# US 2019/0246324 A1 · Radar shield client assurance in wireless networks

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0246324 A1
- Document ID: US20190246324A1
- Status: Published application
- Kind: A1
- Application number: 15/891,488
- Filed: 2018-02-08
- Published: 2019-08-08
- Earliest claimed: 2018-02-08
- Assignees: Cisco Technology, Inc.
- Applicants: Cisco Technology, Inc.
- Inventors: Benjamin Jacob Cizdziel; Vishal Satyendra Desai; Santosh Kulkarni; Young Il Choi; Nafi Ur Rashid; Leela Venkata Kiran Kumar Reddy Chirala
- Web page: https://patentgrep.com/patent/US20190246324A1

## CPC

- H04W 36/06: Reselecting a communication resource in the serving access point
- H04W 16/14: Spectrum sharing arrangements {between different networks}
- H04W 24/08: Testing, {supervising or monitoring} using real traffic
- H04W 36/0088: {Scheduling hand-off measurements}
- H04W 72/0453: Resources in frequency domain, e.g. a carrier in FDMA
- H04W 84/12: WLAN [Wireless Local Area Networks]
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

In one embodiment, a service receives radar data regarding usage of one or more wireless channels by a radar. The service populates a database of radar features with the received radar data. The service trains, using the database of radar features, a machine learning-based model to predict channel usages by the radar. The service causes a wireless access point to change to a different wireless channel, based on the predicted channel usages by the radar.

## Claims

### Claim 1

A method comprising:
receiving, at a service, radar data regarding usage of one or more wireless channels by a radar;
populating, by the service, a database of radar features with the received radar data;
training, by the service and using the database of radar features, a machine learning-based model to predict channel usages by the radar; and
causing, by the service, a wireless access point to change to a different wireless channel, based on the predicted channel usages by the radar.

### Claim 2 (depends on 1)

The method as in claim 1, wherein the received radar data comprises a particular wireless channel on which the radar was detected and at least one of: a time or location at which usage of the particular wireless channel by the radar was detected.

### Claim 3 (depends on 1)

The method as in claim 1, further comprising:
determining, by the service, whether a detection by a first access point of the radar using a particular wireless channel was a false positive by comparing radar data received from a plurality of access points.

### Claim 4 (depends on 1)

The method as in claim 1, wherein the machine learning-based model comprises a logistic regression-based classifier or a nearest neighbor-based classifier.

### Claim 5 (depends on 1)

The method as in claim 1, wherein causing the wireless access point to change to a different wireless channel, based on the predicted channel usages by the radar, comprises:
using, by the service, the machine learning-based model to predict a time at which the radar will begin using a wireless channel in use by the access point; and
causing, by the service, the access point to switch to a different wireless channel, in advance of the predicted time.

### Claim 6 (depends on 1)

The method as in claim 1, wherein causing the wireless access point to change to a different wireless channel, based on the predicted channel usages by the radar, comprises:
notifying the access point of at least one of the wireless channels that is predicted to be clear from use by the radar.

### Claim 7 (depends on 1)

The method as in claim 1, wherein the wireless channels comprise 5 GHz Wi-Fi channels.

### Claim 8 (depends on 1)

The method as in claim 1, wherein the wireless channel to which the access point changes is a dynamic frequency selection (DFS) channel, and wherein the access point uses a second antenna to perform a channel availability check (CAC) before changing channels.

### Claim 9 (depends on 1)

The method as in claim 1, wherein the service is hosted by the access point or by a wireless local area network controller (WLC) that oversees the access point.

### Claim 10

An apparatus comprising:
one or more network interfaces to communicate with a network;
a processor coupled to the network interfaces and configured to execute one or more processes; and
a memory configured to store a process executable by the processor, the process when executed configured to:
receive radar data regarding usage of one or more wireless channels by a radar;
populate a database of radar features with the received radar data;
train, using the database of radar features, a machine learning-based model to predict channel usages by the radar; and
cause a wireless access point to change to a different wireless channel, based on the predicted channel usages by the radar.

### Claim 11 (depends on 10)

The apparatus as in claim 10, wherein the received radar data comprises a particular wireless channel on which the radar was detected and at least one of: a time or location at which usage of the particular wireless channel by the radar was detected.

### Claim 12 (depends on 10)

The apparatus as in claim 10, wherein the process when executed is further configured to:
determine whether a detection by a first access point of the radar using a particular wireless channel was a false positive by comparing radar data received from a s plurality of access points.

### Claim 13 (depends on 10)

The apparatus as in claim 10, wherein the machine learning-based model comprises a logistic regression-based classifier or a nearest neighbor-based classifier.

### Claim 14 (depends on 10)

The apparatus as in claim 10, wherein the apparatus causes the wireless access point to change to a different wireless channel, based on the predicted channel usages by the radar, by:
using the machine learning-based model to predict a time at which the radar will begin using a wireless channel in use by the access point; and
causing the access point to switch to a different wireless channel, in advance of the predicted time.

### Claim 15 (depends on 10)

The apparatus as in claim 10, wherein the apparatus causes the wireless access point to change to a different wireless channel, based on the predicted channel usages by the radar, by:
notifying the access point of at least one of the wireless channels that is predicted to be clear from use by the radar.

### Claim 16 (depends on 15)

The apparatus as in claim 15, wherein the access point continuously performs a channel availability check (CAC) on the at least one wireless channel predicted to be clear from use by the radar, prior to changing channels.

### Claim 17 (depends on 10)

The apparatus as in claim 10, wherein the wireless channel to which the access point changes is a dynamic frequency selection (DFS) channel, and wherein the access point uses a second antenna to perform a channel availability check (CAC) before changing channels.

### Claim 18 (depends on 10)

The apparatus as in claim 10, wherein the apparatus comprises the access point or a wireless local area network controller (WLC) that oversees the access point.

### Claim 19

A tangible, non-transitory, computer-readable medium storing program instructions that cause a service in a network to execute a process comprising:
receiving, at the service, radar data regarding usage of one or more wireless channels by a radar;
populating, by the service, a database of radar features with the received radar data;
training, by the service and using the database of radar features, a machine learning-based model to predict channel usages by the radar; and
causing, by the service, a wireless access point to change to a different wireless channel, based on the predicted channel usages by the radar.

### Claim 20 (depends on 19)

The computer-readable medium as in claim 19, wherein causing the wireless access point to change to a different wireless channel, based on the predicted channel usages by the radar, comprises:
using, by the service, the machine learning-based model to predict a time at which the radar will begin using a wireless channel in use by the access point; and
causing, by the service, the access point to switch to a different wireless channel, in advance of the predicted time.
