Meter Voltage Anomaly Detection for Power Distribution Faults
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Anomalies in power distribution systems can lead to increased downtime and wear on parts, escalating service costs, and existing detection methods using additional equipment are expensive.
Innovation Solution
Utilize machine learning models trained on voltage measurements from electric metering devices to identify anomalies such as loose connections, seasonal overloads, and long secondary lines by recognizing voltage signatures, and send alerts to utility operators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If additional equipment is added to detect anomalies in power distribution systems, then detection capability is improved, but system cost increases
Solution Approach 1:
The existing electric metering devices perform dual functions: their primary function of measuring power consumption and their secondary function of collecting voltage measurements for anomaly detection. This self-service approach eliminates the need for separate dedicated detection equipment, reducing system cost while maintaining anomaly detection capability
Solution Approach 2:
The electric metering devices are utilized for multiple purposes: power consumption measurement, voltage measurement collection, and anomaly detection through machine learning analysis. This multi-functionality approach allows existing infrastructure to serve detection purposes without additional equipment investment
2Reliability
If voltage measurements are continuously monitored to detect anomalies, then system reliability is improved, but data processing complexity increases
Solution Approach 1:
The machine learning model is pre-trained on historical voltage measurements and anomaly patterns before deployment. This preliminary training enables the model to automatically recognize anomaly signatures in real-time data without requiring complex real-time processing algorithms, reducing data processing complexity while maintaining high reliability
Solution Approach 2:
A machine learning model serves as an intermediary between raw voltage measurements and anomaly detection. The model processes the complex patterns in voltage data and outputs simplified anomaly classifications, reducing the computational burden and complexity of direct real-time analysis while improving detection reliability
Data Source
AI summary
Disclosed techniques include using machine learning to detect an electrical anomaly in a power distribution system. In an example, a method includes accessing voltage measurements measured at an electric metering device and over a time period. The method further includes calculating, from voltage measurements and for each time window of a set of time windows, a corresponding average voltage and a corresponding minimum voltage. The method further includes applying a machine learning model to the average voltages and the minimum voltages. The machine learning model is trained to identify one or more predetermined electrical anomalies from voltages. The method further includes receiving, from the machine learning model, a classification indicating an identified anomaly. The method further includes based on the classification, sending an alert to a utility operator.