公开(公告)号：US20240338254A1

公开(公告)日：2024-10-10

申请号：US18131726

申请日：2023-04-06

Applicant: Dell Products L.P.

Inventor： Naveen Silvester Muttikal Thomas ,  Gabrielle Kali Sweda ,  Naga Maneesh Kolisetti

IPC: G06F9/50 ,  G06F9/455

CPC classification number: G06F9/505 ,  G06F9/45558 ,  G06F2009/4557

Abstract: An apparatus comprises a processing device configured to obtain monitoring data characterizing resource utilization by information technology (IT) assets having resources assigned from a shared resource pool, to select features for use in modeling predicted resource utilization by the IT assets in future time periods, to generate predictions of resource utilization by the IT assets in each of the future time periods, and to determine whether the predicted resource utilization by a given IT asset exhibits at least a threshold difference from its current resource allocation. The processing device is further configured, response to the determination, to proactively adjust resource allocation to the given IT asset from the shared resource pool for the given future time period based at least in part on the predicted resource utilization, for the given future time period, by other ones of the IT assets having resources assigned from the shared resource pool.

公开(公告)号：US11514347B2

公开(公告)日：2022-11-29

申请号：US16265171

申请日：2019-02-01

Applicant: Dell Products L.P.

Inventor： Hung Dinh ,  Pravash Ranjan Panda ,  Prince Mathew ,  Tousif Mohammed ,  Sabu Syed ,  Jatin Kamlesh Thakkar ,  Naveen Silvester Muttikal Thomas ,  John K. Maxi

IPC: G06N5/04 ,  H04L41/147 ,  G06N20/00 ,  H04L41/16 ,  H04L41/0823 ,  H04L41/0631

Abstract: Methods, apparatus, and processor-readable storage media for identifying and remediating anomalies through cognitively assorted machine learning algorithms are provided herein. A computer-implemented method includes: identifying, using system log data, a target variable based at least in part on correlations between a set of performance indicators of a system and the target variable, and threshold values for the performance indicators relative to the target variable; generating an inference model to predict when the system will enter an adverse state and identify one or more root causes of the system entering the adverse state; using machine reinforcement learning to determine an action policy including actions that remediate the adverse state; predicting that the system will enter the adverse state by applying the inference model to further system log data; and automatically executing one or more actions of the action policy in response to the prediction.

公开(公告)号：US20200250559A1

公开(公告)日：2020-08-06

申请号：US16265171

申请日：2019-02-01

Applicant: Dell Products L.P.

Inventor： Hung Dinh ,  Pravash Ranjan Panda ,  Prince Mathew ,  Tousif Mohammed ,  Sabu Syed ,  Jatin Kamlesh Thakkar ,  Naveen Silvester Muttikal Thomas ,  John K. Maxi

IPC: G06N5/04 ,  H04L12/24 ,  G06N20/00

Abstract: Methods, apparatus, and processor-readable storage media for identifying and remediating anomalies through cognitively assorted machine learning algorithms are provided herein. A computer-implemented method includes: identifying, using system log data, a target variable based at least in part on correlations between a set of performance indicators of a system and the target variable, and threshold values for the performance indicators relative to the target variable; generating an inference model to predict when the system will enter an adverse state and identify one or more root causes of the system entering the adverse state; using machine reinforcement learning to determine an action policy including actions that remediate the adverse state; predicting that the system will enter the adverse state by applying the inference model to further system log data; and automatically executing one or more actions of the action policy in response to the prediction.