Electricity Meter Phase Identification Using Voltage Correlation Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Inaccurate or outdated phase information in electricity meter records leads to poor phase balancing in electrical grids, causing operational inefficiencies, equipment failure, and delayed power outage management.
Innovation Solution
A clustering algorithm is employed to analyze voltage time series data from electricity meters to accurately identify phase connections by calculating correlation coefficients and hybrid indices, grouping meters into line-to-line and line-to-neutral phases, and correcting meter-phase connectivity records.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual phase identification methods are used, then implementation simplicity is maintained, but phase identification accuracy deteriorates leading to incorrect topology understanding
Solution Approach 1:
The patent replaces manual phase identification methods with an automated machine learning-based system. The system uses voltage time series data from smart meters, processes it through trained machine learning models (such as clustering algorithms or classification models), and automatically determines phase connections and grid topology. This substitution of manual mechanical processes with automated computational processes achieves high accuracy while maintaining operational simplicity for end users.
2Measurement precision
If automated machine learning methods are used, then phase identification accuracy is improved, but computational complexity and data processing requirements increase
Solution Approach 1:
The patent employs pre-trained machine learning models that have been trained offline on historical voltage data. During operational phase identification, the pre-trained models directly process new voltage time series data without requiring real-time training or complex computational resources. This preliminary training action separates the computationally intensive learning phase from the operational phase, reducing real-time computational complexity while maintaining high accuracy.
Solution Approach 2:
The patent uses voltage time series data patterns from known phase configurations as training examples or reference templates. The machine learning models learn to recognize and copy these characteristic voltage patterns, enabling accurate phase identification by matching new measurements against learned patterns rather than requiring complex real-time analysis from scratch.
3Productivity
If phase information is not updated when meters are moved, then recordkeeping simplicity is maintained, but phase balancing capability deteriorates leading to operational inefficiencies
Solution Approach 1:
The patent implements a feedback mechanism where the automated phase identification system continuously monitors voltage data from smart meters and compares determined phase connections against utility company records. When discrepancies are detected (such as when linemen move meters without updating records), the system generates alerts or automatically updates the phase information in the database. This closed-loop feedback ensures phase information remains accurate without requiring manual intervention at each step.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method, apparatus, and system for identifying electrical phases connected to electricity meters are disclosed. Voltage time series data of electricity meters are collected over a preselected collection time period, and three initial kernels representing three line-to-neutral phases are generated based on voltage correlations of meter-to-meter combinations. Three new kernels are then generated based on correlation values calculated for each of the three initial kernels with each electricity meter, and electricity meters are clustered into three groups based on average correlation values associated with each electricity meter. Six new kernels representing six phases are then formed based on the average correlation value associated with each electricity meter, and a predicted phase is assigned to each electricity meter based on correlation values of the electricity meter with each of the six new kernels based on the voltage time series data.