CN115800538A - Intelligent power grid operation and maintenance monitoring method and system based on artificial intelligence - Google Patents

Intelligent power grid operation and maintenance monitoring method and system based on artificial intelligence Download PDF

Info

Publication number
CN115800538A
CN115800538A CN202211536392.4A CN202211536392A CN115800538A CN 115800538 A CN115800538 A CN 115800538A CN 202211536392 A CN202211536392 A CN 202211536392A CN 115800538 A CN115800538 A CN 115800538A
Authority
CN
China
Prior art keywords
power grid
operation data
grid operation
data
key information
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.)
Pending
Application number
CN202211536392.4A
Other languages
Chinese (zh)
Inventor
梁晖辉
张凌浩
庞博
刘雪原
周毅
张克利
高二超
程木团
何孝彬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sichuan Chuangshi Huaruan Technology Co ltd
Electric Power Research Institute of State Grid Sichuan Electric Power Co Ltd
Original Assignee
Sichuan Chuangshi Huaruan Technology Co ltd
Electric Power Research Institute of State Grid Sichuan Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Sichuan Chuangshi Huaruan Technology Co ltd, Electric Power Research Institute of State Grid Sichuan Electric Power Co Ltd filed Critical Sichuan Chuangshi Huaruan Technology Co ltd
Priority to CN202211536392.4A priority Critical patent/CN115800538A/en
Publication of CN115800538A publication Critical patent/CN115800538A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides an artificial intelligence-based intelligent power grid operation and maintenance monitoring method and system, and relates to the technical field of data processing. In the invention, data extraction processing can be firstly carried out on the target power grid component to obtain historical power grid operation data corresponding to the target power grid component; respectively calculating the data correlation degree between the historical power grid operation data and each reference power grid operation data included in a preset reference power grid operation data set; and finally, analyzing and outputting an abnormal degree representation value corresponding to the historical power grid operation data according to the data correlation degree between the historical power grid operation data and each reference power grid operation data and by combining an abnormal degree reference value configured for each reference power grid operation data in advance, and determining a target operation safety degree corresponding to the target power grid component based on the abnormal degree representation value. Based on the above, the reliability of the operation safety analysis can be improved to a certain extent.

Description

Intelligent power grid operation and maintenance monitoring method and system based on artificial intelligence
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent power grid operation and maintenance monitoring method and system based on artificial intelligence.
Background
Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a computer controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence.
Machine Learning (ML) is a multi-domain cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and formula learning.
The operation and maintenance of the power grid generally involve a plurality of layers, which affect the orderly operation of the power grid, so that the power grid needs to be reliably operated and maintained. On the basis of reliable operation maintenance of the power grid, the operation safety of the power grid is effectively monitored, so that the power grid is maintained in time when abnormality occurs, and the fault is avoided from being developed from the abnormality. However, in the prior art, generally, the operation data of a single power device is analyzed, such as threshold comparison, and thus, the reliability of the safety analysis is not high due to the single data analysis basis.
Disclosure of Invention
In view of this, the present invention provides an operation and maintenance monitoring method and system for a smart grid based on artificial intelligence, so as to improve the reliability of operation security analysis to a certain extent.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
an intelligent power grid operation and maintenance monitoring method based on artificial intelligence comprises the following steps:
performing data extraction processing on a target power grid assembly to obtain historical power grid operation data corresponding to the target power grid assembly, wherein the historical power grid operation data comprise historical power parameters of each target power device in the target power grid assembly at a plurality of historical time points, the target power grid assembly comprises a plurality of target power devices, and the plurality of target power devices have correlation;
respectively calculating data correlation between the historical power grid operation data and each reference power grid operation data included in a preset reference power grid operation data set;
and analyzing and outputting an abnormal degree characteristic value corresponding to the historical power grid operation data according to the data correlation degree between the historical power grid operation data and each reference power grid operation data and an abnormal degree reference value configured for each reference power grid operation data in advance, and determining a target operation safety degree corresponding to the target power grid component based on the abnormal degree characteristic value.
In some preferred embodiments, in the method for monitoring operation and maintenance of a smart grid based on artificial intelligence, the step of performing data extraction processing on the target grid component to obtain historical grid operating data corresponding to the target grid component includes:
according to a historical time period, performing data extraction processing on a target power grid component to obtain initial historical power grid operation data corresponding to the target power grid component, wherein the initial historical power grid operation data comprise data of the target power grid component at each time point in the historical time period;
sampling the historical time period to form a plurality of historical time points, wherein the historical time interval lengths among the historical time points have descending corresponding relation along the trend of time;
for each historical time point, extracting historical power parameters of each target power device in the target power grid assembly at the historical time point from the initial historical power grid operation data respectively to obtain historical power grid operation data corresponding to the target power grid assembly.
In some preferred embodiments, in the above method for monitoring operation and maintenance of a smart grid based on artificial intelligence, the step of separately calculating a data correlation between the historical grid operation data and each reference grid operation data included in a preconfigured reference grid operation data set includes:
extracting reference power grid operation data from a plurality of reference power grid operation data included in a preset reference power grid operation data set, and taking the reference power grid operation data and the historical power grid operation data as a data combination of the correlation degree of the data to be calculated;
loading the historical power grid operation data and the reference power grid operation data included in the data combination into an optimized data mining neural network respectively, and mining a power grid operation data key information mining result corresponding to the historical power grid operation data and a power grid operation data key information mining result corresponding to the reference power grid operation data by using the optimized data mining neural network respectively;
and calculating and outputting the matching degree of the key information mining result corresponding to the data combination based on the key information mining result of the power grid operation data corresponding to the historical power grid operation data and the key information mining result of the power grid operation data corresponding to the reference power grid operation data, wherein the matching degree is used as the data correlation degree between the historical power grid operation data and the reference power grid operation data included in the data combination.
In some preferred embodiments, in the above method for monitoring operation and maintenance of a smart grid based on artificial intelligence, the optimization process of the optimized data mining neural network includes:
extracting a plurality of typical power grid operation data, and extracting power grid operation data identification information corresponding to the typical power grid operation data;
mining a key information mining result of the extended power grid operation data corresponding to the at least one typical power grid operation data based on a key information mining result of the power grid operation data corresponding to the at least one typical power grid operation data and corresponding power grid operation data identification information;
optimizing a pre-established initial data mining neural network according to the plurality of typical power grid operation data and the key information mining result of the extended power grid operation data corresponding to the at least one typical power grid operation data to form a corresponding optimized data mining neural network;
the step of extracting a plurality of typical power grid operation data and extracting power grid operation data identification information corresponding to the plurality of typical power grid operation data includes:
extracting a plurality of typical power grid operation data, and screening out at least one first typical power grid operation data from the plurality of typical power grid operation data, wherein the at least one first typical power grid operation data belongs to typical power grid operation data which do not have actual power grid operation data identification information in the plurality of typical power grid operation data; classifying to form at least one corresponding classification identification information based on the key information mining result of the power grid operation data corresponding to the at least one first typical power grid operation data; and for each piece of the first typical power grid operation data, determining power grid operation data identification information corresponding to the first typical power grid operation data according to the classification identification information corresponding to the first typical power grid operation data.
In some preferred embodiments, in the above method for monitoring operation and maintenance of an intelligent power grid based on artificial intelligence, the step of mining the key information mining result of the extended power grid operation data corresponding to the at least one typical power grid operation data based on the key information mining result of the power grid operation data corresponding to the at least one typical power grid operation data and the corresponding identification information of the power grid operation data includes:
mining a first power grid operation data key information mining result corresponding to at least one typical power grid operation data based on a power grid operation data key information mining result corresponding to at least one typical power grid operation data and corresponding power grid operation data identification information;
analyzing and outputting a second power grid operation data key information mining result corresponding to the at least one typical power grid operation data based on a first power grid operation data key information mining result corresponding to the at least one typical power grid operation data;
determining an extended power grid operation data key information mining result corresponding to the at least one typical power grid operation data based on a power grid operation data key information mining result corresponding to the at least one typical power grid operation data, a corresponding first power grid operation data key information mining result and a corresponding second power grid operation data key information mining result;
the step of mining a first power grid operation data key information mining result corresponding to the at least one typical power grid operation data based on a power grid operation data key information mining result corresponding to the at least one typical power grid operation data and corresponding power grid operation data identification information includes:
based on power grid operation data identification information corresponding to at least one typical power grid operation data, attributing the typical power grid operation data with the same corresponding power grid operation data identification information to a power grid operation data set to form at least one power grid operation data set; digging out a key information mining result of the power grid operation data set corresponding to each power grid operation data set based on a key information mining result of the power grid operation data corresponding to typical power grid operation data included in each power grid operation data set; and marking the key information mining result of the power grid operation data set corresponding to the at least one typical power grid operation data pair as the key information mining result of the first power grid operation data of the at least one typical power grid operation data pair.
In some preferred embodiments, in the method for monitoring operation and maintenance of an intelligent power grid based on artificial intelligence, the step of analyzing and outputting a second key information mining result of power grid operation data corresponding to the at least one typical power grid operation data based on a key information mining result of first power grid operation data corresponding to the at least one typical power grid operation data includes:
screening out a to-be-confirmed power grid operation data set corresponding to the at least one typical power grid operation data; analyzing a confirmed power grid operation data set corresponding to the at least one typical power grid operation data in the to-be-confirmed power grid operation data set based on a first power grid operation data key information mining result corresponding to the at least one typical power grid operation data and a power grid operation data set key information mining result corresponding to the to-be-confirmed power grid operation data set;
and marking the key information mining result of the power grid operation data set corresponding to the confirmed power grid operation data set corresponding to the at least one typical power grid operation data as the key information mining result of the second power grid operation data corresponding to the at least one typical power grid operation data.
In some preferred embodiments, in the method for monitoring operation and maintenance of an intelligent power grid based on artificial intelligence, the step of determining an extended power grid operation data key information mining result corresponding to the at least one typical power grid operation data based on a power grid operation data key information mining result corresponding to the at least one typical power grid operation data, a corresponding first power grid operation data key information mining result, and a corresponding second power grid operation data key information mining result includes:
determining a target variable, wherein the target variable has a positive correlation between a current value and an optimization progress for optimizing the initial data mining neural network;
and determining an expanded power grid operation data key information mining result corresponding to the at least one typical power grid operation data based on a power grid operation data key information mining result corresponding to the at least one typical power grid operation data, a corresponding first power grid operation data key information mining result, a corresponding second power grid operation data key information mining result and the target variable.
In some preferred embodiments, in the method for monitoring operation and maintenance of an intelligent power grid based on artificial intelligence, the step of optimizing a pre-established initial data mining neural network according to the key information mining result of the extended power grid operation data corresponding to the plurality of typical power grid operation data and the at least one typical power grid operation data to form an optimized data mining neural network corresponding to the initial data mining neural network includes:
combining to form a first power grid data optimization combination and/or a second power grid data optimization combination based on the key information mining results of the typical power grid operation data and the extended power grid operation data, wherein the typical power grid operation data included in the first power grid data optimization combination is consistent with a power grid operation data set corresponding to the key information mining results of the extended power grid operation data, and the typical power grid operation data included in the second power grid data optimization combination is inconsistent with a power grid operation data set corresponding to the key information mining results of the extended power grid operation data;
and optimizing the pre-established initial data mining neural network based on the first power grid data optimization combination and/or the second power grid data optimization combination to form an optimized data mining neural network corresponding to the initial data mining neural network.
In some preferred embodiments, in the method for monitoring operation and maintenance of an intelligent power grid based on artificial intelligence, the step of analyzing and outputting an abnormal degree characterization value corresponding to the historical power grid operation data according to a data correlation degree between the historical power grid operation data and each reference power grid operation data and in combination with an abnormal degree reference value configured for each reference power grid operation data in advance, and then determining a target operation safety degree corresponding to the target power grid component based on the abnormal degree characterization value includes:
respectively determining a weight coefficient corresponding to each reference power grid operation data according to the data correlation degree between the historical power grid operation data and each reference power grid operation data, wherein the weight coefficient and the data correlation degree can have a positive correlation corresponding relation;
according to a weight coefficient corresponding to each reference power grid operation data, carrying out weighted summation calculation on an abnormal degree reference value configured for each reference power grid operation data in advance so as to output an abnormal degree characterization value corresponding to the historical power grid operation data;
and determining a target operation safety degree corresponding to the target power grid component according to the abnormal degree characteristic value, wherein the target operation safety degree and the abnormal degree characteristic value are in negative correlation.
The embodiment of the invention also provides an artificial intelligence-based intelligent power grid operation and maintenance monitoring system which comprises a processor and a memory, wherein the memory is used for storing the computer program, and the processor is used for executing the computer program so as to realize the artificial intelligence-based intelligent power grid operation and maintenance monitoring method.
According to the method and the system for monitoring the operation and maintenance of the smart power grid based on the artificial intelligence, provided by the embodiment of the invention, data extraction processing can be firstly carried out on a target power grid component to obtain historical power grid operation data corresponding to the target power grid component; respectively calculating the data correlation degree between the historical power grid operation data and each reference power grid operation data included in a preset reference power grid operation data set; and finally, analyzing and outputting an abnormal degree representation value corresponding to the historical power grid operation data according to the data correlation degree between the historical power grid operation data and each reference power grid operation data and by combining an abnormal degree reference value configured for each reference power grid operation data in advance, and determining a target operation safety degree corresponding to the target power grid component based on the abnormal degree representation value. Based on this, because the operation safety analysis is performed from the historical power grid operation data of the target power grid assembly as a whole, rather than performing the safety analysis on the single target power device respectively, and a plurality of target power devices have a correlation relationship, the analysis basis is more sufficient, and the reliability of the operation safety analysis can be improved to a certain extent.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 is a structural block diagram of an artificial intelligence-based smart grid operation and maintenance monitoring system according to an embodiment of the present invention.
Fig. 2 is a schematic flowchart illustrating steps included in the method for monitoring operation and maintenance of an intelligent power grid based on artificial intelligence according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of modules included in the smart grid operation and maintenance monitoring apparatus based on artificial intelligence according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
As shown in fig. 1, an embodiment of the present invention provides an artificial intelligence-based smart grid operation and maintenance monitoring system. The smart grid operation and maintenance monitoring system can comprise a memory and a processor.
It will be appreciated that in some implementations, the memory and processor are electrically connected, directly or indirectly, to enable transfer or interaction of data. For example, they may be electrically connected to each other via one or more communication buses or signal lines. The memory can have stored therein at least one software functional module (computer program) that can be present in the form of software or firmware. The processor may be configured to execute the executable computer program stored in the memory, so as to implement the method for monitoring operation and maintenance of the smart grid based on artificial intelligence provided in the embodiment of the present invention.
It should be appreciated that in some implementations, the Memory may be, but is not limited to, random Access Memory (RAM), read Only Memory (ROM), programmable Read Only Memory (PROM), erasable Read Only Memory (EPROM), electrically Erasable Read Only Memory (EEPROM), and the like. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), a System on Chip (SoC), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
It should be understood that, in some possible embodiments, the structure shown in fig. 1 is only an illustration, and the artificial intelligence based smart grid operation and maintenance monitoring system may further include more or less components than those shown in fig. 1, or have a different configuration than that shown in fig. 1, and for example, may include a communication unit for information interaction with other devices. It should be understood that, in some implementation implementations, the smart grid operation and maintenance monitoring system based on artificial intelligence may be a server with data processing capability, or may also be a server cluster formed based on a combination of servers, and the like.
With reference to fig. 2, an embodiment of the present invention further provides an operation and maintenance monitoring method for an intelligent power grid based on artificial intelligence, which is applicable to the operation and maintenance monitoring system for an intelligent power grid based on artificial intelligence. The method steps defined by the flow related to the artificial intelligence based smart grid operation and maintenance monitoring method can be realized by the artificial intelligence based smart grid operation and maintenance monitoring system.
The specific process shown in FIG. 2 will be described in detail below.
Step S110, data extraction processing is carried out on the target power grid component to obtain historical power grid operation data corresponding to the target power grid component.
In the embodiment of the invention, the intelligent power grid operation and maintenance monitoring system based on artificial intelligence can extract data of a target power grid component to obtain historical power grid operation data corresponding to the target power grid component. The historical grid operation data includes historical power parameters of each target power device in the target grid assembly at a plurality of historical time points, the target grid assembly includes a plurality of target power devices, and the plurality of target power devices have correlation relationships therebetween (the correlation relationship may refer to a relationship on power operation, such as a relationship with electrical connection, or a correlation relationship between operation parameters, such as a relationship with following current change, and the like, and in addition, the specific type of the historical power parameters is not a limitation, and may be a current value, and the like, for example).
Step S120, respectively calculating a data correlation between the historical grid operation data and each reference grid operation data included in the preconfigured reference grid operation data set.
In the embodiment of the present invention, the smart grid operation and maintenance monitoring system based on artificial intelligence may respectively calculate a data correlation between the historical grid operation data and each reference grid operation data included in a preconfigured reference grid operation data set (the reference grid operation data may be grid operation data in the case of a serious fault, a general fault, a minor fault, a normal fault, and the like, and abnormal degree reference values corresponding to the grid operation data in each case are different).
Step S130, analyzing and outputting an abnormal degree characteristic value corresponding to the historical power grid operation data according to the data correlation degree between the historical power grid operation data and each reference power grid operation data and an abnormal degree reference value configured for each reference power grid operation data in advance, and determining a target operation safety degree corresponding to a target power grid component based on the abnormal degree characteristic value.
In the embodiment of the present invention, the smart grid operation and maintenance monitoring system based on artificial intelligence may analyze and output an abnormal degree characteristic value corresponding to the historical grid operation data according to the data correlation between the historical grid operation data and each reference grid operation data and in combination with an abnormal degree reference value configured for each reference grid operation data in advance, and determine a target operation safety degree corresponding to a target grid component based on the abnormal degree characteristic value.
Based on this, because the operation safety analysis is performed from the historical power grid operation data of the target power grid assembly as a whole, rather than performing the safety analysis on the single target power device respectively, and a plurality of target power devices have a correlation relationship, the analysis basis is more sufficient, the reliability of the operation safety analysis can be improved to a certain extent, and the defects in the prior art are overcome.
It should be understood that, in the process of executing the step S110, in some implementation implementations, the following sub-steps may be specifically executed:
according to a historical time period (such as the time duration from the current moment to the previous 10 days, 20 days, one month and the like), performing data extraction processing on a target power grid component to obtain initial historical power grid operation data corresponding to the target power grid component, wherein the initial historical power grid operation data comprise data of the target power grid component at each time point in the historical time period;
sampling the historical time period to form a plurality of historical time points, wherein the lengths of historical time intervals among the historical time points have a decreasing corresponding relationship along the trend of time (for example, data before 10 days can be sampled every hour, data before 5 days can be sampled every 0.5 hour, and data on the latest day can be sampled every 5 minutes);
for each historical time point, extracting historical power parameters of each target power device in the target power grid assembly at the historical time point from the initial historical power grid operation data respectively to obtain historical power grid operation data corresponding to the target power grid assembly.
It should be understood that, in the process of executing the step S120, in some implementation embodiments, the following sub-steps may be specifically executed:
extracting a reference power grid operation data from a plurality of reference power grid operation data included in a pre-configured reference power grid operation data set, and taking the reference power grid operation data and the historical power grid operation data as a data combination of the correlation degree of data to be calculated (based on the data combination, a plurality of corresponding data combinations can be formed for the plurality of reference power grid operation data);
loading the historical power grid operation data and the reference power grid operation data included in the data combination into an optimized data mining neural network respectively, and mining a power grid operation data key information mining result corresponding to the historical power grid operation data and a power grid operation data key information mining result corresponding to the reference power grid operation data by using the optimized data mining neural network respectively (the optimized data mining neural network has a key information mining function which can be obtained by network optimization, and the optimization process can refer to the following related description);
and calculating and outputting a matching degree of a key information mining result corresponding to the data combination as a data correlation degree between the historical power grid operation data and the reference power grid operation data included in the data combination based on a power grid operation data key information mining result corresponding to the historical power grid operation data and a power grid operation data key information mining result corresponding to the reference power grid operation data (for example, when the expression form of the power grid operation data key information mining result and the power grid operation data key information mining result is a vector, calculating a vector distance between the power grid operation data key information mining result and the power grid operation data key information mining result, and calculating a corresponding data correlation degree according to the vector distance obtained by analysis, such as negative correlation between the two, wherein the optimized data mining neural network can comprise a feature mining model for feature mining so as to obtain a key information mining result represented by the vector).
It should be understood that, in the process of executing step S120, in order to facilitate that the optimized data mining neural network may effectively perform mining of key information, the historical grid operation data and the reference grid operation data may also be preprocessed, so as to load the preprocessed historical grid operation data and the preprocessed reference grid operation data into the optimized data mining neural network, and respectively mine a corresponding grid operation data key information mining result and a corresponding grid operation data key information mining result by using the optimized data mining neural network, where in some implementation manners, the preprocessing specifically may include the following sub-steps:
classifying historical power parameters included in the historical power grid operation data according to corresponding target power devices to obtain a plurality of historical power parameter sets corresponding to the target power devices, and then respectively carrying out serialization processing on the historical power parameters included in each historical power parameter set according to corresponding historical time points to form a historical power parameter sequence corresponding to each target power device and a plurality of historical power parameter sequences corresponding to the target power devices;
for each historical power parameter sequence, constructing a corresponding historical power parameter variation amplitude sequence based on the historical power parameter sequence, wherein in the historical power parameter variation amplitude sequence, each historical power parameter variation amplitude is equal to a difference value (such as the difference value between the former and the latter) between two adjacent historical power parameters at the corresponding sequence position in the historical power parameter sequence;
respectively performing two-dimensional space projection processing on the historical power parameter change amplitude included in each historical power parameter change amplitude sequence based on corresponding historical time points to form two-dimensional space coordinate points corresponding to each historical power parameter change amplitude, then connecting every two adjacent two-dimensional space coordinate points through a straight line segment to form a straight line segment connection path corresponding to each historical power parameter change amplitude sequence, and performing curve fitting processing on the two-dimensional space coordinate points to form a curve path corresponding to the historical power parameter change amplitude sequence;
for each curve path, respectively performing difference calculation on the historical power parameter change amplitude corresponding to each two adjacent peak points in the curve path to obtain a historical power parameter change amplitude difference value between each two adjacent peak points, then performing size comparison processing on the historical power parameter change amplitude difference value and a preset difference threshold value, so that under the condition that the historical power parameter change amplitude difference value is greater than or equal to the difference threshold value, a valley point between the two adjacent peak points corresponding to the historical power parameter change amplitude difference value is taken as a dividing point, the curve path is divided on the basis of the dividing point to form a plurality of divided curve path segments corresponding to the curve path, and the straight line segment connecting path corresponding to the curve path is divided on the basis of the plurality of divided curve path segments to form a plurality of divided straight line segment connecting path segments of corresponding number;
for each curve segment included in each of the divided curve path segments, determining a straight line segment corresponding to the curve segment in the corresponding divided straight line segment connection path segment according to the corresponding historical time point, and then adjusting the curve segment according to the straight line segment to form an adjustment curve segment corresponding to the curve segment, wherein a tangent of the adjustment curve segment is parallel to the corresponding straight line segment (the specific adjustment mode is not limited, and the purpose of parallelism can be satisfied);
respectively forming an adjustment curve path corresponding to each historical power parameter variation amplitude sequence according to a corresponding adjustment curve line segment combination, and performing sequence correlation calculation processing on every two historical power parameter sequences in the plurality of historical power parameter sequences according to the adjustment curve paths corresponding to the historical power parameter variation amplitude sequences to output the sequence correlation between every two historical power parameter sequences (for example, the path coincidence degree between two corresponding adjustment curve paths can be used as the sequence correlation degree between the two corresponding historical power parameter sequences);
the plurality of historical power parameter sequences are sorted according to the corresponding sequence relevance to form a historical power parameter sequence ordered set corresponding to the plurality of historical power parameter sequences (in the historical power parameter sequence ordered set, the average value of the sequence relevance between every two adjacent historical power parameter sequences can have the maximum value in various sorts), and the historical power parameter sequence ordered set is networked to form a corresponding historical power parameter distribution network, wherein the historical power parameter distribution network is used as preprocessed historical power grid operation data (in the historical power parameter distribution network, the preprocessing process of the reference power grid operation data can be consistent with the above process, and in addition, the network distribution coordinate of each historical power parameter is determined based on the set position of the corresponding historical power parameter sequence in the historical power parameter sequence ordered set and the corresponding historical time point).
It should be understood that, in some implementation implementations, the optimization process of the optimized data mining neural network may specifically perform the following sub-steps:
extracting a plurality of typical power grid operation data, and extracting power grid operation data identification information corresponding to the plurality of typical power grid operation data (the plurality of typical power grid operation data and the power grid operation data identification information corresponding to the plurality of typical power grid operation data are used as a basis for optimizing an initial data mining neural network, so that the initial data mining neural network has a data key information mining function);
mining a key information mining result of the extended power grid operation data corresponding to the at least one typical power grid operation data based on a key information mining result of the power grid operation data corresponding to the at least one typical power grid operation data and corresponding power grid operation data identification information;
and optimizing the pre-established initial data mining neural network according to the plurality of typical power grid operation data and the key information mining result of the extended power grid operation data corresponding to the at least one typical power grid operation data to form a corresponding optimized data mining neural network (so that on the basis that the plurality of typical power grid operation data are used as the basis for optimization, the key information mining result of the extended power grid operation data corresponding to the at least one typical power grid operation data is mined and also used as the basis for optimization, so that the optimization cost can be reduced to a certain extent, the richness of the optimized data is improved, and the mining function of the optimized data mining neural network is more reliable).
It should be understood that, in the process of performing the step of extracting the plurality of typical grid operation data and extracting the grid operation data identification information corresponding to the plurality of typical grid operation data, in some implementation embodiments, the following sub-steps may be specifically performed:
extracting a plurality of typical power grid operation data, and screening out at least one first typical power grid operation data from the plurality of typical power grid operation data, wherein the at least one first typical power grid operation data belongs to typical power grid operation data which do not have actual power grid operation data identification information in the plurality of typical power grid operation data; classifying to form at least one corresponding classification identification information based on the grid operation data key information mining result corresponding to the at least one first typical grid operation data (for example, the first typical grid operation data with higher matching degree between the corresponding grid operation data key information mining results may be allocated to a classification set, and then the classification identification information, such as a number, etc., corresponding to the classification set is configured); and for each of the first typical grid operation data, determining grid operation data identification information corresponding to the first typical grid operation data according to the classification identification information corresponding to the first typical grid operation data (for example, the grid operation data identification information is used for distinguishing whether the corresponding typical grid operation data are similar or not; in addition, the identification information with the actual grid operation data may be manually labeled).
It should be understood that, in the process of executing the step of mining the extended grid operation data key information mining result corresponding to the at least one typical grid operation data based on the grid operation data key information mining result corresponding to the at least one typical grid operation data and the corresponding grid operation data identification information, in some implementation embodiments, the following sub-steps may be specifically executed:
mining a first power grid operation data key information mining result corresponding to at least one typical power grid operation data based on a power grid operation data key information mining result corresponding to at least one typical power grid operation data and corresponding power grid operation data identification information; analyzing and outputting a second power grid operation data key information mining result corresponding to the at least one typical power grid operation data based on a first power grid operation data key information mining result corresponding to the at least one typical power grid operation data; and determining an extended power grid operation data key information mining result corresponding to the at least one typical power grid operation data based on a power grid operation data key information mining result corresponding to the at least one typical power grid operation data, a corresponding first power grid operation data key information mining result and a corresponding second power grid operation data key information mining result (based on this, an extended power grid operation data key information mining result corresponding to each typical power grid operation data in the at least one typical power grid operation data can be generated through corresponding three key information mining results).
It should be understood that, in the process of executing the step of mining the key information mining result of the first grid operation data corresponding to the at least one typical grid operation data based on the key information mining result of the grid operation data corresponding to the at least one typical grid operation data and the corresponding identification information of the grid operation data, in some implementation embodiments, the following sub-steps may be specifically executed:
based on power grid operation data identification information corresponding to at least one typical power grid operation data, attributing the typical power grid operation data with the same corresponding power grid operation data identification information to a power grid operation data set to form at least one power grid operation data set;
based on a grid operation data key information mining result corresponding to typical grid operation data included in each grid operation data set, respectively mining a grid operation data set key information mining result corresponding to each grid operation data set (illustratively, for each grid operation data set, the grid operation data key information mining result corresponding to the typical grid operation data included in the grid operation data set can be subjected to mean value calculation to obtain a grid operation data set key information mining result corresponding to the grid operation data set;
and marking the key information mining result of the power grid operation data set corresponding to the at least one typical power grid operation data pair as the key information mining result of the first power grid operation data of the at least one typical power grid operation data pair.
It should be understood that, in the process of executing the step of analyzing and outputting the key information mining result of the second grid operation data corresponding to the at least one typical grid operation data based on the key information mining result of the first grid operation data corresponding to the at least one typical grid operation data, in some implementation embodiments, the following sub-steps may be specifically executed:
screening out a to-be-confirmed power grid operation data set corresponding to the at least one typical power grid operation data (for example, at least two other power grid operation data sets except the power grid operation data set corresponding to the typical power grid operation data may be used as any two to-be-confirmed power grid operation data sets corresponding to the typical power grid operation data, or screening is performed based on correlation between power grid operation data identification information corresponding to the typical power grid operation data included in the other power grid operation data sets and power grid operation data identification information corresponding to the typical power grid operation data);
analyzing a confirmed power grid operation data set corresponding to the at least one typical power grid operation data in the to-be-confirmed power grid operation data set based on a first power grid operation data key information mining result corresponding to the at least one typical power grid operation data and a power grid operation data set key information mining result corresponding to the to-be-confirmed power grid operation data set (for example, a matching degree between the first power grid operation data key information mining result and a power grid operation data set key information mining result corresponding to the to-be-confirmed power grid operation data set may be calculated first, and then, the to-be-confirmed power grid operation data set with the matching degree greater than or equal to a matching degree reference value may be marked to form a corresponding confirmed power grid operation data set, and in addition, the to-be-confirmed power grid operation data sets may be one or multiple ones, which is not specifically limited);
and marking the key information mining result of the power grid operation data set corresponding to the confirmed power grid operation data set corresponding to the at least one typical power grid operation data as the key information mining result of the second power grid operation data corresponding to the at least one typical power grid operation data.
It should be understood that, in the process of executing the step of determining the extended grid operation data key information mining result corresponding to the at least one typical grid operation data based on the grid operation data key information mining result corresponding to the at least one typical grid operation data, the corresponding first grid operation data key information mining result, and the corresponding second grid operation data key information mining result, in some implementation embodiments, the following sub-steps may be specifically executed:
determining a target variable, wherein the target variable has a current value having a positive correlation with the optimization progress of optimizing the initial data mining neural network (i.e., the current value of the target variable corresponding to the first optimization may be smaller than the current value of the target variable corresponding to the second optimization, the current value of the target variable corresponding to the second optimization may be smaller than the current value of the target variable corresponding to the third optimization, the current value of the target variable corresponding to the third optimization may be smaller than the current value of the target variable corresponding to the fourth optimization, and so on);
the method comprises the steps of obtaining typical grid operation data, obtaining key information mining results of the power grid operation data corresponding to the typical grid operation data, determining expanded power grid operation data corresponding to the typical grid operation data based on the power grid operation data key information mining results corresponding to the typical grid operation data, obtaining key information of a power grid operation data set corresponding to the typical grid operation data, obtaining key information mining results of other power grid operation data sets similar to the power grid operation data set corresponding to the typical grid operation data by using the key information mining results of the power grid operation data, combining the key information mining results of the typical grid operation data with the key information mining results of the power grid operation data, obtaining key information mining results with richer information, namely the expanded power grid operation data key information mining results of the typical grid operation data, calculating sum values between the second power grid operation data key information mining results and the first power grid operation data key information mining results, performing weighted operation data on the second power grid operation data mining results and the first power grid operation data key information mining results, and performing weighted operation data on the second power grid operation data mining results, and the corresponding to the first power grid operation data, and obtaining the weighted sum of the second power grid operation data mining results, and obtaining the corresponding key information mining results, and obtaining the weighted sum of the second power grid operation data, and obtaining the corresponding key information of the second power grid operation data.
It should be understood that, in the process of executing the step of optimizing the pre-established initial data mining neural network according to the key information mining result of the extended power grid operation data corresponding to the plurality of typical power grid operation data and the at least one typical power grid operation data to form the optimized data mining neural network corresponding to the initial data mining neural network, in some implementation embodiments, the following sub-steps may be specifically executed:
combining to form a first power grid data optimization combination and/or a second power grid data optimization combination based on the key information mining results of the typical power grid operation data and the extended power grid operation data, wherein the typical power grid operation data included in the first power grid data optimization combination is consistent with a power grid operation data set corresponding to the key information mining results of the extended power grid operation data, and the typical power grid operation data included in the second power grid data optimization combination is inconsistent with a power grid operation data set corresponding to the key information mining results of the extended power grid operation data;
and optimizing the pre-established initial data mining neural network based on the first power grid data optimization combination and/or the second power grid data optimization combination to form an optimized data mining neural network corresponding to the initial data mining neural network (that is, the pre-established initial data mining neural network may be optimized based on the first power grid data optimization combination only, the pre-established initial data mining neural network may be optimized based on the second power grid data optimization combination only, and the pre-established initial data mining neural network is also optimized based on the first power grid data optimization combination and the second power grid data optimization combination together, wherein the optimization process may be to optimize network parameters of the initial data mining neural network so that errors obtained based on the optimized parameters are converged, or the optimization times reach reference times and the like, and the errors may be differences between the key information mining results of the extended power grid operation data and the key information mining results of the data mined from the typical power grid operation data by the initial data mining neural network).
It should be understood that, in the process of executing the step S130, in some implementation embodiments, the following sub-steps may be specifically executed:
respectively determining a weight coefficient corresponding to each reference power grid operation data according to the data correlation degree between the historical power grid operation data and each reference power grid operation data, wherein the weight coefficient and the data correlation degree can have a positive correlation correspondence (for example, the sum of the weight coefficients corresponding to each reference power grid operation data can be equal to 1);
according to the weight coefficient corresponding to each reference power grid operation data, performing weighted summation calculation on the abnormal degree reference value configured for each reference power grid operation data in advance to output an abnormal degree representation value (namely a weighted summation value) corresponding to the historical power grid operation data;
and determining a target operation safety degree corresponding to the target power grid component according to the abnormal degree characteristic value, wherein the target operation safety degree and the abnormal degree characteristic value are in negative correlation (namely, the larger the abnormal degree characteristic value is, the lower the target operation safety degree is).
With reference to fig. 3, an embodiment of the present invention further provides an artificial intelligence-based smart grid operation and maintenance monitoring apparatus, which is applicable to the artificial intelligence-based smart grid operation and maintenance monitoring system. The intelligent power grid operation and maintenance monitoring device based on artificial intelligence can comprise software functional modules such as a historical power grid operation data extraction module, a data relevancy calculation module and an operation safety analysis module.
The historical power grid operation data extraction module is used for extracting data of a target power grid assembly to obtain historical power grid operation data corresponding to the target power grid assembly, the historical power grid operation data comprise historical power parameters of each target power device in the target power grid assembly at a plurality of historical time points, the target power grid assembly comprises a plurality of target power devices, and the target power devices have correlation relations; the data relevancy calculation module is used for calculating data relevancy between the historical power grid operation data and each reference power grid operation data included in a preset reference power grid operation data set; the operation safety analysis module is used for analyzing and outputting an abnormal degree characteristic value corresponding to the historical power grid operation data according to the data correlation degree between the historical power grid operation data and each reference power grid operation data and an abnormal degree reference value configured for each reference power grid operation data in advance, and then determining a target operation safety degree corresponding to the target power grid assembly based on the abnormal degree characteristic value.
In summary, according to the method and system for monitoring operation and maintenance of the smart grid based on artificial intelligence provided by the present invention, data extraction processing may be performed on a target grid component to obtain historical grid operation data corresponding to the target grid component; respectively calculating the data correlation degree between the historical power grid operation data and each reference power grid operation data included in a preset reference power grid operation data set; and finally, analyzing and outputting an abnormal degree representation value corresponding to the historical power grid operation data according to the data correlation degree between the historical power grid operation data and each reference power grid operation data and by combining an abnormal degree reference value configured for each reference power grid operation data in advance, and determining a target operation safety degree corresponding to the target power grid component based on the abnormal degree representation value. Based on this, because the operation safety analysis is performed from the historical power grid operation data of the target power grid assembly as a whole, rather than performing the safety analysis on the single target power device respectively, and a plurality of target power devices have a correlation relationship, the analysis basis is more sufficient, and the reliability of the operation safety analysis can be improved to a certain extent.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. An operation and maintenance monitoring method of an intelligent power grid based on artificial intelligence is characterized by comprising the following steps:
performing data extraction processing on a target power grid assembly to obtain historical power grid operation data corresponding to the target power grid assembly, wherein the historical power grid operation data comprise historical power parameters of each target power device in the target power grid assembly at a plurality of historical time points, the target power grid assembly comprises a plurality of target power devices, and the target power devices have correlation relations;
respectively calculating data correlation between the historical power grid operation data and each reference power grid operation data included in a preset reference power grid operation data set;
and analyzing and outputting an abnormal degree representation value corresponding to the historical power grid operation data according to the data correlation degree between the historical power grid operation data and each reference power grid operation data and by combining an abnormal degree reference value configured for each reference power grid operation data in advance, and determining a target operation safety degree corresponding to the target power grid component based on the abnormal degree representation value.
2. The method for monitoring operation and maintenance of the smart grid based on artificial intelligence according to claim 1, wherein the step of performing data extraction processing on the target grid component to obtain historical grid operation data corresponding to the target grid component comprises:
according to a historical time period, data extraction processing is carried out on a target power grid assembly to obtain initial historical power grid operation data corresponding to the target power grid assembly, wherein the initial historical power grid operation data comprise data of each time point of the target power grid assembly in the historical time period;
sampling the historical time period to form a plurality of historical time points, wherein the historical time interval lengths among the historical time points have descending corresponding relation along the trend of time;
for each historical time point, extracting historical power parameters of each target power device in the target power grid assembly at the historical time point from the initial historical power grid operation data respectively to obtain historical power grid operation data corresponding to the target power grid assembly.
3. The method for monitoring the operation and maintenance of the smart grid based on artificial intelligence according to claim 1, wherein the step of calculating the data correlation between the historical grid operation data and each reference grid operation data included in the preconfigured reference grid operation data set comprises:
extracting reference power grid operation data from a plurality of reference power grid operation data included in a preset reference power grid operation data set, and taking the reference power grid operation data and the historical power grid operation data as a data combination of the correlation degree of the data to be calculated;
loading the historical power grid operation data and the reference power grid operation data included in the data combination into an optimized data mining neural network respectively, and mining a power grid operation data key information mining result corresponding to the historical power grid operation data and a power grid operation data key information mining result corresponding to the reference power grid operation data by using the optimized data mining neural network respectively;
and calculating and outputting the matching degree of the key information mining result corresponding to the data combination based on the key information mining result of the power grid operation data corresponding to the historical power grid operation data and the key information mining result of the power grid operation data corresponding to the reference power grid operation data, so as to serve as the data correlation degree between the historical power grid operation data and the reference power grid operation data which are included in the data combination.
4. The artificial intelligence based smart grid operation and maintenance monitoring method of claim 3, wherein the optimization process of the optimized data mining neural network comprises:
extracting a plurality of typical power grid operation data, and extracting power grid operation data identification information corresponding to the plurality of typical power grid operation data;
mining a key information mining result of the extended power grid operation data corresponding to the at least one typical power grid operation data based on a key information mining result of the power grid operation data corresponding to the at least one typical power grid operation data and corresponding power grid operation data identification information;
optimizing a pre-established initial data mining neural network according to the plurality of typical power grid operation data and the key information mining result of the extended power grid operation data corresponding to the at least one typical power grid operation data to form a corresponding optimized data mining neural network;
the step of extracting a plurality of typical power grid operation data and extracting power grid operation data identification information corresponding to the plurality of typical power grid operation data includes:
extracting a plurality of typical power grid operation data, and screening out at least one first typical power grid operation data from the plurality of typical power grid operation data, wherein the at least one first typical power grid operation data belongs to typical power grid operation data which do not have actual power grid operation data identification information in the plurality of typical power grid operation data; classifying to form at least one corresponding classification identification information based on the key information mining result of the power grid operation data corresponding to the at least one first typical power grid operation data; and for each piece of the first typical power grid operation data, determining power grid operation data identification information corresponding to the first typical power grid operation data according to the classification identification information corresponding to the first typical power grid operation data.
5. The method for monitoring operation and maintenance of the smart grid based on artificial intelligence as claimed in claim 4, wherein the step of mining the key information mining result of the extended grid operation data corresponding to the at least one typical grid operation data based on the key information mining result of the grid operation data corresponding to the at least one typical grid operation data and the identification information of the corresponding grid operation data comprises:
mining a first power grid operation data key information mining result corresponding to at least one typical power grid operation data based on a power grid operation data key information mining result corresponding to at least one typical power grid operation data and corresponding power grid operation data identification information;
analyzing and outputting a second power grid operation data key information mining result corresponding to the at least one typical power grid operation data based on a first power grid operation data key information mining result corresponding to the at least one typical power grid operation data;
determining an expanded power grid operation data key information mining result corresponding to the at least one typical power grid operation data based on a power grid operation data key information mining result corresponding to the at least one typical power grid operation data, a corresponding first power grid operation data key information mining result and a corresponding second power grid operation data key information mining result;
the step of mining a first power grid operation data key information mining result corresponding to the at least one typical power grid operation data based on a power grid operation data key information mining result corresponding to the at least one typical power grid operation data and corresponding power grid operation data identification information includes:
based on power grid operation data identification information corresponding to at least one typical power grid operation data, attributing the typical power grid operation data with the same corresponding power grid operation data identification information to a power grid operation data set to form at least one power grid operation data set; digging out a key information mining result of the power grid operation data set corresponding to each power grid operation data set based on a key information mining result of the power grid operation data corresponding to typical power grid operation data included in each power grid operation data set; and marking the key information mining result of the power grid operation data set corresponding to the at least one typical power grid operation data pair as the key information mining result of the first power grid operation data of the at least one typical power grid operation data pair.
6. The method for monitoring operation and maintenance of the smart grid based on artificial intelligence according to claim 5, wherein the step of analyzing and outputting the key information mining result of the second grid operation data corresponding to the at least one typical grid operation data based on the key information mining result of the first grid operation data corresponding to the at least one typical grid operation data comprises:
screening out a to-be-confirmed power grid operation data set corresponding to the at least one typical power grid operation data; analyzing a confirmed power grid operation data set corresponding to the at least one typical power grid operation data in the to-be-confirmed power grid operation data set based on a first power grid operation data key information mining result corresponding to the at least one typical power grid operation data and a power grid operation data set key information mining result corresponding to the to-be-confirmed power grid operation data set;
and marking the key information mining result of the power grid operation data set corresponding to the confirmed power grid operation data set corresponding to the at least one typical power grid operation data as the key information mining result of the second power grid operation data corresponding to the at least one typical power grid operation data.
7. The method for monitoring operation and maintenance of the smart power grid based on artificial intelligence according to claim 5, wherein the step of determining the extended key information mining result of the power grid operation data corresponding to the at least one typical power grid operation data based on the key information mining result of the power grid operation data corresponding to the at least one typical power grid operation data, the corresponding key information mining result of the first power grid operation data, and the corresponding key information mining result of the second power grid operation data comprises:
determining a target variable, wherein the target variable has a positive correlation between a current value and an optimization progress for optimizing the initial data mining neural network;
and determining an extended power grid operation data key information mining result corresponding to the at least one typical power grid operation data based on a power grid operation data key information mining result corresponding to the at least one typical power grid operation data, a corresponding first power grid operation data key information mining result, a corresponding second power grid operation data key information mining result and the target variable.
8. The artificial intelligence based smart grid operation and maintenance monitoring method according to claim 4, wherein the step of optimizing the pre-established initial data mining neural network according to the key information mining result of the extended grid operation data corresponding to the plurality of typical grid operation data and the at least one typical grid operation data to form the optimized data mining neural network corresponding to the initial data mining neural network comprises:
combining to form a first power grid data optimization combination and/or a second power grid data optimization combination based on the key information mining results of the typical power grid operation data and the extended power grid operation data, wherein the typical power grid operation data included in the first power grid data optimization combination is consistent with a power grid operation data set corresponding to the key information mining results of the extended power grid operation data, and the typical power grid operation data included in the second power grid data optimization combination is inconsistent with a power grid operation data set corresponding to the key information mining results of the extended power grid operation data;
and optimizing the pre-established initial data mining neural network based on the first power grid data optimization combination and/or the second power grid data optimization combination to form an optimized data mining neural network corresponding to the initial data mining neural network.
9. The intelligent power grid operation and maintenance monitoring method based on artificial intelligence as claimed in any one of claims 1 to 8, wherein the step of analyzing and outputting an abnormal degree characterization value corresponding to the historical power grid operation data according to the data correlation degree between the historical power grid operation data and each reference power grid operation data and combining an abnormal degree reference value configured for each reference power grid operation data in advance, and then determining a target operation safety degree corresponding to the target power grid component based on the abnormal degree characterization value comprises:
respectively determining a weight coefficient corresponding to each reference power grid operation data according to the data correlation degree between the historical power grid operation data and each reference power grid operation data, wherein the weight coefficient and the data correlation degree can have a positive correlation corresponding relation;
according to a weight coefficient corresponding to each reference power grid operation data, carrying out weighted summation calculation on an abnormal degree reference value configured for each reference power grid operation data in advance so as to output an abnormal degree characterization value corresponding to the historical power grid operation data;
and determining a target operation safety degree corresponding to the target power grid component according to the abnormal degree characteristic value, wherein the target operation safety degree and the abnormal degree characteristic value are in negative correlation.
10. An artificial intelligence based smart grid operation and maintenance monitoring system, comprising a processor and a memory, wherein the memory is used for storing a computer program, and the processor is used for executing the computer program to realize the method of any one of claims 1 to 9.
CN202211536392.4A 2022-12-01 2022-12-01 Intelligent power grid operation and maintenance monitoring method and system based on artificial intelligence Pending CN115800538A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211536392.4A CN115800538A (en) 2022-12-01 2022-12-01 Intelligent power grid operation and maintenance monitoring method and system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211536392.4A CN115800538A (en) 2022-12-01 2022-12-01 Intelligent power grid operation and maintenance monitoring method and system based on artificial intelligence

Publications (1)

Publication Number Publication Date
CN115800538A true CN115800538A (en) 2023-03-14

Family

ID=85444826

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211536392.4A Pending CN115800538A (en) 2022-12-01 2022-12-01 Intelligent power grid operation and maintenance monitoring method and system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN115800538A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116149284A (en) * 2023-04-23 2023-05-23 广东麦可瑞化工科技有限公司 Papermaking defoamer production control method and system
CN117113261A (en) * 2023-10-20 2023-11-24 国网江西省电力有限公司电力科学研究院 Power Internet of things anomaly detection method and system

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116149284A (en) * 2023-04-23 2023-05-23 广东麦可瑞化工科技有限公司 Papermaking defoamer production control method and system
CN116149284B (en) * 2023-04-23 2023-08-04 广东麦可瑞化工科技有限公司 Papermaking defoamer production control method and system
CN117113261A (en) * 2023-10-20 2023-11-24 国网江西省电力有限公司电力科学研究院 Power Internet of things anomaly detection method and system
CN117113261B (en) * 2023-10-20 2024-02-06 国网江西省电力有限公司电力科学研究院 Power Internet of things anomaly detection method and system

Similar Documents

Publication Publication Date Title
CN111368890A (en) Fault detection method and device and information physical fusion system
CN115800538A (en) Intelligent power grid operation and maintenance monitoring method and system based on artificial intelligence
US9379951B2 (en) Method and apparatus for detection of anomalies in integrated parameter systems
CN114090396B (en) Cloud environment multi-index unsupervised anomaly detection and root cause analysis method
CN110059845B (en) Metering device clock error trend prediction method based on time sequence evolution gene model
CN115098705B (en) Network security event analysis method and system based on knowledge graph reasoning
CN105577440A (en) Network fault time location method and analyzing device
CN109409444B (en) Multivariate power grid fault type discrimination method based on prior probability
CN111126820A (en) Electricity stealing prevention method and system
CN116401532B (en) Method and system for recognizing frequency instability of power system after disturbance
CN112070180B (en) Power grid equipment state judging method and device based on information physical bilateral data
CN107274025B (en) System and method for realizing intelligent identification and management of power consumption mode
CN111506636A (en) System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm
Yang et al. Data domain adaptation for voltage stability evaluation considering topology changes
CN115616408A (en) Battery thermal management data processing method and system
CN116757870A (en) Intelligent energy monitoring data processing method and system for energy Internet of things
CN115035966B (en) Superconductor screening method, device and equipment based on active learning and symbolic regression
CN111008673A (en) Method for collecting and extracting malignant data chain in power distribution network information physical system
CN115062686A (en) Multi-KPI (Key performance indicator) time sequence abnormity detection method and system based on multi-angle features
Tian et al. Library-based Fast Algorithm for Simulating the Hodgkin-Huxley Neuronal Networks
CN111476392A (en) Metering device clock error trend prediction method based on social perception
Zhao et al. Research on machine learning-based correlation analysis method for power equipment alarms
CN114741673B (en) Behavior risk detection method, clustering model construction method and device
CN113435915B (en) Method, device, equipment and storage medium for detecting electricity stealing behavior of user
CN116501876B (en) Big data tracking method and AI system for cloud collaborative digital service

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