement data from the data collector agent module, to detect an anomaly in the measurement data, and to provide an indication of the anomaly to the data collector agent module for the data collector agent module to provide a first modified telemetry policy for the measurement sources.

    Automatic model-based computing environment performance monitoring

    公开(公告)号:US11237898B2

    公开(公告)日:2022-02-01

    申请号:US16574597

    申请日:2019-09-18

    Abstract: Various systems and methods for implementing automatic model generation for performance monitoring are described herein. A performance monitoring system includes a model manager to: identify a performance model that predicts performance of an operational node, the performance model based on telemetry data from the operational node; and implement an automatic verification operation to analyze the performance model and revise the performance model when the performance model is no longer valid; and an event processor to: initiate a remedial action at the operational node when the performance model indicates an alert state.

    Technologies for execution acceleration in heterogeneous environments

    公开(公告)号:US10469570B2

    公开(公告)日:2019-11-05

    申请号:US14998308

    申请日:2015-12-26

    Abstract: Technologies for provisioning jobs to servers at a datacenter include a compute device to identify a class of each of a plurality of available servers in the datacenter, wherein the class is indicative of a set of hardware included on the corresponding server. The compute device selects a workload that includes a plurality of jobs to provision to a subset of the available servers and determines a provisioning configuration for the workload from a set of prospective configurations as a function of a rack utilization of each prospective configuration, the classes utilized by each prospective configuration, and a number of racks utilized by each prospective configuration. The provisioning configuration identifies a subset of the available servers to which to provision the jobs of the workload.

    METHODS AND APPARATUS FOR CONDITIONAL CLASSIFIER CHAINING IN A CONSTRAINED MACHINE LEARNING ENVIRONMENT

    公开(公告)号:US20190124488A1

    公开(公告)日:2019-04-25

    申请号:US16226131

    申请日:2018-12-19

    Abstract: Methods, apparatus, systems, and articles of manufacture for conditional classifier chaining in a constrained machine learning environment are disclosed. An example apparatus includes a classification controller to select a first model to be utilized to classify a first feature identified from sensor data. A memory controller is to copy the first model to a memory. A machine learning processor is to apply the first model to the first feature to create a first classification output, the first classification output indicating an identified class. The classification controller is to, in response to a determination that the first classification output identifies a second model to be used for classification, instruct the memory controller to load the second model into the memory. The machine learning processor is to apply the second model to the second feature to create a second classification output.

    METHODS AND APPARATUS TO IMPROVE ACCURACY OF EDGE AND/OR A FOG-BASED CLASSIFICATION

    公开(公告)号:US20190102659A1

    公开(公告)日:2019-04-04

    申请号:US16147043

    申请日:2018-09-28

    Abstract: Methods, apparatus, systems and articles of manufacture to improve accuracy of a fog/edge-based classifier system are disclosed. An example apparatus includes a transducer to mounted on a tracked object, the transducer to generate data samples corresponding to the tracked object; a discriminator to: generate a first classification using a first model based on a first calculated feature of the first data samples from the transducer, the first model corresponding to calculated features determined from second data samples, the second data samples obtained prior to the first data samples; generate an offset based on a difference between a first model feature the first model and a second model feature of a second model, the second model being different than the first model; and adjust the first calculated feature using the offset to generate an adjusted feature; a pattern matching engine to generate a second classification using vectors corresponding to the second model based on the adjusted feature; and a counter to, when the first classification matches the second classification, increment a count.

Patent Agency Ranking