Utility Grid Sensor Characterization via Signal Injection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current utility grid management systems face limitations in real-time, granular monitoring and management due to reliance on big data models that rely on historical correlations, and signal injections are poorly suited for characterizing diverse sensor networks, lacking automation and scalability for concurrent or sequential testing across large networks.
Innovation Solution
Implementing a system with signal injection directors, controllers, sensors, an association module, and an analysis module to compute spatial and temporal reaches of signal injections, associate sensor responses, and update models for improved sensor characterization and classification, enabling automated, concurrent, and sequential testing across large networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If big data models are used to analyze sensor data, then large amounts of historical data can be processed, but real-time granular monitoring and cause-and-effect understanding are limited
Solution Approach 1:
The system performs preliminary actions by injecting signals into the utility grid before actual grid operations, causing sensors to respond to known inputs. This allows the system to pre-characterize sensor responses and build causal models that enable real-time granular monitoring without relying solely on historical correlation data.
2Reliability
If signal injections are used to highlight grid faults, then faults can be detected, but the approach is not scalable for concurrent or sequential testing across large networks
Solution Approach 1:
The system enables self-service by automatically injecting signals, collecting sensor responses, computing spatial-temporal reaches, and updating models without human intervention. This automation makes the signal injection approach scalable across large networks, allowing concurrent and sequential testing to be performed efficiently without requiring manual coordination.
3Measurement precision
If sensors are characterized through bench testing, then sensor performance can be measured, but in-situ characterization is difficult for large numbers of sensors
Solution Approach 1:
The system uses signal injections as intermediaries to transfer known inputs through the utility grid to sensors in their installed locations. By measuring sensor responses to these controlled signals and computing the spatial-temporal reaches, the system can characterize sensors in-situ without requiring physical access or bench testing equipment, simplifying the characterization process for large sensor networks.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present invention is directed towards methods and systems for characterizing sensors and developing classifiers for sensor responses on a utility grid. Experiments are conducted by selectively varying utility grid parameters and observing the responses of utility grid to the variation. Methods and systems of this invention then associate the particular responses of the utility grid sensors with specific variations in the grid parameters, based on knowledge of the areas of space and periods of time where the variation in grid parameters may affect the sensor response. This associated data is then used to updating a model of grid response.