Electric Grid Graph Error Correction for Accurate Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electric power grid models often contain errors in data representing electrical properties of components and connections, leading to inaccurate simulations and fault predictions.
Innovation Solution
A system and method are introduced to train an error-correcting model, such as a graph neural network, to correct errors in electric grid model graphs by generating modified graphs with noise, processing them to produce accurate outputs, and verifying corrections using an electric grid simulator.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional electric grid modeling methods are used, then the modeling process is simple, but the accuracy of grid model data contains errors
Solution Approach 1:
An error-correcting model is introduced as an intermediary component between the traditional grid modeling process and the final grid model output. This intermediary model processes the grid model data to identify and correct errors, thereby improving data accuracy while maintaining a relatively simple implementation approach through machine learning techniques.
Solution Approach 2:
The patent replaces traditional manual or rule-based error detection and correction methods with an automated machine learning-based error-correcting model. This substitution enables the system to automatically identify and correct errors in grid model data without requiring complex manual intervention or intricate error detection algorithms.
2Measurement precision
If error-correcting model is implemented, then the accuracy of grid model data improves, but the computational resources required increase
Solution Approach 1:
The error-correcting model is trained in advance on a dataset of grid model data with known errors and their corrections. This preliminary training phase enables the model to learn error patterns and correction strategies beforehand, so that during actual operation, the model can quickly correct errors in new grid model data without requiring extensive computational resources for real-time analysis.
3Productivity
If manual error detection is used, then the model complexity is low, but the time required to correct errors increases
Solution Approach 1:
The error-correcting model is designed to autonomously identify and correct errors in grid model data without requiring manual intervention. The model automatically processes the input data, detects errors based on learned patterns, and generates corrected output, thereby significantly reducing the time required for error correction while maintaining manageable system complexity through automated decision-making algorithms.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a storage device, for electric grid model error reduction are enclosed. A method includes obtaining graph data defining a graph including nodes and edges. Each node represents a component of an electric grid and is associated with respective node data representing electrical properties of the component of the electric grid, each edge represents a connection between components of the electric grid and is associated with respective edge data representing electrical properties of the connection, and the graph data includes one or more errors, each error including erroneous node data or erroneous edge data. The method includes processing the graph data using an error-correcting model trained to correct errors in the graph data; obtaining, as output from the error-correcting model, output graph data; and verifying accuracy of the output graph data by processing the output graph data using an electric grid simulator.