Contingency Recognition in Power Supply Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In power supply networks, manual analysis of vast measurement data from in-field devices is time-consuming and delays decision-making during contingencies, which can threaten network stability, as it takes months to analyze data that requires immediate action.
Innovation Solution
A method and system that automatically recognize contingencies by processing measurement data using local network state estimation models and neural attention models to generate relevance profiles, comparing them with reference profiles to identify the origin and type of the contingency, enabling rapid identification and response.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis of measurement data is performed by experienced engineers, then analysis accuracy can be maintained, but analysis time becomes extremely long (up to three months)
Solution Approach 1:
The patent replaces the manual mechanical analysis process performed by engineers with an automated computer-based system that uses machine learning models and algorithms to process measurement data, calculate network state profiles, and identify contingencies automatically, thereby eliminating the time-consuming manual analysis while maintaining or improving accuracy through systematic computational methods
Solution Approach 2:
The patent introduces an intermediary automated analysis system that acts as a bridge between raw measurement data and decision-making requirements. This intermediary system processes the data through multiple computational stages including profile calculation, similarity comparison, and contingency identification, enabling fast automated analysis without direct human intervention in the analysis process
2Measurement precision
If high resolution measurement data is collected from in-field devices, then contingency detection capability is improved, but data volume increases leading to huge amounts of data to be processed
Solution Approach 1:
The patent extracts only the most relevant features and patterns from the huge volume of high-resolution measurement data by calculating condensed network state profiles that capture essential contingency information. The system extracts key characteristics through profile calculations and similarity comparisons, eliminating the need to process every raw data point while retaining critical contingency detection capabilities
Solution Approach 2:
The patent transforms the original high-dimensional measurement data into compressed parameter representations through profile calculations. By changing the data parameters from raw measurement values to derived network state profiles and relevance distributions, the system reduces data complexity and volume while preserving the essential information needed for contingency identification
3Loss of time
If automated processing is implemented to reduce analysis time, then decision-making speed is improved, but system complexity increases
Solution Approach 1:
The patent segments the automated processing system into distinct functional modules including measurement data reception, profile calculation units, similarity comparison engines, and contingency identification components. This segmentation allows the complex automated processing task to be divided into manageable stages, each handling specific aspects of the analysis, thereby reducing overall system complexity while enabling fast automated decision-making
Data Source
AI summary
A monitoring system includes in-field measurement devices adapted to generate measurement data of a power supply network, and a processing unit adapted to process the measurement data using a local network state estimation model to calculate local network state profiles used to generate a global network state profile. The processing unit is adapted to process the measurement data to provide a relevance profile comprising, for the in-field measurement devices, a relevance distribution indicating a probability where an origin of a contingency within the power supply network resides. The processing unit is adapted to compute a similarity between a candidate contingency profile formed by the generated global network state profile and by the calculated relevance profile and reference contingency profiles stored in a reference contingency database of the monitoring system to identify a reference contingency profile having a highest computed similarity as a recognized contingency within the power supply network.