AI-Based DRX Wake-Up Control for User Equipment Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile communication systems face challenges in efficiently managing power consumption and latency due to inefficient data traffic prediction during Discontinuous Reception (DRX) cycles, particularly with the integration of AI/ML technologies.
Innovation Solution
Implementing an AI/ML model in user equipment and network nodes to infer data traffic occurrence or non-occurrence during DRX on-durations, allowing for dynamic wake-up or sleep decisions based on inference results, and coordinated dynamic DRX indications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If conventional DRX configuration is used, then power consumption is maintained at acceptable levels, but latency increases due to inability to wake up promptly for data traffic
Solution Approach 1:
The system performs preliminary action by inferring data traffic occurrence in advance for the next DRX on-duration before the actual wake-up decision is made. The network node or UE uses AI/ML models to predict whether data traffic will occur, and sends wake-up indications or makes decisions beforehand, allowing the system to wake up promptly when needed without continuously monitoring, thus reducing latency while maintaining power efficiency.
2Loss of time
If AI/ML model is implemented for traffic prediction, then latency is reduced through intelligent wake-up decisions, but device complexity increases
Solution Approach 1:
The system uses an AI/ML model as an intermediary between raw traffic patterns and wake-up decisions. The model processes historical data and traffic patterns to generate predictions about future data occurrence, which then inform the wake-up decisions. This intermediary layer enables intelligent latency reduction without requiring complex real-time processing in the UE, as the model can be trained offline and deployed as a relatively simple inference engine.
3Use of energy by moving object
If network node performs traffic inference and sends dynamic DRX indications, then power consumption is reduced through optimized wake-up timing, but loss of information increases due to reliance on predictive algorithms
Solution Approach 1:
The system implements feedback by having the UE verify the accuracy of traffic predictions made by the network node's AI/ML model. The UE can report back on whether predicted traffic actually occurred, allowing the network to refine and improve its prediction model over time. This feedback mechanism ensures that power consumption is optimized through accurate predictions while minimizing information loss by continuously validating and improving the predictive algorithm's accuracy.
Data Source
AI summary
The present disclosure relates to a communication control method in a mobile communication system. The communication control method includes inferring, by a user equipment, occurrence or non-occurrence of data traffic in a downlink in a next DRX on-duration by using an AI/ML model. The communication control method also includes performing, by the user equipment, one of wake-up in the next DRX on-duration or skipping of the wake-up in the next DRX on-duration, based on an inference result for occurrence or non-occurrence of the data traffic.