Dynamic Transmit Power Control via Machine Learning

Solution Overview

Problem

Wireless control networks face issues with interference and increased power consumption due to static transmit power levels, which can lead to co-existence problems and inefficient battery operation in devices.

Innovation Solution

Implementing a machine learning (ML) model to dynamically determine transmit power levels based on network traffic information, noise floor, and received power, using a neural network trained in hostile wireless environments to adapt transmit power for each message, reducing interference and power consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a static transmit power level is used in wireless control networks, then device complexity is reduced and ease of operation is improved, but interference between devices increases and power consumption becomes inefficient

Engineering Contradiction:

Improveease of operationVSAvoidinterference

Core Design Contradiction:

Ease of operationVSObject-generated harmful factors

Solution Approach 1:

The patent implements dynamic transmit power adjustment by training a neural network model to predict optimal power levels based on historical network traffic data and environmental conditions. The system transitions from static power settings to adaptive power control, where the transmit power level changes dynamically according to predicted network conditions, thereby reducing interference while maintaining ease of operation through automated control.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of transmit power from a fixed static value to a dynamically adjusted variable. By using machine learning to predict optimal power levels based on network traffic patterns, noise floor conditions, and received signal strength, the system optimizes the power parameter to minimize interference while maintaining communication reliability.

Inventive Principle:

Principle #35Parameter changes

2Device complexity

If a static transmit power level is used, then device complexity is reduced, but power consumption increases due to higher than necessary power levels

Engineering Contradiction:

Improvedevice complexityVSAvoidpower consumption

Core Design Contradiction:

Device complexityVSUse of energy by moving object

Solution Approach 1:

The patent implements dynamic transmit power adjustment by training a neural network model to predict optimal power levels based on historical network traffic data and environmental conditions. The system transitions from static power settings to adaptive power control, where the transmit power level changes dynamically according to predicted network conditions, thereby reducing interference while maintaining ease of operation through automated control.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of transmit power from a fixed static value to a dynamically adjusted variable. By using machine learning to predict optimal power levels based on network traffic patterns, noise floor conditions, and received signal strength, the system optimizes the power parameter to minimize interference while maintaining communication reliability.

Inventive Principle:

Principle #35Parameter changes

3Area of stationary object

If transmit power is increased to improve communication range, then signal coverage is improved, but interference with nearby networks increases

Engineering Contradiction:

Improvecommunication rangeVSAvoidinterference

Core Design Contradiction:

Area of stationary objectVSObject-generated harmful factors

Solution Approach 1:

The system changes the parameter of transmit power from a fixed static value to a dynamically adjusted variable. By using machine learning to predict optimal power levels based on network traffic patterns, noise floor conditions, and received signal strength, the system optimizes the power parameter to minimize interference while maintaining communication reliability.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system uses feedback from received signal strength indicator (RSSI) measurements and noise floor monitoring to adjust transmit power levels. By continuously monitoring the wireless environment and using this feedback to train the neural network model, the system adapts power levels to achieve adequate coverage while minimizing interference with nearby networks.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11375463B2System, apparatus and method for dynamic transmit power determination

Publication Date: 2022.06.28 SILICON LABORATORIES INC

AI summary

In an embodiment, an apparatus includes a transceiver with a receiver signal processing path and a transmitter signal processing path. The receiver signal processing path is to receive and process a message. The apparatus further includes a controller coupled to the transceiver to obtain information regarding the message and to determine, based at least in part on the information, a transmit power level for a next message to be sent from the transceiver according to a machine learning model.