ML Beamforming for Integrated Sensing and Side-Lobe Communication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cellular networks face inefficiencies in beamforming, leading to wasted energy in side lobes and limited frequency spectrum utilization, especially in integrated sensing and communication networks where both communication and sensing tasks are combined.
Innovation Solution
A method using a machine learning model to determine precoding and decoding information for configuring beamforming, selecting main lobes for sensing and side lobes for communication, and continuously re-training the model based on performance data to optimize energy efficiency and frequency spectrum use.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If beamforming is used to direct signals towards a specific target, then energy efficiency is improved, but side lobes still waste energy
Solution Approach 1:
The patent segments the beamforming lobes by assigning different functions to different lobes: main lobes are used for sensing tasks while side lobes are used for communication tasks. This segmentation allows the system to utilize all lobes effectively rather than letting side lobes waste energy, thereby improving overall energy efficiency while reducing energy loss in side lobes.
2Productivity
If frequency spectrum is limited for cellular networks, then regulatory compliance is maintained, but frequency resource utilization is insufficient
Solution Approach 1:
The patent implements multi-functionality by enabling the same beamforming structure to serve dual purposes: main lobes perform sensing functions while side lobes handle communication functions. This allows the limited frequency spectrum to be utilized more effectively by simultaneously supporting both sensing and communication tasks within the same frequency band, thereby improving frequency resource utilization without requiring additional spectrum.
3Adaptability or versatility
If integrated sensing and communication is implemented, then network functionality is enhanced, but beamforming optimization becomes more complex
Solution Approach 1:
The patent employs dynamic optimization using machine learning models that continuously adapt beamforming configurations based on real-time performance data. The system dynamically selects which lobes to use for sensing versus communication and adjusts precoding parameters to optimize both functions simultaneously. This dynamic approach enhances network functionality while managing complexity through automated, data-driven decision-making rather than static manual configuration.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The disclosure provides a method for configuring beamforming for an air interface of an integrated sensing and communications cellular network. The method comprises obtaining data indicative of the performance of the air interface, inputting the obtained data into a model comprising a machine learning model for determining precoding information, using the precoding information for configuring the beamforming of a beam comprising one or more main lobes and one or more side lobes, and selecting at least one of the main lobes for sensing and at least one of the side lobes for communication. The disclosure further provides a method for generating the model.