Machine Learning Engine for Electric Power Event Location
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying the location of events, such as faults, in electric power delivery systems is time-consuming and inefficient due to the large number of sensors and equipment, making it difficult to quickly pinpoint the accurate location of disruptions in the system.
Innovation Solution
Implementing machine learning techniques to determine event locations using a trained machine learning engine and prediction engine, which generates a prediction model based on the system's topology and electrical parameters, allowing for faster and more accurate identification of faulted line sections even when some sensors fail to report events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional monitoring methods are used to track events in electric power delivery systems, then comprehensive monitoring coverage is achieved, but event location identification becomes time-consuming and inefficient
Solution Approach 1:
The system performs preliminary actions by training a machine learning model in advance using historical event data and system topology information. This pre-trained model is then deployed to rapidly identify event locations in real-time, eliminating the need for time-consuming manual analysis during actual events.
Solution Approach 2:
A machine learning model serves as an intermediary between raw sensor data and event location identification. The model processes electrical parameters and sensor readings to predict event locations, acting as a intelligent mediator that bridges the gap between comprehensive monitoring data and actionable event location information.
2Reliability
If comprehensive sensor networks are deployed to monitor all line sections, then complete system coverage is achieved, but system complexity and computational burden increase
Solution Approach 1:
The machine learning model performs multiple functions simultaneously: it processes data from multiple sensors, identifies event locations, and handles cases where sensors fail to report. This multi-functional approach allows the system to maintain comprehensive monitoring coverage without requiring separate specialized systems for each function.
Solution Approach 2:
The system changes parameters by using probabilistic outputs from the machine learning model rather than deterministic sensor readings. This allows the system to handle uncertain or missing sensor data by predicting event locations based on probability distributions, maintaining reliability even with incomplete sensor information.
3Ease of operation
If manual methods are used to identify event locations, then operator control is maintained, but productivity and fault correction efficiency decrease
Solution Approach 1:
The system provides feedback to operators by presenting predicted event locations with associated probabilities. This allows operators to review and verify the AI-generated predictions, maintaining operational control while benefiting from the speed and accuracy of machine learning-based event location identification.
Data Source
AI summary
Systems and methods for determining a location of an event in an electric power delivery system using a machine learning engine are provided. The machine learning engine may be trained based on a topology of the electric power delivery system, where the topology may be a layout of line sections and corresponding sensors of the electric power delivery system. Based on the topology, one or more training matrices that indicate possible event locations may be generated. In turn, the machine learning engine may be trained using the training matrices and logistic regression models to determine locations of events that occur during operation of the electric power delivery system.