Mobile Device Data Pre-loading for Network Coverage Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for mobile devices in distributed wireless networks fail to address the dynamic prediction of network outages and bandwidth availability, leading to interruptions in service, especially in areas with poor coverage or congestion.
Innovation Solution
A method and system that predictively determine a mobile device's coverage area based on user location and movement history, and dynamically adjust data pre-loading to ensure continuous service by analyzing signal strength and bandwidth, storing necessary data locally before network failures occur.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is pre-loaded into mobile device memory before predicted network failures, then service continuity is improved, but device memory usage increases
Solution Approach 1:
The system performs preliminary actions by predicting future network failure events using machine learning models that analyze historical network data, device location, and movement patterns. Before the predicted network failure occurs, the system proactively pre-loads necessary data into the device's local memory, ensuring service continuity without waiting for actual network disruptions.
Solution Approach 2:
The system dynamically adjusts the amount of data to pre-load based on multiple changing parameters including the predicted duration of network failure, device battery level, current memory availability, data priority levels, and network bandwidth conditions. This parameter-driven approach optimizes memory usage while maintaining service continuity.
2Reliability
If data is pre-loaded into mobile device memory, then service during network failure is maintained, but energy consumption increases
Solution Approach 1:
The system performs data pre-loading during periods when network connectivity is available and energy consumption can be distributed over time. By predicting future network failures and pre-loading data during normal operating conditions, the system avoids the higher energy cost of data transmission during actual network disruptions.
Solution Approach 2:
The system monitors and responds to changing energy parameters including device battery level, processor load, and network conditions. When energy levels are high and network availability is good, the system performs aggressive data pre-loading. When energy levels drop or the device is in low-power states, the system reduces or pauses pre-loading activities.
3Reliability
If the system predicts coverage area and pre-loads data proactively, then service interruption is reduced, but system complexity increases
Solution Approach 1:
The system introduces intermediary components including machine learning prediction models that analyze network data, a data prioritization framework that categorizes information by importance, and a selective pre-loading mechanism. These intermediaries manage the complexity of predicting coverage areas and determining what data to pre-load, while presenting a simple interface to the user.
Solution Approach 2:
The system uses multiple parameters to simplify decision-making: network failure probability thresholds, data priority levels, memory availability thresholds, and predicted failure duration. By converting complex predictions into parameter-based decisions, the system manages complexity while maintaining effective service continuity.
4Reliability
If data is cached locally in the mobile device, then network dependency is reduced, but data freshness may deteriorate
Solution Approach 1:
The system implements a time-based parameter where data priority and pre-loading decisions are influenced by the expected duration of network unavailability. For time-critical data with short validity periods, the system reduces pre-loading or uses shorter prediction windows. For less time-sensitive data, more aggressive pre-loading is performed, optimizing the balance between network independence and data freshness.
Data Source
AI summary
A method and system is disclosed for providing continued of streaming content to a mobile device in a distributed wireless network. This includes receiving user location data; receiving user movement history data; receiving user profile data; determining a predicted coverage area based on the user location data and at least one of: the user movement history data and the user profile data; receiving static coverage data for the predicted coverage area; receiving dynamic signal data for the predicted coverage area; determining a predicted probability of network failure in the predicted coverage area based on the static coverage data and the dynamic signal data; determining if the predicted probability exceeds a set threshold value; retrieving desirable data for the predicted coverage area if the predicted probability exceeds a threshold; and storing the desirable data in a computer memory in the mobile device if the predicted probability exceeds the threshold.