Generative Model Radio Coverage Map Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for generating radio coverage maps are either costly and time-consuming due to direct measurement or less accurate due to reliance on radio propagation models, which struggle to account for complex environmental factors like buildings and terrain changes.
Innovation Solution
A method using generative models, specifically deep-learning neural networks like generative adversarial networks (GANs), to translate image data of geographical areas with transmission points into radio coverage maps, trained on pairs of input and output data from conventional methods, allowing for accurate and efficient generation of radio coverage maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If direct measurement methods are used to generate radio coverage maps, then measurement precision is improved, but loss of time and productivity deteriorate
Solution Approach 1:
The system performs preliminary actions by collecting and storing environmental data (building locations, terrain features, objects) in advance through image data and maps. This pre-collected data is then used by the generative model to quickly generate radio coverage maps without requiring time-consuming field measurements, thus resolving the contradiction between measurement precision and time loss.
Solution Approach 2:
The system creates a virtual copy of the geographical environment using image data and map information. This digital replica includes representations of buildings, terrain, and other environmental features. The generative model then operates on this copied environment to produce radio coverage predictions, eliminating the need for physical measurement while maintaining accuracy.
2Productivity
If radio propagation models are used to generate radio coverage maps, then productivity is improved, but measurement precision deteriorates
Solution Approach 1:
The system uses image data to create visual representations and maps of the geographical environment, copying real-world features into digital format. This copied environmental data is then fed to the generative model, which learns from actual measurement data to produce accurate radio coverage predictions, combining the speed of modeling with the precision of measurement-based approaches.
Solution Approach 2:
The system transforms environmental parameters from image data (visual features, spatial relationships, object characteristics) into formats suitable for radio propagation analysis. The generative model learns the complex relationships between these parameters and radio coverage patterns, enabling accurate predictions without traditional modeling limitations.
3Measurement precision
If image data and generative models are used to generate radio coverage maps, then both measurement precision and productivity are improved
Solution Approach 1:
The system introduces an intermediary layer consisting of image processing and map generation components that bridge the gap between raw environmental data and radio propagation analysis. This intermediary transforms complex real-world environments into structured digital representations that the generative model can efficiently process, managing system complexity while maintaining high precision and productivity.
Data Source
AI summary
Embodiments of the disclosure provide methods, apparatus and computer programs for generating a radio coverage map. A method comprises: obtaining image data of a geographical area, the image data comprising: a representation of the environment in the geographical area; and an indication of one or more transmission point locations corresponding to the locations of one or more transmission points in a wireless communications network; and applying a generative model to the image data, to generate a radio coverage map of the geographical area.