Wearable Radio Selection Using Predicted Data Transfer Load
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Consumer electronics, particularly wearable devices with small batteries, face challenges in maintaining connectivity while achieving all-day or multi-day battery life due to inefficient power consumption by communication units like Wi-Fi, Bluetooth, and cellular radios.
Innovation Solution
A wearable computing device routes data through a communication unit with the lowest power cost based on stored routing information and signal conditions, using machine learning to predict data transfer amounts and select the most efficient radio for data transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If Bluetooth or Bluetooth Low Energy is prioritized for connectivity, then connectivity reliability is improved, but power consumption increases and battery life decreases
Solution Approach 1:
The system dynamically selects the optimal communication unit (Wi-Fi, Bluetooth, LTE, or 5G) based on real-time conditions including signal strength, data size, and power consumption characteristics. The routing decision changes adaptively rather than following a fixed priority scheme, allowing the device to switch between communication units to minimize power consumption while maintaining connectivity reliability.
Solution Approach 2:
The system changes the selection parameter from traditional metrics like monetary cost, bandwidth, or latency to power consumption as the primary routing criterion. By using machine learning models to predict power consumption based on data size and signal conditions, the system optimizes the routing decision parameter to achieve lowest power consumption while maintaining acceptable connectivity.
2Speed
If Wi-Fi is used for data transmission, then data transfer speed is improved, but power consumption increases
Solution Approach 1:
The system uses machine learning models to predict the actual power consumption and data transfer characteristics before committing to a communication unit. By analyzing historical data and current conditions, the system makes informed decisions about whether the high speed of Wi-Fi justifies the higher power consumption, or if alternative units like Bluetooth should be used for smaller data transfers.
3Adaptability or versatility
If multiple communication units are maintained ready for connectivity, then connectivity availability is improved, but power consumption increases
Solution Approach 1:
The system performs preliminary analysis using machine learning models to predict future communication needs and power consumption before actually activating communication units. By anticipating data transfer requirements and signal conditions, the system can strategically activate or deactivate communication units to maintain connectivity availability while minimizing power consumption during idle periods.
Data Source
AI summary
In one example, a method for power efficient data routing comprises determining, by a computing device comprising a plurality of radios, one or more signal conditions for each of the plurality of radios, determining, by the computing device, an amount of data the computing device is predicted to transfer within a particular period of time, the amount of data being a predicted amount of data, determining, by the computing device and based on the one or more signal conditions for each of the plurality of radios and the predicted amount of data, a power cost for each of the plurality of radios, selecting, by the computing device, a selected radio from the plurality of radios based on the power cost for each of the plurality of radios, and transferring, by the computing device and using the selected radio, data between the computing device and a remote device.