NWDAF E2E UE Trajectory Prediction Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional network automation systems lack the ability to predict End-to-End (E2E) User Equipment (UE) mobility trajectories with confidence, as they rely solely on historical data and do not have access to future UE locations, limiting their capacity to proactively manage network resources and avoid overload situations.
Innovation Solution
Enhancing the Network Data Analytics Function (NWDAF) to receive and process future UE location information from Third Party Providers, using Machine Learning algorithms to predict E2E mobility trajectories, allowing for proactive network configuration and optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional NWDAF relies solely on historical data for UE location prediction, then system complexity remains low, but prediction accuracy and reliability deteriorate
Solution Approach 1:
The patent applies preliminary action by obtaining future UE location information in advance from third-party providers before the UE actually reaches those locations. This allows the network to proactively prepare resources and configure parameters ahead of time, improving prediction accuracy without waiting for historical patterns to emerge. The future location data serves as advance information that enhances trajectory prediction beyond what historical data alone can provide.
Solution Approach 2:
The patent introduces third-party providers as intermediaries that supply future UE location information to the network automation system. These intermediaries act as mediators between the UE and the network, providing location data that the conventional NWDAF cannot obtain on its own. This intermediary layer enables more accurate prediction while keeping the core network architecture relatively simple.
2Reliability
If the network proactively configures resources based on predicted UE trajectories, then QoS and user experience improve, but the risk of incorrect configuration and resource waste increases
Solution Approach 1:
The patent applies dynamics by making network configuration adaptive and flexible rather than static. The system continuously monitors actual UE trajectory against predicted trajectory and dynamically adjusts resource allocation accordingly. Configuration parameters are updated in real-time based on whether the UE follows the predicted path, allowing the network to scale resources up or down as needed, thus improving QoS reliability while avoiding permanent resource waste.
Solution Approach 2:
The patent implements feedback mechanisms where the actual UE location and trajectory are continuously monitored and compared against predicted values. This feedback loop allows the system to verify whether proactive configuration was appropriate and to adjust future predictions and resource allocations accordingly. The feedback ensures that resource allocation decisions are validated against actual UE behavior, reducing the risk of incorrect configuration and energy waste.
3Adaptability or versatility
If the network obtains future UE location information from third-party providers, then trajectory prediction capability improves, but signaling load and integration complexity increase
Solution Approach 1:
The patent applies universality by designing the network automation function to handle multiple data sources and types uniformly. The system can process both historical location data and future location information from third-party providers through a unified interface and processing mechanism. This multi-functional approach allows the system to adapt to different data sources without requiring separate integration pathways, thereby improving trajectory prediction capability while managing integration complexity through standardized handling.
4Reliability
If conventional systems react to UE location after it occurs, then system simplicity is maintained, but network overload situations cannot be avoided
Solution Approach 1:
The patent applies preliminary action by obtaining future UE location information in advance from third-party providers before the UE actually reaches those locations. This allows the network to proactively prepare resources and configure parameters ahead of time, improving prediction accuracy without waiting for historical patterns to emerge. The future location data serves as advance information that enhances trajectory prediction beyond what historical data alone can provide.
Data Source
AI summary
Methods and systems for End-to-End (E2E) User Equipment (UE) trajectory network automation are herein provided. According to one aspect, a network node for E2E UE trajectory network automation, such as a Network Data Analytics Function (NWDAF), receives, from a requesting entity, information identifying a future E2E UE trajectory, the E2E UE trajectory comprising a start location, an end location, and zero or more intermediate locations between the start location and the end location; calculates a E2E mobility trajectory prediction for the identified future E2E UE trajectory; and sends, to the requesting entity, the calculated E2E mobility trajectory prediction. The requesting entity may be a trusted entity or an untrusted entity, such as a Third Party Provider (3PP) outside of the trusted domain of the network. If the requesting entity selects a mobility trajectory, the network node sends mobility management and optimization information to a Radio Access Network node.