CN117353462B - Power grid operation monitoring analysis method and platform based on artificial intelligence - Google Patents
Power grid operation monitoring analysis method and platform based on artificial intelligence Download PDFInfo
- Publication number
- CN117353462B CN117353462B CN202311630303.7A CN202311630303A CN117353462B CN 117353462 B CN117353462 B CN 117353462B CN 202311630303 A CN202311630303 A CN 202311630303A CN 117353462 B CN117353462 B CN 117353462B
- Authority
- CN
- China
- Prior art keywords
- power grid
- grid operation
- monitoring
- data
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 166
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 23
- 238000004458 analytical method Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000010586 diagram Methods 0.000 claims description 20
- 238000004088 simulation Methods 0.000 claims description 20
- 238000012423 maintenance Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 5
- 230000035945 sensitivity Effects 0.000 claims description 5
- 238000012800 visualization Methods 0.000 claims description 3
- 238000005065 mining Methods 0.000 abstract description 3
- 238000003745 diagnosis Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/001—Methods to deal with contingencies, e.g. abnormalities, faults or failures
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Abstract
The invention discloses an artificial intelligence-based power grid operation monitoring analysis method and platform, and relates to the technical field of power grid operation monitoring, wherein the method comprises the following steps: collecting power grid operation data from a power grid operation monitoring center of a power supply company; analyzing and processing the power grid operation data, and establishing a power grid operation fault prediction model; the method comprises the steps of visualizing power grid operation data acquired in real time to form a power grid operation real-time monitoring large screen; and carrying out fault prediction by using a power grid operation fault prediction model, acquiring the expected fault occurrence position and the expected fault type in the power grid according to a prediction result, and displaying the expected fault occurrence position and the expected fault type in a monitoring large screen in a marked manner. The mining and analysis of the power grid operation data are further enhanced, more useful information is extracted, and more scientific and accurate decision support is provided for power grid operation management.
Description
Technical Field
The invention relates to the technical field of power grid operation monitoring, in particular to a power grid operation monitoring analysis method and platform based on artificial intelligence.
Background
The operation monitoring center of the power supply company is an operation management department which is vital to the power supply company and bears important responsibilities of monitoring the operation state, the power load, the fault condition and the like of the power grid equipment. This center is responsible for continuously monitoring the operation of the power system for 24 hours, ensuring the stability and safety of the power supply. Once an abnormal situation is found, a worker operating the monitoring center needs to make judgment and processing in time, so that the stable operation of the power system is ensured, and the power consumption requirement of the society is met. Meanwhile, the operation monitoring center also needs to predict and analyze the demand of the electric power market, and data support is provided for the decision of the company.
Intelligent analysis and application are one of the important development directions of power grid operation monitoring. At present, most power grid operation monitoring systems are still in the primary stage of data analysis and application, and the intelligent degree is not high, so that the mining and analysis of power grid operation data are further enhanced, more useful information is extracted, more scientific and accurate decision support is provided for power grid operation management, and the method is an important research subject for the person in the field.
Disclosure of Invention
The invention provides an artificial intelligence-based power grid operation monitoring analysis method, which comprises the following steps:
step1, collecting power grid operation data from a power grid operation monitoring center of a power supply company;
step2, analyzing and processing the power grid operation data, and establishing a power grid operation fault prediction model;
step3, visualizing the power grid operation data acquired in real time to form a power grid operation real-time monitoring large screen;
step4, performing fault prediction by using a power grid operation fault prediction model, acquiring the expected fault occurrence position and the expected fault type in the power grid according to a prediction result, and displaying the expected fault occurrence position and the expected fault type in a large monitoring screen in a marked mode.
The power grid operation monitoring and analyzing method based on artificial intelligence, which is used for analyzing and processing power grid operation data and establishing a power grid operation fault prediction model, specifically comprises the following substeps:
extracting operation characteristics of power grid operation data to form a power grid operation data characteristic set as an input set;
extracting fault characteristics in the operation and maintenance data of the power grid to form an output set;
and combining the output set training power grid operation fault prediction model.
The power grid operation monitoring analysis method based on the artificial intelligence, wherein the power grid operation fault prediction model is as follows:wherein the if () function has three parameters, separated by commas, the first parameter being the expression +.>Outputting the second parameter +.>Otherwise, outputting a third parameter 0, wherein similarity () is a similarity function, and the third parameter 0 is two parameters, wherein the first parameter PRE (R, cy) is a prediction function, and the second parameter R is used for predicting the power grid operation data characteristics in the next time period cy according to the power grid operation data characteristic set R j The method comprises the steps of representing the characteristics of power grid operation data contained in the occurrence time period of faults of the j-th power grid operation data record in an R data set, returning true if two parameters are similar, otherwise returning false, wherein j takes a value of 1-q, q is the total number of records of the power grid operation data, and the value of _q is _the total number of records of the power grid operation data>Return to b t *λ i >A at μ i Mu is the preset fault detection sensitivity, a i Number indicating i-th monitoring object, b t Representing the monitored value, lambda, of the ith monitored object at the t time stamp i Representing the association coefficient between the ith monitoring object and the fault j, wherein the value of the association coefficient is 1-m, m is the total number of the monitoring objects, and the association coefficient is +.>Is a connector.
The power grid operation monitoring analysis method based on artificial intelligence, which is disclosed by the invention, comprises the following steps of:
drawing a large-scale power supply circuit simulation diagram;
displaying power grid operation data in real time in a large-scale power supply circuit simulation diagram;
visualization of grid operation history data.
The power grid operation monitoring analysis method based on artificial intelligence, which is characterized by carrying out fault prediction by using a power grid operation fault prediction model, acquiring the expected fault occurrence position and the expected fault type in the power grid according to the prediction result, and displaying the expected fault type in a monitoring large screen, specifically comprises the following substeps:
taking the collected monitoring values of all monitoring objects in the last period as an input set, inputting the input set into a power grid operation fault prediction model, and outputting the number of the monitoring object expected to be faulty and the record mark of the power grid operation data;
acquiring the position of the monitoring object in the large monitoring screen according to the number of the monitoring object;
and marking and displaying the expected faults.
The invention also provides a power grid operation monitoring analysis platform based on artificial intelligence, which comprises the following steps: the system comprises a data source access module, a power grid operation fault prediction model training module and a power grid operation monitoring module.
The power grid operation monitoring analysis platform based on the artificial intelligence, wherein the data source access module is used for collecting power grid operation data from a power grid operation monitoring center of a power supply company;
the power grid operation fault prediction model training module is used for analyzing and processing power grid operation data and establishing a power grid operation fault prediction model;
and the power grid operation monitoring module is used for visualizing the power grid operation data acquired in real time to form a power grid operation real-time monitoring large screen.
The power grid operation monitoring and analyzing platform based on artificial intelligence, wherein the power grid operation monitoring module comprises: large-scale power supply line simulation diagram, grid operation history data list, grid operation fault prediction and fault list.
The power grid operation monitoring analysis platform based on the artificial intelligence is characterized in that a large-scale power supply line simulation diagram is used for displaying a power supply line in a city, namely a monitoring object on a power supply line;
the power grid operation historical data list is used for historical monitoring data of each monitoring object;
the power grid operation fault prediction is used for carrying out fault prediction by using a power grid operation fault prediction model, obtaining the expected fault occurrence position and the expected fault type in the power grid according to the prediction result, and displaying the expected fault occurrence position and the expected fault type in a large monitoring screen in a marked manner;
and the fault list is used for displaying the expected fault information.
The beneficial effects achieved by the invention are as follows: the mining and analysis of the power grid operation data are further enhanced, more useful information is extracted, and more scientific and accurate decision support is provided for power grid operation management.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.
Fig. 1 is a flowchart of a method for monitoring and analyzing operation of a power grid based on artificial intelligence according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in fig. 1, a first embodiment of the present invention provides an artificial intelligence-based power grid operation monitoring and analyzing method, which includes:
step S10: collecting power grid operation data from a power grid operation monitoring center of a power supply company;
the power grid operation data comprise power grid monitoring data, power grid performance data and power grid operation and maintenance data;
and the corresponding data acquisition API acquires power grid operation data by calling a power grid operation monitoring center, so that data support is provided for subsequent data analysis.
Step S20: analyzing and processing the power grid operation data, and establishing a power grid operation fault prediction model;
(1) extracting operation characteristics of power grid operation data to form a power grid operation data characteristic set as an input set;
extracting useful features from the collected data to describe grid operating conditions and performance; and setting weights for the power grid performance data according to the influence degree of each performance index on the power grid operation, and calculating the overall performance value of the power grid performance according to the weights to be used as the characteristic of the power grid performance data. The formula for calculating the overall performance value of the power grid performance is:wherein per t For the whole power grid performance value under the t time stamp, the t takes the value of 1-n, n is the total number of records of the power grid performance data, and each record contains z performance indexes, me p The value of the p-th performance index under the t time stamp is represented, and the p takes the value of 1-z, w p Is the weight of the p-th performance index.
The power grid operation data feature set is expressed as:wherein per t For the whole power grid performance value under the t time stamp, namely the characteristic of the power grid performance data, the t takes the value of 1-n, n is the total record number of the power grid performance data, and MS t For the grid monitoring data set under the t time stamp,wherein a is i Number indicating i-th monitoring object, b i And (3) representing the monitoring value of the ith monitoring object, wherein the value of i is 1-m, and m is the total number of the monitoring objects.
(2) Extracting fault characteristics in the operation and maintenance data of the power grid to form an output set;
the power grid operation and maintenance data refer to the type of faults diagnosed after operation and maintenance personnel analyze and check historical power grid operation abnormal data, and describe and record the data, and the power grid monitoring data and the power grid performance data in the same period can be positioned according to the occurrence time of the problems in the power grid operation and maintenance data, and the two types of data are dependent data of fault diagnosis. Thus, the extracted fault signature is descriptive of the type of fault caused by the grid operation anomaly data.
Encoding the fault type to form an output set, wherein the output set is expressed as:wherein delta j For fault occurrence time period recorded in operation and maintenance data of j-th power grid, f j And j takes a value of 1-q as the fault type recorded in the j-th power grid operation and maintenance data, wherein q is the total recorded number of the power grid operation and maintenance data.
(3) Combining the output set training power grid operation fault prediction model;
the power grid operation fault prediction model obtained after training is completed is as follows:wherein the if () function has three parameters, separated by commas, the first parameter being the expression +.>Outputting the second parameter +.>Otherwise, outputting a third parameter 0, wherein similarity () is a similarity function, and the third parameter 0 is two parameters, wherein the first parameter PRE (R, cy) is a prediction function, and the second parameter R is used for predicting the power grid operation data characteristics in the next time period cy according to the power grid operation data characteristic set R j The method comprises the steps of representing the characteristics of power grid operation data contained in the occurrence time period of faults of the j-th power grid operation data record in an R data set, returning true if two parameters are similar, otherwise returning false, wherein j takes a value of 1-q, q is the total number of records of the power grid operation data, and the value of _q is _the total number of records of the power grid operation data>Return to b t *λ i >A at μ i Mu is the preset fault detection sensitivity, a i Number indicating i-th monitoring object, b t Representing under t time stampMonitoring value, lambda of the ith monitored object i Representing the association coefficient between the ith monitoring object and the fault j, wherein the value of the association coefficient is 1-m, m is the total number of the monitoring objects, and the association coefficient is +.>Is a connector. />Wherein, the method comprises the steps of, wherein,() For cyclic calculation of the bracketed sub-result when k is 1-cy, cy is the prediction period, k represents the timestamp in the prediction period, ζ k Representing the change increment and per of the whole power grid performance value under t-1 time stamps t -per t-1 Calculating the change trend of the whole power grid performance value under t-1 time stamps, and +.>For the connector->() Calculating i as 1~m for the loop and the result of the formula in brackets, m as the total number of monitoring objects, b t Representing the monitored value, b, of the ith monitored object at the t time stamp t -b t-1 Calculating the change trend, theta, of the monitoring value of the ith monitoring object under the t-1 time stamp i Delta, gamma, for the ith monitored object t And taking the values of 0 and 1 as the running mark of the ith monitoring object under the t time stamp to respectively represent whether the monitoring object is in a running state or not.
Step S30: the method comprises the steps of visualizing power grid operation data acquired in real time to form a power grid operation real-time monitoring large screen;
(1) drawing a large-scale power supply circuit simulation diagram;
according to the actual power supply line, the power supply line, namely the monitoring object on the line, is drawn, a map is used for wrapping a city, and the physical positions of the drawn monitoring object and the important line are marked by combining with a city map.
(2) Displaying power grid operation data in real time in a large-scale power supply circuit simulation diagram;
the power grid operation data comprise real-time monitoring data of each monitoring object, a display list is set for each monitoring object in the graph, each monitoring data of the monitoring object is displayed in the display list, the default display list is in a retracted state, and the mouse is unfolded when moving to the monitoring object.
(3) Visualization of grid operation history data;
the grid operation history data is displayed in a tabular mode.
The power grid operation historical data is not displayed in the large-scale power supply line simulation diagram, and two methods are available for checking, namely, by double-clicking a monitoring object icon in the large-scale power supply line simulation diagram, skipping to a power grid operation historical data page, and displaying historical monitoring data of the double-clicked monitoring object in a table form; and secondly, directly entering a power grid operation historical data page, checking historical monitoring data of all monitoring objects, and setting screening conditions through a screening frame to search required data.
Step S40: performing fault prediction by using a power grid operation fault prediction model, acquiring a predicted fault occurrence position and a predicted fault type in a power grid according to a prediction result, and displaying a large monitoring screen in a marked manner;
(1) taking the collected monitoring values of all monitoring objects in the last period as an input set, inputting the input set into a power grid operation fault prediction model, and outputting the number of the monitoring object expected to be faulty and the record mark of the power grid operation data;
the power grid operation fault prediction model is used for predicting whether faults occur in a future period, wherein the future period is a prediction period, and the monitoring values of all monitoring objects in the latest period are the monitoring values of all monitoring objects in the period which is the same as the prediction period in length and is closest to the starting time of the prediction period;
(2) acquiring the position of the monitoring object in the large monitoring screen according to the number of the monitoring object;
basic information of each monitoring object is maintained in a database, the basic information comprises element IDs of each monitoring object in a large-scale power supply line simulation diagram, and the positions of the monitoring objects in a large screen can be obtained by inquiring the element IDs according to numbers.
(3) Marking and displaying the expected faults;
the method comprises the steps that corresponding elements of a monitored object with faults in a large screen are marked, the color is set to be red, a fault list is set on the large screen, and the monitored object in the record can be displayed in the center of the large screen and amplified by double clicking on the record in the fault list for rapid positioning.
The record mark can be positioned to the record according to the power grid operation data, and fault related information in the record is acquired, including fault type, diagnosis information and the like. The acquired fault related information is displayed in a fault list.
Example two
The first embodiment of the invention provides an artificial intelligence-based power grid operation monitoring analysis platform, which comprises: the system comprises a data source access module, a power grid operation fault prediction model training module and a power grid operation monitoring module;
(1) The data source access module is used for collecting power grid operation data from a power grid operation monitoring center of a power supply company. The power grid operation data comprise power grid monitoring data, power grid performance data and power grid operation and maintenance data;
and the corresponding data acquisition API acquires power grid operation data by calling a power grid operation monitoring center, so that data support is provided for subsequent data analysis.
(2) And the power grid operation fault prediction model training module is used for analyzing and processing power grid operation data and establishing a power grid operation fault prediction model.
(1) Extracting operation characteristics of power grid operation data to form a power grid operation data characteristic set as an input set;
extracting useful features from the collected data to describe grid operating conditions and performance; setting weights for the power grid performance data according to the influence degree of each performance index on the power grid operation, and calculating the overall performance value of the power grid performance according to the weights to serve as the characteristics of the power grid performance data. The formula for calculating the overall performance value of the power grid performance is:wherein per t For the whole power grid performance value under the t time stamp, the t takes the value of 1-n, n is the total number of records of the power grid performance data, and each record contains z performance indexes, me p The value of the p-th performance index under the t time stamp is represented, and the p takes the value of 1-z, w p Is the weight of the p-th performance index.
The power grid operation data feature set is expressed as:wherein per t For the whole power grid performance value under the t time stamp, namely the characteristic of the power grid performance data, the t takes the value of 1-n, n is the total record number of the power grid performance data, and MS t For the grid monitoring data set under the t time stamp, < >>Wherein a is i Number indicating i-th monitoring object, b i And (3) representing the monitoring value of the ith monitoring object, wherein the value of i is 1-m, and m is the total number of the monitoring objects.
(2) Extracting fault characteristics in the operation and maintenance data of the power grid to form an output set;
the power grid operation and maintenance data refer to the type of faults diagnosed after operation and maintenance personnel analyze and check historical power grid operation abnormal data, and describe and record the data, and the power grid monitoring data and the power grid performance data in the same period can be positioned according to the occurrence time of the problems in the power grid operation and maintenance data, and the two types of data are dependent data of fault diagnosis. Thus, the extracted fault signature is descriptive of the type of fault caused by the grid operation anomaly data.
Encoding the fault type to form an output set, wherein the output set is expressed as:wherein delta j For fault occurrence time period recorded in operation and maintenance data of j-th power grid, f j For the j-th electric networkAnd j takes values of 1-q as the total number of records of the operation and maintenance data of the power grid.
(3) Combining the output set training power grid operation fault prediction model;
the power grid operation fault prediction model obtained after training is completed is as follows:wherein the if () function has three parameters, separated by commas, the first parameter being the expression +.>Outputting the second parameter when the expression is establishedOtherwise, outputting a third parameter 0, wherein similarity () is a similarity function, and the third parameter 0 is two parameters, wherein the first parameter PRE (R, cy) is a prediction function, and the second parameter R is used for predicting the power grid operation data characteristics in the next time period cy according to the power grid operation data characteristic set R j The method comprises the steps of representing the characteristics of power grid operation data contained in the occurrence time period of faults of the j-th power grid operation data record in an R data set, returning true if two parameters are similar, otherwise returning false, wherein j takes a value of 1-q, q is the total number of records of the power grid operation data, and the value of _q is _the total number of records of the power grid operation data>Return to b t *λ i >A at μ i Mu is the preset fault detection sensitivity, a i Number indicating i-th monitoring object, b t Representing the monitored value, lambda, of the ith monitored object at the t time stamp i Representing the association coefficient between the ith monitoring object and the fault j, wherein the value of the association coefficient is 1-m, m is the total number of the monitoring objects, and the association coefficient is +.>Is a connector.Wherein->() For cyclic calculation of the bracketed sub-result when k is 1-cy, cy is the prediction period, k represents the timestamp in the prediction period, ζ k Representing the change increment and per of the whole power grid performance value under t-1 time stamps t -per t-1 Calculating the change trend of the whole power grid performance value under t-1 time stamps, and +.>For the connector->() Calculating i as 1~m for the loop and the result of the formula in brackets, m as the total number of monitoring objects, b t Representing the monitored value, b, of the ith monitored object at the t time stamp t -b t-1 Calculating the change trend, theta, of the monitoring value of the ith monitoring object under the t-1 time stamp i Delta, gamma, for the ith monitored object t And taking the values of 0 and 1 as the running mark of the ith monitoring object under the t time stamp to respectively represent whether the monitoring object is in a running state or not.
(3) And the power grid operation monitoring module is used for visualizing the power grid operation data acquired in real time to form a power grid operation real-time monitoring large screen.
The power grid operation monitoring module comprises: large-scale power supply line simulation diagram, grid operation history data list, grid operation fault prediction and fault list.
1. The large-scale power supply line simulation diagram is used for displaying a power supply line in a city, namely a monitoring object on a power supply line.
(1) Drawing a large-scale power supply circuit simulation diagram;
according to the actual power supply line, the power supply line, namely the monitoring object on the line, is drawn, a map is used for wrapping a city, and the physical positions of the drawn monitoring object and the important line are marked by combining with a city map.
(2) Displaying power grid operation data in real time in a large-scale power supply circuit simulation diagram;
the power grid operation data comprise real-time monitoring data of each monitoring object, a display list is set for each monitoring object in the graph, each monitoring data of the monitoring object is displayed in the display list, the default display list is in a retracted state, and the mouse is unfolded when moving to the monitoring object.
2. And the power grid operation historical data list is used for historical monitoring data of each monitoring object.
The grid operation history data is displayed in a tabular mode.
The power grid operation historical data is not displayed in the large-scale power supply line simulation diagram, and two methods are available for checking, namely, by double-clicking a monitoring object icon in the large-scale power supply line simulation diagram, skipping to a power grid operation historical data page, and displaying historical monitoring data of the double-clicked monitoring object in a table form; and secondly, directly entering a power grid operation historical data page, checking historical monitoring data of all monitoring objects, and setting screening conditions through a screening frame to search required data.
3. And the power grid operation fault prediction is used for carrying out fault prediction by using a power grid operation fault prediction model, acquiring the expected fault occurrence position and the expected fault type in the power grid according to the prediction result, and displaying the expected fault occurrence position and the expected fault type in a monitoring large screen in a marked manner.
(1) Taking the collected monitoring values of all monitoring objects in the last period as an input set, inputting the input set into a power grid operation fault prediction model, and outputting the number of the monitoring object expected to be faulty and the record mark of the power grid operation data;
the power grid operation fault prediction model is used for predicting whether faults occur in a future period, wherein the future period is a prediction period, and the monitoring values of all monitoring objects in the latest period are the monitoring values of all monitoring objects in the period which is the same as the prediction period in length and is closest to the starting time of the prediction period;
(2) acquiring the position of the monitoring object in the large monitoring screen according to the number of the monitoring object;
basic information of each monitoring object is maintained in a database, the basic information comprises element IDs of each monitoring object in a large-scale power supply line simulation diagram, and the positions of the monitoring objects in a large screen can be obtained by inquiring the element IDs according to numbers.
(3) Marking and displaying the expected faults;
and marking the corresponding elements of the failed monitoring object in the large screen, and setting the color as red.
4. And the fault list is used for displaying the expected fault information.
And setting a fault list on the large screen, and double-clicking the record in the fault list can display the monitored object in the record in the center of the large screen and enlarge the monitored object for quick positioning.
The record mark can be positioned to the record according to the power grid operation data, and fault related information in the record is acquired, including fault type, diagnosis information and the like. The acquired fault related information is displayed in a fault list.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention in further detail, and are not to be construed as limiting the scope of the invention, but are merely intended to cover any modifications, equivalents, improvements, etc. based on the teachings of the invention.
Claims (7)
1. An artificial intelligence-based power grid operation monitoring analysis method comprises the following steps:
step1, collecting power grid operation data from a power grid operation monitoring center of a power supply company;
step2, analyzing and processing the power grid operation data, and establishing a power grid operation fault prediction model;
step3, visualizing the power grid operation data acquired in real time to form a power grid operation real-time monitoring large screen;
step4, performing fault prediction by using a power grid operation fault prediction model, acquiring the expected fault occurrence position and the expected fault type in the power grid according to a prediction result, and marking and displaying in a monitoring large screen;
the analyzing and processing of the power grid operation data specifically comprises the following steps: setting weights for the power grid operation data according to the influence degree of each performance index on the power grid operation, and calculating the overall performance value of the power grid performance according to the weights, wherein the formula for calculating the overall performance value of the power grid performance is as follows:wherein->For the whole power grid performance value under the t time stamp, t takes the value of 1-n, n is the total number of records of the power grid performance data, each record contains z performance indexes, and +>A value representing the p-th performance indicator at t time stamp, p being 1~z, < ->The weight of the p-th performance index;
the power grid operation fault prediction model is as follows:wherein the if () function has three parameters, separated by commas, the first parameter being the expression +.>Outputting the second parameter +.>Otherwise, outputting a third parameter 0, wherein similarity () is a similarity function, and the third parameter 0 is two parameters, wherein the first parameter PRE (R, cy) is a prediction function, and the second parameter R is used for predicting the power grid operation data characteristics in the next time period cy according to the power grid operation data characteristic set R j Representing the characteristics of the power grid operation data contained in the fault occurrence time period of the j-th power grid operation data record in the R data set, and returning if the two parameters are similartrue, otherwise, returning false, wherein j takes a value of 1-q, q is the total number of records of the operation and maintenance data of the power grid, and the value is +.>Return to b t *λ i >A at μ i Mu is the preset fault detection sensitivity, a i Number indicating i-th monitoring object, b t Representing the monitored value, lambda, of the ith monitored object at the t time stamp i Representing the association coefficient between the ith monitoring object and the fault j, wherein the value of the association coefficient is 1-m, m is the total number of the monitoring objects, and the association coefficient is +.>Is a connector.
2. The method for monitoring and analyzing power grid operation based on artificial intelligence according to claim 1, wherein the method is characterized by analyzing and processing power grid operation data and establishing a power grid operation fault prediction model, and specifically comprises the following substeps:
extracting operation characteristics of power grid operation data to form a power grid operation data characteristic set as an input set;
extracting fault characteristics in the operation and maintenance data of the power grid to form an output set;
and combining the output set training power grid operation fault prediction model.
3. The method for monitoring and analyzing the operation of the power grid based on the artificial intelligence according to claim 1, wherein the method is characterized in that the power grid operation data acquired in real time are visualized to form a large power grid operation real-time monitoring screen, and specifically comprises the following substeps:
drawing a large-scale power supply circuit simulation diagram;
displaying power grid operation data in real time in a large-scale power supply circuit simulation diagram;
visualization of grid operation history data.
4. The method for monitoring and analyzing the operation of the power grid based on the artificial intelligence according to claim 1, wherein the power grid operation fault prediction model is used for carrying out fault prediction, the expected fault occurrence position and the expected fault type in the power grid are obtained according to the prediction result, and the expected fault type are marked and displayed on a large monitor screen, and the method specifically comprises the following substeps:
taking the collected monitoring values of all monitoring objects in the last period as an input set, inputting the input set into a power grid operation fault prediction model, and outputting the number of the monitoring object expected to be faulty and the record mark of the power grid operation data;
acquiring the position of the monitoring object in the large monitoring screen according to the number of the monitoring object;
and marking and displaying the expected faults.
5. An artificial intelligence-based power grid operation monitoring analysis platform, comprising: the system comprises a data source access module, a power grid operation fault prediction model training module and a power grid operation monitoring module;
the data source access module is used for collecting power grid operation data from a power grid operation monitoring center of a power supply company;
the power grid operation fault prediction model training module is used for analyzing and processing power grid operation data and establishing a power grid operation fault prediction model;
the power grid operation monitoring module is used for visualizing the power grid operation data acquired in real time to form a power grid operation real-time monitoring large screen;
the analyzing and processing of the power grid operation data specifically comprises the following steps: setting weights for the power grid operation data according to the influence degree of each performance index on the power grid operation, and calculating the overall performance value of the power grid performance according to the weights, wherein the formula for calculating the overall performance value of the power grid performance is as follows:wherein->For the whole power grid performance value under the t time stamp, taking the value of t as 1-n, wherein n is the total number of records of the power grid performance data, and each record is provided withComprises z performance indexes, me p A value representing the p-th performance indicator at t time stamp, p being 1~z, < ->The weight of the p-th performance index;
the power grid operation fault prediction model is as follows:wherein the if () function has three parameters, separated by commas, the first parameter being the expression +.>Outputting the second parameter +.>Otherwise, outputting a third parameter 0, wherein similarity () is a similarity function, and the third parameter 0 is two parameters, wherein the first parameter PRE (R, cy) is a prediction function, and the second parameter R is used for predicting the power grid operation data characteristics in the next time period cy according to the power grid operation data characteristic set R j The method comprises the steps of representing the characteristics of power grid operation data contained in the occurrence time period of faults of the j-th power grid operation data record in an R data set, returning true if two parameters are similar, otherwise returning false, wherein j takes a value of 1-q, q is the total number of records of the power grid operation data, and the value of _q is _the total number of records of the power grid operation data>Return to b t *λ i >A at μ i Mu is the preset fault detection sensitivity, a i Number indicating i-th monitoring object, b t Representing the monitored value, lambda, of the ith monitored object at the t time stamp i Representing the association coefficient between the ith monitoring object and the fault j, wherein the value of the association coefficient is 1-m, m is the total number of the monitoring objects, and the association coefficient is +.>Is a connector.
6. The artificial intelligence based power grid operation monitoring and analysis platform of claim 5, wherein the power grid operation monitoring module comprises: large-scale power supply line simulation diagram, grid operation history data list, grid operation fault prediction and fault list.
7. The artificial intelligence-based power grid operation monitoring analysis platform according to claim 6, wherein the large-scale power supply line simulation diagram is used for displaying a power supply line in a city, namely a monitored object on a power supply line;
the power grid operation historical data list is used for historical monitoring data of each monitoring object;
the power grid operation fault prediction is used for carrying out fault prediction by using a power grid operation fault prediction model, obtaining the expected fault occurrence position and the expected fault type in the power grid according to the prediction result, and displaying the expected fault occurrence position and the expected fault type in a large monitoring screen in a marked manner;
and the fault list is used for displaying the expected fault information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311630303.7A CN117353462B (en) | 2023-12-01 | 2023-12-01 | Power grid operation monitoring analysis method and platform based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311630303.7A CN117353462B (en) | 2023-12-01 | 2023-12-01 | Power grid operation monitoring analysis method and platform based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117353462A CN117353462A (en) | 2024-01-05 |
| CN117353462B true CN117353462B (en) | 2024-02-20 |
Family
ID=89371337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311630303.7A Active CN117353462B (en) | 2023-12-01 | 2023-12-01 | Power grid operation monitoring analysis method and platform based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117353462B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008052042A2 (en) * | 2006-10-24 | 2008-05-02 | Edsa Micro Corporation | Systems and methods for a real-time synchronized electrical power system simulator for 'what-if' analysis and prediction over electrical power networks |
| CN109615226A (en) * | 2018-12-12 | 2019-04-12 | 焦点科技股份有限公司 | A kind of operation indicator method for monitoring abnormality |
| CN113962659A (en) * | 2021-10-25 | 2022-01-21 | 国网山东省电力公司平邑县供电公司 | Cloud computing-based smart power grid big data information management system and method |
| CN116451876A (en) * | 2023-06-15 | 2023-07-18 | 国网江西省电力有限公司信息通信分公司 | Power distribution network fault prediction and active overhaul system based on artificial intelligence |
| CN116468243A (en) * | 2023-04-24 | 2023-07-21 | 云南电网有限责任公司昭通供电局 | Power grid trend early warning method based on monitoring operation data |
| CN116862194A (en) * | 2023-07-31 | 2023-10-10 | 国网青海省电力公司 | Analysis, operation and detection system based on power grid business data |
-
2023
- 2023-12-01 CN CN202311630303.7A patent/CN117353462B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008052042A2 (en) * | 2006-10-24 | 2008-05-02 | Edsa Micro Corporation | Systems and methods for a real-time synchronized electrical power system simulator for 'what-if' analysis and prediction over electrical power networks |
| CN109615226A (en) * | 2018-12-12 | 2019-04-12 | 焦点科技股份有限公司 | A kind of operation indicator method for monitoring abnormality |
| CN113962659A (en) * | 2021-10-25 | 2022-01-21 | 国网山东省电力公司平邑县供电公司 | Cloud computing-based smart power grid big data information management system and method |
| CN116468243A (en) * | 2023-04-24 | 2023-07-21 | 云南电网有限责任公司昭通供电局 | Power grid trend early warning method based on monitoring operation data |
| CN116451876A (en) * | 2023-06-15 | 2023-07-18 | 国网江西省电力有限公司信息通信分公司 | Power distribution network fault prediction and active overhaul system based on artificial intelligence |
| CN116862194A (en) * | 2023-07-31 | 2023-10-10 | 国网青海省电力公司 | Analysis, operation and detection system based on power grid business data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117353462A (en) | 2024-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101354316A (en) | Fleet anomaly detection method | |
| CN107122298A (en) | The methods of exhibiting of visual software development process quality | |
| CN112083244B (en) | Integrated intelligent diagnosis system for faults of avionic equipment | |
| CN109165242B (en) | Fault diagnosis and early warning method based on entropy sorting and space-time analysis | |
| CN113902241A (en) | Power grid equipment maintenance strategy system and method based on comprehensive state evaluation | |
| CN110703743A (en) | Equipment failure prediction and detection system and method | |
| CN110728381A (en) | Intelligent power plant inspection method and system based on RFID and data processing | |
| JP2012018623A (en) | Abnormality data analysis system | |
| CN113468022B (en) | Automatic operation and maintenance method for centralized monitoring of products | |
| CN111768022A (en) | Equipment detection method and device for coal machine production equipment | |
| CN115037603A (en) | Diagnosis evaluation method, device and system of electricity consumption information acquisition equipment | |
| CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
| CN113837591A (en) | Equipment health assessment method oriented to multi-working-condition operation conditions | |
| CN117353462B (en) | Power grid operation monitoring analysis method and platform based on artificial intelligence | |
| CN115640860B (en) | Electromechanical equipment remote maintenance method and system for industrial cloud service | |
| CN116986246A (en) | Intelligent inspection system and method for coal conveying belt | |
| CN116185757B (en) | Intelligent monitoring system for energy consumption of machine room | |
| CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
| Sim et al. | Missing Data Imputation Algorithm for Transmission Systems Based on Multivariate Imputation With Principal Component Analysis | |
| CN113036917B (en) | Power distribution network monitoring information monitoring system and method based on machine learning | |
| CN112732773B (en) | Method and system for checking uniqueness of relay protection defect data | |
| CN114095335A (en) | Network alarm processing method and device and electronic equipment | |
| CN116956174A (en) | Classification model for cold head state classification detection and life prediction and generation method of prediction model | |
| CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
| CN113435689A (en) | Labeled multi-bin modeling automation equipment state evaluation method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |