Synchrophasor Event Detection Using Signal Envelopes and DBSCAN
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The large volume of synchrophasor data in electrical power systems poses challenges for efficient and rapid detection and classification of abnormal events, necessitating a quick and reliable mechanism for event detection and further characterization.
Innovation Solution
The use of signal envelope data and density-based spatial clustering, particularly through the DBSCAN algorithm, to identify outlier points in paired power system signal envelopes, combined with machine-learning algorithms for classification, facilitates high-speed event detection and classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional event detection methods are used on synchrophasor data, then event detection can be performed, but the processing time becomes excessively long due to the massive volume of data (6.8 TB for 2 years)
Solution Approach 1:
The patent extracts only the signal envelope characteristics from the full synchrophasor data, rather than processing the complete raw data. This extraction of essential features (envelope amplitude, frequency, phase) reduces the data volume dramatically while preserving the information needed for event detection, thus resolving the contradiction between detection reliability and processing time
Solution Approach 2:
The patent creates a simplified representation (copy) of the original data by generating signal envelopes that capture the essential characteristics of the power system signals. This envelope representation serves as a compressed copy that retains event information while reducing processing requirements, enabling fast analysis without losing detection accuracy
2Measurement precision
If the entire synchrophasor data set is analyzed in detail, then comprehensive event classification can be achieved, but the processing complexity and time requirements become unmanageable
Solution Approach 1:
The patent segments the event analysis process into distinct stages: (1) signal envelope extraction, (2) event detection using clustering on envelopes, and (3) event classification using selected features. This segmentation allows each stage to process only necessary data with appropriate algorithms, reducing overall complexity while maintaining classification precision
Solution Approach 2:
The patent applies different processing qualities to different aspects of the data: full-resolution processing is applied only to signal envelopes for event detection, while classified events receive targeted feature analysis. This local quality approach ensures high precision where needed while avoiding unnecessary complexity in other areas
Data Source
AI summary
Methods for detecting power system events in an electrical power system. An example method comprises determining a signal envelope for each of at least first and second power system signals and performing density-based spatial clustering of a series of points formed by combining respective values of the signal envelopes for at least the first and second power system signals. The example method further comprises detecting one or more power system events by identifying outlier points or groups of points in the spatial clustering. Some methods may further comprise automatically classifying power system events by collecting a data set comprising, for each detected power system event, power system signal features corresponding to the detected power system event, and classifying each of the detected power system events using the data set and a machine-learning-based classification algorithm, where said classifying comprises determining a classification label from among two or more predetermined classification labels.