Client-aware floorplan management with predicted confidence levels

Patent metadata

Field	Value
Publication number	US-12432115-B2
Application number	US-202318350873-A
Country	US
Kind code	B2
Filing date	Jul 12, 2023
Priority date	Jul 12, 2023
Publication date	Sep 30, 2025
Grant date	Sep 30, 2025

Abstract

Devices, systems, methods, and processes for managing network devices through generated predictions and associated confidence levels are described herein. Networks within a floorplan can be operated at full capacity all day in an inefficient way when not adjusted due to traffic patterns and seasonality changes. Data related to the topology of the network, along with historical data can be utilized to generate predictions of various network needs. For example, the overall network throughput capacity needs may be predicted for a series of points in the future. An associated confidence level can be generated as well including one or more confidence intervals. These can be utilized to select a future need for the network and generate a corresponding sustainable network configuration for the network devices and/or their transceivers that can provide sufficient network needs while minimizing the overall power used. This can be automated over time once trust has been established.

First claim

What is claimed is:

1. A device, comprising:
a processor;
at least one network interface controller configured to provide access to a network; and
a memory communicatively coupled to the processor, wherein the memory comprises a network capacity prediction logic that is configured to:
determine a plurality of network devices within a floorplan;
determine a status of one or more of the plurality of network devices within the floorplan;
predict one or more capacity needs of the plurality of network devices at one more future points of time, wherein a prediction is made at particular intervals based on a desired reaction latency;
generate one or more confidence levels for the predicted capacity needs at the point in time; and
determine one or more network device configurations for at least one of the plurality of network devices.

2. The device of claim 1 , wherein the network capacity prediction logic is further configured to transmit the one or more network device configurations to the plurality of network devices.

3. The device of claim 1 , wherein the one or more needs is bandwidth capacity.

4. The device of claim 3 , wherein the one or more network device configurations comprise at least transceiver power settings.

5. The device of claim 4 , wherein the one or more network device configurations comprise at least a command for a network device to enter a lower-power mode.

6. The device of claim 4 , wherein the one or more network device configurations are configured to provide sufficient bandwidth capacity within the floorplan.

7. The device of claim 6 , wherein the sufficient bandwidth capacity is determined based on the one or more predicted needs of the plurality of network devices.

8. The device of claim 7 , wherein the one or more network configurations provide sufficient bandwidth capacity while minimizing an amount of power required from the plurality of network devices.

9. The device of claim 1 , wherein the network capacity prediction logic is further configured to evaluate historical data associated with the plurality of network devices.

10. The device of claim 9 , wherein the predicted one or more needs is based on at least the determined plurality of network devices and the evaluated historical data.

11. The device of claim 1 , wherein the predicted one or more needs are associated with a series of future time periods.

12. The device of claim 11 , wherein the one or more confidence levels are associated with each of the series of time periods in the future.

13. The device of claim 12 , wherein each of the series of time periods has one or more confidence intervals associated with it.

14. A device, comprising:
a processor;
at least one network interface controller configured to provide access to a network; and
a memory communicatively coupled to the processor, wherein the memory comprises a network capacity prediction logic that is configured to:
determine a plurality of network devices within a floorplan;
determine a status of one or more of the plurality of network devices within the floorplan, wherein the status is associated with a current power or transceiver configuration;
receive a desired latency period;
determine a method of prediction generation based on the desired latency period;
predict a capacity need of those plurality of network devices at
one more future points of time, wherein a prediction is made at particular intervals based on a window of reaction latency;
generate one or more confidence levels corresponding to the predicted capacity need at the point in time; and
determine one or more network device configurations for at least one of the plurality of network devices.

15. The device of claim 14 , wherein the method of prediction can include at least one or more thresholds.

16. The device of claim 14 , wherein the method of prediction can include at least an autoregressive moving average.

17. The device of claim 14 , wherein the method of prediction can include at least one or more machine-learning processes.

18. The device of claim 14 , wherein the method of prediction can include a plurality of methods of increasing complexity.

19. The device of claim 18 , wherein a longer desired latency period can be correlated to a method of prediction of increased complexity.

20. A method for managing a network associated with a floorplan, comprising:
determining a plurality of network devices within a floorplan by receiving topology data;
determining a status of one or more of the plurality of network devices within the floorplan;
receiving a desired latency period;
determining a method of generating predictions based on at least the desired latency period;
predicting one or more capacity needs of those plurality of network devices utilizing the determined method at one more future points of time, wherein a prediction is made at particular interval based on a required latency at which data is needed;
generating one or more confidence levels wherein the one or more confidence levels are based on at least the predicted one or more capacity needs at the point in time;
determining one or more network device configurations for at least one of the plurality of network devices; and
transmitting the one or more network device configurations to the at least one of the plurality of network devices.

Assignees

• Cisco Tech Inc

Inventors

• Voit Eric A
• Pignataro Carlos
• Nalamalapu Kasi R
• Valenza Salvatore
• Salam Samer M

Classifications

• H04L41/147

  for predicting network behaviour · CPC title

• H04L41/12

  Discovery or management of network topologies · CPC title

• H04L41/083

  for increasing network speed · CPC title

• H04W84/12

  WLAN [Wireless Local Area Networks] · CPC title

• H04W88/08

  Access point devices · CPC title