RAN Paging Using UE Trajectory Prediction to Cut Idle-State Delay
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing paging procedures in cellular networks, such as those in 5G networks, are inefficient for user equipment (UE) devices in idle states, leading to increased latency, radio channel interference, and unnecessary energy consumption due to repeated paging attempts across multiple cells.
Innovation Solution
Implementing a radio access network (RAN) device with a trajectory prediction system using machine learning (ML) and artificial intelligence (AI) to predict the future location of idle UE devices, allowing for targeted and optimized paging by mapping predicted cell locations to distributed units (DUs) for efficient message delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional paging procedures are used across multiple cells, then the paging message can reach the idle UE device, but it causes increased latency, radio channel interference, and energy consumption
Solution Approach 1:
The system performs preliminary actions by predicting the future location of idle UE devices using machine learning models before initiating paging. The RAN device uses trajectory prediction to determine which cells the UE is likely to be in, allowing targeted paging attempts only in those predicted cells rather than broadcasting across multiple cells, thus reducing paging wait time while maintaining delivery reliability
Solution Approach 2:
The invention changes the parameter of paging scope from broad multi-cell coverage to focused single-cell or limited-cell targeting based on predicted UE location. By dynamically adjusting the paging area parameters based on ML predictions of UE trajectory and behavior patterns, the system achieves reliable delivery with reduced time loss
2Reliability
If repeated paging attempts are made across multiple cells, then the paging message can reach the idle UE device, but it increases radio channel interference and energy consumption
Solution Approach 1:
The system performs preliminary location prediction using machine learning models to identify the most probable cell where the idle UE device will be located. This allows the RAN device to concentrate paging attempts in predicted cells only, avoiding repeated transmissions across multiple cells, thereby reducing energy consumption while maintaining reliable delivery
Solution Approach 2:
The invention dynamically changes the paging transmission parameters by limiting the paging scope to predicted cell locations rather than broadcasting across all possible cells. This parameter optimization reduces the number of paging transmissions required, conserving device energy while ensuring reliable message delivery
3Reliability
If traditional paging procedures are used across multiple cells, then the paging message can reach the idle UE device, but it causes increased radio channel interference
Solution Approach 1:
The system performs preliminary prediction of UE location using machine learning before initiating paging. By predicting which cells the idle UE will be in and limiting paging transmissions to those specific cells, the invention reduces the number of paging messages broadcast across the network, thereby minimizing radio channel interference while maintaining reliable delivery
Solution Approach 2:
The invention changes the paging scope parameter from broad multi-cell coverage to focused targeted cells based on predicted UE location. This optimization reduces the number of paging transmissions across the radio channel, minimizing interference with other communications while ensuring the paging message reaches its destination reliably
Data Source
AI summary
Systems and methods described herein provide paging optimization using User Equipment (UE) trajectory prediction. A network device in a Radio Access Network (RAN) receives a paging request for an idle UE device. The network device generates a trajectory prediction for the idle UE device based on an inference model. The inference model predicts trajectories of UE devices, and the trajectory prediction includes a list of cells in the RAN where the idle UE device may be located. The network device maps the list of cells to a set of distributed units (DUs) for the RAN and initiates paging of the idle UE device using the set of DUs.