CN118017506A - Low-voltage area topology identification method and system - Google Patents
Low-voltage area topology identification method and system Download PDFInfo
- Publication number
- CN118017506A CN118017506A CN202410417611.XA CN202410417611A CN118017506A CN 118017506 A CN118017506 A CN 118017506A CN 202410417611 A CN202410417611 A CN 202410417611A CN 118017506 A CN118017506 A CN 118017506A
- Authority
- CN
- China
- Prior art keywords
- address
- electric energy
- phase
- topology
- voltage
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000011218 segmentation Effects 0.000 claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 238000004128 high performance liquid chromatography Methods 0.000 claims abstract description 10
- 230000005611 electricity Effects 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 3
- 238000007417 hierarchical cluster analysis Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 6
- 238000003491 array Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a topology identification method and a system for a low-voltage transformer area, which relate to the technical field of electric energy metering and comprise the steps of acquiring split-phase voltage data acquired by HPLC, and generating a tree structure to reflect a power supply topology hierarchical relationship based on kirchhoff's law and combining the similarity of voltage change trend of each phase of electric energy meter under the transformer area with the relationship of phase circuit topology; carrying out structural treatment on the user electricity address, and carrying out analysis and statistics on the address; and distinguishing the power supply topology type of the station area according to the address distribution characteristics, acquiring a branch segmentation threshold value, segmenting, and fusing the segmentation results of all phase branches to acquire the main topological structure of the station area. The low-voltage area topology identification method provided by the invention can accurately determine the area main topology by identifying the area main topology structure, improves the management and control efficiency of the power network, improves the accuracy of topology identification and the robustness of an algorithm, and achieves better effects in the aspects of control efficiency, power consumption address and identification accuracy.
Description
Technical Field
The invention relates to the technical field of electric energy metering, in particular to a topology identification method for a low-voltage transformer area.
Background
In an electric power system, low-voltage area topology identification is a key task, and helps to understand the organization structure of an electric network, the path of electric energy flow and the connection relationship between node nodes. By accurately identifying and modeling the topological structure of the low-voltage area, the electric energy quality can be improved, the electric power system can be effectively monitored and managed, and intelligent power distribution and effective monitoring and management of the electric power system can be realized. Hierarchical clustering is a common data mining technique that discovers the structure inherent in data by grouping the data into clusters of different levels. In the topology identification of the low-voltage transformer area, hierarchical clustering can be applied to grouping grid node nodes so as to form a topological structure of the transformer area. Node nodes may be partitioned into different clusters by calculating a similarity measure, such as distance or correlation coefficient, between the node nodes.
With the rapid expansion of the scale of the power network and the continuous development of intelligent technology, the topology identification of the low-voltage transformer area becomes an important field of attention of the power industry. In recent years, with the widespread use of machine learning-related techniques, a topology recognition method has been improved and optimized. Specifically, topology identification calculates correlation using curve data such as a voltage curve. By analyzing and processing the curve data through an algorithm, the characteristic information can be extracted, and a correlation model between the curve data is established. By training such a model, the system can identify the topology of the low voltage region by comparing the newly acquired curve data to known patterns. The topology identification method based on machine learning can improve the accuracy, speed, reliability and rapidity of topology identification and provide more effective decision support for topology identification.
Disclosure of Invention
The invention is provided in view of the difficulty in accurately capturing and analyzing complex connection relations in a power supply network in the prior art.
Therefore, the technical problems solved by the invention are as follows: the existing low-voltage station topology identification method has the problems of inaccurate power consumption address, untimely updating of address information, high requirement on algorithm adaptability and optimization of accurately identifying main branch topology.
In order to solve the technical problems, the invention provides the following technical scheme: the low-voltage transformer area topology identification method comprises the steps of obtaining split-phase voltage data collected by HPLC, and generating a tree structure to reflect a power supply topology hierarchical relationship based on kirchhoff's law by combining the similarity of voltage change trend of each phase of electric energy meter under a transformer area with the relationship of phase circuit topology; carrying out structural treatment on the user electricity address, and carrying out analysis and statistics on the address; and according to the address distribution characteristics, the power supply topology types of the transformer areas are distinguished, the branch segmentation threshold value is obtained and segmented, and the segmentation results of the branches of each phase division are fused to obtain the main topology structure of the transformer areas.
As a preferable scheme of the low-voltage area topology identification method of the present invention, the method comprises: the obtained phase-separated voltage data collected by the HPLC comprises the relationship between the similarity of the variation trend of the voltage of each phase ammeter under the combined transformer area and the phase line topology, and the voltage data structure is expressed as follows:
；
Wherein, For/>Phase electric energy meter/>According to the voltage data of each phase, respectively calculating the correlation among all the electric energy meters of each phase in the transformer area, and evaluating the relative distance relation of the electric energy meters connected in the topological structure.
As a preferable scheme of the low-voltage area topology identification method of the present invention, the method comprises: the tree structure reflects the hierarchical relationship of the power supply topology and comprises the steps of under a platform area according to a hierarchical clustering machine learning methodThree phases respectively generate a tree structure, the power supply topological hierarchical relationship of each phase electric energy meter among the stations is reflected by the shape of the tree structure, and any phase/>, of the stations is reflectedElectric energy meter set/>Abstracting as a vertex set, taking the correlation obtained by calculating the pearson correlation coefficient as the measurement of the distance between phase electric energy meters under a platform region, and for a preset electric energy meter/>，/>，/>，As a column vector of voltage data, the distance between the electric energy meters can be expressed as:
；
Constructing a complete graph expressed as:
；
Wherein, As an adjacency matrix, the distance weight matrix among nodes of the complete graph is expressed as follows:
；
Selecting two nodes closest to each other in the complete graph to be expressed as Two nodes/>，/>From the complete diagram/>Junction set/>Taken out and combined into node/>Post update put into junction set/>Constructed by nodesIs a father node, node/>，/>Binary tree for left and right child nodes respectively, updating vertex/>Distance from each vertex, vertex/>，/>The mean value from each vertex distance is expressed as:
；
Wherein, Is the distance between two nodes,/>To merge two nodes into a new node/>Then, generating an updated complete graph by the average value of the distance between the new node and each vertex, and iterating until all nodes are combined, and using the last node/>The binary tree for the root node is a hierarchical clustered binary tree structure representing the power topology hierarchy of the region.
As a preferable scheme of the low-voltage area topology identification method of the present invention, the method comprises: the method comprises the steps of carrying out structuring processing, namely respectively obtaining four-level addresses of building, unit, floor and room number in each user electricity utilization address, carrying out position recognition through keywords, wherein the keywords of the building are building, building and number building, the keywords of the unit are unit, door and door opening, the keywords of the floor are floor, layer, the keywords of the room number are room and number, the number in front of the keywords is a level mark, carrying out position recognition through relative relation, judging that the last two digits of the number are room numbers according to the level rule of address naming if the level does not have the keywords, and judging that the rest of the last two digits are floors if the keywords of different levels overlap according to the four-level address sequence and repeated keywords.
As a preferable scheme of the low-voltage area topology identification method of the present invention, the method comprises: the address analysis and statistics comprises the steps of obtaining the number of the ammeter electric energy meters at different positions of each level of building, unit, floor and room number, and the tree-shaped physical topological structure represented by each level, wherein the statistical indexes of the number of the ammeter electric energy meters of each level are represented as follows:
；
Wherein, The standard deviation is used for representing the distribution or variation degree of the number of the electric energy meters of the measuring ammeter around the average value, the larger the standard deviation is, the more the number of the electric energy meters of the measuring ammeter is distributed at different positions, the smaller the standard deviation is, the more the number of the electric energy meters of the measuring ammeter is distributed intensively,/>For the number of address levels,/>The number of the electric energy meters is expressed as the number of the electric energy meters at different positions of each level,Is the average value, which represents the average value of the number of the electric energy meters,/>And the variation coefficient is used for representing the relative variation degree of the quantity distribution of the electric energy meter of the measuring ammeter.
As a preferable scheme of the low-voltage area topology identification method of the present invention, the method comprises: the method comprises judging the overall address structure rule of the area, if the building is more than or equal to 6, the users are more than or equal to 20, the number of single users is more than 20, if the address structure of the users is clear, the building centralized area is judged, the number of the users is gathered in one or less than 6 buildings, or the number of the users of each building is more than or equal to 20, the four-level address structure is clear, the number of electric meters among different parts of the same level is within 20 percent of the average value, the standard deviation and the variation coefficient are smaller than preset values, if the address structure of the users is not clear, the address structure is missing, only building numbers are provided, the number of the buildings meets the standards of independent houses, the similarity of the number rule of each building is higher than the preset value, the method comprises the steps of judging that independent house areas are formed by distributing users in more than or equal to 6 independent buildings, or the number of users of each building is smaller than 20, and the address structure is disordered, but the structural similarity of each building is higher than a preset value, the difference range of the number of electric meters of different parts of each level is within 100% of the average value, the standard deviation and the variation coefficient are within the preset range, judging that rural areas are formed by judging that the number of users of each building is regularly similar to the preset value, the users are distributed in groups with different scales, the address structure is unclear, the scale difference of each group is larger than the preset value, the number of the electric meters of the groups deviates from the average value, and the standard deviation and the variation coefficient are larger than the preset value.
As a preferable scheme of the low-voltage area topology identification method of the present invention, the method comprises: the step of obtaining and splitting the branch splitting threshold value comprises hierarchical clustering analysis based on voltage data, and the splitting threshold value is expressed as follows in combination with structural processing of physical addresses:
；
Wherein, For the branch cut threshold,/>For node/>Maximum distance between sub-nodes,/>For the adjustment factor, the weight of the balance voltage similarity and the address correlation is expressed as/>As a weighted function of the similarity of address and voltage data,Is the physical address of the electric energy meter,/>Binary tree generated for hierarchical clustering,/>And/>And (3) for the electric energy meter, through cross verification of multiple address and distance threshold segmentation, obtaining each phase topological result which accords with an address rule and a correlation distance, combining the address rule statistical index again, fusing the segmentation results of each phase branch, merging branches in the same physical space in different phases into a three-phase fusion branch, and obtaining a main topological structure of the platform region.
Another object of the present invention is to provide a low-voltage transformer area topology identification system, which can reflect the hierarchical relationship of the power supply topology by the collection reflection module, so as to solve the problem that it is difficult to accurately capture and analyze the complex connection relationship in the power supply network at present.
As a preferable scheme of the low-voltage station topology identification system of the present invention, wherein: the system comprises a collection and reflection module, a processing and analysis module and a topological structure module; the acquisition reflection module acquires split-phase voltage data acquired by HPLC, and generates a tree structure reflection power supply topology hierarchical relationship based on kirchhoff's law by combining the similarity of voltage change trend of each phase of electric energy meter under the transformer area and the relationship of phase circuit topology; the processing analysis module is used for carrying out structural processing on the user power consumption address and carrying out analysis statistics on the address; the topological structure module is used for distinguishing the power supply topological type of the transformer area according to the address distribution characteristics, acquiring a branch segmentation threshold value and segmenting, and fusing the segmentation results of all phase branches to acquire the main topological structure of the transformer area.
A computer device comprising a memory and a processor, the memory storing a computer program comprising the steps of the processor executing the computer program to implement a low voltage zone topology identification method.
A computer readable storage medium having stored thereon a computer program comprising the steps of implementing a low voltage zone topology identification method when said computer program is executed by a processor.
The invention has the beneficial effects that: the low-voltage area topology identification method provided by the invention can accurately determine the area main topology by identifying the area main topology structure, improves the management and control efficiency of the electric power network of the low-voltage area, and can reflect the hierarchical relationship of the power supply topology by accurately measuring the voltage correlation among the nodes of the electric power network, thereby effectively improving the accuracy of topology identification and the robustness of an algorithm, carrying out structural processing and statistical analysis on the power consumption address of a user, revealing the distribution mode of the electric energy meter, providing important information about the power demand and distribution, optimizing the power supply structure, improving the operation efficiency and reliability of the electric power network, automatically correcting the inaccuracy of part of the power consumption address, combining the electric energy meter correlation, machine learning and expert system technology, and providing a more efficient and intelligent area management solution for the electric power industry.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without the need of creative efforts for a person of ordinary skill in the art.
Fig. 1 is an overall flowchart of a low-voltage area topology identification method according to a first embodiment of the present invention.
Fig. 2 is a block diagram of a topology identification system for a low-voltage area according to a third embodiment of the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
Referring to fig. 1, for one embodiment of the present invention, there is provided a low-voltage station topology identification method, including:
s1: the method comprises the steps of obtaining split-phase voltage data collected by HPLC, and generating a tree structure to reflect a power supply topology hierarchical relationship based on kirchhoff's law by combining the similarity of voltage change trend of each phase of electric energy meter under a transformer area with the relationship of phase line topology.
Further, the acquisition of the phase-separated voltage data collected by the HPLC includes combining the relationship between the similarity of the variation trend of the voltage of each phase ammeter under the transformer area and the phase line topology.
It should be noted that the voltage data structure is expressed as:
；
Wherein, For/>Phase electric energy meter/>According to the voltage data of each phase, respectively calculating the correlation among all the electric energy meters of each phase in the transformer area, and evaluating the relative distance relation of the electric energy meters connected in the topological structure.
Further, the tree structure reflects the hierarchical relationship of the power supply topology including under the transformer area according to the hierarchical clustering machine learning methodEach phase of the three phases produces a tree structure.
It should be noted that, the power supply topology hierarchical relationship of each phase electric energy meter among the stations is reflected by the shape of the tree structure, and any phase of the stations is reflectedElectric energy meter set/>Abstracting as a vertex set, taking the correlation obtained by calculating the pearson correlation coefficient as the measurement of the distance between phase electric energy meters under a platform region, and for a preset electric energy meter/>，/>，，/>As a column vector of voltage data, the distance between the electric energy meters can be expressed as:
；
Constructing a complete graph expressed as:
；
Wherein, As an adjacency matrix, the distance weight matrix among nodes of the complete graph is expressed as follows:
；
Selecting two nodes closest to each other in the complete graph to be expressed as Two nodes/>，/>From the complete diagram/>Junction set/>Taken out and combined into node/>Post update put into junction set/>Constructed by nodesIs a father node, node/>，/>Binary tree for left and right child nodes respectively, updating vertex/>Distance from each vertex, vertex/>，/>The mean value from each vertex distance is expressed as:
；
Wherein, Is the distance between two nodes,/>To merge two nodes into a new node/>Then, generating an updated complete graph by the average value of the distance between the new node and each vertex, and iterating until all nodes are combined, and using the last node/>The binary tree for the root node is a hierarchical clustered binary tree structure representing the power topology hierarchy of the region.
S2: and carrying out structural processing on the user electricity address, and carrying out analysis and statistics on the address.
Further, the structuring process includes obtaining four-level addresses of building, unit, floor and room number in each user electricity address.
It should be noted that, the position identification is performed by keywords, the keywords of the building are building, building and number building, the keywords of the unit are unit, door and door opening, the keywords of the floor are floor, layer, the keywords of the room number are room and number, the number before the keywords is the level identification, the position identification is performed by the relative relation, if the level has no keyword, the last two digits of the number are room numbers according to the level rule of the address naming, the rest of the previous one or two digits are floors, if the keywords of different levels are overlapped, the level is determined according to the four-level address sequence and repeated keywords.
Further, the analysis and statistics of the addresses include obtaining the number of the electric energy meters at different positions of each level of the building, the unit, the floor and the room number, and the tree-shaped physical topology structure represented by each level.
It should be noted that, the statistical index of the number of ammeter electric energy meters at each level is expressed as:
；
Wherein, The standard deviation is used for representing the distribution or variation degree of the number of the electric energy meters of the measuring ammeter around the average value, the larger the standard deviation is, the more the number of the electric energy meters of the measuring ammeter is distributed at different positions, the smaller the standard deviation is, the more the number of the electric energy meters of the measuring ammeter is distributed intensively,/>For the number of address levels,/>The number of the electric energy meters is expressed as the number of the electric energy meters at different positions of each level,Is the average value, which represents the average value of the number of the electric energy meters,/>And the variation coefficient is used for representing the relative variation degree of the quantity distribution of the electric energy meter of the measuring ammeter.
S3: and distinguishing the power supply topology type of the station area according to the address distribution characteristics, acquiring a branch segmentation threshold value, segmenting, and fusing the segmentation results of all phase branches to acquire the main topological structure of the station area.
Further, distinguishing the power supply topology type of the station area according to the address distribution characteristics comprises judging the overall address structure rule of the station area.
It should be noted that if the building is greater than or equal to 6, the number of users is greater than or equal to 20, the number of single users is greater than 20, if the user address structure is clear, the building centralized area is determined, the building centralized area is that the users are gathered in one or less than 6 buildings, or the number of users in each building is greater than or equal to 20, and the four-level address structure is clear, the number of electric meters between different parts of the same level is within 20% of the mean value, the standard deviation and the variation coefficient are smaller than the preset value, if the user address structure is not clear, the address structure is missing, only building numbers are provided, the number of buildings meets the independent house standard, the similarity of the number of the users in each building is higher than the preset value, the independent house area is determined, the number of the users in the building is distributed in 6 or more independent buildings, or each building user is less than 20, the number of the address structure is chaotic, but the structure similarity of each building is higher than the preset value, the number of the electric meters in different parts of each level is within 100% of the mean value, the standard deviation and the variation coefficient are within the preset range, the standard deviation and the variation coefficient are different from the preset value, and the number of the user is not equal to the average value in the set of the preset value, and the difference is not equal to the same in the size as the standard value.
Further, obtaining a branch segmentation threshold and segmenting comprises hierarchical clustering analysis based on voltage data and structuring processing combined with physical addresses.
Note that the segmentation threshold is expressed as:
；
Wherein, For the branch cut threshold,/>For node/>Maximum distance between sub-nodes,/>For the adjustment factor, the weight of the balance voltage similarity and the address correlation is expressed as/>As a weighted function of the similarity of address and voltage data,Is the physical address of the electric energy meter,/>Binary tree generated for hierarchical clustering,/>And/>And (3) for the electric energy meter, through cross verification of multiple address and distance threshold segmentation, obtaining each phase topological result which accords with an address rule and a correlation distance, combining the address rule statistical index again, fusing the segmentation results of each phase branch, merging branches in the same physical space in different phases into a three-phase fusion branch, and obtaining a main topological structure of the platform region.
Example 2
In order to verify the beneficial effects of the invention, the invention provides a low-voltage area topology identification method, and scientific demonstration is carried out through economic benefit calculation and simulation experiments.
Selecting two low-voltage areas with similar conditions, wherein one area adopts the prior art, the other area adopts the method of the invention, one week of split-phase voltage data is collected in each area to obtain sufficient sample data, meanwhile, user electricity address data in a corresponding period is collected to ensure the relativity and the accuracy of the data, the collected data are subjected to topology identification by using respective technologies, the topology identification results of the two technologies, including the number of main branches and the situation of wrong address identification, the performances of the two technologies on the accuracy of the topology identification are analyzed and compared, and the processing speed and the resource consumption of the respective technologies when the same data amount is processed are measured.
As shown in table 1, the inventive area shows 95% of similarity of voltage data, compared with 85% of the prior art, the inventive method is more accurate in terms of voltage data processing, the inventive method achieves 92% of accuracy of address data, which is significantly higher than 80% of the prior art, indicating that the inventive method is more effective in terms of processing address information, the number of erroneous addresses of the inventive method is 3, which is far lower than 10 of the prior art, indicating that the inventive method is more effective in terms of reducing recognition errors, the inventive area has an overall recognition accuracy of 96%, which is significantly higher than 82% of the prior art, which proves that the inventive method is significantly improved in overall topology recognition performance, and the inventive method exhibits higher efficiency and lower resource consumption when processing the same amount of data, which is more advantageous than the prior art.
Table 1 experiment comparison table
Example 3
Referring to fig. 2, for one embodiment of the present invention, there is provided a low voltage station topology identification system, including: the system comprises a collection reflection module, a processing analysis module and a topological structure module.
The acquisition and reflection module acquires split-phase voltage data acquired by the HPLC, and generates a tree structure to reflect a power supply topology hierarchical relationship based on kirchhoff's law by combining the similarity of voltage change trend of each phase of electric energy meter under the transformer area with the relationship of phase circuit topology; the processing analysis module is used for carrying out structural processing on the user power consumption address and carrying out analysis statistics on the address; the topological structure module is used for distinguishing the power supply topological type of the transformer area according to the address distribution characteristics, acquiring a branch segmentation threshold value and segmenting, and fusing the segmentation results of all phase branches to acquire the main topological structure of the transformer area.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium may even be paper or other suitable medium upon which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like. It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. The low-voltage station topology identification method is characterized by comprising the following steps of:
Acquiring phase-separated voltage data acquired by HPLC, and generating a tree structure to reflect a power supply topology hierarchical relationship by combining the similarity of voltage variation trend of each phase of electric energy meter under a transformer area with the relationship of phase line topology based on kirchhoff's law;
Carrying out structural treatment on the user electricity address, and carrying out analysis and statistics on the address;
and distinguishing the power supply topology type of the station area according to the address distribution characteristics, acquiring a branch segmentation threshold value, segmenting, and fusing the segmentation results of all phase branches to acquire the main topological structure of the station area.
2. The low-voltage station topology identification method of claim 1, wherein: the obtained phase-separated voltage data collected by the HPLC comprises the relationship between the similarity of the variation trend of the voltage of each phase ammeter under the combined transformer area and the phase line topology, and the voltage data structure is expressed as follows:
；
Wherein, For/>Phase electric energy meter/>According to the voltage data of each phase, respectively calculating the correlation among all the electric energy meters of each phase in the transformer area, and evaluating the relative distance relation of the electric energy meters connected in the topological structure.
3. The low-voltage station topology identification method of claim 2, wherein: the tree structure reflects the hierarchical relationship of the power supply topology and comprises the steps of under a platform area according to a hierarchical clustering machine learning methodThree phases respectively generate a tree structure, the power supply topological hierarchical relationship of each phase electric energy meter among the transformer areas is reflected by the shape of the tree structure, and any phase of the transformer areas is reflectedElectric energy meter set/>Abstracting as a vertex set, taking the correlation obtained by calculating the pearson correlation coefficient as the measurement of the distance between phase electric energy meters under a platform region, and for a preset electric energy meter/>，/>，/>，/>As a column vector of voltage data, the distance between the electric energy meters can be expressed as:
；
Constructing a complete graph expressed as:
；
Wherein, As an adjacency matrix, the distance weight matrix among nodes of the complete graph is expressed as follows:
；
Selecting two nodes closest to each other in the complete graph to be expressed as Two nodes/>，/>From the complete diagram/>Junction set/>Taken out and combined into node/>Post update put into junction set/>Constructed with nodes/>Is a father node, node/>，/>Binary tree for left and right child nodes respectively, updating vertex/>Distance from each vertex, vertex/>，/>The mean value from each vertex distance is expressed as:
；
Wherein, Is the distance between two nodes,/>To merge two nodes into a new node/>Then, generating an updated complete graph by the average value of the distance between the new node and each vertex, and iterating until all nodes are combined, and using the last node/>The binary tree for the root node is a hierarchical clustered binary tree structure representing the power topology hierarchy of the region.
4. A low voltage station topology identification method as recited in claim 3, wherein: the method comprises the steps of carrying out structuring processing, namely respectively obtaining four-level addresses of building, unit, floor and room number in each user electricity utilization address, carrying out position recognition through keywords, wherein the keywords of the building are building, building and number building, the keywords of the unit are unit, door and door opening, the keywords of the floor are floor, layer, the keywords of the room number are room and number, the number in front of the keywords is a level mark, carrying out position recognition through relative relation, judging that the last two digits of the number are room numbers according to the level rule of address naming if the level does not have the keywords, and judging that the rest of the last two digits are floors if the keywords of different levels overlap according to the four-level address sequence and repeated keywords.
5. The low-voltage station topology identification method of claim 4, wherein: the address analysis and statistics comprises the steps of obtaining the number of the ammeter electric energy meters at different positions of each level of building, unit, floor and room number, and the tree-shaped physical topological structure represented by each level, wherein the statistical indexes of the number of the ammeter electric energy meters of each level are represented as follows:
；
Wherein, The standard deviation is used for representing the distribution or variation degree of the number of the electric energy meters of the measuring ammeter around the average value, the larger the standard deviation is, the more the number of the electric energy meters of the measuring ammeter is distributed at different positions, the smaller the standard deviation is, the more the number of the electric energy meters of the measuring ammeter is distributed intensively,/>For the number of address levels,/>For the number of the electric energy meters, the number of the electric energy meters at different positions of each level is expressed by the number of the electric energy meters,/>Is the average value, which represents the average value of the number of the electric energy meters,/>And the variation coefficient is used for representing the relative variation degree of the quantity distribution of the electric energy meter of the measuring ammeter.
6. The low-voltage station topology identification method of claim 5, wherein: the method comprises judging the overall address structure rule of the area, if the building is more than or equal to 6, the users are more than or equal to 20, the number of single users is more than 20, if the address structure of the users is clear, the building centralized area is judged, the number of the users is gathered in one or less than 6 buildings, or the number of the users of each building is more than or equal to 20, the four-level address structure is clear, the number of electric meters among different parts of the same level is within 20 percent of the average value, the standard deviation and the variation coefficient are smaller than preset values, if the address structure of the users is not clear, the address structure is missing, only building numbers are provided, the number of the buildings meets the standards of independent houses, the similarity of the number rule of each building is higher than the preset value, the method comprises the steps of judging that independent house areas are formed by distributing users in more than or equal to 6 independent buildings, or the number of users of each building is smaller than 20, and the address structure is disordered, but the structural similarity of each building is higher than a preset value, the difference range of the number of electric meters of different parts of each level is within 100% of the average value, the standard deviation and the variation coefficient are within the preset range, judging that rural areas are formed by judging that the number of users of each building is regularly similar to the preset value, the users are distributed in groups with different scales, the address structure is unclear, the scale difference of each group is larger than the preset value, the number of the electric meters of the groups deviates from the average value, and the standard deviation and the variation coefficient are larger than the preset value.
7. The low-voltage station topology identification method of claim 6, wherein: the step of obtaining and splitting the branch splitting threshold value comprises hierarchical clustering analysis based on voltage data, and the splitting threshold value is expressed as follows in combination with structural processing of physical addresses:
；
Wherein, For the branch cut threshold,/>For node/>Maximum distance between sub-nodes,/>For the adjustment factor, the weight of the balance voltage similarity and the address correlation is expressed as/>As a weighted function of address and voltage data similarity,/>Is the physical address of the electric energy meter,/>Binary tree generated for hierarchical clustering,/>And/>And (3) for the electric energy meter, through cross verification of multiple address and distance threshold segmentation, obtaining each phase topological result which accords with an address rule and a correlation distance, combining the address rule statistical index again, fusing the segmentation results of each phase branch, merging branches in the same physical space in different phases into a three-phase fusion branch, and obtaining a main topological structure of the platform region.
8. A system employing the low voltage station topology identification method of any one of claims 1 to 7, characterized in that: the system comprises a collection and reflection module, a processing and analysis module and a topological structure module;
the acquisition reflection module acquires split-phase voltage data acquired by HPLC, and generates a tree structure reflection power supply topology hierarchical relationship based on kirchhoff's law by combining the similarity of voltage change trend of each phase of electric energy meter under the transformer area and the relationship of phase circuit topology;
the processing analysis module is used for carrying out structural processing on the user power consumption address and carrying out analysis statistics on the address;
the topological structure module is used for distinguishing the power supply topological type of the transformer area according to the address distribution characteristics, acquiring a branch segmentation threshold value and segmenting, and fusing the segmentation results of all phase branches to acquire the main topological structure of the transformer area.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the low voltage zone topology identification method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the low voltage station topology identification method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410417611.XA CN118017506B (en) | 2024-04-09 | 2024-04-09 | Low-voltage area topology identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410417611.XA CN118017506B (en) | 2024-04-09 | 2024-04-09 | Low-voltage area topology identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118017506A true CN118017506A (en) | 2024-05-10 |
| CN118017506B CN118017506B (en) | 2024-06-18 |
Family
ID=90950336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410417611.XA Active CN118017506B (en) | 2024-04-09 | 2024-04-09 | Low-voltage area topology identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118017506B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112165171A (en) * | 2020-10-10 | 2021-01-01 | 江苏方天电力技术有限公司 | Method for identifying topology of low-voltage distribution station area |
| WO2022016903A1 (en) * | 2020-07-24 | 2022-01-27 | 石家庄科林电气股份有限公司 | Automatic low-voltage area topology identification method |
| WO2023000797A1 (en) * | 2021-07-23 | 2023-01-26 | 石家庄科林电气股份有限公司 | Hplc-based plug and play method for power distribution internet of things device |
| CN116011158A (en) * | 2022-12-14 | 2023-04-25 | 国网江苏省电力有限公司营销服务中心 | Topology identification method, system and device for low-voltage transformer area |
| CN116317094A (en) * | 2022-09-07 | 2023-06-23 | 东南大学溧阳研究院 | Low-voltage distribution network topology identification method based on Internet of things equipment measurement data |
| CN116845971A (en) * | 2023-07-10 | 2023-10-03 | 国网山东省电力公司营销服务中心(计量中心) | Automatic identification method for topological structure of photovoltaic grid-connected low-voltage transformer area |
-
2024
- 2024-04-09 CN CN202410417611.XA patent/CN118017506B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022016903A1 (en) * | 2020-07-24 | 2022-01-27 | 石家庄科林电气股份有限公司 | Automatic low-voltage area topology identification method |
| CN112165171A (en) * | 2020-10-10 | 2021-01-01 | 江苏方天电力技术有限公司 | Method for identifying topology of low-voltage distribution station area |
| WO2023000797A1 (en) * | 2021-07-23 | 2023-01-26 | 石家庄科林电气股份有限公司 | Hplc-based plug and play method for power distribution internet of things device |
| CN116317094A (en) * | 2022-09-07 | 2023-06-23 | 东南大学溧阳研究院 | Low-voltage distribution network topology identification method based on Internet of things equipment measurement data |
| CN116011158A (en) * | 2022-12-14 | 2023-04-25 | 国网江苏省电力有限公司营销服务中心 | Topology identification method, system and device for low-voltage transformer area |
| CN116845971A (en) * | 2023-07-10 | 2023-10-03 | 国网山东省电力公司营销服务中心(计量中心) | Automatic identification method for topological structure of photovoltaic grid-connected low-voltage transformer area |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118017506B (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110231528B (en) | Transformer household variation common knowledge identification method and device based on load characteristic model library | |
| CN108733631A (en) | A kind of data assessment method, apparatus, terminal device and storage medium | |
| CN109597757B (en) | Method for measuring similarity between software networks based on multidimensional time series entropy | |
| CN112149873A (en) | Low-voltage transformer area line loss reasonable interval prediction method based on deep learning | |
| CN114610706A (en) | Electricity stealing detection method, system and device based on oversampling and improved random forest | |
| CN116148753A (en) | Intelligent electric energy meter operation error monitoring system | |
| CN111177216A (en) | Association rule generation method and device for behavior characteristics of comprehensive energy consumer | |
| CN111709668A (en) | Power grid equipment parameter risk identification method and device based on data mining technology | |
| CN112001644A (en) | Power distribution network operation reliability detection method, device, terminal and storage medium | |
| CN112308341A (en) | Power data processing method and device | |
| CN109902133B (en) | Multi-source data error correction processing method and system based on arbitrary partition area of power grid | |
| CN117078048A (en) | Digital twinning-based intelligent city resource management method and system | |
| CN114547816A (en) | Intelligent analysis method and device for reliability of power distribution network | |
| CN115545280A (en) | Low-voltage distribution network topology generation method and device | |
| CN114978877A (en) | Exception handling method and device, electronic equipment and computer readable medium | |
| Ullah et al. | Adaptive data balancing method using stacking ensemble model and its application to non-technical loss detection in smart grids | |
| CN114781688A (en) | Method, device, equipment and storage medium for identifying abnormal data of business expansion project | |
| CN110597792A (en) | Multistage redundant data fusion method and device based on synchronous line loss data fusion | |
| CN109858667A (en) | It is a kind of based on thunder and lightning weather to the short term clustering method of loading effects | |
| CN118017506B (en) | Low-voltage area topology identification method and system | |
| CN113094448A (en) | Method and device for analyzing vacant state of house and electronic equipment | |
| CN117331017A (en) | Method and system for studying and judging misconnection of three-phase four-wire electric energy meter | |
| CN115603320A (en) | Real-time sensing and online evaluation method and system based on wide area measurement data | |
| CN114757097B (en) | Line fault diagnosis method and device | |
| CN116010831A (en) | Combined clustering scene reduction method and system based on potential decision result |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |