Power Grid Fault Level Estimation Using Virtual Measurements

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing electric power grid monitoring systems face challenges in accurately estimating fault levels across different locations, especially where measurement data is unavailable or outdated, leading to limited visibility and real-time monitoring capabilities.

Innovation Solution

A method and system that utilize machine learning to correlate measurement data from one location to another, enabling the estimation of fault levels by generating physical stimuli and using these correlations to map electric parameters across the grid, even where data is not currently available, and predicting future behavior.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If measurement devices are deployed at all locations to obtain accurate fault level data, then measurement precision is improved, but device complexity and cost increase significantly

Engineering Contradiction:

Improvefault level measurement accuracyVSAvoidmeasurement device deployment complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates a virtual copy of the measurement capability by training a machine learning model on measurement data from one location, then using this trained model to estimate fault levels at other locations without physical measurement devices. This allows accurate fault level estimation at multiple locations while deploying measurement devices at only one location, resolving the contradiction between measurement precision and device complexity

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent introduces a machine learning model as an intermediary between the physical measurement device and the fault level estimation process. The model learns the relationship between measurements and fault levels, then uses this learned relationship to estimate fault levels at locations without direct measurements, enabling accurate estimation without direct measurement devices at each location

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If measurement data is collected continuously at all locations, then real-time monitoring capability is improved, but loss of energy and data processing requirements increase

Engineering Contradiction:

Improvereal-time monitoring capabilityVSAvoidenergy consumption for data collection and processing

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The patent creates a virtual measurement system by training a machine learning model on measurement data, then using this trained model to generate real-time fault level estimates at multiple locations without continuous physical measurements. This allows real-time monitoring capability across the grid while significantly reducing energy consumption compared to continuous measurements at all locations

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent performs preliminary action by training the machine learning model offline using historical measurement data. Once trained, the model can rapidly estimate fault levels in real-time without requiring continuous data collection and processing, reducing energy consumption while maintaining real-time monitoring capability

Inventive Principle:

Principle #10Preliminary action

3Loss of information

If measurement devices are installed at every location, then visibility of grid parameters is improved, but device complexity and infrastructure requirements increase

Engineering Contradiction:

Improvegrid parameter visibilityVSAvoidmeasurement infrastructure complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The patent creates virtual measurement capabilities by training a machine learning model on measurement data from one location, then using this model to estimate fault levels at other locations. This provides comprehensive grid parameter visibility across multiple locations without requiring physical measurement devices at each location, significantly reducing infrastructure complexity

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent makes a single measurement device universal by using its data to train a machine learning model that can estimate fault levels at multiple locations. This one measurement device performs the function of multiple devices, providing comprehensive grid visibility while minimizing infrastructure requirements

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11215979B2System for determining electric parameters of an electric power grid

Publication Date: 2022.01.04 REACTIVE TECH

AI summary

This document discloses a solution for a method of monitoring an electric power grid. According to an aspect, a method comprises: detecting one or more physical stimuli in the electric power grid; obtaining, while the one or more physical stimuli is effective, a first set of measurement data associated with a first location of the electric power grid; computing operational information such as a fault level of the first location of the electric power grid on the basis of the first set of measurement data; mapping the operational information to corresponding operational information of a second location of the electric power grid on the basis of the first set of measurement data and correlation between electrical characteristics of the first location and the second location.