Composite Beam Generation Using Machine Learning for 5G mmWave
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The 5G mmWave base stations face challenges in designing efficient beam codebooks due to the need for numerous narrow beams to cover wide angular regions, which increases the number of synchronization signal block (SSB) beams, leading to higher overhead and deployment complexities.
Innovation Solution
The generation of composite beams using machine learning, where two narrow beams are transmitted simultaneously for a single SSB index, reducing the number of SSB beams and using a hierarchical tree structure to determine beamforming weights, allowing for efficient beamforming with a smaller form factor base station.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If numerous narrow beams are used to cover wide angular regions, then coverage is improved, but the number of SSB beams increases leading to higher overhead
Solution Approach 1:
The patent combines multiple narrow beams into a single composite beam that is transmitted simultaneously for a single SSB index. This merging approach allows the system to cover wide angular regions using fewer SSB beams, thereby reducing the overhead associated with beam signaling while maintaining comprehensive coverage.
2Area of stationary object
If numerous narrow beams are used to cover wide angular regions, then coverage is improved, but deployment complexity increases
Solution Approach 1:
By merging multiple narrow beams into composite beams that can be transmitted simultaneously for a single SSB index, the system reduces the total number of beams that need to be managed during deployment. This simplifies the deployment process and reduces operational complexity while maintaining wide angular coverage.
3Quantity of substance
If the number of SSB beams is reduced, then overhead is decreased, but beamforming precision may be compromised
Solution Approach 1:
The patent applies different beamforming weights to different antenna elements or sub-arrays within each composite beam to maintain precision in specific directions. This local quality approach allows the system to achieve accurate beamforming for each narrow beam component while transmitting them as a single composite beam, thus maintaining precision without increasing the number of SSB beams.
Solution Approach 2:
The system uses machine learning to determine optimal beamforming weights as parameters for composite beams. By adjusting these weights dynamically or pre-computing them based on training data, the system maintains beamforming precision even when reducing the number of SSB beams, as the weights are optimized to preserve the directional characteristics of individual narrow beams within the composite structure.
Data Source
AI summary
Methods, apparatuses, systems, and computer-readable media for a composite beam generation using machine learning. A method includes identifying a narrow beam for a transmission, identifying a composite beam including the narrow beam based on an association between one or more composite beams and one or more narrow beams, identifying one or more beamforming weights for transmitting the composite beam, and transmitting the composite beam using the one or more beamforming weights. The one or more beamforming weights are determined based on machine learning. In some embodiments, the method includes generating a composite beam codebook including information indicating sets of one or more beamforming weights corresponding to composite beam indexes, respectively. The sets of one or more beamforming weights are determined using respective parameters of a machine learning algorithm that are separately updated for coverage regions of composite beams corresponding to the composite beam indexes, respectively.