IP Library › Granted Patent US 12,614,008
Granted Patent B2
US 12,614,008 · App. 18/128,471 · Granted Apr 28, 2026

Artificial aging of digital twin to predict health condition of infrastructure

Inventors: Judith A. Furlong (Natick, MA); Aidan O Mahony (Cork, IE); Robert A. Lincourt, Jr. (Franklin, MA); Said Tabet (Austin, TX)
Assignee: Dell Products L.P.
G06F30/20G06F21/577G06F2119/04
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,614,008
App. No.
18/128,471
Granted
Apr 28, 2026
Kind
B2
Abstract

A method obtains at least one virtual representation representing an infrastructure in a first state and applies a first dataset to the virtual representation to artificially advance the virtual representation to represent the infrastructure in a second state. The method obtains results representing the infrastructure in the second state, wherein at least a portion of the results are indicative of a predicted health condition associated with the infrastructure. The method applies a second dataset to the virtual representation to artificially advance the virtual representation to represent the infrastructure in a third state and obtains results representing the infrastructure in the third state, wherein at least a portion of the results are indicative of an outcome to a solution applied via the second dataset to the predicted health condition associated with the infrastructure.

Claims (46)

1 . A method, comprising:

obtaining at least one virtual representation of an infrastructure which is physically deployed, wherein the virtual representation represents the infrastructure in a first state;

applying a first dataset to the virtual representation of the infrastructure in the first state to artificially advance the virtual representation to represent the infrastructure in a second state and to predict a health condition associated with the infrastructure as represented by the virtual representation of the infrastructure in the second state;

obtaining results representing the infrastructure in the second state, responsive to applying the first dataset to the virtual representation, wherein at least a portion of the results include a predicted health condition associated with the infrastructure as represented by the virtual representation of the infrastructure in the second state;

applying a second dataset to the virtual representation of the infrastructure in the second state to artificially advance the virtual representation to represent the infrastructure in a third state, the second dataset comprising a solution dataset which is applied to address the predicted health condition;

obtaining results representing the infrastructure in the third state, responsive to applying the second dataset to the virtual representation, wherein at least a portion of the results include an outcome to the solution dataset applied to address the predicted health condition; and

initiating one or more actions with respect to the infrastructure to address the predicted health condition, when the outcome to the solution dataset applied to address the predicted health condition is deemed successful;

wherein the steps are performed by at least one processor and at least one memory storing executable computer program instructions.

2 . The method of claim 1 , wherein, when the infrastructure comprises a computing infrastructure, the first state, the second state, and the third state of the computing infrastructure, which the virtual representation represents, corresponds to at least one of a hardware configuration, a software configuration, and a data configuration of the computing infrastructure at a first time instance, a second time instance, and a third time instance, respectively.

3 . The method of claim 2 , wherein the first time instance comprises a time instance prior to an occurrence of the predicted health condition in the infrastructure, the second time instance comprises a time instance at or about the occurrence of the predicted health condition in the infrastructure, and the third time instance comprises a time instance at or about a resolution of the predicted health condition in the infrastructure.

4 . The method of claim 1 , wherein, when the outcome to the solution dataset applied to address the predicted health condition is deemed unsuccessful, further comprising:

applying a third dataset to the virtual representation of the infrastructure in the third state to artificially advance the virtual representation to represent the infrastructure in a fourth state, the third dataset comprising an alternative solution dataset which is applied to address the predicted health condition of the infrastructure; and

obtaining results representing the infrastructure in the fourth state, responsive to applying the third dataset to the virtual representation, wherein at least a portion of the results include an outcome to the alternative solution dataset applied to address the predicted health condition associated with the infrastructure.

5 . The method of claim 1 , further comprising storing a description of the solution dataset applied to address the predicted health condition when the outcome to the solution dataset is deemed successful.

6 . The method of claim 5 , wherein the description of the solution dataset deemed to have a successful outcome is stored in a preventive maintenance recommendation catalog.

7 . The method of claim 1 , further comprising obtaining the first dataset from the infrastructure.

8 . The method of claim 7 , wherein the first dataset represents measurement data collected at the infrastructure.

9 . The method of claim 8 , wherein the measurement data comprises at least one of one or more workloads, historical health data, and vendor provided health data, associated with the infrastructure.

10 . The method of claim 1 , wherein the virtual representation comprises at least one digital twin.

11 . An apparatus, comprising:

at least one processor and at least one memory storing computer program instructions wherein, when the at least one processor executes the computer program instructions, the apparatus is configured to:

obtain at least one virtual representation of an infrastructure which is physically deployed, wherein the virtual representation represents the infrastructure in a first state;

apply a first dataset to the virtual representation of the infrastructure in the first state to artificially advance the virtual representation to represent the infrastructure in a second state and to predict a health condition associated with the infrastructure as represented by the virtual representation of the infrastructure in the second state;

obtain results representing the infrastructure in the second state, responsive to applying the first dataset to the virtual representation, wherein at least a portion of the results include a predicted health condition associated with the infrastructure as represented by the virtual representation of the infrastructure in the second state;

apply a second dataset to the virtual representation of the infrastructure in the second state to artificially advance the virtual representation to represent the infrastructure in a third state, the second dataset comprising a solution dataset which is applied to address the predicted health condition;

obtain results representing the infrastructure in the third state, responsive to applying the second dataset to the virtual representation, wherein at least a portion of the results include an outcome to the solution dataset applied to address the predicted health condition; and

initiate one or more actions with respect to the infrastructure to address the predicted health condition, when the outcome to the solution dataset applied to address the predicted health condition is deemed successful.

12 . The apparatus of claim 11 , wherein, when the infrastructure comprises a computing infrastructure, the first state, the second state, and the third state of the computing infrastructure, which the virtual representation represents, corresponds to at least one of a hardware configuration, a software configuration, and a data configuration of the computing infrastructure at a first time instance, a second time instance, and a third time instance, respectively.

13 . The apparatus of claim 12 , wherein the first time instance comprises a time instance prior to an occurrence of the predicted health condition in the infrastructure, the second time instance comprises a time instance at or about the occurrence of the predicted health condition in the infrastructure, and the third time instance comprises a time instance at or about a resolution of the predicted health condition in the infrastructure.

14 . The apparatus of claim 11 , wherein, when the outcome to the solution dataset applied to address the predicted health condition is deemed unsuccessful, the apparatus is further configured to:

apply a third dataset to the virtual representation of the infrastructure in the third state to artificially advance the virtual representation to represent the infrastructure in a fourth state, the third dataset comprising an alternative solution dataset which is applied to address the predicted health condition of the infrastructure; and

obtain results representing the infrastructure in the fourth state, responsive to applying the third dataset to the virtual representation, wherein at least a portion of the results include an outcome to the alternative solution dataset applied to address the predicted health condition associated with the infrastructure.

15 . The apparatus of claim 11 , wherein the apparatus is further configured to store a description of the solution dataset applied to address the predicted health condition when the outcome to the solution dataset is deemed successful.

16 . The apparatus of claim 15 , wherein the description of the solution dataset deemed to have a successful outcome is stored in a preventive maintenance recommendation catalog.

17 . A computer program product stored on a non-transitory computer-readable medium and comprising machine executable instructions, the machine executable instructions, when executed, causing a processing device to perform steps of:

obtaining at least one virtual representation of an infrastructure which is physically deployed, wherein the virtual representation represents the infrastructure in a first state;

applying a first dataset to the virtual representation of the infrastructure in the first state to artificially advance the virtual representation to represent the infrastructure in a second state and to predict a health condition associated with the infrastructure as represented by the virtual representation of the infrastructure in the second state;

obtaining results representing the infrastructure in the second state, responsive to applying the first dataset to the virtual representation, wherein at least a portion of the results include a predicted health condition associated with the infrastructure as represented by the virtual representation of the infrastructure in the second state;

applying a second dataset to the virtual representation of the infrastructure in the second state to artificially advance the virtual representation to represent the infrastructure in a third state, the second dataset comprising a solution dataset which is applied to address the predicted health condition;

obtaining results representing the infrastructure in the third state, responsive to applying the second dataset to the virtual representation, wherein at least a portion of the results include an outcome to the solution dataset applied to address the predicted health condition; and

initiating one or more actions with respect to the infrastructure to address the predicted health condition, when the outcome to the solution dataset applied to address the predicted health condition is deemed successful.

18 . The computer program product of claim 17 , wherein, when the infrastructure comprises a computing infrastructure, the first state, the second state, and the third state of the computing infrastructure, which the virtual representation represents, corresponds to at least one of a hardware configuration, a software configuration, and a data configuration of the computing infrastructure at a first time instance, a second time instance, and a third time instance, respectively, and wherein the first time instance comprises a time instance prior to an occurrence of the predicted health condition in the infrastructure, the second time instance comprises a time instance at or about the occurrence of the predicted health condition in the infrastructure, and the third time instance comprises a time instance at or about a resolution of the predicted health condition in the infrastructure.

19 . The computer program product of claim 17 , wherein, when the outcome to the solution dataset applied to address the predicted health condition is deemed unsuccessful, further comprising:

applying a third dataset to the virtual representation of the infrastructure in the third state to artificially advance the virtual representation to represent the infrastructure in a fourth state, the third dataset comprising an alternative solution dataset which is applied to address the predicted health condition of the infrastructure; and

obtaining results representing the infrastructure in the fourth state, responsive to applying the third dataset to the virtual representation, wherein at least a portion of the results include an outcome to the alternative solution dataset applied to address the predicted health condition associated with the infrastructure.

20 . The computer program product of claim 17 , further comprising storing a description of the solution dataset applied to address the predicted health condition when the outcome to the solution dataset is deemed successful.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 30, 2023
From: FURLONG, JUDITH A.; O MAHONY, AIDAN; LINCOURT, ROBERT A., JR.; TABET, SAID
To: DELL PRODUCTS L.P.
Reel/Frame 063168/0100 →
Continuity (1)
Related Publication 20240330530A1 · Oct 3, 2024
References Cited (41)
US 7246056B1 · Brewton · 2007 [cited by applicant]
US 11216261B1 · Moyal · 2022 [cited by examiner]
US 11283863B1 · Cleaver et al. · 2022 [cited by applicant]
US 11463322B1 · Sha et al. · 2022 [cited by applicant]
US 11595271B2 · Sha et al. · 2023 [cited by applicant]
US 20160218933A1 · Porras et al. · 2016 [cited by applicant]
US 20160239333A1 · Cowperthwaite et al. · 2016 [cited by applicant]
US 20180137219A1 · Goldfarb et al. · 2018 [cited by applicant]
US 20190079849A1 · Korn et al. · 2019 [cited by applicant]
US 20190356556A1 · Vicat-Blanc · 2019 [cited by applicant]
US 20200026575A1 · Guim Bernat et al. · 2020 [cited by applicant]
US 20200211699A1 · Nuthi · 2020 [cited by examiner]
US 20200244722A1 · Jeuk et al. · 2020 [cited by applicant]
US 20200363850A1 · Lee et al. · 2020 [cited by applicant]
US 20200401456A1 · Sivak et al. · 2020 [cited by applicant]
US 20210021126A1 · Hall et al. · 2021 [cited by applicant]
US 20210383611A1 · Kanski et al. · 2021 [cited by applicant]
US 20220029930A1 · Yilma et al. · 2022 [cited by applicant]
US 20220076151A1 · Loesch et al. · 2022 [cited by applicant]
US 20220100182A1 · Mehrotra et al. · 2022 [cited by applicant]
US 20220167262A1 · Ding et al. · 2022 [cited by applicant]
US 20220173979A1 · Wickes et al. · 2022 [cited by applicant]
US 20220309079A1 · Kurniawan et al. · 2022 [cited by applicant]
US 20230026782A1 · Sha et al. · 2023 [cited by applicant]
US 20230108874A1 · Morlot et al. · 2023 [cited by applicant]
US 20230115586A1 · Song · 2023 [cited by examiner]
US 20240168857A1 · Ahuja et al. · 2024 [cited by applicant]
US 20240172001A1 · Farooq et al. · 2024 [cited by applicant]
US 20240185048A1 · Sebastian et al. · 2024 [cited by applicant]
US 20240232360A1 · Dunning et al. · 2024 [cited by applicant]
US 20240330532A1 · Furlong et al. · 2024 [cited by applicant]
US 20240330533A1 · Lincourt, Jr. et al. · 2024 [cited by applicant]
US 20240330544A1 · Furlong et al. · 2024 [cited by applicant]
A. Cichocki et al., “Era of Big Data Processing: A New Approach via Tensor Networks and Tensor Decompositions,” arXiv:1403.2048v4, https://arxiv.org/abs/1403.2048, Aug. 24, 2014, 30 pages. [cited by applicant]
C. Sonmez et al., “EdgeCloudSim,” https://github.com/CagataySonmez/EdgeCloudSim, Nov. 2, 2020, 11 pages. [cited by applicant]
Melbourne Clouds Lab, “CloudSim: A Framework For Modeling And Simulation Of Cloud Computing Infrastructures And Services,” http://www.cloudbus.org/cloudsim/, Accessed Aug. 12, 2021, 8 pages. [cited by applicant]
S. Kekki et al., “MEC in 5G Networks,” ETSI White Paper No. 28, https://www.etsi.org/images/files/ETSIWhitePapers/etsi_wp28_mec_in_5G_FINAL.pdf, Jun. 2018, 28 pages. [cited by applicant]
ETSI, “Multi-access Edge Computing (MEC); Application Mobility Service API,” Group Specification MEC 021 V2.1.1, https://www.etsi.org/deliver/etsi_gs/MEC/001_099/021/02.01.01_60/gs_MEC021v020101p.pdf, Jan. 2020, 47 page… [cited by applicant]
ETSI, “ETSI MEC: An Introduction,” https://www.etsi.org/images/files/technologies/ETSI-MEC-Public-Overview.pdf, Apr. 2021, 39 pages. [cited by applicant]
W. Sun et al., “Reducing Offloading Latency for Digital Twin Edge Networks in 6G,” IEEE Transactions on Vehicular Technology, Oct. 2020, pp. 12240-12251, vol. 69, No. 10. [cited by applicant]
S.N. Das et al., “Digital Twin based Fault Analysis in Hybrid-cloud Applications,” 2022 IEEE/ACM 10th International Workshop on Software Engineering for Systems-of-Systems and Software Ecosystems (SESoS), Pittsburgh, PA… [cited by applicant]