RL-Based DRX Cycle Configuration for XR Traffic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current DRX cycle configurations in cellular networks are inefficient for Extended Reality (XR) traffic, leading to energy wastage and potential data loss due to desynchronization between the DRX cycle and XR traffic periodicity.
Innovation Solution
A Reinforcement Learning (RL) process is employed to dynamically configure the Discontinuous Reception (DRX) cycle for User Equipment (UE), optimizing DRX cycle parameters such as active period duration, start offset, and cycle length based on real-time power consumption and Quality of Service (QoS) indications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If DRX cycle parameters are configured for power saving, then battery life is extended, but responsiveness to XR traffic deteriorates
Solution Approach 1:
The patent applies dynamics by enabling the DRX cycle parameters to be dynamically adjusted based on XR traffic conditions. The system transitions from static DRX configuration to dynamic adaptation where the network can modify active period duration, cycle length, and start offset in real-time according to traffic patterns, thereby optimizing both power efficiency and responsiveness for XR applications
Solution Approach 2:
The patent implements parameter changes by modifying key DRX configuration parameters including active period duration, DRX cycle length, and start offset. These parameter adjustments are made specifically for XR traffic to align the DRX wake-up periods with XR frame transmission timing, resolving the contradiction between power saving and responsiveness
2Reliability
If DRX cycle parameters are configured for responsiveness, then QoS for XR traffic is improved, but power consumption increases
Solution Approach 1:
The patent applies periodic action by synchronizing the DRX cycle wake-up periods with the periodic nature of XR traffic. The system configures the DRX active periods to coincide with XR frame transmission intervals, ensuring that the UE wakes up exactly when XR data is expected to arrive, thereby maintaining high QoS while minimizing unnecessary wake-ups and power consumption
3Device complexity
If fixed DRX cycle configuration is used, then device complexity is reduced, but adaptability to XR traffic patterns deteriorates
Solution Approach 1:
The patent implements self-service by enabling the network to automatically adapt DRX parameters based on observed XR traffic patterns. The system uses machine learning models to analyze traffic characteristics and autonomously configure optimal DRX parameters without requiring complex manual configuration or high device complexity, achieving both simplicity and adaptability
Data Source
AI summary
A RL agent performs a RL process to configure at least one Discontinuous Reception, DRX, cycle for a User Equipment, UE. An action is selected by the RL agent in an action space. Each action in the action space corresponds to a DRX cycle configuration. The RL agent sends to the UE indication to use the DRX cycle configuration corresponding to the selected action. The RL agent receives state information computed over at least one DRX cycle configured based on a DRX cycle configuration indicated by the RL agent. The RL agent computes a reward on the basis of the state information.