Neural-Network Uplink Control Transmission for Shared PUCCH Resources
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in efficiently utilizing resources and improving performance through the incorporation of AI, particularly in transmitting uplink control information.
Innovation Solution
The use of a neural network for transmitting uplink control information, enabling more efficient resource utilization and performance enhancement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple users are multiplexed on the same PUCCH resource, then resource utilization improves, but error probability increases
Solution Approach 1:
The patent segments the PUCCH transmission by introducing user-specific orthogonal cover codes (OCC) that divide the shared resource into orthogonal sub-channels for different users. This allows multiple users to simultaneously occupy the same time-frequency resources while maintaining distinguishable signal paths, thereby improving resource utilization without compromising error probability through the orthogonality property.
Solution Approach 2:
The patent extends the multiplexing capability by adding the orthogonal cover code dimension to the existing time-frequency resource allocation. By mapping users to different OCC sequences in addition to time-frequency resources, the system creates an additional orthogonal separation dimension that enables more users to share the same PUCCH resources while maintaining low error rates through proper orthogonal code design.
2Adaptability or versatility
If different types of uplink control information are transmitted, then communication versatility improves, but resource allocation complexity increases
Solution Approach 1:
The patent implements a universal PUCCH transmission framework where a single resource structure supports multiple types of uplink control information (HARQ-ACK, SR, CSI) through configurable parameters. The neural network-based transmitter and receiver are designed to handle different UCI types by adjusting input configurations rather than requiring separate dedicated resources for each type, thereby achieving versatility without proportional increases in resource allocation complexity.
Solution Approach 2:
The patent utilizes parameter-based differentiation to handle various UCI types. By changing parameters such as the orthogonal cover code sequence, resource block allocation, and neural network input formatting based on the UCI type being transmitted, the system achieves versatile support for multiple control information types while maintaining a unified resource allocation mechanism that does not scale linearly in complexity with the number of UCI types.
3Reliability
If neural network-based transmission is implemented, then error probability performance improves, but computational complexity increases
Solution Approach 1:
The patent replaces traditional mechanical signal processing operations (channel estimation, equalization, decoding) with a neural network-based computational system. The neural network is trained offline to learn optimal transmission and reception strategies, and during actual operation, it performs inference that achieves superior error probability performance compared to conventional methods. The computational complexity is managed by using efficient neural network architectures and performing heavy computation during training rather than during real-time transmission.
Data Source
AI summary
The present disclosure relates to a method and a device for transmitting uplink control information on the basis of a neural network, the method comprising: transmitting a random access preamble to a base station; receiving a random access response from the base station in response to the random access preamble; receiving configuration information from the base station; and transmitting UCI to the base station on the basis of a neural network transmitter, wherein the configuration information indicates a transmission resource allocated for the transmission of the UCI and the number of terminals using the transmission resource, a terminal determines a weight related to the transmission of the UCI on the basis of the number of the terminals, and a sequence for the UCI transmitted by the terminal is non-orthogonal to a sequence of UCI transmitted by each of the terminals remaining after excluding the terminal from the terminals.