A distribution network map digital-analog integrated data platform based on regulation cloud

Abstract

The application discloses a distribution network diagram module integrated data platform based on regulation and control cloud, comprising an integrated data structure of fused node power equipment attribute data and power connection line diagram data, and construction and application of the data structure. The data structure is based on a distribution network regulation and control cloud data system, and takes standardized and normalized power dispatch general data objects, metadata and data dictionary sets in the regulation and control cloud data system as underlying data objects. The structured data of power equipment and the graphic topology data associated with the spatial distribution of power lines in the regulation and control cloud data system are reconstructed and fused in data path and data content, thereby laying a foundation for improvement and reconstruction of the regulation and control cloud data system in the aspect of data architecture for machine learning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart grid, in particular to a distribution network diagram digital-analog integrated data structure of a regulation and control cloud, a construction method of the data structure and an application thereof. BACKGROUND

[0002] At present, with the development of smart grid technology, the scale and complexity of power grid data are increasing, which poses new challenges to data processing and analysis. Under this technical background, State Grid Corporation of China proposes the construction idea of power dispatching and control informatization based on cloud computing, which is led by the Electric Power Research Institute and Nanrui Company and introduces multiple resources. On the theoretical and practical levels, the "regulation and control cloud" system (sometimes referred to as "sky cloud" internally) is preliminarily constructed, which aims to improve the automation, informatization and intelligence level of power grid dispatching through highly integrated and intelligent information technology means. The regulation and control cloud system is constructed based on a cloud computing platform, has high scalability and flexibility, and can dynamically adjust resources according to the actual needs of power grid operation. On the data level, the regulation and control cloud constructs a centralized data warehouse, realizes the centralized storage of node devices, power connection line diagrams and other forms of software and hardware elements from power grid dispatching, and at the same time, is compatible with the access of power internet of things to obtain and update various power grid equipment and sensor data in real time. On the functional orientation, the regulation and control cloud system is constructed as an integrated platform application, which is theoretically compatible with various functions of power grid regulation and control, such as power grid monitoring, fault analysis, decision support, optimal dispatching, etc.

[0003] However, in terms of data optimization of the regulation and control cloud system, at present, it is mainly for the standardization of data format, such as data format alignment based on various specifications such as general data object structured design of power dispatching, and data mapping consistency with the original D5000 regulation and control system, etc. Although automatic and information models are introduced in the surface area of data presentation, the bottom logic of data processing and the bottom architecture of data structure still mainly rely on traditional data analysis and processing methods. For example, in terms of data structure, the data island problem is widespread, which makes the data in the regulation and control cloud usually scattered in different subsystems and databases and lacks effective data integration mechanism. In terms of data processing, it still fundamentally relies on a large number of manual participation and expert knowledge. These data structure and data processing methods have many limitations when facing large-scale, high-dimensional power grid data, especially in the introduction and application of advanced data processing methods such as machine learning and artificial intelligence models. SUMMARY

[0004] The technical problem solved by the present application is to provide a distribution network map and model and digit integrated data platform based on regulation and control cloud, comprising an integrated data structure that integrates node power equipment attribute data and power connection line map data, and construction and application of the data structure.

[0005] To solve the above technical problems, the technical solutions adopted by the present application are as follows.

[0006] A distribution network map and model and digit integrated data structure based on regulation and control cloud, which is based on a power distribution network regulation and control cloud system data system, takes the standardized and standardized power dispatch general data objects, metadata and data dictionary set in the regulation and control cloud data system as the bottom layer data object, and is guided by the improvement and reconstruction of the regulation and control cloud data system for machine learning.

[0007] As a preferred technical solution of the present application, it at least includes the following data structure elements: two-dimensional homogenization data set DxD, data spine structure, A-O-Z data structure.

[0008] As a preferred technical solution of the present application, the two-dimensional homogenization data set DxD is based on the standardized ID of the node power equipment in the regulation and control cloud system to construct a basic two-dimensional data space.

[0009] As a preferred technical solution of the present application, the data spine structure dominates the characterization of the structured attribute data of the node power equipment in the regulation and control cloud data system.

[0010] As a preferred technical solution of the present application, the A-O-Z data structure dominates the data-based characterization of the spatial distribution association of the graphical power line between the node power equipment.

[0011] As a preferred technical solution of the present application, the data spine structure and the A-O-Z data structure are respectively or sequentially constructed in the data space of the two-dimensional homogenization data set DxD.

[0012] As a preferred technical solution of the present application, the data spine structure is located in the diagonal line area of the two-dimensional homogenization data set DxD, and the A-O-Z data structure is located in the non-diagonal line area of the two-dimensional homogenization data set DxD.

[0013] A construction method of a distribution network diagram digital-analog integrated data structure based on a regulation cloud, the integrated data structure taking node information in the regulation cloud system as an initial data set, specifically, using the standardized ID of the node power equipment in the regulation cloud system (other representation data types of the node power equipment can also be used) as the initial data set D;

[0014] Step 1, all elements in the D set, i.e., the standardized ID of all node power equipment recorded in the regulation cloud, are specified and ordered or randomly ordered, and are taken as the permanent serial number identification of each node power equipment in this data structure in the form of read-only; wherein the random ordering operation will first generate a random order, and then directly sort all elements in the D set according to the random order and generate serial number identification; the serial number identification generated this time is taken as the permanent serial number identification of each node power equipment in this data structure in the form of read-only;

[0015] Step 2, the purpose of the above ordering of node equipment is mainly to matrix the node power equipment in this step, specifically, all node power equipment in the D set is simultaneously unfolded in the same order in two orthogonal dimensions according to the permanent serial number identification, which is realized by two data operations:

[0016] 2-1, the first operation, all node power equipment in the D set is unfolded in order according to one dimension, such as x dimension, wherein the order is the size order according to the permanent serial number identification;

[0017] 2-2, the second operation, all node power equipment in the D set is unfolded in order according to another orthogonal dimension, such as y dimension, the order of the second operation is consistent with that of the first operation, so it is called "unfolded in the same order", and the obtained two-dimensional data set unfolded in the same order is denoted as DxD;

[0018] Step 3, this step is the core of data processing, reconstructing and fusing the structured data in the regulation cloud data system and the topological data associated with the spatial distribution of power equipment and lines, and constructing an integrated data structure with pure structured data as the skeleton and adapting to the internal multi-dimensional discrete data configuration requirements of the machine learning model; specifically, in the two-dimensional data set unfolded in the same order DxD, all regulation cloud node power equipment in the initial D set is aligned on the diagonal line, which is equivalent to unfolding all regulation cloud node power equipment in the initial D set on the diagonal line in the two-dimensional data set unfolded in the same order DxD according to the set permanent serial number identification, specifically including:

[0019] 3-1, the first operation of this data step is to fill the attribute data of each node power equipment of the regulation cloud data system into the diagonal line in the two-dimensional data set unfolded in the same order DxD;

[0020] 3-1-1. First, the attribute data may or may not contain the normalized ID of the node power equipment in the initial D set. When it contains ID data from the D set, this ID data is used as the first data in the attribute data set, and the remaining attribute data of the node power equipment are filled in sequentially. Similar to the ID data of the power equipment, the remaining attribute data of the node power equipment uniformly adopts the normalized attribute data in the metadata and data dictionary of the control cloud system. The remaining attribute data of the node power equipment includes its electrical attribute parameters and identification attribute parameters. The electrical attribute parameters include physical parameters related to grid operation, such as rated voltage, rated load, and rated capacity. The identification attribute parameters include equipment name, manufacturer, and other non-physical parameters.

[0021] 3-1-2. When filling the attribute data of different node power equipment on the diagonal of the two-dimensional homogenized data set D×D, the same type of attribute data of different power equipment shall be arranged in the same order. For example, if the normalized ID of the node power equipment is in the first data position and the equipment manufacturer is in the second position, then when filling the attribute data of different node power equipment on the diagonal of the two-dimensional homogenized data set D×D, the manufacturer data of all node power equipment shall be filled into the second data position.

[0022] 3-1-3. Based on the data rules in 3-1-1 and 3-1-2 above, the most important point is that the attribute data set as a whole is configured on the diagonal of the two-dimensional homogenized data set D×D. Although the two-dimensional homogenized data set D×D has formed a data space unfolded on a plane, considering that this data space will be occupied by the AOZ data structure used later to characterize the spatial distribution topology of the power equipment in the control cloud nodes, the attribute data set as a whole is unfolded on the third dimension or z-dimension orthogonal to the two-dimensional homogenized data set space.

[0023] Thus, through the first operation, a data ridge, called the data ridge structure, is constructed along the third dimension on the diagonal of the two-dimensional homogenized data set D×D. This ridge structure accommodates the attribute data of the power equipment of the control cloud nodes.

[0024] 3-2、This data step of the second operation is: in the non-diagonal line area of the two-dimensional homogenization data set D x D, construct A-O-Z data structure for representing the spatial connection topology characteristics of the node power equipment in the regulation cloud; Specifically, in the data space of the two-dimensional homogenization data set D x D data structure, assuming that the number of node power equipment recorded in the regulation cloud data system is n, n is generally a large number, then there are n(n-1) line connection possibilities between the node power equipment in the data space of the two-dimensional homogenization data set D x D data structure, n(n-1) compared with all the n square points of the two-dimensional homogenization data set D x D data structure itself, the difference of N data points is just located on the diagonal line of this data structure, and the N data points on the diagonal line have been filled and constructed in the first operation; This perfect coincidence is the basis for constructing the following A-O-Z data structure, and for the A-O-Z data structure, specifically:

[0025] 3-2-1、In the non-diagonal line area of the two-dimensional homogenization data set D x D data space, for any data point, respectively examine the projection of the x dimension and the y dimension of the D x D data space corresponding to the node power equipment ID, if there is no direct power line connection between the two power equipment, then fill the letter O in this data point;

[0026] 3-2-2、In the non-diagonal line area of the two-dimensional homogenization data set D x D data space, for any data point, respectively examine the projection of the x dimension and the y dimension of the D x D data space corresponding to the node power equipment ID, and define that from x dimension to y dimension is positive, and from y dimension to x dimension is negative, if there is a direct power line connection between the two power equipment, and it is a positive connection, then fill the letter A in this data point;

[0027] 3-2-3、In the non-diagonal line area of the two-dimensional homogenization data set D x D data space, for any data point, respectively examine the projection of the x dimension and the y dimension of the D x D data space corresponding to the node power equipment ID, and define that from x dimension to y dimension is positive, and from y dimension to x dimension is negative, if there is a direct power line connection between the two power equipment, and it is a negative connection, then fill the letter Z in this data point;

[0028] Thus, the A-O-Z data structure purely dataizes the connotative characterization of the spatial connection topology characteristics of the node power equipment in the regulation cloud; at this time, the A-O-Z data structure is combined with the above-mentioned data ridge structure to form an integrated data structure in the DxD data space in terms of data appearance, and not only to fuse the attribute-related structure data of the node power equipment in the regulation cloud system, but especially to integrally fuse the topological distribution of the power equipment and its associated elements in the power distribution network in a pure data mode in terms of data connotation.

[0029] As a preferred technical solution of the present application, it further comprises a subsequent data step 4:

[0030] Step 4, after the above-mentioned data step operation is completed, the structured data in the regulation cloud data system and the topological data associated with the spatial distribution of the power equipment and lines are reconstructed and fused in terms of data path and data connotation; however, there is still non-standardization of data configuration, especially non-regularity of the data ridge structure, and machine learning models need to be introduced in the later stage, and the data objects directly applicable to the latter are generally tensor data configurations with standard regularity in multiple dimensions; at the same time, the A-O-Z data structure has regularity in data structure, but lacks attribute information between the connection lines of the power equipment in data connotation; further investigation of the constructed data structure shows that the above two defects can be compatible and complementary to each other; therefore:

[0031] 4-1, on the diagonal data bit of the two-dimensional homogenization data set DxD data space, based on the consistency of the data bit order in the data step 3-1-2, further zero padding of the blank data bit is implemented to realize the standard regularity of data construction on the entire diagonal line;

[0032] 4-2, the next step is really critical, the non-diagonal line region of the two-dimensional homogenization data set DxD data space, based on the above-mentioned A-O-Z data structure, it can be seen that the data on the entire non-diagonal line region is a, o, z data for representing the topological relationship of the connection lines of the node power equipment in the regulation cloud, which is single data without dimension expansion characteristics; at this time, considering the lack of attribute information between the connection lines of the power equipment in the A-O-Z data structure in terms of data connotation, in the non-diagonal line region of the two-dimensional homogenization data set DxD data space, the standardized attribute information of the power connection lines in the regulation cloud system metadata and the data dictionary is taken as the subsequent data for data fusion as the first data of the existing a, o, z data;

[0033] 4-2-1. First, the attribute data of the power connection line includes data a, o, and z, with these as the first and second data. For data o, all possible extended data bits are filled with zeros. For data a and z, the attribute data of the power connection line are filled in order. The attribute data of the power connection line includes impedance, capacity, transmission cost, connectivity, connectivity adjustability, etc. Similar to the processing in the construction of the data ridge structure, the attribute data of the power connection line uniformly adopts the standardized attribute data in the metadata and data dictionary of the control cloud system.

[0034] 4-2-2 Next, corresponding to the operation in step 3-1-2, when filling the attribute data of different power connection lines under the guidance of a or z, the attribute data of the same type of different power connection lines adopt the same ranking.

[0035] 4-2-3, which corresponds to the operation in step 3-1-3, involves extending the data along another dimension orthogonal to the D×D data space when filling the attribute data of different power connection lines under the guidance of a or z. Specifically, the z dimension of 3-1-3 can be used or a new dimension can be created as needed.

[0036] The aforementioned data structure is used to introduce machine learning and artificial intelligence platforms into the control of cloud data for data training.

[0037] The beneficial effects of adopting the above technical solution are as follows: Addressing the shortcomings of existing data systems, such as fragmented data structures and related data silos, as well as the reliance on human expert knowledge for data analysis and processing at the underlying data structure level, this invention proposes a modular-digital integrated data platform for distribution network diagrams based on a control cloud. The core of this platform is the construction of a novel integrated data structure that effectively integrates the structured attribute data of power equipment with the graphical topology data of power lines. The integrated data structure, its internal data partitions (diagonal and off-diagonal regions), and the global fusion of power equipment attribute information and connection line diagram attribute data based on data partitioning and data dimension extension lay a data foundation for the introduction of advanced data analysis models such as machine learning and artificial intelligence. Detailed technical features and beneficial effects of this invention are described in the embodiments below. Detailed Implementation

[0038] In the following description of the embodiments, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail.

[0039] As used in the description of the application and the appended claims, the term “if’ can be interpreted as meaning “when” or “upon” or “in response to a determination” or “in response to a detection” depending on the context. Similarly, the phrase “if it is determined” or “if [the described condition or event] is detected” can be interpreted as meaning “upon a determination” or “in response to a determination” or “upon a detection of [the described condition or event]” or “in response to a detection of [the described condition or event]” depending on the context.

[0040] In addition, in the description of the application and the appended claims, the terms “first”, “second”, “third”, etc. are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance. The reference “one embodiment” or “some embodiments” and the like described in the application means that the specific features, structures or characteristics described in connection with the embodiment are included in one or more embodiments of the application. Therefore, the statements “in one embodiment”, “in some embodiments”, “in other some embodiments”, “in further some embodiments” and the like appearing in different places in the specification are not necessarily all referring to the same embodiment, but mean “one or more but not all embodiments”, unless otherwise specifically emphasized. The terms “include”, “contain”, “have” and their variants mean “include but not limited to”, unless otherwise specifically emphasized.

[0041] Embodiment 1, integrated data structure

[0042] Based on the existing power grid regulation cloud system and the standard data set constructed under various specifications such as power dispatch general data object structured design, as well as the maturity and increasingly widespread application of machine learning and artificial intelligence, the application is based on the power distribution network regulation cloud (internally referred to as “sky cloud”) data system, and the standardized and standardized power dispatch general data object and its metadata and data dictionary set in the regulation cloud data system are the underlying data object. The regulation cloud data system is oriented to the improvement and reconstruction of machine learning. The structured data of power equipment in the regulation cloud data system and the graph topology data associated with the spatial distribution of power lines are reconstructed and fused in data path and data content. Then a pure data skeleton is obtained, and the multi-dimensional discrete data configuration requirement of the machine learning model is adapted.

[0043] In addition to the fusion of the structure data of the node power equipment in the regulation cloud system, the application integrates the graph topology distribution of the associated elements such as the power line diagram in the distribution network in a pure data mode.

[0044] Embodiment 2, basic data construction process

[0045] Data construction is to take the node information in the regulation and control cloud system as the initial data set, and use the standardized ID of the node power equipment in the regulation and control cloud system as the initial data set D. All elements in the D set, that is, the standardized ID of all node power equipment recorded in the regulation and control cloud, are first generated in a random order, and then all elements are sorted in order according to the random order and generate serial number identification. The serial number identification generated this time is in the form of read-only as the permanent serial number identification of each node power equipment in this data structure. The purpose of the above sorting of node equipment is mainly to matrix the node power equipment in this step, specifically, according to the permanent serial number identification, all node power equipment of D set is simultaneously expanded in the same order in two orthogonal dimensions, which is executed by two data operations: the first operation is to expand all node power equipment of D set in order according to one dimension such as x dimension, wherein the order is according to the size order of the permanent serial number identification; the second operation is to expand all node power equipment of D set in order according to another orthogonal dimension such as y dimension, the order of the second operation is consistent with the order of the first operation, so it is called "same order expansion", and the obtained two-dimensional same order data set is denoted as DxD.

[0046] Example 3, core data process

[0047] As the core of data processing, on the basis of example 2, the structured data in the regulation and control cloud data system and the topological data associated with the spatial distribution of power equipment and lines are reconstructed and fused to form an integrated data structure with pure structured data as the skeleton and adapt to the internal multi-dimensional discrete data configuration requirements of machine learning model. Specifically, on the two-dimensional same order data set DxD, the alignment of all node power equipment in the initial D set in the regulation and control cloud is realized on the diagonal line, which is equivalent to expanding all node power equipment in the initial D set in the regulation and control cloud in the diagonal line of the two-dimensional same order data set DxD in order according to the set permanent serial number identification,

[0048] Therefore, the first operation of this data step is to fill the attribute data of the power equipment of each node of the regulation cloud data system into the diagonal line in the two-dimensional homogenization data set D x D. First, the attribute data contains or does not contain the normalized ID of the node power equipment in the initial D set. When the ID data in the D set is contained, the ID data is taken as the first data of the attribute data set, and the remaining attribute data of the node power equipment is sequentially arranged and filled. Similar to the ID data of the power equipment, the remaining attribute data of the node power equipment uniformly uses the normalized attribute data in the regulation cloud system metadata and the data dictionary. The remaining attribute data of the node power equipment includes the electrical property parameters and the identification property parameters of the equipment. The electrical property parameters include the rated voltage, the rated load, the rated capacity and other physical parameters associated with the power grid operation. The identification property parameters include the equipment name, the manufacturer and other non-physical parameters. Then, when the attribute data of different node power equipment is filled in the diagonal line of the two-dimensional homogenization data set D x D, the same arrangement is used for the same type of attribute data of different power equipment. For example, the normalized ID of the node power equipment is in the first data bit, and the equipment manufacturer is in the second bit. Therefore, when the attribute data of different node power equipment is filled in the diagonal line of the two-dimensional homogenization data set D x D, the manufacturer data of all node power equipment is filled in the second data bit. At this time, the most important thing is that the attribute data set is configured in the diagonal line of the two-dimensional homogenization data set D x D. Although the two-dimensional homogenization data set D x D has formed a data space expanded on a plane, it is considered that this data space will be occupied by the A-O-Z data structure used to represent the spatial connection topology characteristics of the node power equipment in the regulation cloud. Therefore, the attribute data set is expanded in the third dimension, i.e. the z dimension, which is orthogonal to the two-dimensional homogenization data set space. Thus, a data ridge structure is constructed in the diagonal line of the two-dimensional homogenization data set D x D, which is expanded along the third dimension and contains the attribute data of the node power equipment of the regulation cloud.

[0049] The second operation of this data step is to construct an A-O-Z data structure for representing the spatial connection topology characteristics of the node power equipment in the regulation cloud in the non-diagonal line area of the two-dimensional homogenization data set D x D. Specifically, in the data space of the two-dimensional homogenization data set D x D data structure, assuming that the number of node power equipment recorded in the regulation cloud data system is n, n is generally a large number, then there are n(n-1) line connection possibilities between the node power equipment in the data space of the two-dimensional homogenization data set D x D data structure, n(n-1) compared with all the n square points of the two-dimensional homogenization data set D x D data structure itself, the difference of N data points is located on the diagonal line of this data structure, and the N data points on the diagonal line have been filled and constructed in the first operation. This perfect coincidence is the basis for constructing the following A-O-Z data structure. For the A-O-Z data structure, specifically:

[0050] In the n(n-1) data points on the non-diagonal line area of the two-dimensional homogenization data set D x D data space, for any data point, respectively investigate the node power equipment ID corresponding to its projection in the x dimension and y dimension of the D x D data space. If there is no direct power line connection between the two power equipment, fill the letter O in this data point. Then, define the positive direction from x dimension to y dimension, and the negative direction from y dimension to x dimension. If there is a direct power line connection between the two power equipment, and it is a positive connection, fill the letter A in this data point. If it is a negative connection, fill the letter Z in this data point. In this way, the A-O-Z data structure purely dataizes the connotation representation of the spatial connection topology characteristics of the node power equipment in the regulation cloud. At this time, the A-O-Z data structure is combined with the above-mentioned data data spine structure to form an integrated data structure in the D x D data space in terms of data appearance, and not only integrates the attribute-related structure data of the node power equipment in the regulation cloud system, but especially integrates the topology distribution of the power equipment and its associated elements in the power distribution network in a pure data mode.

[0051] After the above data step operation is completed, it has been realized to reconstruct and fuse the structured data in the cloud data system and the topological data associated with the spatial distribution of power equipment and lines on the data path and data connotation; However, there is still non-standardization of data configuration, especially non-regularity of data roof structure. Considering the need to introduce machine learning models later, the data objects directly applicable to the latter are generally tensor data configurations with standard regularity in multiple dimensions. At the same time, the A-O-Z data structure has regularity in data structure, but lacks attribute information between power equipment connection lines in data connotation. In-depth exploration of the constructed data structure, the above two defects can be compatible and complementary to each other.

[0052] Therefore, first, on the diagonal data bit of the two-dimensional homogenization data set D x D data space, based on the setting of the data ridge structure about the consistency of the data bit order, the standardization of the data construction on the entire diagonal line is realized by zero padding of blank data bits. The real key is the non-diagonal line area of the two-dimensional homogenization data set D x D data space. Based on the above A-O-Z data structure, it can be seen that the data on the entire non-diagonal line area is a, o, z data for representing the topological relationship of the power equipment spatial connection line of the cloud node, which is single data without dimension expansion characteristics. At this time, considering the lack of attribute information between power equipment connection lines in the data connotation of the A-O-Z data structure, in the non-diagonal line area of the two-dimensional homogenization data set D x D data space, the standardized attribute information about the power connection line in the cloud system metadata and the data dictionary is taken as the subsequent data for data fusion, with the existing a, o, z data as the first data;

[0053] Specifically, first, the attribute data of the power connection line contains a, o, z data and takes them as the first data, for data o, all possible extension data bits are all zero padded; for data a and z, the attribute data of the power connection line is sequentially arranged and filled; the attribute data of the power connection line includes impedance, capacity, transmission cost, connectivity, connectivity adjustability, etc.; similar to the processing in the data roof structure construction, the attribute data of the power connection line uniformly adopts the standardized attribute data in the regulation cloud system metadata and data dictionary; as for subsequent structured processing, reference can be made to the processing of the data ridge structure of the diagonal area on the node power equipment attribute data, and the attribute data of the power line is processed in a similar ordered and dimension extension manner; wherein, for the dimension extension processing, when the attribute data of different power connection lines is filled with data under the guidance of a or z, the data is extended along another dimension orthogonal to the DxD data space, which can be introduced in the z dimension (a new dimension can also be created as needed) in the data ridge structure. When the z dimension is used, after the ordered filling based on the standardized data of the power connection line in the regulation cloud under the guidance of a or z and the zero padding of the blank data bit, the standardized data configuration directly applicable to machine learning is obtained; for the case of using a newly created dimension, the data processing logic and path are also the same (the difference lies in that more zero padding may be involved, and the parameter size of the data structure is further expanded, etc.).

[0054] As can be seen from the above embodiments, in view of the problems of scattered data structure and related data island existing in the existing data system, and the defects that the bottom layer of the data structure relies on artificial expert knowledge for data analysis and processing, the research of the present application proposes a distribution network graph and digital integrated data platform based on regulation cloud. The core of the platform is the construction of a new type of integrated data structure, which can effectively fuse the structured attribute data of power equipment and the graph topology data of power lines. The integrated data structure and the data partition (diagonal area and non-diagonal area) inside it, as well as the global fusion of power equipment attribute information and connection line graph attribute data based on data partition and data dimension extension, lay a data foundation for the introduction of advanced data analysis models such as machine learning and artificial intelligence.

[0055] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0056] The above-described embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1.A method for constructing a modulated cloud-based distribution network diagram digital-analog integrated data structure, characterized in that: the integrated data structure takes node information in a modulated cloud system as an initial data set, specifically, using the standardized ID of the node power equipment in the modulated cloud system as the initial data set D; in the first step, all elements in the D set, i.e., the standardized ID of all node power equipment recorded in the modulated cloud, are specified and ordered or randomly ordered, and are taken as the permanent serial number identification of each node power equipment in this data structure in a read-only form; wherein the random ordering operation first generates a random order, and then directly sorts all elements in the D set according to the random order and generates serial number identification; the generated serial number identification is taken as the permanent serial number identification of each node power equipment in this data structure in a read-only form; in the second step, two data operations are included: 2-1, the first operation, the node power equipment of the D set is sequentially expanded according to one dimension, i.e., the x dimension, wherein the sequence is according to the size order of the permanent serial number identification; 2-2, the second operation, the node power equipment of the D set is sequentially expanded according to another orthogonal dimension, i.e., the y dimension, the sequence of the second operation is consistent with that of the first operation, and the obtained two-dimensional same sequence data set is denoted as D×D; in the third step, which is the core data processing step, specifically includes: 3-1, the first operation of this data step is to fill the attribute data of each node power equipment of the modulated cloud data system into the diagonal line of the two-dimensional same sequence data set D×D; 3-1-1, first, the attribute data does or does not contain the node power equipment standardized ID in the initial D set, when containing the ID data in the D set, the ID data is taken as the first data of the attribute data set, and the remaining attribute data of the node power equipment is sequentially ranked and filled; in addition to the ID data of the power equipment, the remaining attribute data of the node power equipment uniformly uses the standardized attribute data in the metadata and data dictionary of the modulated cloud system; the remaining attribute data of the node power equipment includes the electrical property parameters and the identification property parameters of the equipment; the electrical property parameters include the rated voltage, the rated load, the rated capacity and the physical parameters associated with the power grid operation; the identification property parameters include the equipment name and the manufacturer non-physical parameters; 3-1-2, when filling the attribute data of different node power equipment on the diagonal line of the two-dimensional same sequence data set D×D, the same type attribute data of different power equipment adopts the same ranking order; 3-1-3, on the basis of the above 3-1-1 and 3-1-2 data rules, the attribute data set is expanded in the third dimension orthogonal to the two-dimensional same sequence data set space, i.e., the z dimension; thus, through the first operation, a data ridge structure is constructed on the diagonal line of the two-dimensional same sequence data set D×D, which contains the attribute data of the node power equipment of the modulated cloud along the third dimension, and is called a data ridge structure. ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ 3-2、The second operation of this data step is to construct the A-O-Z data structure for representing the spatial connection topology characteristics of the node power equipment in the regulation cloud in the non-diagonal line area of the two-dimensional homogenization data set D x D; 3-2-1、in the non-diagonal line region of the two-dimensional homogenization data set D x D data space data sites, for any data site, respectively investigate the node power equipment ID corresponding to its projection on the x dimension and y dimension of the D x D data space, if there is no direct power line connection between the two power equipment, then fill the data site with the letter O; 3-2-2、in the non-diagonal line region of the two-dimensional homogenization data set D x D data space data sites, for any data site, respectively investigate the node power equipment ID corresponding to its projection on the x dimension and y dimension of the D x D data space, and define that the direction from x dimension to y dimension is positive, the direction from y dimension to x dimension is negative, if there is a direct power line connection between the two power equipments, and it is a positive connection, then this data site is filled with the letter A; 3-2-3、in the non-diagonal line region of the two-dimensional homogenization data set D x D data space data bit, respectively, investigate the node power equipment ID corresponding to its projection on the x dimension and y dimension of the D x D data space, and define the positive direction from x dimension to y dimension, and the negative direction from y dimension to x dimension. If there is a direct power line connection between the two power equipment, and the connection is negative, then fill the data bit with the letter Z; Thus, the A-O-Z data structure purely dataizes the connotation representation of the spatial connection topology characteristics of the node power equipment in the regulation cloud; at this time, the A-O-Z data structure is combined with the above-mentioned data spine structure to form an integrated data structure in the D x D data space in terms of data appearance, and not only the attribute-related structure data of the node power equipment in the regulation cloud system is fused, but especially the topology distribution of the power equipment and its associated elements in the distribution network is integrated and fused in a pure data mode. 2.The method of claim 1, wherein the method is characterized by: It also includes subsequent data step 4: 4-1, on the diagonal data bit of the two-dimensional homogenization data set D x D data space, based on the consistency of the data bit order in data step 3-1-2, further through zero padding of blank data bit to realize the standardization of data construction on the entire diagonal line; 4-2, the next step, the real key is that in the non-diagonal line area of the two-dimensional homogenization data set D x D data space, based on the A-O-Z data structure, the data on the entire non-diagonal line area is a, o, z data for representing the spatial connection line topology relationship of the regulation cloud node power equipment, which is single data without dimension expansion characteristics; At this time, considering the lack of attribute information between the A-O-Z data structure and the power connection line, in the non-diagonal line area of the two-dimensional homogenization data set D x D data space, the standardized attribute information about the power connection line in the regulation cloud system metadata and data dictionary is taken as the subsequent data for data fusion; 4-2-1, first, the attribute data of the power connection line contains a, o, z data and takes them as the first data, for data o, all possible extension data bits are zero filled; for data a and z, the attribute data of the power connection line is sequentially arranged and filled; the attribute data of the power connection line includes impedance, capacity, transmission cost, connectivity, and connectivity adjustability; the attribute data of the power connection line uniformly uses the standardized attribute data in the regulation cloud system metadata and data dictionary; 4-2-2, then, corresponding to the operation in data step 3-1-2, when filling the attribute data of different power connection lines under the guidance of a or z, the same type of attribute data of different power connection lines is arranged in the same position; 4-2-3, here, corresponding to the operation of data step 3-1-3, when filling the attribute data of different power connection lines under the guidance of a or z, the data is expanded along the other dimension orthogonal to the D x D data space; Specifically, the z dimension of 3-1-3 or a new dimension can be used as needed.