Predicting Wi-Fi Access Point Availability via Cellular Fingerprints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cellular network communications devices face limitations in bandwidth and battery life due to frequent use of Wi-Fi radios for data offloading, which can result in slow data transmission and battery drainage, especially when connecting to access points with low signal strength.
Innovation Solution
A computing device generates access point profiles based on cellular fingerprints to predict the availability and quality of Wi-Fi access points, allowing devices to conserve battery life and ensure successful handoffs by selectively activating the Wi-Fi radio only when a suitable access point is within range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If Wi-Fi radio is frequently used to scan for access points, then data offloading capability is improved, but battery life deteriorates
Solution Approach 1:
The system performs preliminary actions by using cellular fingerprints to predict access point availability before the device actually needs to offload data. This allows the device to know in advance whether suitable access points will be available, avoiding the need for frequent active scanning and Wi-Fi radio usage, thereby conserving battery life while maintaining data offloading capability.
Solution Approach 2:
The patent introduces cellular fingerprints as an intermediary mechanism between cellular network status and Wi-Fi access point availability. Instead of directly scanning for Wi-Fi access points, the system uses cellular tower signal patterns as a predictive indicator, eliminating the need for frequent Wi-Fi radio activation and reducing energy consumption.
2Adaptability or versatility
If Wi-Fi radio is activated frequently to find access points, then network switching capability is improved, but data transmission reliability deteriorates due to low signal strength connections
Solution Approach 1:
The system predicts access point availability and signal quality in advance using cellular fingerprints before the device attempts to connect. This preliminary assessment ensures that the device only switches to Wi-Fi when a reliable connection is predicted, avoiding connections to access points with low signal strength and thereby maintaining data transmission reliability.
Solution Approach 2:
The system uses historical data about cellular fingerprints and their correlation with successful Wi-Fi connections to create predictive models. This feedback mechanism continuously improves the accuracy of predictions about access point availability and quality, enabling more reliable network switching decisions.
3Speed
If cellular network bandwidth is limited, then data transmission speed deteriorates, but switching to non-cellular networks requires frequent Wi-Fi scanning which increases energy consumption
Solution Approach 1:
The system performs preliminary prediction of access point availability using cellular fingerprints before data transmission needs to be offloaded. This allows the device to proactively identify when non-cellular network paths will be available, enabling efficient bandwidth utilization without requiring frequent active scanning, thus improving data transmission speed while minimizing energy consumption.
Data Source
Figure 1A
Figure 1B
Figure 2A
AI summary
Examples relate to predicting access point availability. In one example, a computing device may: obtain a set of training fingerprints, each training fingerprint specifying, for a client device, an access point to which the client device successfully connected and cellular signal strength for each cellular tower in a set of cellular towers; and for each access point: generate an access point profile for the access point, the access point profile indicating, for each cellular tower in the set of cellular towers specified by a first subset of the set of training fingerprints, a probability that a randomly selected training fingerprint included in the first subset specified a particular cellular signal strength for the cellular tower, wherein each training fingerprint included in the first subset specifies the access point as the access point to which the client device specified by the training fingerprint included in the first subset successfully connected.