Distribution network single line diagram intelligent analysis optimization method based on artificial intelligence

Abstract

The invention discloses a distribution network single line diagram intelligent analysis optimization method based on artificial intelligence, and belongs to the technical field of distribution network single line diagram supervision. The method is used for solving the technical problem of poor autonomous supervision analysis and autonomous optimization management effects of the distribution network single line diagram in the existing scheme. Different local abnormal data appearing in the distribution network single line diagram in the basic period are processed and calculated from different dimensions, the local abnormal influence appearing in different dimensions can be digitally represented, and reliable data support can be provided for subsequent abnormal overall influence expansion analysis of the abnormal distribution network single line diagram in the basic period; the abnormal monitoring analysis data of different dimensions in the early stage are integrated and calculated to obtain an abnormal overall influence identifier corresponding to the distribution network single line diagram in the basic period, the abnormal overall influence identifier is analyzed to determine the corresponding abnormal overall influence, and the normal state of the abnormal overall influence is traced and evaluated. And further, the states of the abnormal overall influence on the normal state can be subjected to detailed and classified management.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network single-line diagram supervision, and in particular to an artificial intelligence-based intelligent analysis and optimization method for a distribution network single-line diagram. Background Art

[0002] The distribution network single-line diagram is a method of diagramming the power system. It uses simple lines and symbols to represent the main wiring method of the power system. This diagram is usually used to describe the electrical connection of a distribution network, including the connection relationship between major electrical components such as power sources, transformers, switchgear, lines and loads.

[0003] The existing distribution network diagram and model management system has certain defects during operation. There are problems such as inconsistency between existing diagrams and objects, questionable equipment status, unreasonable graphic drawing, missing equipment names, and non-standard equipment names. It still remains at the level of single monitoring statistics and cannot implement diverse quality supervision on the distribution network single-line diagram from different dimensions, and adaptively optimize the management of the distribution network single-line diagram based on the quality supervision results, resulting in poor results in autonomous supervision analysis and autonomous optimization management of the distribution network single-line diagram. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent analysis and optimization method for a distribution network single-line diagram based on artificial intelligence, which is used to solve the technical problem that the autonomous supervision and analysis and autonomous optimization management effects of the distribution network single-line diagram in the existing solutions are poor.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] The distribution network single-line diagram intelligent analysis and optimization method based on artificial intelligence includes:

[0007] Monitor, count and digitally process the abnormalities occurring in different dimensions of the distribution network single-line diagram to obtain the corresponding abnormal active processing sequence and abnormal passive processing sequence, and perform data processing on the abnormal active processing sequence and abnormal passive processing sequence respectively to obtain the abnormal impact processing sequence corresponding to the monitoring period;

[0008] The abnormal impact processing sequence obtained from the distribution network single-line diagram processing within the basic period is integrated and calculated to determine the corresponding overall abnormal impact. According to the analysis of the overall abnormal impact obtained, the corresponding distribution network single-line diagram is adaptively optimized for active optimization management and subsequent basic period adaptive dynamic management.

[0009] Preferably, during the monitoring period, all first anomalies and corresponding first anomaly targets discovered by active operation and maintenance in the distribution network single-line diagram work, as well as all second anomalies and corresponding second anomaly targets discovered by passive operation and maintenance are counted;

[0010] Digitally process all first anomalies and second anomalies to obtain corresponding first anomaly impact factors and second anomaly impact factors;

[0011] Sort and combine the first anomaly and the first anomaly influencing factor, the second anomaly and the second anomaly influencing factor respectively to obtain a corresponding first anomaly subsequence and a second anomaly subsequence;

[0012] All first abnormal subsequences and second abnormal subsequences are sorted and combined respectively to obtain corresponding abnormal active processing sequences and abnormal passive processing sequences.

[0013] Preferably, the acquired first anomaly and second anomaly are input into an anomaly impact database for traversal matching to acquire anomaly impact factors corresponding to the respective anomalies; the anomaly impact database pre-stores a number of sample anomalies and their corresponding anomaly impact factors.

[0014] Preferably, the abnormal active processing sequence and the abnormal passive processing sequence are respectively calculated by the abnormal impact formula to obtain the corresponding abnormal active impact coefficient and abnormal passive impact coefficient;

[0015] The calculated abnormal active influence coefficients and abnormal passive influence coefficients are sorted and combined to obtain the abnormal influence processing sequence corresponding to the monitoring period.

[0016] Preferably, the expression of the abnormal impact formula is In the formula, k=1, 2; YYk is YY1 and YY2, which are the abnormal active influence coefficient and the abnormal passive influence coefficient respectively; YXik is YXi 1 and YXi 2, which are the different first abnormal influence factors in the abnormal active processing sequence and the different second abnormal influence factors in the abnormal passive processing sequence respectively; Nk is N1 and N2, which are the total number of the first abnormal influence factors in the abnormal active processing sequence and the total number of the second abnormal influence factors in the abnormal passive processing sequence respectively; αk is α1 and α2, which are the abnormal active processing correction factor and the abnormal passive processing correction factor respectively; A is the standard abnormal influence value.

[0017] Preferably, the abnormal active impact coefficient YY1 and the abnormal passive impact coefficient YY2 in the abnormal impact processing sequence are obtained, and the abnormal overall impact identifier corresponding to the distribution network single line diagram within the basic period is determined by performing data analysis through the abnormal impact integration identification piecewise function;

[0018] Among them, the expression of the abnormal impact integrated identification piecewise function is: Wherein, ω is the abnormal overall impact mark corresponding to the distribution network single line diagram within the basic period; β is the abnormal type weight coefficient; B is the abnormal overall impact standard value;

[0019] The abnormal overall impact indicator contains a value of 0 or 1, which indicates that the overall impact of the abnormality corresponding to the distribution network single-line diagram within the basic period is normal or abnormal;

[0020] According to the abnormal overall impact indicator with a value of 1, targeted upgrade and optimization management is immediately implemented on the distribution network single-line diagram.

[0021] Preferably, the validity verification of the abnormal overall impact on normality is implemented according to the abnormal overall impact flag with a value of 0, and the abnormal impact verification flag HB corresponding to the distribution network single line diagram in different basic periods is calculated by the impact normal verification formula; the expression of the impact normal verification formula is Where, YY1′ and YY2′ are the abnormal active influence coefficient and abnormal passive influence coefficient corresponding to the previous basic period; C is the abnormal influence verification standard value.

[0022] Preferably, if the abnormal impact verification flag is not greater than 0, it is prompted that the abnormal impact verification is normal and the existing basic cycle is maintained to perform supervision analysis of the distribution network single line diagram in the next cycle;

[0023] If the abnormal impact verification flag is greater than 0, it will prompt that the abnormal impact verification is abnormal and shorten the existing basic cycle to conduct supervision and analysis of the distribution network single-line diagram in the next cycle.

[0024] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0025] The present invention processes and calculates different local abnormal data appearing in the distribution network single-line diagram within the basic period from different dimensions, which can not only digitally represent the local abnormal impacts appearing in different dimensions, but also provide reliable data support for the subsequent abnormal overall impact expansion analysis of the abnormal distribution network single-line diagram within the basic period, thereby improving the overall effect of processing and analyzing the abnormal monitoring data of different dimensions of the distribution network single-line diagram and expanding and integrating the analysis.

[0026] The present invention integrates and calculates the abnormal monitoring and analysis data of different dimensions in the early stage to obtain the abnormal overall impact identification corresponding to the distribution network single-line diagram within the basic period, determines the corresponding abnormal overall impact by analyzing the abnormal overall impact identification, and retroactively evaluates the normal state of the abnormal overall impact, thereby refining and classifying the normal state of the abnormal overall impact, thereby improving the autonomous supervision and analysis effect and the autonomous optimization management effect of the distribution network single-line diagram. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The present invention will be further described below in conjunction with the accompanying drawings.

[0028] Figure 1 The present invention is a flowchart of the distribution network single-line diagram intelligent analysis and optimization method based on artificial intelligence.

[0029] Figure 2 The flowchart of the present invention is a flowchart of the validity verification of the abnormal overall impact on normality. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] like Figure 1 As shown, the present invention is an intelligent analysis and optimization method for a distribution network single-line diagram based on artificial intelligence, comprising:

[0032] Monitor, count and digitally process the abnormalities occurring in different dimensions of the distribution network single line diagram to obtain the corresponding abnormal active processing sequence and abnormal passive processing sequence, and process the data of the abnormal active processing sequence and abnormal passive processing sequence respectively to obtain the abnormal impact processing sequence corresponding to the monitoring period; including:

[0033] During the monitoring period, which is measured in days, specifically 30 days, statistics are collected on all first anomalies and corresponding first anomaly targets discovered by active operation and maintenance in the distribution network single-line diagram work, as well as all second anomalies and corresponding second anomaly targets discovered by passive operation and maintenance;

[0034] It should be noted that active operation and maintenance can be achieved by automatically monitoring the overall abnormality of the distribution network single-line diagram through existing automated operation and maintenance technologies, including but not limited to using smart meters, sensors, telemetry devices and other equipment to continuously monitor the status information of distribution network equipment, and using streaming data processing frameworks (such as Apache Kafka, Apache Storm, Apache Flink, etc.) to achieve real-time data analysis and active monitoring of abnormalities;

[0035] Passive operation and maintenance is a prompt that is performed only after a fault occurs on the corresponding target of the distribution network single-line diagram; the targets on the distribution network single-line diagram include but are not limited to power points, feeders, switchgear, transformers, protection equipment, grounding devices, etc.;

[0036] Digitally process all first anomalies and second anomalies to obtain corresponding first anomaly impact factors and second anomaly impact factors;

[0037] The first anomaly and the second anomaly obtained are input into the anomaly impact database for traversal matching to obtain the anomaly impact factors corresponding to the anomalies; the anomaly impact database pre-stores a number of sample anomalies and their corresponding anomaly impact factors;

[0038] The abnormal impact factor is used to digitally represent the impact of the sample abnormality. The specific values ​​of the abnormal impact factors corresponding to different sample abnormalities can be determined by professional operation and maintenance personnel in this field and the total number of abnormalities in the corresponding history.

[0039] Sort and combine the first anomaly and the first anomaly influencing factor, the second anomaly and the second anomaly influencing factor respectively to obtain a corresponding first anomaly subsequence and a second anomaly subsequence;

[0040] All first abnormal subsequences and second abnormal subsequences are sorted and combined respectively to obtain corresponding abnormal active processing sequences and abnormal passive processing sequences;

[0041] In the embodiment of the present invention, by implementing periodic supervision and data processing on the distribution network single line diagram from the dimensions of active operation and maintenance and passive operation and maintenance, the corresponding abnormal active processing sequence and abnormal passive processing sequence are obtained, thereby providing reliable monitoring and processing data support for the subsequent local abnormal impact analysis in different dimensions;

[0042] The abnormal active processing sequence and the abnormal passive processing sequence are calculated by the abnormal impact formula to obtain the corresponding abnormal active impact coefficient YY1 and abnormal passive impact coefficient YY2; the expression of the abnormal impact formula is Wherein, k=1, 2; YYk is YY1 and YY2; YXik is YXi 1 and YXi2, which are different first abnormal impact factors in the abnormal active processing sequence and different second abnormal impact factors in the abnormal passive processing sequence respectively; Nk is N1 and N2, which are the total number of first abnormal impact factors in the abnormal active processing sequence and the total number of second abnormal impact factors in the abnormal passive processing sequence respectively; αk is α1 and α2, which are the abnormal active processing correction factor and the abnormal passive processing correction factor respectively, which can be determined according to the total value of the total number of first abnormal impact factors and the total value of the total number of second abnormal impact factors appearing in different historical monitoring periods of the corresponding dimension; A is the standard abnormal impact value, which can be determined according to the design requirement data or quality specification requirement data corresponding to the distribution network single line diagram;

[0043] It should be noted that the abnormal active influence coefficient and the abnormal passive influence coefficient are used to integrate and calculate various abnormal data appearing in the corresponding dimension to digitally represent the local abnormal influence of its dimension; at the same time, the processing and calculation of the abnormal active influence coefficient and the abnormal passive influence coefficient can also provide reliable multi-dimensional abnormal processing data support for the subsequent abnormal overall impact analysis of the distribution network single line diagram within the basic period;

[0044] The calculated abnormal active influence coefficient YY1 and abnormal passive influence coefficient YY2 are sorted and combined to obtain the abnormal influence processing sequence corresponding to the corresponding monitoring period;

[0045] In the embodiment of the present invention, by processing and calculating different local abnormal data appearing in the distribution network single-line diagram within the basic period from different dimensions, it is possible to digitally represent the local abnormal impacts appearing in different dimensions, and provide reliable data support for the subsequent expansion analysis of the overall abnormal impact of the abnormal distribution network single-line diagram within the basic period, thereby improving the overall effect of the processing and analysis of abnormal monitoring data in different dimensions of the distribution network single-line diagram and the expansion and integration analysis.

[0046] The abnormal integration evaluation and optimization module is used to integrate and calculate the abnormal impact processing sequence obtained by processing the distribution network single line diagram within the basic period to determine the corresponding abnormal overall impact, and to actively optimize the corresponding distribution network single line diagram adaptively based on the abnormal overall impact obtained by analysis, as well as the subsequent basic period adaptive dynamic management; including:

[0047] Obtain the abnormal active impact coefficient YY1 and abnormal passive impact coefficient YY2 in the abnormal impact processing sequence, and perform data analysis through the abnormal impact integration identification piecewise function to determine the abnormal overall impact identifier corresponding to the distribution network single line diagram within the basic period;

[0048] Among them, the expression of the abnormal impact integrated identification piecewise function is: Wherein, ω is the abnormal overall impact identifier corresponding to the distribution network single line diagram within the basic period; β is the abnormal type weight coefficient, which is a real number greater than 1; B is the abnormal overall impact standard value, which can be determined according to the design requirement data or quality specification requirement data corresponding to the distribution network single line diagram;

[0049] The abnormal overall impact indicator contains a value of 0 or 1, which indicates that the overall impact of the abnormality corresponding to the distribution network single-line diagram within the basic period is normal or abnormal;

[0050] It should be noted that the overall abnormal impact indicator is used to integrate and calculate the abnormal analysis data obtained from monitoring different dimensions of the distribution network single-line diagram within the basic period to digitally represent its overall abnormal impact;

[0051] According to the abnormal overall impact indicator with a value of 1, the distribution network single-line diagram is immediately upgraded and optimized in a targeted manner;

[0052] like Figure 2As shown, according to the abnormal overall impact mark with a value of 0, the validity verification of the abnormal overall impact on normal is implemented, and the abnormal impact verification mark HB corresponding to the distribution network single line diagram in different basic periods is calculated through the normal impact verification formula; the expression of the normal impact verification formula is Where, YY1′ and YY2′ are the abnormal active influence coefficient and abnormal passive influence coefficient corresponding to the previous basic period; C is the abnormal influence verification standard value;

[0053] It should be explained that when the value of the abnormal overall identification is 0, it means that the corresponding abnormal overall impact is normal, but it is necessary to further conduct a retrospective assessment of the status of the abnormal overall impact on normal, so as to refine and classify the status of the abnormal overall impact on normal;

[0054] If the abnormal impact verification flag is not greater than 0, an abnormal impact verification normal instruction is generated and prompted, and the existing basic cycle is maintained to conduct supervision and analysis of the distribution network single line diagram in the next cycle;

[0055] If the abnormal impact verification flag is greater than 0, an abnormal impact verification abnormal instruction is generated and prompted, and the existing basic cycle is shortened to conduct supervision and analysis of the distribution network single line diagram in the next cycle;

[0056] The shortening of the existing basic cycle can be determined according to the value of the abnormal overall identification. For example, when the value of the abnormal overall identification is less than or equal to 0.5, the existing basic cycle is shortened by one quarter for implementation; when the value of the abnormal overall identification is greater than 0.5, the existing basic cycle is shortened by one half for implementation;

[0057] In an embodiment of the present invention, the abnormal monitoring and analysis data of different dimensions in the early stage are integrated and calculated to obtain the abnormal overall impact identification corresponding to the distribution network single line diagram within the basic period, and the corresponding abnormal overall impact is determined by analyzing the abnormal overall impact identification, and the state of the abnormal overall impact being normal is retroactively evaluated, and then the state of the abnormal overall impact being normal can be refined and classified for management, thereby improving the autonomous supervision and analysis effect and the autonomous optimization management effect of the distribution network single line diagram.

[0058] In addition, the formulas involved in the above are all dimensionless and numerical calculations. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and simulating it with simulation software.

[0059] In the several embodiments provided by the present invention, it should be understood that the disclosed method can be implemented in other ways. For example, the above-described embodiments of the invention are only illustrative, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0060] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0061] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0062] It is obvious to a person skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0063] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. The distribution network single-line diagram intelligent analysis and optimization method based on artificial intelligence is characterized by: include: Monitor, count and digitally process the abnormalities occurring in different dimensions of the distribution network single-line diagram to obtain the corresponding abnormal active processing sequence and abnormal passive processing sequence, and perform data processing on the abnormal active processing sequence and abnormal passive processing sequence respectively to obtain the abnormal impact processing sequence corresponding to the monitoring period; The abnormal impact processing sequence obtained from the distribution network single-line diagram processing within the basic period is integrated and calculated to determine the corresponding overall abnormal impact. According to the analysis of the overall abnormal impact obtained, the corresponding distribution network single-line diagram is adaptively optimized for active optimization management and subsequent basic period adaptive dynamic management.

2. The method for intelligent analysis and optimization of distribution network single-line diagram based on artificial intelligence according to claim 1 is characterized in that: During the monitoring period, statistics are collected on all first anomalies and corresponding first anomaly targets found by active operation and maintenance in the distribution network single-line diagram work, as well as all second anomalies and corresponding second anomaly targets found by passive operation and maintenance; Digitally process all first anomalies and second anomalies to obtain corresponding first anomaly impact factors and second anomaly impact factors; Sort and combine the first anomaly and the first anomaly influencing factor, the second anomaly and the second anomaly influencing factor respectively to obtain a corresponding first anomaly subsequence and a second anomaly subsequence; All first abnormal subsequences and second abnormal subsequences are sorted and combined respectively to obtain corresponding abnormal active processing sequences and abnormal passive processing sequences.

3. The distribution network single-line diagram intelligent analysis and optimization method based on artificial intelligence according to claim 2 is characterized in that: The acquired first anomaly and second anomaly are input into an anomaly impact database for traversal matching to obtain anomaly impact factors corresponding to the respective anomalies; the anomaly impact database pre-stores a number of sample anomalies and their corresponding anomaly impact factors.

4. The method for intelligent analysis and optimization of distribution network single-line diagram based on artificial intelligence according to claim 2 is characterized in that: The abnormal active processing sequence and the abnormal passive processing sequence are calculated by the abnormal impact formula to obtain the corresponding abnormal active impact coefficient and abnormal passive impact coefficient; The calculated abnormal active influence coefficients and abnormal passive influence coefficients are sorted and combined to obtain the abnormal influence processing sequence corresponding to the monitoring period.

5. The method for intelligent analysis and optimization of distribution network single-line diagram based on artificial intelligence according to claim 4 is characterized in that: The expression of the abnormal impact formula is: Wherein, k=1, 2; YYk is YY1 and YY2, which are abnormal active influence coefficient and abnormal passive influence coefficient respectively; YXik is YXi 1 and YXi 2, which are different first abnormal influence factors in abnormal active processing sequence and different second abnormal influence factors in abnormal passive processing sequence respectively; Nk is N1 and N2, which are the total number of first abnormal influence factors in abnormal active processing sequence and the total number of second abnormal influence factors in abnormal passive processing sequence respectively; αk is α1 and α2, which are abnormal active processing correction factors and abnormal passive processing correction factors respectively; A is the standard abnormal impact value.

6. The method for intelligent analysis and optimization of distribution network single-line diagram based on artificial intelligence according to claim 4 is characterized in that: Obtain the abnormal active impact coefficient YY1 and abnormal passive impact coefficient YY2 in the abnormal impact processing sequence, and perform data analysis through the abnormal impact integration identification piecewise function to determine the abnormal overall impact identifier corresponding to the distribution network single line diagram within the basic period; Among them, the expression of the abnormal impact integrated identification piecewise function is: Wherein, ω is the abnormal overall impact mark corresponding to the distribution network single line diagram within the basic period; β is the abnormal type weight coefficient; B is the abnormal overall impact standard value; The abnormal overall impact indicator contains a value of 0 or 1, which indicates that the overall impact of the abnormality corresponding to the distribution network single-line diagram within the basic period is normal or abnormal; According to the abnormal overall impact indicator with a value of 1, targeted upgrade and optimization management is immediately implemented on the distribution network single-line diagram.

7. The method for intelligent analysis and optimization of distribution network single-line diagram based on artificial intelligence according to claim 6 is characterized in that: According to the abnormal overall impact flag with a value of 0, the effectiveness verification of the abnormal overall impact on normality is implemented, and the abnormal impact verification flag HB corresponding to the distribution network single line diagram in different basic periods is calculated through the normal impact verification formula; The expression that affects the normal verification formula is Where, YY1′ and YY2′ are the abnormal active influence coefficient and abnormal passive influence coefficient corresponding to the previous basic period; C is the abnormal influence verification standard value.

8. The method for intelligent analysis and optimization of distribution network single-line diagram based on artificial intelligence according to claim 7 is characterized in that: If the abnormal impact verification flag is not greater than 0, it will prompt that the abnormal impact verification is normal and maintain the existing basic cycle to conduct supervision and analysis of the distribution network single line diagram in the next cycle; If the abnormal impact verification flag is greater than 0, it will prompt that the abnormal impact verification is abnormal and shorten the existing basic cycle to conduct supervision and analysis of the distribution network single-line diagram in the next cycle.

Images