Systems and Methods for Network Configuration Management

• US 20200136898A1
• Filed: 10/24/2019
• Published: 04/30/2020
• Est. Priority Date: 10/24/2018
• Status: Active Grant

• Current Assignee: Cox Communications Incorporated (Cox Enterprises Incorporated)
• Original Assignee: Cox Communications Incorporated (Cox Enterprises Incorporated)
• Inventors: Patel, Jignesh, Boone, Ted, Young, Richard, Cooper, Kyle, Bantug, Derek
• Granted Patent: US 11,133,987 B2
• Time in Patent Office: Days
• CPC Class Codes: H04L 41/082 the condition being updates or upgrades of network functionality
• CPC Class Codes: H04L 41/0823 characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability for optimising operational conditions of wireless networks H04W24/02
• CPC Class Codes: H04L 41/0893 Assignment of logical groups to network elements
• 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 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 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/149 for prediction of maintenance
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 41/5096 wherein the managed service relates to distributed or central networked applications

Abstract

Disclosed are systems and methods for network configuration management systems and methods. In some embodiments, the discloses systems and methods may involve receiving data from one or more nodes within a particular network. The data may include, for example, topology, telemetry, geographical, and other data relating to the nodes, the network, and/or the functionality of the nodes or network. Once received, such data may be cleaned and processing may be performed on the data. Such processing may involve clustering the data into groups based on various parameters and performing forecasting on the data to determine future usage rates and capacity information, for example. The clustering and forecasting results may be fed to a rules engine and/or an optimization engine, which may then determine appropriate actions to take on the network (e.g., changes to various nodes in terms of technology and/or number of nodes).

Claims

1. An network configuration management system comprising:

a computer processor operable to execute a set of computer-readable instructions; and

a memory operable to store the set of computer-readable instructions operable to;

receive data associated with a network node;

assign the network node to a first cluster based on at least a first portion of the data;

determine, using the data, a forecast of a bandwidth demand of the network node at a first time;

assign the network node to a second cluster based on at least a second portion of the data; and

determine, based on the forecast and the assignment of the network node to the second cluster, an indication of a change to be made to a network including the network node, wherein the change includes at least one of a technology change, a node split, or an addition of a new network node.

2. The system of claim 1, wherein the data includes at least one of topology data, telemetry data, geography data, configuration information, or input information.

3. The system of claim 1, where in the computer-readable instructions are further operable to:

perform, using fuzzy logic, an analysis of the data to generate second data;

determine a cadence of the second data, wherein the cadence comprises a frequency at which the data is received from the network node; and

perform de-noising of the second data, wherein de-noising removes one or more abnormalities in the cadence from the network node.

4. The system of claim 1, where to assign the network node to a first cluster based on at least the first portion of the data further comprises:

determine, based on the forecast, that the network node is associated with a growth rate; and

determine, based on the growth rate, to assign the network node the first cluster.

5. The system of claim 1, wherein to determine, using the data, the forecast of the bandwidth demand of the network node at the first time further comprises:

receive a regressor set; and

perform, using a first statistical model, dynamic time-warping on the data, wherein the dynamic time-warping is based on at least one of seasonality or periodicity.

6. The system of claim 5, wherein the regressor set includes either time-based regressors or external regressors, the external regressors including at least one of customer counts, value-per-node, number of commercial passings, or socioeconomic data.

7. The system of claim 5, where in the computer-readable instructions are further operable to:

perform, using a second statistical model, dynamic time-warping on the data;

receive an error rate associated with the first statistical model and an error rate associated with the second statistical model;

determine that the error rate associated with the first statistical model is less than the error rate associated with the second statistical model; and

select, based on the determination that the error rate associated with the first statistical model is less than the error rate associated with the second statistical model, an output associated with the first statistical model.

8. The system of claim 1, wherein the first portion of the data comprises growth rate information associated with the network node, and wherein the second portion of the data is different than the first portion of the data.

9. The system of claim 1, wherein to determine, based on the forecast and the assignment of the network node to the second cluster, an indication of a change to be made to a network including the network node further comprises:

receive a constraint, wherein the constraint is configured to at least one of minimize a cost of the network node or maximize a profitability of the network node,

wherein the change is further based on the constraint.

10. An intelligent networking planning method comprising:

receiving data associated with a network node;

assigning the network node to a first cluster based on at least a first portion of the data;

determining, using the data, a forecast of a bandwidth demand of the network node at a first time;

assigning the network node to a second cluster based on at least a second portion of the data; and

determining, based on the forecast and the assignment of the network node to the second cluster, an indication of a change to be made to a network including the network node, wherein the change includes at least one of a technology change, a node split, or an addition of a new network node.

11. The method of claim 10, wherein the data includes at least one of topology data, telemetry data, geography data, configuration information, or input information.

12. The method of claim 10, further comprising:

perform, using fuzzy logic, an analysis of the data to generate second data;

determine a cadence of the second data, wherein the cadence comprises a frequency at which the data is received from the network node; and

perform de-noising of the second data, wherein de-noising removes one or more abnormalities in the cadence from the network node.

13. The method of claim 10, where to assign the network node to a first cluster based on at least the first portion of the data further comprises:

determine, based on the forecast, that the network node is associated with a growth rate; and

determine, based on the growth rate, to assign the network node the first cluster.

14. The method of claim 10, wherein to determine, using the data, the forecast of the bandwidth demand of the network node at the first time further comprises:

receive a regressor set; and

perform, using a first statistical model, dynamic time-warping on the data, wherein the dynamic time-warping is based on at least one of seasonality or periodicity.

15. The method of claim 14, wherein the regressor set includes either time-based regressors or external regressors, the external regressors including at least one of customer counts, value-per-node, number of commercial passings, or socioeconomic data.

16. The method of claim 14, further comprising:

perform, using a second statistical model, dynamic time-warping on the data;

receive an error rate associated with the first statistical model and an error rate associated with the second statistical model;

determine that the error rate associated with the first statistical model is less than the error rate associated with the second statistical model; and

select, based on the determination that the error rate associated with the first statistical model is less than the error rate associated with the second statistical model, an output associated with the first statistical model.

17. The method of claim 10, wherein the first portion of the data comprises growth rate information associated with the network node, and wherein the second portion of the data is different than the first portion of the data.

18. The method of claim 10, wherein to determine, based on the forecast and the assignment of the network node to the second cluster, an indication of a change to be made to a network including the network node further comprises:

receive a constraint, wherein the constraint is configured to at least one of minimize a cost of the network node or maximize a profitability of the network node,

wherein the change is further based on the constraint.

19. A computer-readable medium storing computer-executable instructions, that when executed by at least one processor, cause the at least one processor to:

receive data associated with a network node;

assign the network node to a first cluster based on at least a first portion of the data;

determine, using the data, a forecast of a bandwidth demand of the network node at a first time;

assign the network node to a second cluster based on at least a second portion of the data; and

determine, based on the forecast and the assignment of the network node to the second cluster, an indication of a change to be made to a network including the network node, wherein the change includes at least one of a technology change, a node split, or an addition of a new network node.

20. The computer-readable medium of claim 19, wherein the data includes at least one of topology data, telemetry data, geography data, configuration information, or input information.