GIS Network Model Validation via Smart Meter Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current outage management systems for electric utilities face challenges in accurately mapping smart meters to transformers and substations due to inaccurate connectivity models, leading to inefficiencies and reduced value from digital investments, as there is no automated process for ensuring high certainty in these mappings.
Innovation Solution
A system and method that uses existing smart grid sensor data to validate and correct utility GIS network models by correlating meter data, analyzing geospatial proximity, and performing statistical tests to propose refined hypotheses for correct relationships between meters, transformers, and phases, without requiring specialized data sources or field instrumentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual field verification methods are used to validate connectivity models, then mapping accuracy between meters and transformers can be improved, but labor costs and time requirements increase significantly making the process economically unfeasible
Solution Approach 1:
The patent replaces manual field verification (mechanical/systematic physical inspection) with automated data analysis using statistical methods and machine learning algorithms. The system processes existing smart meter and SCADA data through analytical models to validate connectivity relationships, eliminating the need for physical field verification while maintaining or improving accuracy.
Solution Approach 2:
The system enables the data infrastructure to self-validate by using existing operational data from smart meters and SCADA systems to automatically verify connectivity models. The analytical component uses statistical tests and pattern recognition on readily available data to identify errors and assert correct topology without external manual intervention.
2Productivity
If existing connectivity models are used without validation, then system operation continues without interruption, but mapping errors accumulate leading to garbage-in-garbage-out situations that reduce the value of digital investments
Solution Approach 1:
The patent implements a feedback mechanism where the analytical component continuously evaluates existing connectivity models against operational data from smart meters and SCADA systems. When mapping errors are detected through statistical analysis, the system generates corrective actions that feed back into the engineering model, creating a continuous improvement loop that maintains both operational continuity and data accuracy.
Solution Approach 2:
The system performs preliminary validation of connectivity models using existing operational data before errors significantly impact system performance. By proactively identifying and correcting mapping inaccuracies through automated analysis, the system prevents the accumulation of errors that would otherwise lead to garbage-in-garbage-out situations, maintaining reliability without interrupting operations.
3Measurement precision
If automated data analysis methods are implemented to validate connectivity models, then mapping accuracy and reliability can be improved, but system complexity and computational requirements increase
Solution Approach 1:
The patent leverages existing multi-functional data infrastructure components that serve multiple purposes. The same smart meter and SCADA systems used for operational control also provide the data foundation for connectivity validation. The analytical component uses general-purpose statistical and machine learning techniques that can validate various types of relationships (meter-to-transformer, transformer-to-substation, phase assignments) through a unified approach, reducing the need for specialized validation systems.
Data Source
AI summary
A system and method for learning and asserting what portions of a utility GIS network model are incorrect or flawed as they relate to real world conditions, and what the correct real world relationships are in the field is described. The system and method leverage available smart grid data to assess the quality of a primary (GIS) source data set; quality data renders derived analyzes across the utility valid, sound, and action worthy. The system and method utilize existing partially correct electrical network distribution model data and various non-specialized source data including smart meter, spatial, and customer information data collected from the network to test, validate and suggest corrections to the connectivity model. By forming putative ground truth assignments between utility components, the system tests the assumptions by examining the geospatial proximity and correlating voltage and event data over time to form refined hypothesis. These hypotheses are compared to the existing model and statistical tests are performed at a variety of confidence levels to propose a corrected network model to the user.