Electric Grid Connection Mapping Using Geospatial Imagery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current electrical power grid modeling techniques fail to accurately predict the locations of important electric grid assets, particularly underground connections between transformers and electrical loads, leading to inaccurate simulations and fault predictions.
Innovation Solution
A system and method that uses a connection model trained with geospatial data and machine learning algorithms to map both visible and hidden connections between electric grid assets, including underground cables, by integrating overhead and street-level imagery with auxiliary data such as smart meter and historical outage data to generate accurate connection paths.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional electrical power grid modeling techniques are used, then the modeling process is simple, but the accuracy of predicting connection locations is poor
Solution Approach 1:
The patent introduces an intermediary connection model that acts as a mediator between geospatial data and grid connection predictions. This model processes satellite imagery, street-level imagery, and auxiliary data to infer hidden underground connections, thereby improving prediction accuracy without requiring direct observation of all connections.
Solution Approach 2:
The patent replaces traditional mechanical surveying and physical inspection methods with machine learning-based image processing. By substituting physical measurement systems with computational models that analyze satellite and street-level imagery, the system achieves higher accuracy while reducing the complexity of field operations.
2Measurement precision
If comprehensive geospatial data and machine learning models are integrated, then the accuracy of mapping hidden connections is improved, but the system complexity increases
Solution Approach 1:
The patent segments the complex data integration task into distinct modules: satellite image processing, street-level image processing, auxiliary data integration, and connection model inference. Each module handles specific data types and processing steps independently, improving accuracy while managing system complexity through modular architecture.
Solution Approach 2:
The connection model serves multiple functions: it processes diverse data types (satellite imagery, street-level imagery, auxiliary data), predicts both visible and hidden connections, and generates comprehensive grid models. This multi-functionality improves mapping accuracy without proportionally increasing system complexity.
3Loss of information
If traditional methods are used for identifying grid connections, then the process is straightforward, but hidden underground connections cannot be accurately detected
Solution Approach 1:
The patent creates visual copies of underground connections by analyzing surface-level satellite and street-level imagery. The connection model generates inferred representations of hidden cables and connections based on patterns visible in aerial and ground-level images, thereby recovering information about underground infrastructure without direct physical access.
Solution Approach 2:
The patent transitions from two-dimensional surface observations to three-dimensional spatial understanding of underground connections. By integrating satellite imagery (top-down view) with street-level imagery (ground-level view) and auxiliary data, the system infers the three-dimensional paths of hidden connections, reducing information loss about subsurface infrastructure.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a storage device, for predicting connections in electric grid models are disclosed. A method includes obtaining geospatial data representing a geographic area that includes an electrical distribution system; and generating, from the geospatial data, asset data that represents characteristics of electrical distribution system assets. The asset data includes: load data representing electrical loads of the electrical distribution system; and node data representing nodes of the electrical distribution system. The method includes processing the asset data using a connection model that is configured to predict electrical connections between assets of the electrical distribution system; and obtaining, from the connection model; output data indicating predicted electrical connections between assets of the electrical distribution system. The geospatial data includes at least one of overhead imagery or street level imagery of the geographic area.