Network orchestration

• US 10,523,503 B2
• Filed: 04/11/2017
• Issued: 12/31/2019
• Est. Priority Date: 11/10/2016
• Status: Active Grant

• Current Assignee: Metaswitch Networks Limited (Microsoft Corporation)
• Original Assignee: Metaswitch Networks Limited (Microsoft Corporation)
• Inventors: Williams, Matthew, Evans, Michael, Lawn, Jonathan, Loudon, Calum, MacKenzie, Diarmid
• Primary Examiner(s): Celani, Nicholas P
• Application Number:
  US15/485,056
• Publication Number:
  US 20180131565A1
• Time in Patent Office: 994 Days
• CPC Class Codes: G06F 11/008 Reliability or availability analysis
• CPC Class Codes: G06F 2209/501 Performance criteria
• CPC Class Codes: G06F 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455
• CPC Class Codes: H04L 12/4641 Virtual LANs, VLANs, e.g. virtual private networks [VPN] LAN interconnection over a bridge based backbone H04L12/462; encapsulation techniques H04L12/4633; routing of packets H04L45/00; packet switches H04L49/00; virtual private networks for security H04L63/0272
• CPC Class Codes: H04L 41/044 comprising hierarchical management structures
• CPC Class Codes: H04L 41/0806 for initial configuration or provisioning, e.g. plug-and-play
• CPC Class Codes: H04L 41/12 Discovery or management of network topologies
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 41/40 using virtualisation of network functions or resources, e.g. SDN or NFV entities
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Measures, including methods, apparatuses and non-transitory computer-readable storage media, associated with network orchestration. A model of a physical resources part of a network and a model of a virtualised resources part of the network are obtained. The physical/virtualised resources part of the network includes a plurality of physical resources/at least one virtualised network function and represents dependencies between different physical/virtualised resources in the physical/virtualised resources part of the network. At least one optimisation operation is performed using the models of the physical and virtualised resources parts of the network to identify an optimised mapping of the at least one virtualised network function onto at least one of the plurality of physical resources. The at least one virtualised network function is instantiated on the at least one of the plurality of physical resources based on the identified optimised mapping.

Claims

1. A method of network orchestration, the method comprising, by an orchestrator:

obtaining a model of a physical resources part of a network, the physical resources part of the network comprising a plurality of physical resources, the model of the physical resources part of the network representing dependencies between different physical resources in the physical resources part of the network;

obtaining a model of a virtualised resources part of the network, the virtualised resources part of the network comprising at least one virtualised network function, the model of the virtualised resources part of the network representing dependencies between different virtualised resources in the virtualised resources part of the network;

representing the network using a combined model of the network, the combined model of the network combining the model of the physical resources part of the network and the model of the virtualised resources part of the network,

wherein the combined model of the network models at least one performance-related variable related to an availability of at least one of the physical resources, and wherein the availability is determined using a mean time between failures (MTBF) and a mean time to recover (MTTR), and wherein the availability is equal to MTBF/(MTBF+MTTR);

performing at least one optimisation operation using the combined model to identify an optimised mapping of the at least one virtualised network function onto at least one of the plurality of physical resources, the optimised mapping optimising the at least one performance-related variable; and

instantiating the at least one virtualised network function on the at least one of the plurality of physical resources based on the identified optimised mapping to optimise the at least one performance-related variable.

2. The method of claim 1, wherein the at least one virtualised network function is dependent on availability of some or all of the plurality of physical resources.

3. The method of claim 1, wherein the combined model of the network comprises a dependency model.

4. The method of claim 1, wherein the combined model of the network represents the virtual resources part of the network using at least one hierarchical level and represents the physical resources part of the network using at least one additional hierarchical level.

5. The method of claim 1, wherein the combined model of the network is based on one or more reliability block diagram models and/or one or more Markov models.

6. The method of claim 1, wherein the combined model of the network models at least one performance-related variable associated with the at least one virtualised network function.

7. The method of claim 6, wherein the at least one performance-related variable comprises availability.

8. The method of claim 1, wherein the identified optimised mapping comprises a one-to-one mapping, a one-to-many mapping, a many-to-one mapping, and/or a many-to-many mapping.

9. The method of claim 1, wherein the physical resources part of the network comprises one or more power feeds, one or more power supplies, one or more servers, one or more central processing units, one or more air-conditioning supplies, one or more network routers, one or more network switches, one or more network cables, Random Access Memory (RAM) and/or magnetic storage.

10. The method of claim 1, wherein the virtual resources part comprises one or more containers, one or more virtual machines, one or more virtualisation network function components and/or one or more virtualisation network function instances.

11. The method of claim 1, wherein the at least one virtualised network function is mapped onto the at least one of the plurality of physical resources via at least one intermediate virtualised resource.

12. The method of claim 1, comprising:

determining a first performance metric associated with the identified optimised mapping; and

selecting the identified optimised mapping based on a comparison of the first performance metric with a first reference metric.

13. The method of claim 12, wherein the first performance metric and the first reference metric relate to availability, capacity, power consumption, operating cost, capital cost, cooling requirement, a measure of time between failures and/or a measure of time to recover.

14. The method of claim 12, comprising determining a second performance metric associated with the identified optimised mapping, wherein said selecting of the first mapping is based further on a comparison of the second performance metric with a second reference metric.

15. The method of claim 14, wherein the second performance metric and the second reference metric relate to availability, capacity, power consumption, operating cost, capital cost, cooling requirement, a measure of time between failures and/or a measure of time to recover.

16. The method of claim 12, comprising determining a performance metric associated with a second, different identified optimised mapping of the at least one virtualised network function onto some or all of the plurality of physical resources.

17. The method of claim 16, wherein the first reference metric is the performance metric associated with the second mapping.

18. The method of claim 1, wherein at least part of the method is performed:

during network planning;

during simulation of operation of the network;

prior to adding one or more additional physical resources and/or virtualised resources and/or services to the network;

prior to modifying one or more physical resources and/or virtualised resources and/or services in the network;

prior to removing one or more physical resources and/or virtualised resources and/or services from the network;

in response to adding one or more additional physical resources and/or virtualised resources and/or services to the network;

in response to failure of one or more physical resources and/or one or more virtualised resources in the network;

in response to a performance metric being below a predetermined threshold;

following one or more upgrades;

continuously;

periodically;

intermittently;

at one or more scheduled times; and

/or

in response to predetermined user input.

19. The method of claim 1, wherein the at least one optimisation operation is based on availability, reliability, processing requirements, capacity, power consumption, operating cost, cooling requirement, and/or expandability.

20. The method of claim 1, wherein performing the at least one optimisation operation comprises using a discrete optimisation algorithm.

21. The method of claim 20, wherein using the discrete optimisation algorithm comprises using a genetic algorithm and/or using simulated annealing.

22. Apparatus configured to be used in network orchestration, the apparatus comprising at least one memory including computer program code and at least one processor in data communication with the at least one memory, wherein the at least one processor is configured to:

obtain a model of a physical resources part of a network, the physical resources part of the network comprising a plurality of physical resources, the model of the physical resources part of the network representing dependencies between different physical resources in the physical resources part of the network;

obtain a model of a virtualised resources part of the network, the virtualised resources part of the network comprising at least one virtualised network function, the model of the virtualised resources part of the network representing dependencies between different virtualised resources in the virtualised resources part of the network;

represent the network using a combined model of the network, the combined model of the network comprising a combination of the model of the physical resources part of the network and the model of the virtualised resources part of the network,

wherein the combined model of the network is arranged to model at least one performance-related variable related to an availability of at least one of the physical resources, and wherein the processor is configured to determine using a mean time between failures (MTBF) and a mean time to recover (MTTR), and wherein the availability is equal to MTBF/(MTBF+MTTR);

perform at least one optimisation operation using the combined model to identify an optimised mapping of the at least one virtualised network function onto at least one of the plurality of physical resources, the optimised mapping optimising the at least one performance-related variable; and

instantiate the at least one virtualised network function on the at least one of the plurality of physical resources based on the identified optimised mapping to optimise the at least one performance-related variable.

23. A non-transitory computer-readable storage medium comprising computer-executable instructions which, when executed by a processor, cause a computing device to perform a method of network orchestration, the method comprising, by an orchestrator:

obtaining a model of a physical resources part of a network, the physical resources part of the network comprising a plurality of physical resources, the model of the physical resources part of the network representing dependencies between different physical resources in the physical resources part of the network;

obtaining a model of a virtualised resources part of the network, the virtualised resources part of the network comprising at least one virtualised network function, the model of the virtualised resources part of the network representing dependencies between different virtualised resources in the virtualised resources part of the network;

representing the network using a combined model of the network, the combined model of the network combining the model of the physical resources part of the network and the model of the virtualised resources part of the network,

wherein the combined model of the network models at least one performance-related variable related to an availability of at least one of the physical resources, and wherein the availability is determined using a mean time between failures (MTBF) and a mean time to recover (MTTR), and wherein the availability is equal to MTBF/(MTBF+MTTR);

performing at least one optimisation operation using the combined model to identify an optimised mapping of the at least one virtualised network function onto at least one of the plurality of physical resources, the optimised mapping optimising the at least one performance-related variable; and

instantiating the at least one virtualised network function on the at least one of the plurality of physical resources based on the identified optimised mapping to optimise the at least one performance-related variable.