System and method for predictive analytics in an electrical grid network

BACKGROUND

[0001] The present technique relates to the field of electrical grid. In particular, this invention relates to a system and method of monitoring performance and reliability in electrical grid.

[0002] Electrical grid is a network for delivering electricity from electricity suppliers to consumers. Smart grid is a form of electrical grid which uses two-way digital communications technology to control and monitor power consumption at consumption points or appliances attached to the electricity distribution network. Some of the advantages of smart grids are saving in energy, improvements in reliability and reduction in costs.

[0003] The electrical grid is composed of networked equipment whose performance and reliability is dependent on parameters like atmospheric temperature, humidity, reliability of its component parts, age of the equipment, system load, etc. Failure in equipment is usually attributed to one or more of the above mentioned parameters. There are instances where failure of one of the equipment leads to failure of several other equipment attached to the electrical grid or disruption in electricity supply. This disruption is due to failure of equipment or as a mechanism to protect grid from spreading the failure. Hence, it becomes complex to accurately determine which combination of parameters led to the failure of equipment or a cascade of failures in subsequent equipment connected to the electricity distribution network.

[0004] While there are methods in electrical equipment control systems that indicate failure using diagnostic tests to monitor performance and reliability metrics of individual equipment. These diagnostic tests report failure only after an event has occurred. Often, causes of equipment failure are directly related to multiple parameters measured from the electrical grid equipment over a period of time.

[0005] Therefore, there is a particular need for a method and system that predicts reliability and performance metrics of the electrical grid equipment using historic and real-time measurements available.

SUMMARY OF THE INVENTION

[0006] The present invention relates to a method of predictive analytics in an electrical grid network. The method includes aggregating a plurality of events an electrical grid network. The aggregated events are then analyzed to recognize an event pattern in the plurality of events aggregated from electrical grid network. The event pattern is then . serialized in a database. Based on the plurality of event patterns that are recognized, predicting a future event pattern by correlation.

[0007] The present invention relates to a system of predictive analytics in an electrical grid network. The system comprises an integration module which receives plurality of events from an electrical grid network. Using the plurality of events, an analysis module is configured to recognize a plurality of event patterns using the plurality of events. The event patterns recognized by the analysis module are then stored in a database. A prediction module predicts a future event pattern based on correlation of event patterns.

[0008] The present invention relates to a computer implemented method for monitoring performance and predicting reliability of equipment. The method comprises aggregating a plurality of events from electrical equipment connected to the electrical grid network. Applying a time-slice parameter to the events and analyzing the events within the selected time-slice to recognize event patterns. The event patterns that are recognized are then stored in a database. Using the event patterns, predicting a future event pattern based on correlation of the event patterns. Determining the accuracy of the predicted event pattern by using an accuracy parameter. Adjusting the time-slice parameter in order to increase the accuracy parameter.

[0009] The present invention relates to a system for monitoring performance and predicting reliability of equipment. The system comprises an integration module which aggregates a plurality of events using measurements from at least one equipment connected to an electrical grid network. An analysis module configured to apply a time-slice parameter to the plurality of events to recognize at least one event pattern within the time-slice. A database configured to store the time-slice parameter and at least one event. A prediction module configured to predict a future event pattern based on correlation of the plurality of event patterns. A feedback module configured to determine an accuracy parameter by comparing the predicted future event pattern with an actual event and adjust the time-slice parameter to increase the accuracy parameter.

DRAWINGS

[0010] These and other features, aspects, and advantages of the present invention will be better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

[0011] FIG.l shows an environment in which the present invention can be practiced, in accordance with an embodiment of the present invention;

[0012] FIG.2 is a block diagram of a system in which the present invention can be practiced, in accordance with another embodiment of the present invention;

[0013] FIG.3 shows an environment in which the present invention can be practiced, in accordance with another embodiment of the present invention;

[0014] FIG. 4 is a flowchart describing a method, in accordance with an embodiment of the present invention;

[0015] FIG. 5 is a flowchart describing a method, in. accordance with another embodiment of the present invention; and

[0016] FIG. 6 illustrates a generalized example of a computing environment 600.

DETAILED DESCRIPTION

[0017] The following description is the full and informative description of the best method and system presently contemplated for carrying out the present invention which is known to the inventors at the time of filing the patent application. Of course, many modifications and adaptations will be apparent to those skilled in the relevant arts in view of the following description in view of the accompanying drawings and the appended claims. While the system and method described herein are provided with a certain degree of specificity, the present technique may be implemented with either greater or lesser specificity, depending on the needs of the user. Further, some of the features of the present technique may be used to get an advantage without the corresponding use of other features described in the following paragraphs. As such, the present description should be considered as merely illustrative of the principles of the present technique and not in limitation thereof, since the present technique is defined solely by the claims.

[0018] FIG.l shows an environment 100 in which the present invention can be practiced, in accordance with an embodiment of the present invention. Environment 100 includes a server 102, a communication network 110, a client device 112, and an electrical grid network 114.

[0019] The server 102 is used as an application server which performs the business logic functions. The server 102 also acts as a database where information received from the electrical grid network 114 and the client device 112 are stored. The server 102 is connected to the client device 112 over the communication network 110. The server 102 is also connected to the electrical grid network 114. The server 102 receives information from the electrical grid network 114 using the communication network 110. The client device 112 communicates with the server 102 using the communication network 110 for receiving and sending information.

[0020] FIG.2 is a block diagram of a system 200 in which the present invention can be practiced, in accordance with another embodiment of the present invention. The system comprises a server 202, a network 214, an electrical grid network 218 and a client device 216. The server 202 has an integration module 204, an analysis module 206, a database 208 and a prediction module 210.

[0021] As shown, the integration module 204 communicates with the electrical grid network 218 using the communication network 214 to collect events from electrical grid network. The electrical grid network comprises electrical power transmission equipment for transfer of power from power generation plants to electricity consumers. The events collected from the electrical grid network may include non-operational assets, equipment measurements, alerts, alarms and weather. The historic measurements of events are also part of the database. The integration module 204 may also communicate with supervisory control and data acquisition (SCADA) to collect information from the electrical grid network. SCADA refers to control systems that monitor and control electricity supply infrastructure or facilities.

[0022] The analysis module 206 performs the function of analyzing the events from the electrical grid network to recognize an event pattern. The input to the analysis module is in the form of a time series with events from electrical grid network.

[0023] In accordance with one embodiment of the invention, the analysis module may use time domain correlation to analyze the events time series received from the electrical grid network. Time domain correlation may be performed using autocorrelation. Autocorrelation is the cross-correlation of the events time series with itself.

[0024] For example, let 'X' be an even that is repeatable and 'i' a point in time after the start of the events. Then 'Xi' is the value of an event measurement at time 'i'. The definition of auto correlation between two points in time series 's' and 't' is

Where, E is the expectation operator, ms and mt are the mean values at times 's' and 't' crtz and os2 are known variance values at times 't' and 's'.

The autocorrelation operation generates information about repeating events. An example of a repeating event is adverse effects on electrical power transmission caused by storm weather. An autocorrelation operation of a time series tracking power outages caused by storms generates patterns of storm related power outages. After the time domain correlation, the patterns found are stored in the database 208. The prediction module 210 reads the database for the correlation patterns and historic measurements from the electrical grid network. The prediction module 210 predicts future event patterns using regression analysis. An example of prediction of future event patterns can be performed using a linear regression in order to assess the association between time and frequency of outages. In case of a linear regression, the relationship between time 'x' and frequency of outages 'y' is

Where 'a' is the intercept point of regression line and the y axis; 'b' is the slope of the regression line. Slope of the regression line is calculated using and intercept a is calculated using

Using historic information from electrical grid network and the regression equation y — a + bx, prediction is performed.

[0025] In another embodiment of the invention, the integration module 204 receives events from operations technology systems and information technology systems. An example of operations technology systems include power supply instrumentation and control systems. An example of information technology system is a software application or a web service that acts as a source for events.

[0026] In another embodiment of the invention, the events received at the integration module 204 are data cleansed by removing incorrect data. This is performed by replacing, modifying or deleting the event related data. This is performed to ensure high quality data to be used by the system.

[0027] FIG. 3 is a block diagram of a system 300 in which the present invention can be practiced, in accordance with another embodiment of the present invention. The system comprises a server 302, a communication network 314, an electrical grid network 318 and a client device 316. The server 302 has an integration module 304, an analysis module 306, a database 308, a prediction module 310 and a feedback module 312.

[0028] It should be noted that details of various components shown in the figure, namely, the server 302, a communication network 314, the electrical grid network 318, the client device 316, integration module 304, the analysis module 306, the database 308, the prediction module 310 have been described earlier in conjunction with Fig. 2 and hence, are not described again. The analysis module applies a time-slice parameter to the events time series and analyzes events within the time-slice in order to recognize an event pattern. The feedback module 312 performs the function of determining the accuracy of the predicted event by comparing the actual events with historic values of electrical grid network from the database. Accuracy parameter is the ratio of the number of events predicted and the number of actual events that occurred. The feedback module also adjusts the time-slice parameter in order to increase accuracy parameter.

[0029] Fig.4 is a flowchart of a method for predictive analytics in an electrical grid network, in accordance with an embodiment of the invention.

[0030] Events from electrical grid network are aggregated at step 402. The events are measurements from equipment and information technology systems that are connected to the electrical grid network.

[0031] At step 404, the events from the electrical network are analyzed to recognize event patterns. This analysis is performed using at least one of time domain or frequency domain correlation. Time domain correlation is performed using correlation operations. Examples of correlation operations may include auto correlation and cross correlation. Frequency domain correlation is performed using mathematical transform operations. Examples of mathematical transformations may include Fast Fourier Transform and Fractional Fourier Transform.

[0032] The event patterns are stored in the database at step 406. Examples of database may include relational database, temporal database, flat file database and object oriented database.

[0033] At step 408, using the event patterns stored in the database, future events are predicted. Examples of methods used for prediction may include regression analysis, Monte-Carlo simulation, artificial neural network, recurrence quantification analysis, correlation dimension and nonlinear autoregressive exogenous model.

[0034] Fig.5 is a flowchart of a method for predictive analytics in an electrical grid network, in accordance with an embodiment of the invention.

[0035] Events from electrical grid network are aggregated at step 502. The events are measurements from equipment and information technology systems that are connected to the electrical grid network.

[0036] A time-slice parameter is applied to the events at step 504. A time-slice parameter is a fixed duration of time within which all events are analyzed in the subsequent steps. This operation result in multiple time-slices with fixed time duration and within each time-slice is events.

[0037] At step 506, the events from the electrical network are analyzed to recognize event patterns within each time-slice obtained in step 504. This analysis is performed using at least one of time domain or frequency domain correlation. Time domain correlation is performed using correlation operations. Examples of correlation operations may include auto correlation and cross correlation. Frequency domain correlation is performed using mathematical transform operations. Examples of mathematical transformations may include Fast Fourier Transform and Fractional Fourier Transform.

[0038] The event patterns recognized within each time-slice is stored in a database at step 508. Examples of database may include relational database, temporal database, flat file database and object oriented database.

[0039] Future event patterns are predicted at step 510 using the event patterns stored in the database at step 510. Examples of methods used for prediction may include regression analysis, Monte-Carlo simulation, artificial neural network, recurrence quantification analysis, correlation dimension and nonlinear autoregressive exogenous model.

[0040] At step 512, by comparing the actual events with the predicted events obtained at step 510 an accuracy parameter is found. An example of the accuracy parameter is difference between the number of predicted events and the number of actual events.

[0041] The accuracy parameter is used to adjust the time-slice parameter at step 514. Time slice parameter is increased or decreased based on the accuracy parameter. By increasing or decreasing the time-slice parameter, the accuracy parameter which is a measure of accuracy of prediction is optimized. Time-slice parameter is usually measured in units of time, for example in seconds or minutes.

[0042] Exemplary Computing Environment

[0043] One or more of the above-described techniques can be implemented in or involve one or more computer systems. FIG. 6 illustrates a generalized example of a computing environment 600. The computing environment 600 is not intended to suggest any limitation as to scope of use or functionality of described embodiments.

[0044] With reference to Fig. 6, the computing environment 600 includes at least one processing unit 610 and memory 620. In Fig. 6, this most basic configuration 630 is included within a dashed line. The processing unit 610 executes computer-executable instructions and may be a real or a virtual processor. In a multi-processing system, multiple processing units execute computer-executable instructions to increase processing power. The memory 620 may be volatile memory (e.g., registers, cache, RAM), nonvolatile memory (e.g., ROM, EEPROM, flash memory, etc.), or some combination of the two. In some embodiments, the memory 620 stores software 680 implementing described techniques.

[0045] A computing environment may have additional features. For example, the computing environment 600 includes storage 640, one or more input devices 650, one or more output devices 660, and one or more communication connections 670. An interconnection mechanism (not shown) such as a bus, controller, or network interconnects the components of the computing environment 600. Typically, operating system software (not shown) provides an operating environment for other software executing in the computing environment 600, and coordinates activities of the components of the computing environment 600.

[0046] The storage 640 may be removable or non-removable, and includes magnetic disks, magnetic tapes or cassettes, CD-ROMs, CD-RWs, DVDs, or any other medium which can be used to store information and which can be accessed within the computing environment 600. In some embodiments, the storage 640 stores instructions for the software 680.

[0047] The input device(s) 650 may be a touch input device such as a keyboard, mouse, pen, trackball, touch screen, or game controller, a voice input device, a scanning device, a digital camera, or another device that provides input to the computing environment 600. The output device(s) 660 may be a display, printer, speaker, or another device that provides output from the computing environment 600.

[0048] The communication connection(s) 670 enable communication over a communication medium to another computing entity. The communication medium conveys information such as computer-executable instructions, audio or video information, or other data in a modulated data signal. A modulated data signal is a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media include wired or wireless techniques implemented with an electrical, optical, RF, infrared, acoustic, or other carrier.

[0049] Implementations can be described in the general context of computer-readable media. Computer-readable media are any available media that can be accessed within a computing environment. By way of example, and not limitation, within the computing environment 600, computer-readable media include memory 620, storage 640, communication media, and combinations of any of the above.

[0050] Having described and illustrated the principles of our invention with reference to described embodiments, it will be recognized that the described embodiments can be modified in arrangement and detail without departing from such principles. It should be understood that the programs, processes, or methods described herein are not related or limited to any particular type of computing environment; unless indicated otherwise Various types of general purpose or specialized computing environments may be used with or perform operations in accordance with the teachings described herein. Elements of the described embodiments shown in software may be implemented in hardware and vice versa.

[0051] As will be appreciated by those ordinary skilled in the art, the foregoing example, demonstrations, and method steps may be implemented by suitable code on a processor base system, such as general purpose or special purpose computer. It should also be noted that different implementations of the present technique may perform some or all the steps described herein in different orders or substantially concurrently, that is, in parallel. Furthermore, the functions may be implemented in a variety of programming languages. Such code, as will be appreciated by those of ordinary skilled in the art, may be stored or adapted for storage in one or more tangible machine readable media, such as on memory chips, local or remote hard disks, optical disks or other media, which may be accessed by a processor based system to execute the stored code. Note that the tangible media may comprise paper or another suitable medium upon which the instructions are printed. For instance, the instructions may be electronically captured via optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

[0052] The following description is presented to enable a person of ordinary skill in the art to make and use the invention and is provided in the context of the requirement for a obtaining a patent. The present description is the best presently-contemplated method for carrying out the present invention. Various modifications to the preferred embodiment will be readily apparent to those skilled in the art and the generic principles of the present invention may be applied to other embodiments, and some features of the present invention may be used without the corresponding use of other features. Accordingly, the present invention is not intended to be limited to the embodiment shown but is to be accorded the widest scope consistent with- the principles and features described herein.

CLAIMS What is claimed is:

1. A method for predictive analytics in an electrical grid network implemented at least in part by a computer, comprising:

aggregating a plurality of events from an electrical grid network;

analyzing the plurality of events to recognize one or more event patterns;

serializing the one or more event patterns in a database; and

predicting a future event pattern based on correlation of the plurality of event patterns.

2. The method of claim 1, wherein the events are cleansed by removing incorrect temporal data based on associated time stamp information.

3. The method of claim 1, wherein the plurality of events comprise a measurement history database, an alerts database, an alarm database and a weather history database.

4. The method of claim 1, wherein the plurality of event patterns is indicative of the past and present events.

5. The method of claim 1, wherein analyzing the plurality of events is performed using time domain correlation.

6. The method of claim 1, wherein analyzing the plurality of events is performed using frequency domain correlation.

7. The method of claim 5, wherein time domain correlation is performed using auto correlation.

8. The method of claim 5, wherein time domain correlation is performed using cross correlation.

9. The method of claim 6, wherein frequency domain correlation is performed using mathematical transforms.

10. The method of claim 6, wherein frequency domain correlation is performed using a Fast Fourier transform.

11. The method of claim 6, wherein frequency domain correlation is performed using Fractional Fourier transforms.

12. The method of claim 1, wherein prediction comprises using method of, forecasting selected from the group consisting of regression analysis, Monte-Carlo simulation, artificial neural network, recurrence quantification analysis, correlation dimension and nonlinear autoregressive exogenous model.

13. A system for predictive analytics in an electrical grid network comprising:

an integration module configured to aggregate a plurality of events from an electrical grid network;

an analysis module configured to recognize a plurality of event patterns from the plurality of events;

a database configured to store the plurality of events; and

a prediction module configured to predict a future event pattern based on correlation of the plurality of event patterns.

14. The system of claim 13, wherein the integration module receives events from information technology systems.

15. The system of claim 13, wherein the integration module receives events from operations technology systems.

16. A computer implemented method for monitoring performance and predicting reliability of equipment in electrical grid network comprising:

aggregating a plurality of events using measurements from a plurality of equipment connected to an electrical grid network;

applying a time-slice parameter to the plurality of events;

analyzing a plurality of events to recognize a plurality of event patterns;

serializing the plurality of event patterns in a database;

predicting, a future event pattern based on correlation of the plurality of event patterns;

determining an accuracy parameter by comparing the predicted future event pattern with an actual event; and

adjusting the time-slice parameter to increase the accuracy parameter.

17. The method of claim 16, wherein the events are cleansed by removing incorrect temporal data based on associated time stamp information.

18. The method of claim 16, wherein the plurality of events comprise a measurement history database, an alerts database, an alarm database and a weather history database.

19. The method of claim 16, wherein the plurality of event patterns is indicative of the past and present events.

20. The method of claim 16, wherein analyzing the plurality of events is performed using time domain correlation.

21. The method of claim 16, wherein analyzing the plurality of events is performed using frequency domain correlation.

22. The method of claim 20, wherein time domain correlation is performed using auto correlation.

23. The method of claim 20, wherein time domain correlation is performed using cross correlation.

24. The method of claim 21, wherein frequency domain correlation is performed using mathematical transforms.

25. The method of claim 21, wherein frequency domain correlation is performed using a Fast Fourier transform.

26. The method of claim 21, wherein frequency domain correlation is performed using Fractional Fourier transforms.

27. The method of claim 16, wherein prediction comprises using method of forecasting selected from the group consisting of regression analysis, Monte-Carlo simulation, artificial neural network, recurrence quantification analysis, correlation dimension and nonlinear autoregressive exogenous model.

28. A computer implemented system for monitoring performance and predicting reliability of equipment in electrical grid network comprising:

an integration module configured to aggregate a plurality of events using measurements from at least one equipment connected to an electrical grid network;

an analysis module configured to apply a time-slice parameter to the plurality of events to recognize at least one event pattern within the time-slice;

a database configured to store the time-slice parameter and at least one event;

a prediction module configured to predict a future event pattern based on correlation of the plurality of event patterns; and

a feedback module configured to determine an accuracy parameter by comparing the predicted future event pattern with an actual event and adjust the time-slice parameter to increase the accuracy parameter.

29. The system of claim 28, wherein the integration module receives events from information technology systems.

30. The system of claim 28, wherein the integration module receives events from operations technology systems.