Systems and Methods for Automatic Real-Time Capacity Assessment for Use in Real-Time Power Analytics of an Electrical Power Distribution System

Abstract

A system for conducting a real-time power capacity assessment of an electrical system is disclosed. The system includes a data acquisition component, a power analytics server and a client terminal. The data acquisition component is communicatively connected to a sensor configured to acquire real-time data output from the electrical system. The power analytics server is communicatively connected to the data acquisition component and is comprised of a virtual system modeling engine, an analytics engine and a machine learning engine. The machine learning engine is configured to store and process patterns observed from the real-time data output and the predicted data output, forecasting power capacity of the electrical system subjected to a simulated contingency event.

The invention claimed is: 
     
         1 . A system for real-time power capacity assessment of an electrical system, comprising:
 a data acquisition component configured to acquire real-time output data from the electrical system;   a power analytics server communicatively connected to the data acquisition component, comprising,
 a virtual system modeling engine configured to create a virtual system model of the electrical system and generate predicted output data of the electrical system; 
 an analytics engine configured to initiate a calibration and synchronization operation to update the virtual system model when a difference between the real-time data output data and the predicted output data output exceeds a threshold; 
 a machine learning engine configured to store and process patterns observed from the real-time output data and the predicted output data, the machine learning engine further configured to forecast a power capacity of the electrical system subjected to a contingency event in real time, wherein the machine learning engine comprises an associative memory layer, a sensor layer and a neocortical model; and 
   a client terminal communicatively connected to the power analytics server, the client terminal configured to enable the selection of the contingency event and display a report of the power capacity.   
     
     
         2 . The system of  claim 1 , wherein the threshold is a Defined Difference Tolerance (DDT) value for at least one of the frequency deviation, voltage deviation, power factor deviation, and other deviations between the real-time output data and the predicted output data. 
     
     
         3 . The system of  claim 1 , wherein the power capacity is a measure of the electrical system's ability to maintain an acceptable voltage profile under different electrical system topologies and load changes. 
     
     
         4 . The system of  claim 1 , wherein the contingency event relates to load shedding. 
     
     
         5 . The system of  claim 1 , wherein the contingency event relates to load adding. 
     
     
         6 . The system of  claim 1 , wherein the contingency event relates to a loss of utility power supply to the electrical system. 
     
     
         7 . The system of  claim 1 , wherein the contingency event relates to a loss of distribution infrastructure associated with the electrical system. 
     
     
         8 . The system of  claim 1 , wherein the report includes a forecast of total system power capacity. 
     
     
         9 . The system of  claim 1 , wherein the report includes a forecast of available system power capacity. 
     
     
         10 . The system of  claim 1 , wherein the report includes a forecast of present utilized system capacity. 
     
     
         11 . A method for assessing real-time power capacity of an electrical system, comprising:
 providing a data acquisition component and a client terminal constructed and configured in network communication with a server processor, wherein the server processor comprises a virtual system modeling engine, an analytics engine, and a machine learning engine;   the data acquisition component acquiring real-time output data from the electrical system;   the virtual system modeling engine generating predicted output data of the electrical system based on a virtual system model of the electrical system;   the analytics engine initiating a calibration and synchronization operation to update the virtual system model when a difference between the real-time output data and the predicated output data exceeds a threshold;   the machine learning engine forecasting a power capacity of the electrical system subjected to a contingency event in real time;   the machine learning engine generating a report of the power capacity of the electrical system subjected to the contingency event; and   the client terminal displaying the report of the power capacity.   
     
     
         12 . The method of  claim 11 , wherein the threshold is a Defined Difference Tolerance (DDT) value for at least one of the frequency deviation, voltage deviation, power factor deviation, and other deviations between the real-time output data and the predicted output data. 
     
     
         13 . The method of  claim 11 , wherein the virtual system model comprises voltage stability model data for components in the electrical system. 
     
     
         14 . The method of  claim 13 , wherein the voltage stability model data comprises load scaling data, generation scaling data, load growth factor data, load growth increment data. 
     
     
         15 . The method of  claim 11 , wherein the contingency event relates to load shedding, load adding, a loss of utility power supply to the electrical system, a loss of distribution infrastructure associated with the electrical system. 
     
     
         16 . The method of  claim 11 , wherein the power capacity is a measure of the electrical system's ability to maintain an acceptable voltage profile when subjected to the contingency event. 
     
     
         17 . The method of  claim 11 , wherein the report comprises a forecast of total system power capacity, a forecast of available system power capacity, and/or a forecast of present utilized system capacity. 
     
     
         18 . The method of  claim 11 , wherein the machine learning engine comprises an associative memory layer, a sensor layer and a neocortical model. 
     
     
         19 . The method of  claim 11 , further comprising the machine learning engine storing and processing patterns observed from the real-time output data and the predicted output data. 
     
     
         20 . The method of  claim 11 , further comprising the client terminal selecting the contingent event for the forecasting of the power capacity.