Methods, devices and systems for managing network video traffic

• US 10,410,133 B2
• Filed: 03/22/2017
• Issued: 09/10/2019
• Est. Priority Date: 03/22/2017
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Gopalan, Raghuraman
• Primary Examiner(s): Swearingen, Jeffrey R
• Application Number:
  US15/465,834
• Publication Number:
  US 20180278543A1
• Time in Patent Office: 902 Days
• Field of Search: None
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04L 41/0806 for initial configuration or provisioning, e.g. plug-and-play
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 43/16 Threshold monitoring
• CPC Class Codes: H04L 45/08 Learning-based routing, e.g. using neural networks or artificial intelligence
• CPC Class Codes: H04L 45/125 based on throughput or bandwidth
• CPC Class Codes: H04L 45/22 Alternate routing
• CPC Class Codes: H04L 45/243 using M+N parallel active paths
• CPC Class Codes: H04L 47/83 based on usage prediction

Abstract

Aspects of the subject disclosure may include, for example, embodiments include receiving training data comprising historical states for network resources of a communication network. Further embodiments include generating a Riemannian geometry of the communication network according to the historical states for network resources. Each network resource is one of a vertex or an edge within the first Riemannian geometry. Additional embodiments include determining paths along the Riemannian geometry. Each path comprises at least one network resource. Also, embodiments include determining a velocity vector of each path according to at least one historical state. Embodiments include identifying a group of velocity vectors that generate a sub-geometry within the Riemannian geometry and provisioning a portion of network resources according to the group of velocity vectors and the sub-geometry. Other embodiments are disclosed.

Claims

1. A device, comprising:

a processing system including a processor; and

a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, comprising;

receiving training data comprising a plurality of historical states for each of a plurality of network resources of a communication network;

generating a first Riemannian geometry of the communication network according to the plurality of historical states for each of the plurality of network resources, wherein each of the plurality of network resources is one of a vertex or an edge within the first Riemannian geometry;

determining a first plurality of paths along the first Riemannian geometry, wherein each path in the first plurality of paths comprises at least one of the plurality of network resources;

determining a velocity vector of each path of the first plurality of paths according to at least one state of the plurality of historical states;

identifying a first group of velocity vectors that generate a first sub-geometry within the first Riemannian geometry; and

provisioning a first portion of the plurality of network resources according to the first group of velocity vectors and the first sub-geometry.

2. The device of claim 1, wherein each velocity vector of the first group of velocity vectors is associated with a velocity.

3. The device of claim 2, wherein the velocity of each velocity vector of the first group of velocity vectors represents one of a bandwidth capacity, processor capacity, and storage capacity.

4. The device of claim 2, wherein the operations further comprise:

calculating a first aggregate velocity for the first group of velocity vectors according to the velocity associated with each velocity vector of the first group of velocity vectors; and

determining the first aggregate velocity is above a predetermined threshold.

5. The device of claim 1, wherein the operations further comprise:

identifying a second group of velocity vectors that generate a second sub-geometry within the first Riemannian geometry, wherein each velocity vector of the first group of velocity vectors and the second group of velocity vectors is associated with a velocity;

calculating a first aggregate velocity for the first group of velocity vectors according to the velocity associated with each velocity vector of the first group of velocity vectors;

calculating a second aggregate velocity for the second group of velocity vectors according to the velocity associated with each velocity vector of the second group of velocity vectors; and

determining the first aggregate velocity is lower than the second aggregate velocity.

6. The device of claim 1, wherein identifying the first group of velocity vectors comprise implementing a game-theoretic approach in identifying the first group of velocity vectors.

7. The device of claim 1, wherein the operations comprise:

monitoring a plurality of current states for each of the plurality of network resources in the communication network;

calculating a current aggregate velocity for the first group of velocity vectors according to the plurality of current states;

identifying a model error according to the current aggregate velocity and a first aggregate velocity; and

determining the model error is above a tolerance.

8. The device of claim 7, wherein the operations further comprise:

generating a second Riemannian geometry of the communication network according to the plurality of current states for each of the plurality of network resources, wherein each of the plurality of network resources is one of a vertex or an edge within the second Riemannian geometry;

determining a second plurality of paths along the second Riemannian geometry, wherein each path in the second plurality of paths comprises at least one of the plurality of network resources;

determining a velocity vector of each path of the second plurality of paths according to at least one state of the plurality of current states;

identifying a third group of velocity vectors that generate a third sub-geometry within the second Riemann geometry; and

provisioning a second portion of the plurality of network resources according to the third group of velocity vectors and the third sub-geometry.

9. A non-transitory computer-readable storage medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, comprising:

receiving a plurality of historical states for each of a plurality of network resources of a communication network;

generating a first Riemannian geometry of the communication network according to the plurality of historical states for each of the plurality of network resources, wherein each of the plurality of network resources is one of a vertex or an edge within the first Riemannian geometry;

determining a first plurality of paths along the first Riemannian geometry, wherein each path in the first plurality of paths comprises at least one of the plurality of network resources;

determining a velocity vector of each path of the first plurality of paths according to at least one state of the plurality of historical states;

identifying a first group of velocity vectors that generate a first sub-geometry within the first Riemannian geometry;

calculating a first aggregate velocity for the first group of velocity vectors according to a velocity associated with each velocity vector of the first group of velocity vectors;

determining the first aggregate velocity is above a predetermined threshold; and

provisioning a first portion of the plurality of network resources according to the first group of velocity vectors and the first sub-geometry.

10. The non-transitory computer-readable storage medium of claim 9, wherein the velocity of each velocity vector of the first group of velocity vectors represents one of a bandwidth capacity, processor capacity, and storage capacity.

11. The non-transitory computer-readable storage medium of claim 9, wherein the operations further comprise:

identifying a second group of velocity vectors that generate a second sub-geometry within the first Riemannian geometry, wherein each velocity vector of the first group of velocity vectors and the second group of velocity vectors is associated with a velocity;

calculating a first aggregate velocity for the first group of velocity vectors according to the velocity associated with each velocity vector of the first group of velocity vectors;

calculating a second aggregate velocity for the second group of velocity vectors according to the velocity associated with each velocity vector of the second group of velocity vectors; and

determining the first aggregate velocity is lower than the second aggregate velocity.

12. The non-transitory computer-readable storage medium of claim 9, wherein identifying the first group of velocity vectors comprise implementing a game-theoretic approach in identifying the first group of velocity vectors.

13. The non-transitory computer-readable storage medium of claim 9, wherein the operations comprise:

monitoring a plurality of current states for each of the plurality of network resources in the communication network;

calculating a current aggregate velocity for the first group of velocity vectors according to the plurality of current states;

identifying a model error according to the current aggregate velocity and the first aggregate velocity; and

determining the model error is above a tolerance.

14. The non-transitory computer-readable storage medium of claim 13, wherein the operations comprise:

generating a second Riemannian geometry of the communication network according to the plurality of current states for each of the plurality of network resources, wherein each of the plurality of network resources is one of a vertex or an edge within the second Riemannian geometry;

determining a second plurality of paths along the second Riemannian geometry, wherein each path in the second plurality of paths comprises at least one of the plurality of network resources;

determining a velocity vector of each path of the second plurality of paths according to at least one state of the plurality of current states;

identifying a third group of velocity vectors that generate a third sub-geometry within the second Riemann geometry; and

provisioning a second portion of the plurality of network resources according to the third group of velocity vectors and the third sub-geometry.

15. A method, comprising:

monitoring, by a processing system including a processor, a plurality of current states for each of a plurality of network resources in a communication network;

calculating, by the processing system, a current aggregate velocity for a first group of velocity vectors according to the plurality of current states;

identifying, by the processing system, a model error according to the current aggregate velocity and a first aggregate velocity, wherein the first aggregate velocity is for the first group of velocity vectors according to a plurality of historical states for each of the plurality of network resources;

determining, by the processing system, that the model error is above a tolerance;

generating, by the processing system, a first Riemannian geometry of the communication network according to the plurality of historical states for each of the plurality of network resources, wherein each of the plurality of network resources is one of a vertex or an edge within the first Riemannian geometry, wherein the first group of velocity vectors generates a first sub-geometry within the first Riemannian geometry; and

provisioning, by the processing system, a first portion of the plurality of network resources according to the first group of velocity vectors and the first sub-geometry.

16. The method of claim 15, comprising:

receiving, by the processing system, training data comprising the plurality of historical states for each of the plurality of network resources of the communication network;

determining, by the processing system, a first plurality of paths along the first Riemannian geometry, wherein each path in the first plurality of paths comprises at least one of the plurality of network resources; and

determining, by the processing system, a velocity vector of each path of the first plurality of paths according to at least one state of the plurality of historical states.

17. The method of claim 16, comprising:

calculating, by the processing system, the first aggregate velocity for the first group of velocity vectors according to a velocity associated with each velocity vector of the first group of velocity vectors; and

determining, by the processing system, the first aggregate velocity is above a predetermined threshold.

18. The method of claim 16, comprising:

identifying a second group of velocity vectors that generate a second sub-geometry within the first Riemannian geometry, wherein each velocity vector of the first group of velocity vectors and the second group of velocity vectors is associated with a velocity;

calculating the first aggregate velocity for the first group of velocity vectors according to the velocity associated with each velocity vector of the first group of velocity vectors;

calculating a second aggregate velocity for the second group of velocity vectors according to the velocity associated with each velocity vector of the second group of velocity vectors; and

determining the first aggregate velocity is lower than the second aggregate velocity.

19. The method of claim 16, wherein identifying the first group of velocity vectors comprise implementing a game-theoretic approach in identifying the first group of velocity vectors.

20. The method of claim 15, comprising:

generating, by the processing system, a second Riemannian geometry of the communication network according to the plurality of current states for each of the plurality of network resources, wherein each of the plurality of network resources is one of a vertex or an edge within the second Riemannian geometry;

determining, by the processing system, a second plurality of paths along the second Riemannian geometry, wherein each path in the second plurality of paths comprises at least one of the plurality of network resources;

determining, by the processing system, a velocity vector of each path of the second plurality of paths according to at least one state of the plurality of current states;

identifying, by the processing system, a third group of velocity vectors that generate a third sub-geometry within the second Riemann geometry; and

provisioning, by the processing system, a second portion of the plurality of network resources according to the third group of velocity vectors and the third sub-geometry.