Distributed Power Event Detection From Clustered Grid Anomalies
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Power companies face challenges in timely detection and identification of electrical grid events that disrupt power transmission, leading to prolonged outages and increased risks such as fires, due to inadequate reporting of anomalies from end users and employees.
Innovation Solution
Implementing distributed computing and machine learning techniques using power monitors at various grid points to identify and classify anomalies, combining sensor data with weather and building information, and clustering reports to determine power events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If distributed power monitors are deployed at multiple grid points to detect anomalies, then the detection coverage and timeliness of power events are improved, but the system complexity and data processing requirements increase
Solution Approach 1:
The electrical grid is divided into multiple monitoring zones with distributed power monitors at different grid points (substations, distribution transformers, end-user premises). Each monitor independently detects local anomalies and reports to a central system, enabling comprehensive coverage while maintaining modular system architecture that manages complexity through division.
2Measurement precision
If machine learning classifiers process all power-anomaly reports to identify event types, then the accuracy of power event identification is improved, but the computational time and processing resources increase
Solution Approach 1:
Power anomaly reports are pre-filtered and pre-processed before classification. The system selects a subset of relevant reports based on initial criteria (anomaly type, location, time) and applies machine learning classifiers only to this reduced set. This preliminary filtering action reduces computational burden while maintaining identification accuracy for critical events.
3Measurement precision
If location information and time information are used to cluster power-anomaly reports, then the localization precision of power events is improved, but the data processing complexity increases
Solution Approach 1:
The system creates simplified representations (copies) of power anomaly data that include essential location and time features. These copied data structures are used for clustering operations instead of processing raw, complex sensor data. This approach maintains localization precision by preserving key spatial-temporal information while reducing overall data complexity for clustering algorithms.
Data Source
AI summary
Information about power events on the electrical grid may be determined by processing reports of power anomalies from power monitors installed at various points on the electrical grid, such as in buildings of end users of electrical power. A power monitor may process sensor measurements of the power line to determine that a power anomaly has occurred. The power monitor may transmit information about the power anomaly, such as the time and location, to a processing location. The processing location may select power anomaly reports having a similar time and location to determine information about a power event that caused the power anomalies. The information about the power event may include the type, time, and location of the power event. A notification may be sent about the power event to facilitate repairs and reduce risks, such as the risk of electrical fires.