Antenna Selection via Contextual Sensor Data and Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current information handling systems face challenges in optimizing wireless antenna selection due to factors like orientation, location, and configuration, which affect mm-wave signal performance and lead to dropout issues, especially when intervening structures are present.

Innovation Solution

A method utilizing a sensor module and antenna performance module to track and measure parameters like RSSI, bit error rates, and latency, combined with machine learning techniques to develop antenna use profiles and provide prioritized recommendations for optimal antenna selection based on tracked parameters and crowd-sourced data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If mm-wave antennas are used to improve wireless performance, then bandwidth and speed are improved, but signal dropout occurs due to orientation and location sensitivity

Engineering Contradiction:

Improvewireless communication speedVSAvoidsignal connectivity reliability

Core Design Contradiction:

SpeedVSReliability

Solution Approach 1:

The patent implements dynamic antenna selection based on real-time sensor data (accelerometer, gyroscope, magnetometer) to adapt to changing device orientation and location. The system continuously monitors contextual parameters and switches between mm-wave and non-mm-wave antennas accordingly, making the system dynamic rather than static to resolve the contradiction between speed and reliability.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes operational parameters by switching between different antenna types (mm-wave vs. non-mm-wave) based on detected orientation and location parameters. When sensors detect unfavorable conditions for mm-wave operation, the system changes to alternative antennas, thereby maintaining reliability while preserving the ability to achieve high speed when conditions are favorable.

Inventive Principle:

Principle #35Parameter changes

2Adaptability or versatility

If multiple antennas are provided to improve connectivity options, then adaptability is improved, but device complexity increases

Engineering Contradiction:

Improveantenna selection adaptabilityVSAvoidantenna system complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system employs automated sensor-based detection and machine learning algorithms to autonomously select the optimal antenna without user intervention. The contextual awareness module continuously monitors device state and automatically determines which antenna to use, making the system self-managing and reducing the perceived complexity for users while maintaining high adaptability.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent pre-configures multiple antennas with different characteristics (mm-wave and non-mm-wave options) and pre-trains machine learning models with contextual data. This preliminary preparation allows the system to quickly adapt to various situations without requiring complex real-time decision-making, thereby managing complexity while maintaining versatility.

Inventive Principle:

Principle #10Preliminary action

3Reliability

If sensor tracking and machine learning are implemented to optimize antenna selection, then connectivity reliability is improved, but energy consumption increases

Engineering Contradiction:

Improvewireless connection reliabilityVSAvoidenergy consumption for processing

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system uses rapid sensor-based detection to quickly assess whether conditions are favorable for mm-wave operation. When unfavorable conditions are detected, the system rapidly switches to non-mm-wave antennas without requiring extensive machine learning analysis, thereby reducing processing energy consumption while maintaining connection reliability through quick contextual assessment.

Inventive Principle:

Principle #21Skipping (Rushing through)

Solution Approach 2:

The patent implements a hierarchical approach where basic sensor tracking is always active (partial action), and machine learning analysis is performed only when needed or at scheduled intervals. This selective application of processing resources maintains reliability through continuous monitoring while reducing overall energy consumption by avoiding excessive computational activity.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS11558090B2Systems and methods to utilize contextual awareness and machine learning to optimize antenna selection

Publication Date: 2023.01.17 DELL PROD LP

AI summary

A system and method of optimizing a selection of an antenna on an information handling system comprising executing a sensor module to receive data from a plurality of sensors for tracking orientations, configurations, and locations of the information handling system and an antenna performance tracking system for measuring antenna performance parameters at a plurality of locations and training an antenna selection machine learning algorithm of an antenna selection machine learning module with training inputs of the orientations, configurations, and antenna performance parameters for a plurality of locations to determine an antenna system recommendation from a plurality of available antenna systems deployed on the information handling system. Executing the trained antenna selection machine learning module with operating inputs for an orientation and configuration at an operation location to determine a recommended antenna system from the plurality of available antenna systems for use in wireless communication.