Systems and methods for classifying in-situ sensor response data patterns representative of grid pathology severity

Abstract

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 update a model of grid response.

Description

Background technique [0001] The performance of utility grids—their reliability, safety, and efficiency—can be measured by sensing key parameters and using those results to identify faults, direct appropriate responses, and enable proactive management such as incorporating renewable sources into The simultaneous maintenance of power quality in the grid leads to radical improvements in grid operation and maintenance. [0002] Sensor networks are often used to monitor utility grids. These sensor networks may include smart meters at the ends of the grid, sensors at grid nodes, and sensors on or around utility lines that measure grid parameters such as flow velocity in the water network, power quality in the grid Or stress in the utility grid. These sensors are transducers that typically output an analog signal representative of the measured property. These outputs need to be characterized to map to specific values ​​of those properties, and / or classified so that they can repres...

AI Technical Summary

Problems solved by technology

Those whose signal injections are large, individual, and human-involved, not susceptible to automation, local testing of a smaller scope, or simultaneous or sequential implementation of tests

Occasional full-grid and almost necessarily human-directed signal injections are less suitable for characterizing extended networks of various sensors placed along the grid in various contexts, since they can only generate small sample sizes and cannot Varies widely enough to be tailored to individual conditions and idiosyncrasies of sensor locations

Images