AI-Assisted Beam Selection Across Frequency Bands
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in efficiently selecting beams while maintaining accurate signal transmission and reducing power consumption in user equipment devices, which can strain battery life.
Innovation Solution
Implementing machine learning-assisted beam selection techniques that utilize channel information from one frequency range to optimize beam selection in another range, reducing the need for direct downlink beam measurements and associated high-power reference signal transmissions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If direct downlink beam measurement is used for beam selection, then beam selection accuracy is improved, but power consumption increases due to higher powered reference signal transmission and measurement requirements
Solution Approach 1:
The patent introduces an artificial intelligence model as an intermediary that maps channel impulse response information from a first frequency range to beam selection decisions in a second frequency range. This mediator enables indirect beam selection without requiring direct downlink beam measurements, thereby reducing reference signal transmission power and measurement requirements while maintaining selection accuracy through the learned mapping relationship.
Solution Approach 2:
The system performs preliminary channel impulse response measurement in a first frequency range where measurements are less demanding, then uses the pre-trained artificial intelligence model to infer beam selection for a second frequency range. This preliminary action in a more favorable frequency range avoids the need for high-power direct measurements in the target frequency range, reducing overall power consumption while maintaining accuracy.
2Use of energy by moving object
If channel information from one frequency range is used to perform beam selection in another frequency range, then power consumption is reduced, but beam selection accuracy may be compromised
Solution Approach 1:
The artificial intelligence model serves as a learned intermediary that captures the complex mapping relationship between channel characteristics in different frequency ranges. By training the model on paired data from both frequency ranges, it learns to accurately translate channel impulse response information from the first frequency range into accurate beam selection decisions for the second frequency range, preserving accuracy despite the indirect approach.
Solution Approach 2:
The system changes the operational parameters by performing measurements in a first frequency range with more favorable characteristics (lower power requirements) and then transforms this information through the artificial intelligence model to achieve beam selection in a second frequency range. This parameter transformation approach allows operating in a more energy-efficient regime while achieving the desired outcome in the target frequency range.
Data Source
AI summary
This disclosure relates to techniques for performing beam selection using machine learning assistance in a wireless communication system. A wireless device and a cellular base station may establish a wireless link. An artificial intelligence model to use for beam selection may be determined. Channel impulse response information for a cell in a first frequency range may be determined. A downlink beam for a cell in a second frequency range may be selected based at least in part on the artificial intelligence model and the channel impulse response information for the cell in the first frequency range.