Method And Apparatus For Provisioning Resources Using Clustering

Patent metadata

Field	Value
Publication number	US-2016294722-A1
Application number	US-201514674812-A
Country	US
Kind code	A1
Filing date	Mar 31, 2015
Priority date	Mar 31, 2015
Publication date	Oct 6, 2016
Grant date	—

Abstract

Various embodiments provide a method and apparatus for allocating resources to applications (e.g., application processes) using pre-provisioned resource configurations (e.g., VMs or containers) that are based on clustered historical resource usage data. In particular, the set of pre-provisioned resources required to support elasticity in a set of applications is reduced by determining a subset of pre-provisioned resource configurations that are able to be reused across multiple applications. A pre-provisioned resource configuration being based on a determined dominant center for the resource cluster associated with the pre-provisioned resource configuration.

First claim

What is claimed is:

1 . An apparatus for providing resource allocation, the apparatus comprising:
a data storage; and a processor communicatively connected to the data storage, the processor being configured to:
determine a plurality of available resources and a plurality of applications;
determine an input dataset, the input dataset comprising a plurality of data points indicating an expected resource usage occurring within a future time period and associated with one of the plurality of applications; and
determine a plurality of pre-provisioned resource set types based on the plurality of available resources and the input dataset;
wherein a first pre-provisioned resource set type is configured to provide automatic resource scaling of a first plurality of the plurality of applications and a second pre-provisioned resource set type is configured to provide automatic resource scaling of a second plurality of the plurality of applications, the plurality of pre-provisioned resources types comprising the first and second pre-provisioned resource set types; and
wherein the first pre-provisioned resource set type is distinct from the second pre-provisioned resource set type.

2 . The apparatus of claim 1 , wherein the first pre-provisioned resource set type is a first pre-provisioned virtual machine type and the second pre-provisioned resource set type is a second pre-provisioned virtual machine type.

3 . The apparatus of claim 1 , wherein the number of pre-provisioned resource set types is constrained to a predetermined number of distinct resource set configurations.

4 . The apparatus of claim 1 , wherein the determination of the plurality of pre-provisioned resource set types is further based on a maximum allowed over-provisioning overhead.

5 . The apparatus of claim 1 , wherein the determination of the plurality of pre-provisioned resource set types is further based on an over-provisioning cost.

6 . The apparatus of claim 5 , wherein the over-provisioning cost is based the difference between an aggregate of a plurality of first resource requirements corresponding to the input data points and an aggregate of a corresponding plurality of second resource assignments based on the pre-provisioned resource set types.

7 . The apparatus of claim 1 , wherein the determination of the plurality of pre-provisioned resource set types comprises the processor being further configured to:
determine a plurality of (V; f) pairs where V is the plurality of pre-provisioned resource set types and f is a function used for selecting a select resource set type from the plurality of pre-configure resource set types for ones of the plurality of data points.

8 . The apparatus of claim 7 , wherein the determination of the plurality of pre-provisioned resource set types is further based on minimizing a sum of the squares of the distances between the plurality of data points and corresponding ones of the plurality of pre-provisioned resource set types.

9 . The apparatus of claim 7 , wherein the determination of the plurality of pre-provisioned resource set types is further based on minimizing a maximum overhead across the plurality of available resources.

10 . The apparatus of claim 7 , wherein the determination of the plurality of pre-provisioned resource set types is further based on minimizing a maximum worst case over-provisioning.

11 . The apparatus of claim 1 , wherein the determination of the plurality of pre-provisioned resource set types comprises the processor being configured to:
cluster the plurality of data points into a first cluster comprising a first plurality of data points and a second cluster comprising a second plurality of data points, the plurality of data points comprising the first plurality of data points and the second plurality of data points; determine a first dominant configuration corresponding to the first plurality of data points and a second dominant configuration corresponding to the second plurality of data points; wherein the first dominant configuration comprises a first dc resource type and a second dc resource type and the second dominant configuration comprises a third dc resource type and a fourth dc resource type; and wherein the first dc resource type and second dc resource type dominates each of the first plurality of data points and the third dc resource type and fourth dc resource type dominates each of the second plurality of data points; and further base the determination of the pre-provisioned resource set types based on the first dominant configuration and the second dominant configuration.

12 . The apparatus of claim 11 , wherein the clustering of the data points is based on an objective of minimizing an over-provisioning cost.

13 . A method for providing resource allocation, the method comprising:
at a processor communicatively connected to a data storage, determining a plurality of available resources and a plurality of applications; determining, by the processor in cooperation with the data storage, an input dataset, the input dataset comprising a plurality of data points indicating an expected resource usage occurring within a future time period and associated with one of the plurality of applications; and determining, by the processor in cooperation with the data storage, a plurality of pre-provisioned resource set types based on the plurality of available resources and the input dataset; wherein a first pre-provisioned resource set type is configured to provide automatic resource scaling of a first plurality of the plurality of applications and a second pre-provisioned resource set type is configured to provide automatic resource scaling of a second plurality of the plurality of applications, the plurality of pre-provisioned resources types comprising the first and second pre-provisioned resource set types; and wherein the first pre-provisioned resource set type is distinct from the second pre-provisioned resource set type.

14 . The method of claim 13 , wherein the first pre-provisioned resource set type is a first pre-provisioned virtual machine type and the second pre-provisioned resource set type is a second pre-provisioned virtual machine type.

15 . The method of claim 13 , wherein the determination of the plurality of pre-provisioned resource set types is further based on an over provisioning cost.

16 . The method of claim 13 , wherein the step of determining the plurality of pre-provisioned resource set types comprises:
determining a plurality of (V; f) pairs where V is the plurality of pre-provisioned resource set types and f is a function used for selecting a select resource set type from the plurality of pre-configure resource set types for ones of the plurality of data points.

17 . The method of claim 16 , wherein the step of determining the plurality of pre-provisioned resource set types is further based on minimizing a sum of the squares of the distances between the plurality of data points and corresponding ones of the plurality of pre-provisioned resource set types.

18 . The method of claim 16 , wherein the step of determining the plurality of pre-provisioned resource set types is further based on minimizing a maximum overhead across the plurality of available resources.

19 . The method of claim 16 , wherein the step of determining the plurality of pre-provisioned resource set types is further based on minimizing a maximum worst case over-provisioning.

20 . The method of claim 13 , wherein the number of pre-provisioned resource s

Assignees

• Alcatel Lucent Usa Inc
• Alcatel Lucent

Inventors

• Bhatia Randeep S
• Gupta Bhawna
• Rosensweig Elisha

Classifications

• H04L47/83

  based on usage prediction · CPC title

• H04L47/70 Primary

  Admission control; Resource allocation · CPC title

• H04L43/10 Primary

  Active monitoring, e.g. heartbeat, ping or trace-route · CPC title

• H04L41/0806

  for initial configuration or provisioning, e.g. plug-and-play · CPC title

• H04L41/5012

  determining service availability, e.g. which services are available at a certain point in time · CPC title