Abstract: A system can determine performance data for updates created by update creators that execute on devices during a time period, the performance data indicating performance of a group of metrics for a respective update of the updates. The system can determine a first ranking of the update creators for the time period based on the performance data. The system can determine a second ranking of the update creators based on applying a pairwise comparison count of respective rankings of update creators of the first ranking and rankings for time periods prior to the time period. The system can determine whether to publish a first update from a first update creator of the update creators based on a position of the first update creator among the update creators in the second ranking.

Abstract: Predictive build quality assessment is disclosed, e.g., to predict performance of a candidate software build prior to deploying the candidate software build in a production environment. An example method can include comparing performance of a candidate software build with performance data associated with clusters of previous builds. A cluster having similar performance to the candidate software build can be selected. A source code graph for the candidate software build can be compared to source code graphs of builds included in the selected cluster. A previous build in the cluster, which is associated with a source code graph that is similar to the candidate software build's source code graph, can be selected. Individual performance data associated with the selected previous build can be inferred to be the predicted performance of the candidate software build, thereby informing decision making regarding further testing, modification, and/or deployment of the candidate software build into production.

Abstract: A method may include receiving data from a device within a network, wherein the data is associated with one or more features of the device, and determining a subset of the features of the device that is associated with a runtime behavior of the device. The method may also perform a univariate analysis on a feature dataset that is associated with the subset of the features of the device, perform a multivariate analysis on the feature dataset that is associated with correlated features in the subset of the features, and generate a device signature based on the univariate analysis and the multivariate analysis.

Abstract: An apparatus comprises a processing device configured to generate a model of a plurality of devices characterizing relationships between the devices, to build a device dependency chain for the devices based on the model, to predict workload for each of the devices in one or more time slots of a given time period, and to determine a deployment schedule for the devices based on the device dependency chain and the predicted workload. The processing device is also configured to utilize the deployment schedule to select a device of the devices on which to perform an operation, to determine whether the selected device corresponds to an additional device of the devices configured to operate in place of the selected device during performance of the operation, and to control performance of the operation on the selected device responsive to the determination of whether the selected device corresponds to the additional device.

Abstract: A system can determine performance data for updates created by update creators that execute on devices during a time period, the performance data indicating performance of a group of metrics for a respective update of the updates. The system can determine a first ranking of the update creators for the time period based on the performance data. The system can determine a second ranking of the update creators based on applying a pairwise comparison count of respective rankings of update creators of the first ranking and rankings for time periods prior to the time period. The system can determine whether to publish a first update from a first update creator of the update creators based on a position of the first update creator among the update creators in the second ranking.

Abstract: An apparatus comprises a processing device configured to monitor, over time intervals each comprising multiple time slices, client requests to access software container instances hosted by container host devices of a geographically-distributed software container platform, and to generate cluster pattern data comprising geographic clusters for the software container instances in each of the time slices. The processing device is also configured to predict, for a given time slice in a given subsequent time interval, formation of a geographic cluster of client requests for a given software container instance based on the cluster pattern data. The processing device is further configured to calculate network distances from the predicted geographic cluster to each of the container host devices, to select one of the container host devices based on the calculated network distances, and to proactively replicate the given software container instance in the selected container host device.

Abstract: An apparatus comprises a processing device configured to generate a model characterizing relationships between devices in an information technology infrastructure, to build a device dependency chain for the devices based at least in part on the generated model, and to predict workload for each of the devices in each of two or more time slots of a given time period. The processing device is also configured to determine a deployment schedule for the devices based at least in part on the device dependency chain and the predicted workload for each of the devices in each of the two or more time slots of the given time period, to identify an operation to be performed on the devices, and to utilize the deployment schedule to select ones of the devices on which to perform the identified operation in each of the two or more time slots of the given time period.

Abstract: Predictive build quality assessment is disclosed, e.g., to predict performance of a candidate software build prior to deploying the candidate software build in a production environment. An example method can include comparing performance of a candidate software build with performance data associated with clusters of previous builds. A cluster having similar performance to the candidate software build can be selected. A source code graph for the candidate software build can be compared to source code graphs of builds included in the selected cluster. A previous build in the cluster, which is associated with a source code graph that is similar to the candidate software build's source code graph, can be selected. Individual performance data associated with the selected previous build can be inferred to be the predicted performance of the candidate software build, thereby informing decision making regarding further testing, modification, and/or deployment of the candidate software build into production.

Abstract: An apparatus includes at least one processing device configured to obtain event metadata for events published by event sources to an event platform, the event metadata comprising static event tags for respective ones of the events. The at least one processing device is also configured to generate dynamic event tags having an association with event types based at least in part on analysis of real-time event traffic comprising a subset of the events published by the event sources to the event platform over a designated time period. The at least one processing device is further configured to train a machine learning model utilizing the static event tags and the association of the dynamic event tags with the event types, receive a query comprising event parameters, and provide a response to the query by utilizing the trained machine learning model to match events with the event parameters in the query.

Abstract: A method includes monitoring client requests to access software container instances hosted by container host devices of a geographically-distributed software container platform and identifying, for a given software container instance hosted by a first one of the container host devices, geographic clusters of the client requests. The method also includes calculating a network distance from a given one of the geographic clusters to each of at least a subset of the container host devices. The method further includes replicating the given software container instance in a second one of the container host devices responsive to determining that the calculated network distance from the given geographic cluster to the second container host device is at least a threshold amount less than the calculated network distance from the given geographic cluster to the first container host device.

Abstract: An apparatus includes a processing device configured to obtain time series diagnostic data associated with assets in an information technology (IT). The processing device is also configured to generate first modality information comprising behavior labels assigned to each of a plurality of time periods, a given behavior label for a given time period being based at least in part on measured feature values for the features collectively in the given time period. The processing device is further configured to generate second modality information comprising feature deltas characterizing differences between measured feature values for interdependent feature pairs.

Abstract: An apparatus comprises a processing device configured to generate a model of a plurality of devices characterizing relationships between the devices, to build a device dependency chain for the devices based on the model, to predict workload for each of the devices in one or more time slots of a given time period, and to determine a deployment schedule for the devices based on the device dependency chain and the predicted workload. The processing device is also configured to utilize the deployment schedule to select a device of the devices on which to perform an operation, to determine whether the selected device corresponds to an additional device of the devices configured to operate in place of the selected device during performance of the operation, and to control performance of the operation on the selected device responsive to the determination of whether the selected device corresponds to the additional device.

Abstract: A method comprises receiving a request to execute an instance of a given software container, determining source code entities of source code of the given software container, and generating a given software container profile for the given software container based at least in part on rankings associated with the source code entities. The method also comprises creating a resource management plan for the given software container utilizing one or more machine learning algorithms, the resource management plan comprising resource management metric thresholds determined based at least in part on historical resource utilization data for additional software containers having associated software container profiles similar to the given software container profile.

Abstract: A method includes detecting an error that has occurred in one or more assets of an enterprise system and generating a visual error signature of the detected error, the visual error signature comprising at least a portion of a graph-based visualization of operation of the assets. The method also includes providing the generated visual error signature for the detected error as input to a machine learning model and utilizing the machine learning model to classify the visual error signature for the detected error as belonging to at least a given one of a plurality of error classes, the machine learning model being trained using historical visual error signatures for previously-detected errors. The method further includes identifying at least one action taken to remediate each of one or more previously-detected errors of the given error class and remediating the detected error utilizing one or more of the identified actions.

Abstract: An apparatus comprises a processing device configured to generate a model characterizing relationships between devices in an information technology infrastructure, to build a device dependency chain for the devices based at least in part on the generated model, and to predict workload for each of the devices in each of two or more time slots of a given time period. The processing device is also configured to determine a deployment schedule for the devices based at least in part on the device dependency chain and the predicted workload for each of the devices in each of the two or more time slots of the given time period, to identify an operation to be performed on the devices, and to utilize the deployment schedule to select ones of the devices on which to perform the identified operation in each of the two or more time slots of the given time period.

Abstract: An apparatus comprises a processing device configured to monitor, over time intervals each comprising multiple time slices, client requests to access software container instances hosted by container host devices of a geographically-distributed software container platform, and to generate cluster pattern data comprising geographic clusters for the software container instances in each of the time slices. The processing device is also configured to predict, for a given time slice in a given subsequent time interval, formation of a geographic cluster of client requests for a given software container instance based on the cluster pattern data. The processing device is further configured to calculate network distances from the predicted geographic cluster to each of the container host devices, to select one of the container host devices based on the calculated network distances, and to proactively replicate the given software container instance in the selected container host device.

Abstract: A method may include receiving data from a device within a network, wherein the data is associated with one or more features of the device, and determining a subset of the features of the device that is associated with a runtime behavior of the device. The method may also perform a univariate analysis on a feature dataset that is associated with the subset of the features of the device, perform a multivariate analysis on the feature dataset that is associated with correlated features in the subset of the features, and generate a device signature based on the univariate analysis and the multivariate analysis.

Abstract: An apparatus includes a processing device comprising a processor coupled to a memory. The processing device is configured to obtain metrics characterizing performance, over two or more periods of time, of software container instances of each of a plurality of software container images. The processing device is also configured to determine, for each of the two or more periods of time, a periodic quality ranking of the plurality of software container images based at least in part on the obtained metrics. The processing device is further configured to generate an overall quality ranking of the plurality of software container images utilizing a consensus ranking aggregation algorithm configured to aggregate the periodic quality rankings of the plurality of software container images across the two or more periods of time, and to publish the overall quality ranking of the plurality of software container images to a software container registry.

Abstract: An apparatus comprises a processing device configured to obtain, for a given issue associated with one or more assets of an information technology infrastructure, a description of the given issue and system logs characterizing operation of the one or more assets. The processing device is also configured to generate one or more semantic graphs characterizing the description of the given issue and one or more state transition graphs characterizing a sequence of occurrence of states of the operation of the one or more assets. The processing device is further configured to provide a combined representation of the semantic and state transition graphs for the given issue to a machine learning model, to identify recommended classifications for the given issue based on an output of the machine learning model, and to initiate remedial action in the information technology infrastructure based on the recommended classifications for the given issue.

Abstract: An apparatus includes a processing device configured to obtain time series diagnostic data associated with assets in an information technology (IT). The processing device is also configured to generate first modality information comprising behavior labels assigned to each of a plurality of time periods, a given behavior label for a given time period being based at least in part on measured feature values for the features collectively in the given time period. The processing device is further configured to generate second modality information comprising feature deltas characterizing differences between measured feature values for interdependent feature pairs.