Abstract: An apparatus comprises a processing device configured to obtain monitoring data for devices comprising a plurality of features, determining two or more rankings of the features using two or more filter-based feature selection algorithms, and selecting a subset of the features based at least in part on the two or more rankings. The processing device is also configured to generate a failure prediction for a given one of the devices using at least one classifier that takes as input the selected subset of features, and applying a conformal prediction framework to the generated failure prediction to obtain a confidence measure indicating a quality of the generated failure prediction and a credibility measure indicating a quality of the monitoring data. The processing device is further configured to initiate one or more remedial actions based at least in part on the generated failure prediction, the confidence measure, and the credibility measure.

Abstract: An apparatus comprises a processing device configured to receive a request to schedule a workload and to generate a graph representation of tasks of the workload, the graph representation comprising two or more levels each comprising nodes representing tasks of the workload. The processing device is also configured to identify a plurality of paths each representing a sequence of tasks of the workload that starts at a root node in a first level of the graph representation and traverses one or more additional nodes in one or more additional levels of the graph representation. The processing device is further configured to determine a ranking of the plurality of paths and to assign the tasks of the workload for execution on assets of an information technology infrastructure based at least in part on the determined ranking of the plurality of paths.

Abstract: An apparatus comprises a processing device configured to select prioritization criteria for a plurality of virtual computing resources and to determine, for at least one criterion in the selected prioritization criteria, at least one directional correlation between the at least one criterion and at least one other criterion in the selected prioritization criteria. The processing device is also configured to generate a prioritization of the plurality of virtual computing resources utilizing a multi-criteria decision analysis algorithm. The multi-criteria decision analysis algorithm is based at least in part on the determined at least one directional correlation. The processing device is further configured to perform one or more scheduling operations for the plurality of virtual computing resources based at least in part on the generated prioritization of the plurality of virtual computing resources.

Abstract: Embodiments are described for an autonomously and dynamically allocating resources in a distributed network based on forecasted a-priori CPU resource utilization, rather than a manual throttle setting. A multivariate (CPU idle %, disk I/O, network and memory) rather than single variable approach for Probabilistic Weighted Fuzzy Time Series (PWFTS) is used for forecasting compute resources. The dynamic throttling is combined with an adaptive compute change rate detection and correction. A single spike detection and removal mechanism is used to prevent the application of too many frequent throttling changes. Such a method can be implemented for several use cases including, but not limited to: cloud data migration, replication to a storage server, system upgrades, bandwidth throttling in storage networks, and garbage collection.

Abstract: Systems and methods for implementing a workload fairness policy at the data cache level within a non-volatile memory express solid-state drive utilizes a prioritization technique that predicts a degree of intensity for workloads based on a request generation rate. The degree of intensity is used to prioritize and rank workloads, thereby, avoiding interference between requests from each other.

Abstract: Security drift can be automatically handled in cloud environments. A security audit engine can be configured to extract security configuration datasets from cloud resources and create text sentences from the datasets as well as from a golden configuration. These text sentences can be encoded as vectors in an n-dimensional space. Probability distributions can then be generated using the vectors such as by using an unsupervised clustering algorithm. Distance matrixes can then be generated from the probability distributions. A probability distribution pertaining to a dataset and a probability distribution pertaining to the golden configuration can then be compared and normalized using a transport to thereby yield a security drift score representing a divergence of the corresponding security settings from the golden configuration. When a security drift score exceeds a threshold, the security audit engine can take appropriate action.

Abstract: A method and system for reliably forecasting storage disk failure. Specifically, the method and system disclosed herein entail predicting whether one or more storage disks may fail within a future time period. Further, the storage disk failure forecasts may rely on machine learning classification coupled with prediction reliability scoring.

Abstract: An apparatus comprises a processing device configured to obtain workload traces characterizing resource execution metrics associated with workloads executing in an information technology infrastructure and to generate sets of workload causality profiles characterizing relationships between the resource execution metrics, the sets of workload causality profiles comprising first and at least second sets of workload causality profiles generated using first and at least second different types of models. The processing device is also configured to determine sets of causal topics comprising recurring patterns of the relationships between different ones of the resource execution metrics found in each of the sets of workload causality profiles. The processing device is further configured to identify clusters of causal topics each comprising at least one causal topic that is part of the first and second sets of causal topics, and to perform diagnosis of issues affecting the workloads based on the identified clusters.

Abstract: Presented herein are embodiments that use a language model to embed or encode configuration elements (e.g., commands, prompts, etc.) into dense, latent representations that incorporate semantic and contextual information. Using a trained language model, a configuration for a network device may be converted into a set of configuration path sentences. Given a first set of encoded configuration path sentences for a first configuration and a second set of encoded configuration path sentences for a second configuration, these two sets may be compared to gauge a degree of difference between the two sets. In one or more embodiments, an Optimal Transport method with Wasserstein distance metric may be used to obtain a comparison value that gauges difference between the two configurations. In one or more embodiments, the comparison valuation may be labeled or classified by comparing the comparison value to one or more pre-defined thresholds.

Abstract: A first cloud vendor is registered by a backup application. A file is moved from backup storage of the backup application to the first cloud vendor. A reference is maintained at the backup storage to the first file residing at the first cloud vendor. A second cloud vendor is registered by the backup application. The backup application directs a migration of the file from the first cloud vendor to the second cloud vendor without recalling the file to the backup storage. A reference maintained at the backup storage is updated to refer to the file now residing at the second cloud vendor. The updated reference is maintained at the backup storage.

Abstract: A method for managing bugs includes obtaining, by a bug deduplication system, a set of bugs, performing an encoding on each section of a first bug of the set of bugs to obtain encoded sections, wherein the encoded sections comprise a first encoded section and a second encoded section, applying a first classification model to the first encoded section to obtain a first section score, applying a second classification model to the second encoded section to obtain a second section score, generating a confidence score based on the first encoded section and the second section, and providing the confidence score to a client, wherein the client initiates a corrective action for the first bug based on the confidence score.

Abstract: An apparatus comprises a processing device configured to identify a plurality of workloads to be scheduled for execution on a storage system and to analyze the plurality of workloads to predict a magnitude of storage capacity savings achieved by applying one or more deduplication algorithms to data of the plurality of workloads. The processing device is further configured to determine a prioritization of the plurality of workloads based at least in part on the predicted magnitude of the storage capacity savings achieved by applying the one or more deduplication algorithms to the data of the plurality of workloads, and to schedule the plurality of workloads for execution on the storage system based at least in part on the determined prioritization of the plurality of workloads.

Abstract: An apparatus comprises a processing device configured to select prioritization criteria for a plurality of virtual computing resources and to determine, for at least one criterion in the selected prioritization criteria, at least one directional correlation between the at least one criterion and at least one other criterion in the selected prioritization criteria. The processing device is also configured to generate a prioritization of the plurality of virtual computing resources utilizing a multi-criteria decision analysis algorithm. The multi-criteria decision analysis algorithm is based at least in part on the determined at least one directional correlation. The processing device is further configured to perform one or more scheduling operations for the plurality of virtual computing resources based at least in part on the generated prioritization of the plurality of virtual computing resources.

Abstract: A method for managing bugs includes obtaining, by a bug deduplication system, a set of bugs, performing an encoding on each section of a first bug of the set of bugs to obtain encoded sections, wherein the encoded sections comprise a first encoded section and a second encoded section, applying a first classification model to the first encoded section to obtain a first section score, applying a second classification model to the second encoded section to obtain a second section score, generating a confidence score based on the first encoded section and the second section, and providing the confidence score to a client, wherein the client initiates a corrective action for the first bug based on the confidence score.

Abstract: An apparatus comprises a processing device configured to receive a request to schedule a workload and to generate a graph representation of tasks of the workload, the graph representation comprising two or more levels each comprising nodes representing tasks of the workload. The processing device is also configured to identify a plurality of paths each representing a sequence of tasks of the workload that starts at a root node in a first level of the graph representation and traverses one or more additional nodes in one or more additional levels of the graph representation. The processing device is further configured to determine a ranking of the plurality of paths and to assign the tasks of the workload for execution on assets of an information technology infrastructure based at least in part on the determined ranking of the plurality of paths.

Abstract: An apparatus comprises at least one processing device configured to generate, for a storage system that is part of an active tier of a storage environment, at least one storage capacity forecast comprising probability values for storage capacity of the storage system over a designated time period. The processing device is also configured to determine whether any of the probability values exceed at least one designated storage capacity threshold and, responsive to determining that a given one of the probability values exceeds the at least one designated storage capacity threshold, to select remedial actions for freeing up space on the active tier of the storage environment. The processing device is further configured to initiate the selected remedial actions for freeing up space on the active tier of the storage environment to prevent the storage system from reaching a designated storage capacity error condition.

Abstract: An apparatus comprises a processing device configured to obtain monitoring data for devices comprising a plurality of features, determining two or more rankings of the features using two or more filter-based feature selection algorithms, and selecting a subset of the features based at least in part on the two or more rankings. The processing device is also configured to generate a failure prediction for a given one of the devices using at least one classifier that takes as input the selected subset of features, and applying a conformal prediction framework to the generated failure prediction to obtain a confidence measure indicating a quality of the generated failure prediction and a credibility measure indicating a quality of the monitoring data. The processing device is further configured to initiate one or more remedial actions based at least in part on the generated failure prediction, the confidence measure, and the credibility measure.

Abstract: An apparatus comprises at least one processing device configured to generate, for a storage system that is part of an active tier of a storage environment, at least one storage capacity forecast comprising probability values for storage capacity of the storage system over a designated time period. The processing device is also configured to determine whether any of the probability values exceed at least one designated storage capacity threshold and, responsive to determining that a given one of the probability values exceeds the at least one designated storage capacity threshold, to select remedial actions for freeing up space on the active tier of the storage environment. The processing device is further configured to initiate the selected remedial actions for freeing up space on the active tier of the storage environment to prevent the storage system from reaching a designated storage capacity error condition.

Abstract: A method and system for policy class based data migration. Specifically, the method and system disclosed herein entail dynamically changing policy classes with which any given data migration may be associated while the given data migration is transpiring. In transitioning between policy classes, different levels of resources, available to different policy classes, respectively, may be allocated to supporting the given data migration.

Abstract: Embodiments are described for an autonomously and dynamically allocating resources in a distributed network based on forecasted a-priori CPU resource utilization, rather than a manual throttle setting. A multivariate (CPU idle %, disk I/O, network and memory) rather than single variable approach for Probabilistic Weighted Fuzzy Time Series (PWFTS) is used for forecasting compute resources. The dynamic throttling is combined with an adaptive compute change rate detection and correction. A single spike detection and removal mechanism is used to prevent the application of too many frequent throttling changes. Such a method can be implemented for several use cases including, but not limited to: cloud data migration, replication to a storage server, system upgrades, bandwidth throttling in storage networks, and garbage collection.