RF Propagation Model Determination via Morphology Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The expansion of 5G/NR networks faces challenges in efficiently adjusting radio frequency propagation models due to the increased number of smaller cells and narrower beam-formed directional transmissions, which requires more frequent and costly manual adjustments by experienced RF domain experts.
Innovation Solution
A method using machine learning to determine RF propagation models from image views of coverage areas, recognizing morphology types such as buildings, trees, and foliage, and selecting appropriate RF models to automate the optimization process, reducing human error and costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual adjustment by RF domain experts is used to determine RF propagation models, then accuracy of morphology recognition is improved, but cost and time consumption increase significantly
Solution Approach 1:
The patent uses aerial images as copies of the physical terrain to create virtual morphology representations. These image copies are processed by machine learning models to identify morphology types, replacing the need for physical site visits while maintaining recognition accuracy through automated image analysis algorithms
Solution Approach 2:
The patent replaces the mechanical process of manual site inspection and physical measurement with an automated computer vision system. Machine learning models process aerial images to automatically determine morphology types and select propagation models, substituting human experts' mechanical work with algorithmic processing
2Area of stationary object
If the number of cells and sectors is increased to expand 5G network coverage, then network coverage area is improved, but the number of required RF propagation adjustments increases
Solution Approach 1:
The patent implements self-service by enabling the system to automatically determine propagation models for each cell and sector without requiring external expert intervention. The machine learning model processes aerial images and autonomously selects appropriate propagation models, allowing the network to self-configure as it expands
Solution Approach 2:
The patent creates a universal automated system that can handle all morphology recognition and propagation model selection tasks across the entire 5G network. The machine learning model serves multiple cells and sectors simultaneously, providing a multi-functional solution that scales with network expansion without increasing operational complexity
3Productivity
If automated machine learning methods are used to determine RF propagation models, then cost and time are reduced, but complexity of the system increases
Solution Approach 1:
The patent introduces aerial images as an intermediary between the physical terrain and the propagation model selection process. These images serve as a mediator that captures terrain morphology and translates it into data that machine learning models can process, simplifying the overall system architecture by creating a clear input-output relationship
Data Source
AI summary
A method and network node for determining a Radio Frequency (RF) propagation model for a coverage area from an image view of the coverage area. The method selects a coverage area for a transmission point of a transmitter and obtains an image view of the selected coverage area. The method further recognizes, from a plurality of morphology types, a morphology type for the selected coverage area from the obtained image view using a machine learning model; and determines a RF propagation model for the selected coverage area based on the recognized morphology type.