Enhancing initial resource allocation management to provide robust reconfiguration

Patent metadata

Field	Value
Publication number	US-9864634-B2
Application number	US-201213366438-A
Country	US
Kind code	B2
Filing date	Feb 6, 2012
Priority date	Feb 6, 2012
Publication date	Jan 9, 2018
Grant date	Jan 9, 2018

Abstract

A description of a resource associated with a service of an entity can be captured. The service can be associated with one or more resources, a constraint, and a demand. The resource can be associated with one or more characteristics including a utility, a limited availability, and a consumption rate. The entity can be an organization or a system. An initial allocation problem associated with the resource can be formulated as a two phase problem. The first phase can be an optimization problem and the second phase can be a restricted allocation problem. The initial allocation problem can be associated with reconfiguring a previously established allocation of a baseline scenario. The optimization problem can be solved optimally or approximately to establish a favorable allocation. The favorable allocation can minimizes the reconfiguration cost of the reconfiguring. The baseline scenario can be a normal operation of the service.

First claim

What is claimed is:

1. A method for reconfiguration aware initial allocation comprising:
capturing, by a computer, a description of one or more resources associated with a service of an entity, wherein the service is associated with at least one of the one or more resources, a constraint, and a demand, wherein each of the one or more resources is associated with at least three characteristics comprising a utility, a limited availability, and a consumption rate, wherein the entity is at least one of an organization and a system;
formulating, by the computer using an algorithm, an initial allocation problem associated with the one or more resources as a two phase problem, wherein the first phase is an optimization problem and the second phase is a restricted allocation problem, wherein the initial allocation problem is associated with reconfiguring a previously established allocation of a baseline scenario; and
solving, by the computer, the optimization problem to establish an allocation, wherein the favorable allocation minimizes the reconfiguration cost of the reconfiguring, wherein the baseline scenario is a normal operation of the service;
wherein a reconfiguration cost is a network utilization overhead associated with a session initiation setup; and
wherein the initial allocation comprises a reconfiguration capable allocation of resources including an allocation associated with one or more resources and a metric; wherein the initial allocation decreases reconfiguration time of a service from approximately three minutes twenty seconds to approximately two minutes resulting in a time savings of approximately one minute twenty seconds; wherein the initial allocation reduces reconfiguration costs while maintaining a minimum level of service by service.

2. The method of claim 1 , wherein the formulating the optimization problem is associated with a Centroid cost and a Median cost; and
wherein the algorithm performs a minimization of the maximum cost or a minimization of the average cost corresponding to a Centroid cost and a Median cost;
wherein the algorithm establishes k types of resources for an organization; wherein each resource of type i has N i resources denoted by T(i,N i ).

3. The method of claim 1 , wherein the solving minimizes at least one of the maximum reconfiguration cost and the average reconfiguration cost; wherein the service is a Web service for handling Session Initiated Protocol communication having one or more demand points requiring service availability; and wherein the service is specified by a k-tuple and a set of constraints.

4. The method of claim 1 , wherein the resource is at least one of an economic resource, a biological resource, a computer resource, a land management resource, and a human resource, wherein the computing is performed when the configuration cost is unknown;
wherein when a cost function is unknown, the algorithm determines a cost by the number of resources to be reallocated.

5. The method of claim 1 , further comprising:
computing the reconfiguration of the service associated with the favorable allocation for a contingency scenario; and
associating the reconfiguration with the service when at least one of a plurality of contingency scenarios occur.

6. The method of claim 1 , further comprising:
presenting at least one of the baseline allocation and a contingency allocation within a user interface, wherein the baseline allocation is associated a baseline scenario, wherein the contingency allocation is associated with a contingency scenario.

7. The method of claim 1 , wherein the presenting overlays the contingency allocation upon a graph of at least one of the entity, the service, and the resource.

8. The method of claim 1 , wherein the solving utilizes a greedy heuristic.

9. The method of claim 1 , wherein the service is at least one of a public service, a private service, and a computer service.

10. A system for reconfiguration aware initial allocation comprising:
at least one processor connected to at least one non-transitory storage medium;
a reconfiguration engine stored in the at least one non-transitory storage medium configured to cause the processor to establish an initial allocation associated with one or more resources of a service, wherein the initial allocation is associated with at least one of a reconfiguration setting and a reconfiguration cost, wherein the service is associated with at least one of the one or more resources, a constraint, and a demand, wherein the resource is associated with at least three characteristics comprising a utility, a limited availability, and a consumption rate, wherein the entity is at least one of an organization and a system; and
a data store configured to persist at least one of a reconfiguration mapping and an action plan associated with the service;
wherein the reconfiguration engine computes the configuration cost required to change service configuration from a contingency scenario to another contingency scenario; and
wherein the initial allocation comprise a reconfiguration capable allocation of resources including an allocation associated with one or more resources and a metric; wherein the initial allocation decreases reconfiguration time of a service from approximately three minutes twenty seconds to approximately two minutes resulting in a time savings of approximately one minute twenty seconds; wherein the initial allocation reduces reconfiguration costs while maintaining a minimum level of service by service.

11. The system of claim 10 , further comprising:
a resource handler stored in the at least one non-transitory storage medium configured to cause the processor to identify the resource associated with the service and determine a resource description, wherein the resource description is at least one of a dependency information, an access information, and an availability information, wherein the resource handler automatically determines junctions with critical path properties and determine resource limitations that produce service level constraints;
an optimization component stored in the at least one non-transitory storage medium configured to cause the processor to determine the initial allocation for the resource; and
a reconfiguration element stored in the at least one non-transitory storage medium configured to cause the processor to determine at least one reconfiguration setting associated with the initial allocation of the resource;
wherein the action plan comprises a set of scenarios associated with a number of allocations wherein each scenario includes allocation information for each baseline scenario and/or contingency scenario and each allocation represents a computer configuration as an arrangement of functional units, including a computer file, a service, a computing resource, and a database record;
wherein the reconfiguration cost comprises a temporal cost, a resource cost, a human resource cost, and a monetary cost; and
wherein the initial allocation comprises a portion of a reconfiguration mapping.

12. The system of claim 10 , wherein the reconfiguration engine is associated with a minimization algorithm, wherein the minimization algorithm is configured to minimize the maximum reconfiguration cost.

13. The system of claim 10 , wherein the reconfiguration engine is associated with a minimization algorithm, wherein the minimization algorithm is configured to minimize the average reconfiguration cost.

14. The system of claim 10 , wherein the reconfiguration engine utilizes a greedy heuristic to solve an optimization problem associated with a reconfiguration of a resource associated with the service.

Assignees

• Kenkre Sreyash D
• Mehta Sameep
• Narayanam Krishnasuri
• Pandit Vinayaka D
• Soni Soujanya
• IBM

Inventors

• Kenkre Sreyash D
• Mehta Sameep
• Narayanam Krishnasuri
• Pandit Vinayaka D
• Soni Soujanya

Classifications

• G06F9/50 Primary

  Allocation of resources, e.g. of the central processing unit [CPU] · CPC title