Power Distribution Grid Criticality Using Smart Meter ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional power-flow models for electrical power distribution grids are cumbersome to create and often inaccurate, lacking a reliable method to predict voltage changes and evaluate grid impact scores, especially with the integration of distributed energy resources, leading to incomplete assessment of grid criticality.
Innovation Solution
A machine learning model is used to determine the criticality of an electrical power distribution grid by analyzing smart meter data and voltage information from selected conducting equipment, allowing for the calculation of a grid impact score that represents the grid state based on power and voltage limit violations, without requiring a conventional power-flow model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a conventional power-flow model is used to evaluate grid criticality, then voltage and power calculations can be performed, but the model creation requires substantial manual engineering effort and high digitalization
Solution Approach 1:
The patent replaces the manual mechanical process of creating power-flow models with an automated machine learning approach. The system uses smart meter data and voltage measurements to train a model that automatically calculates voltage and power, eliminating the need for manual model creation while maintaining calculation accuracy.
Solution Approach 2:
The system enables the power distribution grid to evaluate its own criticality automatically. By using readily available smart meter data and voltage measurements, the grid infrastructure self-generates the necessary information for criticality assessment without requiring external manual intervention or specialized engineering expertise.
2Measurement precision
If a power-flow model is created with manual engineering efforts, then accurate grid state evaluation is possible, but the process is time-consuming and difficult to maintain
Solution Approach 1:
The system performs preliminary actions by continuously collecting and storing smart meter data and voltage measurements in advance. This pre-processed data is readily available when criticality evaluation is needed, eliminating the time-consuming process of creating and updating power-flow models while maintaining measurement precision.
Solution Approach 2:
The patent implements a dynamic evaluation system that automatically adapts to changing grid conditions. The machine learning model is trained on historical data and continuously updated with new measurements, allowing the system to maintain accurate grid state evaluation without manual reconfiguration or model updates.
3Loss of information
If GIS data is used for grid modeling, then location information of assets is available, but accurate electrical connectivity and phase information are lacking
Solution Approach 1:
The patent introduces smart meter data and voltage measurements as intermediary data sources that bridge the gap between GIS location information and accurate electrical connectivity data. These intermediaries provide the missing phase and connectivity information that GIS alone cannot supply, enabling reliable grid state evaluation while preserving the useful location information from GIS.
Data Source
AI summary
Various embodiments of the teachings herein include a method for determining a criticality of an electrical power distribution grid. An example method includes: providing a machine learning model of the power distribution grid fitted to smart meter data representing a power consumption of customers connected via a distribution transformer to conducting equipment of a substation of the power distribution grid and fitted to data representing voltages at selected conducting equipment of the power distribution grid and at the customers' service delivery points; using the provided machine learning model for calculating a grid impact score representing the grid state of the power distribution grid based on power limit violations and/or based on voltage limit violations; and evaluating the calculated grid impact score to determine the criticality of the electrical power distribution grid.