ML Wireless Network Design Using 3D Point Cloud Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional wireless network design relies on manual or semi-manual processes, which are inefficient and predominantly two-dimensional, failing to optimize network design for complex environments with growing data usage demands and IoT devices across various dimensions.
Innovation Solution
An intelligent machine learning (ML)-based automated system that uses aerial surveillance data from UAS and 3-D mapping data to generate predictive models for optimal wireless network design, considering signal quality and network configuration parameters, and selecting optimal tower locations and backhaul types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual or semi-manual network design processes are used, then engineers can apply intuition and experience, but the process is inefficient and difficult to scale
Solution Approach 1:
The patent replaces manual mechanical design processes with an automated machine learning system that uses aerial surveillance data and 3-D mapping to generate predictive models for network design, eliminating the need for manual RF engineering calculations and tower site selection
Solution Approach 2:
The system enables automated self-service network design by using AI algorithms to independently analyze surveillance data, generate predictive models, and optimize network configurations without requiring human engineer intervention for routine design tasks
2Adaptability or versatility
If traditional two-dimensional network design approaches are used, then the design process is simpler, but it fails to optimize for complex environments with IoT devices across various dimensions
Solution Approach 1:
The patent transitions from two-dimensional network design maps to three-dimensional predictive models by incorporating aerial surveillance data and 3-D mapping, enabling the system to account for vertical dimensions, building heights, and spatial relationships in complex environments
Solution Approach 2:
The system integrates multiple data types (aerial surveillance imagery, 3-D mapping data, network configuration parameters) into a composite predictive model that captures the complexity of modern wireless environments with diverse devices and structures
3Quantity of substance
If more tower locations are selected to meet growing data usage demands, then network capacity increases, but the complexity of site selection and construction optimization increases
Solution Approach 1:
The system performs preliminary automated analysis of potential tower locations by evaluating aerial surveillance data and 3-D mapping information before site selection, pre-identifying optimal locations that meet capacity requirements while simplifying subsequent construction processes
4Extent of automation
If automated ML-based design is implemented, then design efficiency and optimization improve, but the system complexity and data processing requirements increase
Solution Approach 1:
The patent creates a universal automated design system that handles multiple network design tasks (site selection, capacity planning, configuration optimization) through a single machine learning platform, reducing overall system complexity by consolidating functions
Data Source
AI summary
A system for automated ML-based design of a wireless network. The system includes a processor and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire aerial surveillance data of a target area, the aerial surveillance data comprising a point cloud dataset; initiate parsing of the point cloud dataset in intervals defined by a plurality of 3-D units of a predetermined volume; and replace the plurality of point cloud data points within the particular 3-D unit with a single data point indicative of a common surface classification type. The system can generate a discretized 3-D mapping of point cloud dataset.