# US 2026/0101207 A1 · Location determination in wireless networks using machine learning

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

- Number: US 2026/0101207 A1
- Document ID: US20260101207A1
- Status: Published application
- Kind: A1
- Application number: 18/982,588
- Filed: 2024-12-16
- Published: 2026-04-09
- Earliest claimed: 2024-10-07
- Assignees: Hewlett Packard Enterprise Development LP
- Applicants: Hewlett Packard Enterprise Development LP
- Inventors: Siva Lingeswara Reddy Onteddu; Sachin Shamrao Sanap; Mayuri Pawar; Akshay Ganesh Kini; Naveen Holla
- Web page: https://patentgrep.com/patent/US20260101207A1

## CPC

- H04W 24/08: Testing, {supervising or monitoring} using real traffic
- H04W 24/02: Arrangements for optimising operational condition
- H04W 64/003: {locating network equipment}
- 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

An example method for determining the distance between the network devices thereby enhancing the accuracy of location determination is presented. In one example implementation, the proposed method entails training, during a training phase, a machine learning (ML) model based on test environmental condition metrics about the network devices. Further, during an inference phase, a network controller may first determine a coarse distance between a pair of network devices using wireless signal strength between the pair of network devices, and then finetune the coarse distance to generate a refined distance using a trained ML model. Further, using the refined distance, the network controller may more accurately determine the location of a network device of the pair of network devices whose location was unknown.

## Claims

### Claim 1

A method comprising:
receiving, by a network controller, a runtime signal strength metric indicative of wireless signal power between a first network device and a second network device in a network infrastructure;
receiving, by the network controller, a runtime environmental condition metrics corresponding to one or both of the first network device and the second network device;
determining, by the network controller, a coarse distance between the first network device and the second network device based on the runtime signal strength metric; and
determining, by the network controller, a refined distance between the first network device and the second network device based on the coarse distance and the runtime environmental condition metrics using a machine learning (ML) model, wherein the ML model is trained to infer the refined distance based at least on a set of test environmental condition metrics corresponding to a set of network devices installed at known locations in the network infrastructure.

### Claim 2 (depends on 1)

The method of claim 1, wherein the first network device is one of the set of network devices installed at the known locations.

### Claim 3 (depends on 1)

The method of claim 1, wherein the runtime environmental condition metrics comprises measures of one or more of humidity, temperature, pressure, or signal absorption by physical objects in the vicinity of one or both of the first network device and the second network device.

### Claim 4 (depends on 1)

The method of claim 1, wherein the runtime signal strength metric is a received signal strength indicator (RSSI) determined by the first network device corresponding to the second network device.

### Claim 5 (depends on 4)

The method of claim 4, wherein the wireless signal is transmitted in accordance with any of the Bluetooth Standards or the Wireless-Fidelity (Wi-Fi) Standards.

### Claim 6 (depends on 2)

The method of claim 2, further comprising determining by the network controller, a location of the second network device based on the refined distance between the first network device and the second network device and a known location of the first network device.

### Claim 7 (depends on 1)

The method of claim 1, further comprising training the ML model during a training phase.

### Claim 8 (depends on 4)

The method of claim 4, wherein training the ML model comprises:
receiving, by the network controller, a first test signal strength metric between a first network device and a third network device of the set of network devices;
receiving by the network controller, an actual distance between the first network device and the second network device; and
determining, by the network controller, a preliminary distance between the first network device and the third network device based on the first test signal strength metric.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
receiving, by the network controller, the set of test environmental condition metrics corresponding to the first network device and the third network device; and
finetuning, by the network controller, the preliminary distance to generate a finetuned preliminary distance using the ML model, the set of test environmental condition metrics, and a set of ML feature weights;
updating, by the network controller, the set of ML feature weights to generate a set of updated ML feature weights based on a difference between the actual distance and the finetuned preliminary distance; and
storing, by the network controller, the set of updated NN weights.

### Claim 10 (depends on 9)

The method of claim 9, wherein determining the refined distance between the first network device and the second network device comprises using the ML model with the set of updated ML feature weights.

### Claim 11 (depends on 1)

The method of claim 1, wherein the ML model comprises a neural network or a deep neural network.

### Claim 12

A network controller comprising:
a processing resource; and
a non-transitory machine-readable storage medium storing instructions executable by the processing resource, wherein the processing resource is configured to execute one or more of the instructions to:
receive, from an access point (AP), a runtime signal strength metric indicative of wireless signal power between the AP and a client device in a network infrastructure;
receive, from the AP, a runtime environmental condition metrics corresponding to one or both of the AP and the client device;
determine a coarse distance between the AP and the client device based on the runtime signal strength metric; and
determine a refined distance between the AP and the client device based on the coarse distance and the runtime environmental condition metrics using a machine learning (ML) model, wherein the ML model is trained to infer the refined distance based at least on a set of test environmental condition metrics corresponding to a set of network devices installed at known locations in the network infrastructure and one or more test signal strength metrics reported by the set of network devices.

### Claim 13 (depends on 12)

The network controller of claim 12, wherein the runtime environmental condition metrics comprises measures of one or more of humidity, temperature, pressure, or signal absorption by physical objects in the vicinity of the AP, the client device, or both.

### Claim 14 (depends on 12)

The network controller of claim 12, wherein the processing resource is configured to execute one or more of the instructions to determine a location of the client device based on the refined distance and a known location of the AP using a triangulation technique or a trilateration technique, or both.

### Claim 15 (depends on 12)

The network controller of claim 12, wherein the processing resource, during a training phase, is configured to execute one or more of the instructions to:
receive a test signal strength metric between a first AP and a second AP of the set of APs;
receive an actual distance between the first AP and the second AP; and
determine a preliminary distance between the first AP and the second AP based on the test signal strength metric.

### Claim 16 (depends on 15)

The network controller of claim 15, wherein the processing resource, during a training phase, is configured to execute one or more of the instructions to:
receive the set of test environmental condition metrics corresponding to the first AP and the second AP; and
finetune the preliminary distance to generate a finetuned preliminary distance using the ML model, the set of test environmental condition metrics, and a set of ML feature weights;
update the set of ML feature weights to generate a set of updated ML feature weights based on a difference between the actual distance and the refined distance; and
store the set of updated ML feature weights.

### Claim 17 (depends on 16)

The network controller of claim 16, wherein to determine the refined distance the processing resource is configured to execute one or more of the instructions to apply the set of updated ML feature weights to the ML model.

### Claim 18

A computer-implemented method comprising:
receiving a test signal strength metric between a pair of network devices positioned at known locations in a network infrastructure;
receiving an actual distance between the pair of network devices;
determining a preliminary distance between the pair of network devices based on the test signal strength metric;
finetuning the preliminary distance to generate a finetuned preliminary distance using a neural network, a set of test environmental condition metrics, and a set of neural network weights, wherein the set of test environmental condition metrics comprises measures of one or more of humidity, temperature, pressure, or signal absorption by physical objects;
updating the set of neural network feature weights to generate a set of updated neural network weights based on a difference between the actual distance and the finetuned preliminary distance; and
recording the set of updated neural network weights.

### Claim 19 (depends on 18)

The computer-implemented method of claim 18, further comprising:
inferring a distance between a first network device and a second network device located in the network infrastructure using the neural network and the set of updated neural network weights, wherein the first network device is positioned at a known location in the network infrastructure; and
determining a location of the second network device based on the distance between the first network device and the second network device.

### Claim 20 (depends on 18)

The computer-implemented method of claim 18, wherein the test signal strength metric is determined by one of the pair of network devices based on a BLE beacon transmitted by the other of the pair of network devices.
