Systems and methods for network configuration management

Patent metadata

Field	Value
Publication number	US-11996980-B2
Application number	US-202117410374-A
Country	US
Kind code	B2
Filing date	Aug 24, 2021
Priority date	Oct 24, 2018
Publication date	May 28, 2024
Grant date	May 28, 2024

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).

First claim

The invention claimed is:

1. An intelligent networking planning method comprising:
receiving data associated with a network node, the data including data of a first type and data of a second type, the data of the first type and the data of the second type being different, wherein the data includes a node identifier for the network node;
extracting, subsequent to receiving the data and using fuzzy logic, a node number from the node identifier;
assigning the network node to a first cluster based on the data of the first type, the data of the first type including bandwidth data;
determining, using the data of the first type and subsequent to extracting the node number from the node identifier, a forecast of a bandwidth demand of the network node at a first time;
assigning the network node to a second cluster based on the data of the second type; and
determining, based on the forecast and the assignment of the network node to the second cluster, an indication of a first change to be made to a network including the network node, wherein the first change includes at least one of: a technology change, a node split, or an addition of a new network node;
determining a first rule that results in the first change and a second rule that results in a second change, wherein the first change is different than the second change, wherein the first rule is associated with a first weight value indicative of a priority, and the second rule is associated with a second weight value indicative of a different priority; and
determining, based on the first rule and first weight value and second rule and second weight value, that the second change is to be made to the network including the network node, wherein the second change includes at least one of: a firmware change, a node split, or an addition of a new network node.

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

3. The method of claim 1 , further comprising:
performing, using fuzzy logic, an analysis of the data to generate second data;
determining a cadence of the second data, wherein the cadence comprises a frequency at which the data is received from the network node;
comparing the frequency at which the data is received from the network node to a threshold frequency; and
performing de-noising of the second data, wherein de-noising removes one or more abnormalities in the cadence from the network node.

4. The method of claim 1 , where to assign the network node to a first cluster based on the data of the first type further comprises:
determining, based on the forecast, that the network node is associated with a growth rate; and
determining, based on the growth rate, to assign the network node the first cluster.

5. The method 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:
receiving a regressor set; and
performing, 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 method 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 method of claim 5 , further comprising:
performing, using a second statistical model, dynamic time-warping on the data;
receiving an error rate associated with the first statistical model and an error rate associated with the second statistical model;
determining that the error rate associated with the first statistical model is less than the error rate associated with the second statistical model; and
selecting, 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 method 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:
identifying a plurality of indications of changes;
receiving 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; and
selecting, based on the constraint, the first change to be made to the network from the plurality of indications of changes to the network.

9. The method of claim 3 , wherein performing de-noising of the second data further comprises:
determining, that the frequency at which the data is received from the network node is below the threshold frequency; and
imputing, based on the determination that the frequency is below the threshold frequency, a missing data value for the network node.

10. A 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, the data including data of a first type and data of a second type, the data of the first type and the data of the second type being different, wherein the data includes a node identifier for the network node;
extract, subsequent to receiving the data and using fuzzy logic, a node number from the node identifier;
assign the network node to a first cluster based on the data of the first type, the data of the first type including bandwidth data;
determine, using the data of the first type and subsequent to extracting the node number from the node identifier, a forecast of a bandwidth demand of the network node at a first time;
assign the network node to a second cluster based on the data of the second type;
determine, based on the forecast and the assignment of the network node to the second cluster, an indication of a first change to be made to a network including the network node, wherein the first change includes at least one of: a firmware change, a node split, or an addition of a new network node;
determine a first rule that results in the first change and a second rule that results in a second change, wherein the first change is different than the second change, wherein the first rule is associated with a first weight value, and the second rule is associated with a second weight value; and
determine, based on the first rule and first weight value and second rule and second weight value, that the second change is to be made to the network including the network node, wherein the second change includes at least one of: a firmware change, a node split, or an addition of a new network node.

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

12. The system of claim 10 , wherein the computer-readable instructions are further operable to:
determine a cadence of the data, wherein the cadence comprises a frequency at which the data is received from the network node; and
perform de-noising of the data, wherein de-noising removes one or more abnormalities in the cadence from the network node.

13. The system of claim 10 , where to assign the network node to a first cluster based on the data of the first type further comprises:
determine, based on the forecast, that the network node is assoc

Assignees

• Cox Communications Inc

Inventors

• Patel Jignesh
• Boone Ted
• Brown Richard
• Cooper Kyle
• Bantug Derek

Classifications

• H04L41/0893

  Assignment of logical groups to network elements · CPC title

• H04L41/12

  Discovery or management of network topologies · CPC title

• H04L41/149

  for prediction of maintenance · CPC title

• H04L41/147

  for predicting network behaviour · CPC title

• H04L41/082 Primary

  the condition being updates or upgrades of network functionality · CPC title