Monitor-mine-manage cycle

Patent metadata

Field	Value
Publication number	US-11080159-B2
Application number	US-201816136952-A
Country	US
Kind code	B2
Filing date	Sep 20, 2018
Priority date	Jan 5, 2013
Publication date	Aug 3, 2021
Grant date	Aug 3, 2021

Abstract

A monitor-mine-manage cycle is described, for example, for managing a data center, a manufacturing process, an engineering process or other processes. In various example, the following steps are performed as a continuous automated loop: receiving raw events from an observed system; monitoring the raw events and transforming them into complex events; mining the complex events and reasoning on results; making a set of proposed actions based on the mining; and managing the observed system by applying one or more of the proposed actions to the system. In various examples, the continuous automated loop proceeds while raw events are continuously received from the observed system and monitored. In some examples an application programming interface is described comprising programming statements which allow a user to implement a monitor-mine-manage loop.

First claim

The invention claimed is:

1. A computer-implemented method comprising:
monitoring a client request queue size of an observed system over time;
predicting a future client request queue size based on the monitored client request queue size;
determining a number of servers to be deployed in the observed system at a future time based on the predicted future client request queue size and a service level agreement associated with the observed system; and
deploying a server to the observed system or removing a server from the observed system based on the determined number of servers, while continuing to monitor the client request queue size of the observed system over time.

2. A computer-implemented method according to claim 1 , wherein predicting the future client request queue size comprises detecting a pattern in the client request queue size over time.

3. A computer-implemented method according to claim 2 , wherein determining the number of servers is based on the detected pattern.

4. A computer-implemented method according to claim 3 , wherein determining the number of servers comprises determining whether the detected pattern is indicative of fulfillment of the service level agreement.

5. A computer-implemented method according to claim 4 , wherein determining the number of servers is based on a cost associated with server deployment.

6. A computer-implemented method according to claim 1 , wherein determining the number of servers comprises determining compliance with one or more measurable details of the service level agreement.

7. A computer-implemented method according to claim 1 , wherein monitoring the client request queue size comprises monitoring a plurality of events indicative of the client request queue size.

8. A computer-implemented method according to claim 7 , wherein monitoring the client request queue size comprises:
extracting one or more features from the plurality of events; and
aggregating the one or more features into one or more other events indicative of the client request queue size over time.

9. A system comprising:
a data center comprising one or more application servers, a monitoring system and a management system,
the monitoring system operable to:
monitor a client request queue size of the data center over time;
predict a future client request queue size based on the monitored client request queue size;
determine a number of servers to be deployed in the data center at a future time based on the predicted future client request queue size and a service level agreement associated with the data center, while continuing to monitor the client request queue size of the data center over time; and
output a recommendation to the management system, the recommendation comprising the number of application servers to be deployed in the data center at the future time, while continuing to monitor the client request queue size of the data center over time; and

the management system operable to:
deploy an application server to the data center or remove an application server from the data center based on the recommendation.

10. A system according to claim 9 , wherein prediction of the future client request queue size comprises detection of a pattern in the client request queue size over time.

11. A system according to claim 10 , wherein determination of the number of servers is based on the detected pattern.

12. A system according to claim 11 , wherein determination of the number of servers comprises determination of whether the detected pattern is indicative of fulfillment of the service level agreement.

13. A system according to claim 12 , wherein determination of the number of servers is based on a cost associated with server deployment.

14. A system according to claim 9 , wherein determination of the number of servers comprises determining compliance with one or more measurable details of the service level agreement.

15. A system according to claim 9 , wherein monitoring of the client request queue size comprises monitoring of a plurality of events indicative of the client request queue size.

16. A system according to claim 15 , wherein monitoring of the client request queue size comprises:
extraction of one or more features from the plurality of events; and
aggregation of the one or more features into one or more other events indicative of the client request queue size over time.

17. A computer-implemented system to:
monitor a client request queue size of the observed system over time;
determine a number of servers to be deployed in the observed system at a future time based on the monitored client request queue size and a service level agreement associated with the observed system;
determine a recommendation comprising the number of servers to be deployed in the observed system; and
configure one or more servers of the observed system based on the recommendation, while continuing to monitor the client request queue size of the observed system over time.

18. A system according to claim 17 , wherein prediction of the future client request queue size comprises detection of a pattern in the client request queue size over time, and wherein determination of the number of servers is based on the detected pattern.

19. A system according to claim 18 , wherein determination of the number of servers comprises determination of whether the detected pattern is indicative of fulfillment of the service level agreement.

20. A system according to claim 17 , wherein monitoring of the client request queue size comprises:
monitoring of a plurality of events indicative of the client request queue size;
extraction of one or more features from the plurality of events; and
aggregation of the one or more features into one or more other events indicative of the client request queue size over time.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Periorellis Panos
• Akchurin Eldar
• Claessens Joris
• Dos Santos Ivo Jose Garcia
• Nano Oliver

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N5/02 Primary

  Knowledge representation; Symbolic representation · CPC title

• G06F11/3006 Primary

  where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems (multiprogramming arrangements G06F9/46; allocation of resources G06F9/50) · CPC title

• G06F11/301

  where the computing system is a virtual computing platform, e.g. logically partitioned systems (virtual machines G06F9/45533; logical partitioning of resources G06F9/5077) · CPC title

• G06F2201/86

  Event-based monitoring · CPC title