Antenna Radiation Pattern Modeling for Fast Cellular Coverage Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Planning cellular networks is complex due to the need to optimize antenna placement for maximum coverage and minimal interference, which is computationally demanding, especially with newer generations like 5G, where obstacles significantly affect signal propagation, and current methods like ray tracing are time-consuming and inefficient.
Innovation Solution
Employing machine learning models, such as neural networks, to estimate antenna coverage and interference by transforming radiation patterns into signal strength arrays, incorporating both antenna parameters and environmental features, reducing computation time from seconds to milliseconds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ray tracing methods are used to compute antenna coverage, then coverage computation accuracy is improved, but computation time increases significantly
Solution Approach 1:
The patent creates a simplified representation (copy) of the complex ray tracing computation by transforming radiation patterns into signal strength arrays that can be processed by machine learning models. This copy captures the essential coverage information without requiring full ray tracing complexity, enabling rapid evaluation while maintaining accuracy.
Solution Approach 2:
The patent changes the computational parameters by transforming the problem from physical ray tracing computations to machine learning inference. The radiation patterns are converted into signal strength arrays with augmented parameters (antenna parameters and environmental values), which are then processed by trained ML models to produce coverage estimates in milliseconds instead of seconds.
2Measurement precision
If comprehensive antenna parameters and environmental features are included in coverage computation, then coverage estimation accuracy is improved, but device complexity increases
Solution Approach 1:
The patent performs preliminary action by pre-processing and transforming radiation patterns into signal strength arrays before the actual coverage computation. The machine learning model is trained in advance with augmented data that includes all necessary antenna parameters and environmental features, so that during deployment, the model simply needs to infer coverage from the transformed arrays without requiring complex real-time processing.
3Measurement precision
If traditional coverage computation methods are used, then computational accuracy is maintained, but planning efficiency decreases
Solution Approach 1:
The patent replaces the mechanical/computational system of ray tracing with an information-processing system using machine learning. Instead of performing complex geometric ray tracing computations, the system transforms radiation patterns into signal strength arrays and uses trained neural networks to infer coverage, substituting computational geometry with data-driven inference that is both accurate and efficient.
Data Source
AI summary
In one example, a method performed by a processing system including at least one processor includes creating a geospatial model of an environment in which a cellular network is to be deployed, transforming, for each cellular antenna of a proposed antenna layout of the cellular network, a radiation pattern of the each cellular antenna into a signal strength array, to create a plurality of signal strength arrays, augmenting, for each signal strength array of the plurality of signal strength arrays, the each signal strength array with at least one parameter of a corresponding cellular antenna of the proposed antenna layout and at least one value describing the environment in which the cellular network is to be deployed, and estimating a coverage of the proposed antenna layout based on the signal strength array, as augmented, using a machine learning model.