Cognitive quality of service monitoring

Patent metadata

Field	Value
Publication number	US-11057284-B2
Application number	US-201715615151-A
Country	US
Kind code	B2
Filing date	Jun 6, 2017
Priority date	Jun 6, 2017
Publication date	Jul 6, 2021
Grant date	Jul 6, 2021

Abstract

One embodiment provides a quality of service (QoS) monitoring framework for dynamically binding one or more customer applications to one or more microservices in a dynamic service environment, collecting compliance data and contextual data from the dynamic service environment and one or more hosting environments, and modifying a monitoring infrastructure for the one or more customer applications based on the compliance data and the contextual data.

First claim

What is claimed is:

1. A quality of service (QoS) monitoring framework comprising:
at least one processor; and
a non-transitory processor-readable memory device storing instructions that when executed by the at least one processor causes the at least one processor to perform operations including:
dynamically binding one or more customer applications to one or more microservices in a dynamic service environment;
collecting compliance data and contextual data from the dynamic service environment and one or more hosting environments;
training a predictive model by applying machine learning to a portion of the compliance data that is indicative of occurrence of one or more historical service level agreement (SLA) violations;
predicting probability of a SLA violation occurring by applying the predictive model to the compliance data and the contextual data; and
dynamically switching a frequency at which a monitoring infrastructure for the one or more customer applications collects monitoring data for the one or more customer applications between a continuous basis or a periodic basis based on the predicted probability, wherein the dynamically switching comprises:
if the monitoring data is collected continuously and the predicted probability is less than a pre-determined threshold, dynamically switching the frequency from the continuous basis to the periodic basis; and
if the monitoring data is collected at pre-determined intervals and the predicted probability exceeds the pre-determined threshold, dynamically switching the frequency from the periodic basis to the continuous basis.

2. The QoS monitoring framework of claim 1 , wherein:
the compliance data comprises QoS and SLA compliance data indicative of the occurrence of the one or more historical SLA violations; and
the contextual data comprises information indicative of performance of the one or more customer applications, the one or more hosting environments, and one or more requirements of one or more customers utilizing the one or more customer applications.

3. The QoS monitoring framework of claim 2 , further comprising:
predictively analyzing and modeling the one or more requirements based on the contextual data and the compliance data.

4. The QoS monitoring framework of claim 3 , further comprising:
generating one or more segmentation models representing one or more behavioral characteristics of the one or more customers based on the compliance data and the contextual data.

5. The QoS monitoring framework of claim 4 , further comprising:
generating one or more predictive models based on the one or more segmentation models, the compliance data, and the contextual data.

6. The QoS monitoring framework of claim 5 , further comprising:
determining one or more modifications actions for modifying and optimizing the monitoring infrastructure based on the one or more predictive models to reduce costs associated with monitoring the one or more customer applications.

7. The QoS monitoring framework of claim 6 , wherein the one or more modification actions comprises adapting a monitoring policy controlling the frequency at which the monitoring infrastructure collects the monitoring data.

8. The QoS monitoring framework of claim 7 , wherein the monitoring policy is adapted to a continuous monitoring policy specifying collection of the monitoring data on the continuous basis.

9. The QoS monitoring framework of claim 7 , wherein the monitoring policy is adapted to a dynamic monitoring policy specifying collection of the monitoring data on the periodic basis.

10. The QoS monitoring framework of claim 1 , wherein the dynamic service environment comprises a dynamic cloud service environment.

11. A method comprising:
dynamically binding one or more customer applications to one or more microservices in a dynamic service environment;
collecting compliance data and contextual data from the dynamic service environment and one or more hosting environments;
training a predictive model by applying machine learning to a portion of the compliance data that is indicative of one or more historical service level agreement (ISLA) violations;
predicting probability of a SLA violation occurring by applying the predictive model to the compliance data and the contextual data; and
dynamically switching a frequency at which a monitoring infrastructure for the one or more customer applications collects monitoring data for the one or more customer applications between a continuous basis or a periodic basis based on the predicted probability, wherein the dynamically switching comprises:
if the monitoring data is collected continuously and the predicted probability is less than a pre-determined threshold, dynamically switching the frequency from the continuous basis to the periodic basis; and
if the monitoring data is collected at pre-determined intervals and the predicted probability exceeds the pre-determined threshold, dynamically switching the frequency from the periodic basis to the continuous basis.

12. The method of claim 11 , wherein:
the compliance data comprises QoS and SLA compliance data indicative of the occurrence of the one or more historical SLA violations; and
the contextual data comprises information indicative of performance of the one or more customer applications, the one or more hosting environments, and one or more requirements of one or more customers utilizing the one or more customer applications.

13. The method of claim 12 , further comprising:
predictively analyzing and modeling the one or more requirements based on the contextual data and the compliance data.

14. The method of claim 13 , further comprising:
generating one or more segmentation models representing one or more behavioral characteristics of the one or more customers based on the compliance data and the contextual data.

15. The method of claim 14 , further comprising:
generating one or more predictive models based on the one or more segmentation models, the compliance data, and the contextual data.

16. The method of claim 15 , further comprising:
determining one or more modifications actions for modifying and optimizing the monitoring infrastructure based on the one or more predictive models to reduce costs associated with monitoring the one or more customer applications.

17. The method of claim 16 , wherein the one or more modification actions comprises adapting a monitoring policy controlling the frequency at which the monitoring infrastructure collects the monitoring data.

18. The method of claim 17 , wherein the monitoring policy is adapted to a continuous monitoring policy specifying collection of the monitoring data on the continuous basis.

19. The method of claim 17 , wherein the monitoring policy is adapted to a dynamic monitoring policy specifying collection of the monitoring data on the periodic basis.

20. A computer program product comprising a computer-readable hardware storage medium having program code embodied therewith, the program code being executable by a computer to implement a method comprising:
dynamically binding one or more customer applications to one or more microservices in a dynamic service environment;
training a predictive model by applying machine learning to a portion of the compliance data that is indicative of one or more historical service level agreement (SLA) violations;
predicting probability of a SLA violation occurring by applying the predictive model to the compliance data and the contextual data; and
dynamically switching a f

Assignees

• IBM

Inventors

• Anya Obinna B
• Ludwig Heiko H
• Mandagere Nagapramod S
• Mohamed Mohamed
• Qiao Mu
• Routray Ramani R
• Tata Samir

Classifications

• H04L43/08 Primary

  Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters · CPC title

• H04L41/147 Primary

  for predicting network behaviour · CPC title

• H04L41/0816

  the condition being an adaptation, e.g. in response to network events · CPC title

• H04L41/5009

  Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF] · CPC title

• G06F11/3072

  where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting · CPC title