AI-Enabled HARQ Retransmissions for Low-Latency PDU Buffering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wireless communication systems face challenges with high latency and increased resource usage due to asynchronous HARQ retransmissions, leading to strained memory and power consumption.
Innovation Solution
Implementing an AI/ML model to manage buffer and enable AI-enabled retransmissions or discards of protocol data units (PDUs) based on hybrid automatic repeat request (HARQ) feedback, allowing for early retransmission or discard of PDUs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If asynchronous HARQ retransmissions are implemented to improve reliability, then data transmission reliability is improved, but processing latency and power consumption increase
Solution Approach 1:
The AI/ML model predicts future HARQ feedback outcomes before actual retransmissions occur, enabling the system to prepare for potential retransmissions in advance. This preliminary prediction allows the buffer to be managed proactively, reducing the latency impact when retransmissions are needed while maintaining reliability improvements.
Solution Approach 2:
The system continuously monitors HARQ feedback and uses this information to train and refine the AI/ML prediction model. This feedback loop enables the model to improve its accuracy over time in predicting which PDUs will require retransmission, thereby optimizing the balance between reliability and latency more effectively.
2Reliability
If asynchronous HARQ retransmissions are implemented to improve reliability, then data transmission reliability is improved, but power consumption increases
Solution Approach 1:
By predicting future HARQ feedback outcomes in advance, the system can proactively manage buffer resources and prepare for retransmissions, avoiding unnecessary power consumption associated with waiting and reactive processing. This preliminary action enables more efficient power management while maintaining reliability.
Solution Approach 2:
The AI/ML model autonomously analyzes historical HARQ feedback data and makes independent predictions about future retransmission needs, reducing the need for continuous manual intervention and optimization. This self-service capability enables the system to automatically balance reliability improvements with power consumption efficiency.
3Reliability
If buffer size is increased to accommodate more PDUs for retransmission, then retransmission capability is improved, but memory resources are strained
Solution Approach 1:
The AI/ML model predicts which PDUs are most likely to require retransmission in advance, allowing the system to prioritize buffer allocation to only those critical PDUs rather than accommodating all possible PDUs. This preliminary prediction enables more efficient memory utilization while maintaining adequate retransmission capability.
Solution Approach 2:
The system dynamically adjusts buffer management parameters based on AI/ML predictions about PDU retransmission probabilities. By changing buffer allocation parameters according to predicted needs rather than using a fixed large buffer, the system optimizes the balance between retransmission capability and memory resource consumption.
Data Source
AI summary
Methods, systems, and devices for wireless communication are described. A device may receive control signaling that indicates a configuration that includes a first set of one or more parameters for hybrid automatic repeat request (HARQ) associated with a radio link control (RLC) entity of the device. The device may receive at least one HARQ feedback for at least one protocol data unit (PDU) of a set of one or more PDUs associated with the RLC entity of the device. The device may perform one or more operations based on the at least one HARQ feedback and in accordance with the first set of one or more parameters for HARQ, wherein the one or more operations include a discard of the at least one PDU or a retransmission of the at least one PDU.