Beam Prediction Input Selection for Adaptive Wireless Communication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing beam management methods in wireless communication, such as those based on beam scanning, channel modeling, and deep learning, are inadequate for adapting to users with different movement speeds and channel environments, leading to reduced performance and sensitivity to noise.
Innovation Solution
An electronic apparatus dynamically or semi-statically determines the category of input information for a prediction model, using a deep learning model to improve beam prediction by integrating multiple sources of information, including user capability and channel environment, and provides beam prediction configuration information to user equipment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If beam scanning method is used to traverse all possible beam pairs, then complete beam coverage is achieved, but beam training overhead increases and noise sensitivity increases
Solution Approach 1:
The patent applies preliminary action by using a prediction model to predict future optimal beams based on historical beam information and user equipment movement patterns. This allows the system to prepare beam predictions in advance rather than performing exhaustive beam scanning when needed, significantly reducing beam training overhead while maintaining reliable beam selection.
Solution Approach 2:
The patent uses copying by creating a prediction model that learns from historical beam pairing information and replicates successful beam selection patterns. Instead of scanning all beams each time, the system copies effective beam patterns from historical data and adapts them to current conditions, reducing overhead while maintaining accuracy.
2Measurement precision
If deep learning based beam management is used, then feature extraction capability is improved, but adaptability to different users and channel environments is reduced
Solution Approach 1:
The patent applies dynamics by making the prediction model configurable and adaptable to different user equipment and channel conditions. The system dynamically adjusts the prediction model's input parameters, time windows, and configuration based on specific user scenarios and environmental conditions, enabling the same deep learning framework to adapt to diverse users and channels rather than being fixed.
Solution Approach 2:
The patent applies local quality by customizing the prediction model's parameters and configuration for different user equipment and channel environments. Each user or scenario can have locally optimized prediction model settings, allowing the system to maintain high feature extraction capability while adapting to specific local conditions of different users and environments.
3Ease of operation
If fixed channel model assumptions are used, then angle estimation is simplified, but scope of use is limited
Solution Approach 1:
The patent applies universality by creating a prediction model that can handle multiple channel conditions and user scenarios within a single unified framework. Rather than requiring different fixed channel models for different scenarios, the system uses one adaptable prediction model that can be configured to work across various channel environments and user types, expanding the scope of use while maintaining operational simplicity.
Data Source
Figure 1~2
Figure 3~4(b)
Figure 5~6
AI summary
An electronic device and a method for wireless communication, and a computer-readable storage medium. The electronic device for wireless communication comprises a processing circuit, wherein the processing circuit is configured to: dynamically or semi-statically determine the category of input information of a prediction model for a user equipment which is within a service range of the electronic device, wherein the prediction model is used for performing beam prediction on a beam to be used for communication between the electronic device and the user equipment; and provide the user equipment with beam prediction configuration information which comprises the determined category of the input information, so that the user equipment collects the input information according to the beam prediction configuration information. (Fig. 3)