Neural Transmission Feedback for Adaptive Cellular Retransmission
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional transmission feedback schemes in wireless communication networks, such as HARQ with soft combining, are complex and inflexible, requiring extensive design, testing, and implementation efforts, and are resistant to updates, leading to compatibility issues and obsolescence.
Innovation Solution
Implementing neural networks at both the transmitting and receiving devices to dynamically adapt transmission feedback, allowing for soft feedback signals and retransmission control based on neural network processing, enabling flexible and efficient data retransmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional HARQ with soft combining is implemented, then data transmission reliability is improved, but device complexity and implementation difficulty increase
Solution Approach 1:
The patent replaces the conventional mechanical/hard-coded HARQ feedback mechanism with a neural network-based system. The neural network processes channel conditions and transmission outcomes to dynamically generate feedback signals, substituting the rigid rule-based HARQ protocol with an adaptive learning-based approach that reduces implementation complexity while maintaining reliability
Solution Approach 2:
The invention changes the feedback parameter from binary ACK/NACK to continuous soft feedback values generated by the neural network. This parameter transformation allows for more granular transmission adjustments and enables the system to convey richer information about channel quality and reception confidence, thereby improving reliability without requiring complex hard-coded logic
2Stability of the object's composition
If hard-coded transmission feedback schemes are used, then implementation is standardized, but adaptability to changing conditions deteriorates
Solution Approach 1:
The patent introduces dynamics into the feedback system by using a neural network that continuously learns from and adapts to changing channel conditions. The feedback mechanism transitions from static hard-coded rules to a dynamic system that adjusts its behavior based on real-time observations, enabling adaptability while maintaining implementation stability through the standardized neural network architecture
Solution Approach 2:
The neural network performs self-learning and self-adjustment by processing transmission outcomes and channel feedback automatically. This self-service capability allows the system to adapt to changing conditions without requiring external reconfiguration or updates to the underlying protocol, maintaining implementation stability while achieving environmental adaptability
3Reliability
If retransmission of corrupted data blocks is performed, then data transmission reliability is maintained, but spectral efficiency decreases
Solution Approach 1:
Instead of always retransmitting entire corrupted data blocks, the neural network enables partial retransmission by generating feedback that identifies specific erroneous portions. This partial action approach transmits only the necessary correction data rather than redundant full-block retransmissions, improving spectral efficiency while maintaining reliability through targeted error correction
Solution Approach 2:
The invention enhances the feedback mechanism to provide detailed information about transmission quality and error locations. This enriched feedback enables the transmitting device to make informed decisions about whether retransmission is necessary and what specific data should be retransmitted, optimizing the balance between reliability and spectral efficiency by avoiding unnecessary retransmissions
Data Source
AI summary
Two devices in wireless communication implement a soft transmission feedback scheme. A data-sending device wirelessly communicates a first transmission representing a data block and generated using one or more neural networks to a data-receiving device, which processes the first transmission using one or more neural networks to attempt to recover the data block, as well as to generate transmission feedback indicating a status of the recovery attempt. The feedback is used by one or more neural networks to generate a second transmission that is wirelessly communicated to the data-sending device. One or more neural networks process the second transmission to generate a retransmit control signal. One or more neural networks selectively include at least a portion of the data block for retransmission in a third transmission to the data-receiving device based on the retransmit control signal.