ML-Based Priority Cell Reentry for UE Network Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing blind cell search process in user equipment (UE) is time-consuming and power-intensive when reentering a network after coverage loss or shutdown, affecting user experience and battery life.
Innovation Solution
Implementing a machine learning (ML) component that determines a set of priority reentry cells based on mobility data and network connectivity context history, allowing the UE to attempt network reentry with these cells first, reducing the need for a blind search and conserving battery power.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the UE performs a blind cell search to identify network cells after reentering the network, then the UE can reliably reconnect to the network, but the process consumes excessive battery power and takes too much time
Solution Approach 1:
The system performs preliminary actions by maintaining context history and mobility data before network exit occurs. The ML model pre-processes this information to predict priority reentry cells, so when reentry is needed, the UE can skip the blind search and directly attempt connection to predicted cells, significantly reducing power consumption and time
Solution Approach 2:
The patent replaces the traditional mechanical blind cell search process with an intelligent ML-based prediction system. Instead of systematically searching through all possible cells (mechanical approach), the system uses machine learning to intelligently predict which cells are most likely to be available, substituting computational intelligence for exhaustive physical search
2Reliability
If the UE performs a blind cell search to identify network cells after reentering the network, then the UE can reliably reconnect to the network, but the process takes too much time
Solution Approach 1:
The system performs preliminary actions by maintaining context history and mobility data before network exit occurs. The ML model pre-processes this information to predict priority reentry cells, so when reentry is needed, the UE can skip the blind search and directly attempt connection to predicted cells, significantly reducing reconnection time
Solution Approach 2:
The patent applies the skipping principle by allowing the UE to bypass the time-consuming blind cell search process. Instead of rushing through all possible cells systematically, the ML model identifies and prioritizes the most likely candidate cells, enabling the UE to rush directly to the most promising reentry targets
3Productivity
If the UE uses a machine learning component to determine priority reentry cells based on mobility data and network connectivity context history, then the cell search process is accelerated and battery power is saved, but the device complexity increases
Solution Approach 1:
The ML component operates autonomously using self-service principles. It automatically collects mobility data and network connectivity context history, trains itself on this data, and generates predictions without requiring manual intervention or complex external control systems, thereby limiting the increase in overall device complexity
Data Source
AI summary
Solutions for accelerating cell search and selection by a user equipment (UE) include: detecting, by the UE, a network exit; determining, by the UE, a network reentry condition; based on at least mobility data for the UE and a network connectivity context history, determining, by the UE, using a machine learning (ML) component, a set of priority reentry cells; attempting network reentry with the set of priority reentry cells; and based on at least failing network reentry with the set of priority reentry cells, attempting network reentry with a cell search. In some examples, mobility data for the UE is also used for determining the set of priority reentry cells. By searching the set of priority reentry cells first , rather than starting with a blind search, the UE may save not only battery power, but also reconnect to the network more quickly, thereby improving the user experience.