# US 12,114,185 B2 · Method and system to predict network performance of a fixed wireless network

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

- Number: US 12,114,185 B2
- Document ID: US12114185B2
- Status: Granted
- Kind: B2
- Application number: 17/299,759
- Filed: 2018-12-11
- Published: 2022-01-20
- Granted: 2024-10-08
- Earliest claimed: 2018-12-11
- Assignees: Teleonaktiebolaget LM Ericsson (Publ)
- Applicants: Telefonaktiebolaget LM Ericsson (publ)
- Inventors: Sri Harsha Anand Pushkala; Vinod Kumar Jammula; Ankita Chowdhury; David Reboredo; Amr Shehata
- Web page: https://patentgrep.com/patent/US12114185B2

## CPC

- H04L 41/147: for predicting network behaviour
- H04L 41/145: {involving simulating, designing, planning or modelling of a network}
- H04W 24/04: Arrangements for maintaining operational condition
- H04W 24/08: Testing, {supervising or monitoring} using real traffic
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

Methods and systems to predict network performance of a fixed wireless network is disclosed. In one embodiment, a method is performed by an electronic device, the method comprises receiving data of a fixed wireless network; modeling the data using a plurality of functions, where the modeling comprises identifying a prediction function that provides a best approximation of the data based on a user preference of approximation speed and accuracy; predicting a network performance value in a future time using the prediction function; and notifying when the predicted network performance value fails to meet a threshold value.

## Claims

### Claim 1

A method performed by an electronic device to predict network performance of a fixed wireless network, the method comprising:
receiving data of the fixed wireless network, the data including one or more of weather condition samples, man-made structure data sample, or geographic data samples;
modeling the data using a plurality of functions, the modeling comprises:
identifying a prediction function that provides a best approximation of the data based on a user preference of approximation speed and accuracy;
predicting a network performance value in a future time using the prediction function, the network performance value being a value for signal strength; and
notifying when the predicted network performance value fails to meet a threshold value.

### Claim 2 (depends on 1)

The method of claim 1, wherein the data comprises data from a single geographic area or from a single time duration.

### Claim 3 (depends on 1)

The method of claim 1, wherein identifying the prediction function that provides the best approximation of the data comprises:
providing the data to an offline computing system;
approximating the data using the plurality of functions simultaneously; and
identifying the prediction function using an accuracy measure of the approximation of the plurality of functions based on the user preference.

### Claim 4 (depends on 1)

The method of claim 1, wherein the plurality of functions comprises:
a function determining a moving average of the data;
a function determining a weighted moving average of the data;
a function determining a trend of the data using exponential smoothing;
a function determining seasonality of the data using Holt Winters filtering; and
a function determining a seasonality of the data based on lagging data values.

### Claim 5 (depends on 1)

The method of claim 1, wherein the data comprises a same type of data as that of the network performance value.

### Claim 6 (depends on 1)

The method of claim 1, wherein the data comprises a plurality of types of data to predict the network performance value.

### Claim 7 (depends on 6)

The method of claim 6, wherein the plurality of functions comprises:
a multi-variate linear regression (MLR) function, wherein each type of the data is a variable of the MLR function; and
an autoregressive integrated moving average function with an external factor (ARIMAX), wherein each type of the data is a variable of the ARIMAX function.

### Claim 8 (depends on 1)

The method of claim 1, wherein the notifying comprises using a Representational state transfer (REST) application programming interface (API).

### Claim 9 (depends on 1)

The method of claim 1, wherein the user preference of approximation speed and accuracy is provided through a Representational state transfer (REST) application programming interface (API).

### Claim 10

An electronic device to be deployed in a fixed wireless network, comprising:
a processor and computer-readable storage medium that provides instructions that, when executed by the processor, cause the electronic device to perform:
receiving data of the fixed wireless network, the data including one or more of weather condition samples, man-made structure data sample, or geographic data samples;
modeling the data using a plurality of functions, the modeling comprises: identifying a prediction function that provides a best approximation of the data based on a user preference of approximation speed and accuracy;
predicting a network performance value in a future time using the prediction function, the network performance value being a value for signal strength; and
notifying when the predicted network performance value fails to meet a threshold value.

### Claim 11 (depends on 10)

The electronic device of claim 10, wherein the identification of the prediction function is to perform:
providing the data to an offline computing system;
approximating the data using the plurality of functions simultaneously; and
identifying the prediction function using an accuracy measure of the approximation of the plurality of functions based on the user preference.

### Claim 12 (depends on 10)

The electronic device of claim 10, wherein the data comprises a plurality of types of data that are distinct from that of the network performance value.

### Claim 13

A non-transitory computer-readable storage medium that provides instructions that, when executed by a processor of an electronic device, cause the electronic device to perform:
receiving data of a fixed wireless network, the data including one or more of weather condition samples, man-made structure data sample, or geographic data samples;
modeling the data using a plurality of functions, the modeling comprises: identifying a prediction function that provides a best approximation of the data based on a user preference of approximation speed and accuracy;
predicting a network performance value in a future time using the prediction function, the network performance value being a value for signal strength; and
notifying when the predicted network performance value fails to meet a threshold value.

### Claim 14 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, where the plurality of functions comprises:
a function determining a moving average of the data;
a function determining a weighted moving average of the data;
a function determining a trend of the data using exponential smoothing;
a function determining seasonality of the data using Holt Winters filtering; and
a function determining a seasonality of the data based on lagging data values.

### Claim 15 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein the user preference of approximation speed and accuracy is provided through a Representational state transfer (REST) application programming interface (API).