Microgrid equipment dynamic portrait construction method and system based on full-factor tags

Abstract

The present invention discloses a method and system for constructing a dynamic portrait of a microgrid device based on full-factor labels, which belongs to the field of information processing technology, and includes: S1, clustering analysis of the full-factor labels of the microgrid and constructing a regional grid of the microgrid system according to functional attributes, determining the initial boundary and initial context of the regional grid to construct a microgrid device portrait; S2, obtaining the device variables corresponding to the regional grid to construct a triple matrix, and determining the boundary correction factor and the context correction factor according to the state transition path of each device variable in the triple matrix; S3, correcting the initial boundary and the initial context in response to the boundary correction factor and the context correction factor to reconstruct the microgrid device portrait. By constructing a triple matrix, the changes in the device state are fully captured, the state transition path is analyzed and the grid boundary and context are dynamically adjusted, and the microgrid device state portrait is accurately portrayed in real time, thereby improving the comprehensiveness and accuracy of device state monitoring.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a method and system for constructing a dynamic portrait of a microgrid device based on full-factor tags. Background Art

[0002] With the rapid development of distributed energy and smart grids, the importance of microgrids, as small power systems that connect distributed power sources, energy storage devices and loads, has become increasingly prominent. However, microgrid equipment is diverse and its operating status is complex and changeable. How to effectively monitor and manage these devices has become the key to optimizing the operation of microgrids. Traditional methods are mostly based on monitoring of a single or a few key indicators, which makes it difficult to fully reflect the actual operating status and potential risks of the equipment. When the system encounters a single point failure or multiple point failures, it is difficult to accurately characterize the cause of the failure and make a timely and effective response.

[0003] The above information disclosed in the Background section is only for enhancement of understanding of the background of the present application and therefore it may contain information that does not constitute the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0004] The present invention aims to solve the problem that it is difficult for existing microgrid systems to accurately characterize the causes of faults and make timely and effective responses; a method and system for constructing dynamic portraits of microgrid equipment based on full-factor labels are proposed. Through cluster analysis of full-factor labels in the microgrid system, scientific classification and regional grid division of microgrid equipment are achieved, and then an initial portrait including the physical and logical connection relationships between devices is constructed. On this basis, a triple matrix is ​​constructed to comprehensively capture changes in device states, and state transition path analysis is used to dynamically adjust grid boundaries and contexts, so as to accurately characterize the state portrait of microgrid equipment in real time. This not only improves the comprehensiveness and accuracy of equipment state monitoring, but also provides strong data support for the optimized operation and fault prevention of microgrids.

[0005] In a first aspect, a technical solution provided in an embodiment of the present invention is a method for constructing a dynamic portrait of a microgrid device based on full-factor tags, comprising the following steps:

[0006] S1. Perform cluster analysis on all element labels of the microgrid and construct the regional grid of the microgrid system according to the functional attributes, determine the initial boundary and initial context of the regional grid to construct the microgrid equipment portrait;

[0007] S2, obtaining the device variables corresponding to the regional grid to construct a triple matrix, and determining the boundary correction factor and the vein correction factor according to the state transition path of each device variable in the triple matrix;

[0008] S3. In response to the boundary correction factor and the context correction factor, the initial boundary and the initial context are corrected respectively to reconstruct the microgrid device portrait.

[0009] In this scheme, through the cluster analysis of all-factor labels, the scientific classification and regional grid division of microgrid equipment are realized, and the initial boundaries and initial context of the regional grid are determined, which provides an initial framework for the construction of microgrid equipment portraits, helps to fully capture the associations between devices, and provides a solid foundation for the subsequent dynamic portrait construction; further, by constructing a triple matrix to fully capture the changes in equipment status, it provides data support for the analysis of state transition paths; through the analysis of state transition paths, abnormal changes in equipment status can be discovered in time, and timely and effective preventive measures can be formulated based on abnormal changes. By obtaining correction factors, it provides a basis for subsequent dynamic corrections, realizes real-time updating of microgrid equipment portraits, ensures the accuracy and timeliness of portraits, and can more clearly display the associations and status changes between devices through portrait reconstruction, providing strong support for the optimized operation and fault handling of microgrids.

[0010] Preferably, the cluster analysis of all element labels of the microgrid and construction of a regional grid of the microgrid system according to functional attributes comprises the following steps:

[0011] S101, obtaining all-factor information of the area covered by the microgrid system, wherein the all-factor information includes equipment structure topology data, equipment real-time status data, and equipment historical maintenance data;

[0012] S102, performing cluster analysis on all factor information according to functional attributes combined with a clustering algorithm to obtain a device set, and using the geographical attributes of the devices in the device set as grid units to determine a regional grid.

[0013] Preferably, determining the initial boundary and initial context of the regional grid to construct a microgrid device portrait comprises the following steps:

[0014] S111, taking the physical connection and logical connection between each device in the regional grid as the first initial context, and determining the grid space according to the first initial context and the geographical coordinates of the device; taking the regional outline of the two-dimensional mapping area of ​​the grid space on the geographical coordinates corresponding to the regional grid as the initial boundary of each regional grid;

[0015] S122, determining the physical connection and logical connection of each device between the regional grids as the second initial context; and constructing a microgrid device portrait according to the first initial context, the initial boundary and the second initial context.

[0016] Preferably, the step of obtaining device variables corresponding to the regional grid and constructing a triple matrix comprises the following steps:

[0017] S201, acquiring state variable data, control variable data and clock variable data in the microgrid system to construct a triplet of each device;

[0018] S202, constructing a triplet matrix according to the triplet of each device in the regional grid on the time section;

[0019] Wherein, the state variable data at least includes voltage data and current data;

[0020] The control variable data at least includes switch state data and parameter adjustment data;

[0021] The clock variable data at least includes timestamp data and state duration data.

[0022] Preferably, the boundary correction factor and the context correction factor are determined according to the state transition path of each device variable in the triple matrix; the steps include:

[0023] S211, setting a state threshold of a state variable corresponding to each device, and when it is detected that the state variable exceeds the set state threshold, determining a faulty device and determining a state transition direction according to a correlation matrix corresponding to the faulty device;

[0024] S212, determining a target transition device according to a state transition direction, and determining transition content according to a state change of the target transition device;

[0025] S213, determining a state callback factor according to the transition content and transition direction of each device in the regional grid, and determining a state transition path on each time section of the regional grid according to the state callback factor;

[0026] S214: taking each device and its connection in the state transition path as a context correction factor, and taking each device and its geographical coordinates in the state transition path as a boundary correction factor.

[0027] Preferably, the step of determining the faulty device and determining the state transition direction according to the association matrix corresponding to the faulty device comprises the following steps:

[0028] Determine the relevance of each device to the faulty device based on the functional similarity and the fault coupling degree, and then determine the relevance matrix;

[0029] Determine the faulty device and obtain the cluster center corresponding to the faulty device, and determine the functional similarity based on the ratio of the distance from each faulty device to the cluster center and the distance from the remaining devices to the cluster center in the regional grid;

[0030] Determine the fault coupling degree based on the state change rate of each device when the faulty device fails in the historical time section;

[0031] The correlation value of each device relative to the faulty device is obtained by weighted summation according to the functional similarity, fault coupling degree and their corresponding weight factors, and the correlation matrix corresponding to the faulty device is constructed based on the correlation value; the element with the largest value in the correlation matrix is ​​taken as the state transition direction.

[0032] Preferably, the method of determining the state callback factor according to the transition content and transition direction of each device in the regional grid, and determining the state transition path on each time section of the regional grid according to the state callback factor comprises the following steps:

[0033] If the transition direction points to a device in the regional grid, the transition content includes the parameter change of the first initial context corresponding to the change of the physical connection and the logical connection in the first initial context, as well as the time and duration of determining the transition change, and the change parameter in the transition content is extracted as the first state callback factor; wherein the physical connection and the logical connection between each device in the regional grid are taken as the first initial context;

[0034] If the transition direction points to the device between the regional grids, the transition content includes the change of the physical connection and the logical connection in the second initial context corresponding to the parameter change of the second initial context and the time and duration of the transition change, and the change parameter in the transition content is extracted as the second state callback factor; wherein the physical connection and the logical connection of each device between the regional grids are determined as the second initial context;

[0035] The adjustment direction, adjustment content, and adjustment time of each metadata in the triple matrix are determined according to the first state callback factor and / or the second state callback factor; the state transition path of each time section of the regional grid is determined according to the adjustment direction, adjustment content, and adjustment time state corresponding to the devices within and between the regional grids.

[0036] Preferably, in S214, using each device and its connection in the state transition path as a context correction factor comprises the following steps:

[0037] Each device and its connection in the grid space is determined through the state transition path as the first initial context correction factor; each device and its connection between grid spaces is determined through the state transition path as the second initial context correction factor.

[0038] Preferably, the method of correcting the initial boundary and the initial context in response to the boundary correction factor and the context correction factor respectively and reconstructing the microgrid device portrait comprises the following steps:

[0039] S31, correcting the initial boundary of each grid space according to the boundary correction factor to obtain an updated boundary;

[0040] Synchronously, the first initial context in each grid space is corrected according to the first initial context correction factor to obtain a first updated context;

[0041] Synchronously, the second initial context between the grid spaces is corrected according to the second initial context correction factor to obtain a second updated context;

[0042] S32. Reconstruct the microgrid device portrait according to the first update context, the second update context, and the update boundary.

[0043] In the second aspect, a technical solution provided in an embodiment of the present invention is a system for constructing a dynamic portrait of a microgrid device, which is applicable to a method for constructing a dynamic portrait of a microgrid device based on full-factor tags, including:

[0044] Initial construction module: cluster analysis is performed on all element labels of the microgrid and the regional grid of the microgrid system is constructed according to the functional attributes. The initial boundary and initial context of the regional grid are determined to construct the microgrid equipment portrait.

[0045] Correction module: obtain the device variables corresponding to the regional grid to construct a triple matrix, and determine the boundary correction factor and the vein correction factor according to the state transition path of each device variable in the triple matrix;

[0046] Reconstruction module: in response to the boundary correction factor and the context correction factor, respectively correct the initial boundary and the initial context to reconstruct the microgrid device portrait.

[0047] In the third aspect, a technical solution provided in an embodiment of the present invention is an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of a method for constructing a dynamic portrait of a microgrid device based on full-factor tags are implemented.

[0048] In a fourth aspect, a technical solution provided in an embodiment of the present invention is a storage medium, in which computer executable instructions are stored. When the computer executable instructions are loaded and executed by a processor, the steps of a method for constructing a dynamic portrait of a microgrid device based on full-factor tags are implemented.

[0049] The present invention has at least the following substantial effects:

[0050] (1) The present invention classifies microgrid devices scientifically according to their functional attributes through cluster analysis of all element labels in the microgrid system, and constructs regional grids, ensuring that the devices in each grid have similar functional characteristics and operating status, providing a basis for subsequent status monitoring. Furthermore, by constructing a triple matrix and analyzing the state transition path, it is possible to capture changes in device status in real time, including abnormal fluctuations in state variables and potential fault signs. This comprehensive monitoring not only covers the real-time status of the device, but also takes into account historical data and future trends, thereby achieving an accurate characterization of the device status. This technical effect is of great significance for timely detection of equipment failures, prevention of potential risks, and improvement of the overall operating efficiency of the microgrid;

[0051] (2) In view of the disadvantages of the traditional method of monitoring based on a single or a few key indicators, it is difficult to fully reflect the actual operating status and potential risks of the equipment. When the system encounters a single point failure or multiple point failures, it is difficult to accurately characterize the cause of the failure and make a timely and effective response. The present invention introduces boundary correction factors and context correction factors to dynamically adjust the boundaries and contexts in the portrait according to the changes in the equipment status, ensuring that the portrait is always consistent with the actual operating status of the equipment, providing accurate and timely decision support for operation and maintenance personnel. In particular, when the system equipment has multiple point failures or abnormal status, the dynamic portrait can quickly reflect these changes, helping the operation and maintenance personnel to quickly locate the problem and take corresponding measures;

[0052] (3) By comprehensively monitoring the equipment status and dynamically updating the equipment portrait, the present invention can timely detect potential faults and abnormal conditions. Once a fault or abnormality is detected, the present invention can immediately trigger the early warning mechanism and notify the operation and maintenance personnel to handle it. At the same time, since the equipment portrait contains detailed information and associations of the equipment, the operation and maintenance personnel can quickly locate the fault point and take corresponding treatment measures. This fault prevention and rapid response mechanism significantly enhances the safety and stability of the microgrid. Traditional methods can often only perform passive processing after the fault occurs, while the present invention can detect potential faults in advance and take preventive measures, which helps to reduce the frequency and scope of faults and improve the reliability and availability of the microgrid.

[0053] The above invention content is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts.

[0055] Figure 1 The present invention is a flowchart of a method for constructing a dynamic portrait of a microgrid device based on full-factor tags.

[0056] Figure 2 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0057] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation method described herein is only an optimal embodiment of the present invention, which is only used to explain the present invention and does not limit the scope of protection of the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0058] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the drawings; the process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0059] Example: Figure 1 As shown, a technical solution is a method for constructing a dynamic portrait of a microgrid device based on full-factor tags, comprising the following steps:

[0060] S1. Perform cluster analysis on all element labels of the microgrid and construct the regional grid of the microgrid system according to the functional attributes, determine the initial boundary and initial context of the regional grid to construct the microgrid equipment portrait.

[0061] Specifically, the cluster analysis of all element labels of the microgrid and construction of a regional grid of the microgrid system according to functional attributes includes the following steps:

[0062] S101, obtaining all-factor information of the area covered by the microgrid system, wherein the all-factor information includes equipment structure topology data, equipment real-time status data, and equipment historical maintenance data;

[0063] S102, performing cluster analysis on all factor information according to functional attributes combined with a clustering algorithm to obtain a device set, and using the geographical attributes of the devices in the device set as grid units to determine a regional grid.

[0064] In this embodiment, it is first required to collect all-round information or all-element information of all relevant equipment in the microgrid system, including but not limited to equipment structure topology (i.e., connection relationship between equipment (including physical connection and logical connection), layout, etc.), real-time status data (such as voltage, current, power factor and other operating parameters) and historical maintenance data (maintenance records, fault history, etc.); by combining the structural information of the equipment with the dynamic operation data, multi-dimensional information fusion from static to dynamic, from macro to micro is realized. This fusion not only improves the comprehensive understanding of the equipment status, but also provides a rich data feature set for subsequent clustering analysis. Traditional clustering is mostly based on distance or similarity, while this solution innovatively introduces functional attributes as an important basis for clustering. In the clustering process, in addition to considering the numerical similarity of data points, more attention is paid to the actual functional role and interaction of equipment in the microgrid, such as power generation, energy storage, transmission, distribution, etc., so as to ensure that the clustering results are more in line with the actual operation logic of the microgrid; clustering algorithms such as K-means, DBSCAN, hierarchical clustering, etc. can be used to adapt to functional attribute orientation. For example, when K-means is used for clustering, K initial cluster centers are first selected from the device data set. These cluster centers should cover devices with different functional attributes as much as possible. Power generation equipment, energy storage equipment, transmission equipment, etc. can be classified into different functional categories respectively. In the K-means algorithm, Euclidean distance or cosine similarity is used to measure the similarity between data points. In order to incorporate functional constraints, the distance metric is modified to take the similarity of functional attributes into consideration. For example, a weighted distance metric is defined in which the weight corresponding to the functional attribute is set to a higher value. According to the modified distance metric, each device is assigned to the nearest cluster center, and the cluster center is calculated in rounds until the cluster center no longer changes or the maximum number of iterations is reached. The above clustering method ensures that the devices in the same cluster have a high degree of functional consistency.

[0065] Then, the equipment set obtained after clustering, for example: Power generation equipment set: mainly composed of distributed power sources such as solar photovoltaic panels, wind turbines, small hydropower equipment, fuel cells, micro gas turbines, and internal combustion engines. The power generation equipment collection is jointly responsible for the power supply of the microgrid; the energy storage equipment collection: composed of energy storage devices such as batteries, supercapacitors, and flywheel energy storage. The energy storage equipment collection plays a role in balancing supply and demand fluctuations, providing frequency regulation, voltage support, and emergency backup power supply in the microgrid; the power electronic equipment collection: including inverters and converters, etc., which are used to convert different forms of power supply power into the form of power required by the grid or load, and realize the effective control and management of power; the distribution facility collection: including transformers, distribution lines, switchgear, etc., responsible for the distribution and transmission of power; the monitoring and protection device collection: including energy management system (EMS), smart meters, protection relays, etc., responsible for real-time monitoring, data collection, load forecasting, power generation scheduling and optimized operation of the microgrid, as well as fault detection and isolation; further grid division is carried out according to its geographical attributes (such as geographical location, distribution density, etc.), for example, the area where power generation equipment is concentrated is divided into power generation grid, the area where energy storage equipment is concentrated is divided into energy storage grid, and the area where distribution facilities are concentrated is divided into distribution grid, etc.; each regional grid has clear boundaries and context. The boundary defines the geographic scope of the grid, while the context describes the connection relationship and energy flow path between devices in the grid. These boundaries and contexts can be visualized through the Geographic Information System (GIS) as a data framework to depict the initial microgrid equipment portrait, so that operation and maintenance personnel can intuitively understand the distribution and operating status of equipment in each grid. The solution not only considers the functional relevance of the equipment, but also takes into account the optimization of the spatial layout, which facilitates subsequent operation and maintenance management and resource scheduling. By mapping the device collection to a specific geographic grid, regionalized and refined management of the microgrid system is achieved.

[0066] Furthermore, the determining of the initial boundary and initial context of the regional grid to construct the microgrid device portrait comprises the following steps:

[0067] S111, taking the physical connection and logical connection between each device in the regional grid as the first initial context, and determining the grid space according to the first initial context and the geographical coordinates of the device; taking the regional outline of the two-dimensional mapping area of ​​the grid space on the geographical coordinates corresponding to the regional grid as the initial boundary of each regional grid;

[0068] S122, determining the physical connection and logical connection of each device between the regional grids as the second initial context; and constructing a microgrid device portrait according to the first initial context, the initial boundary and the second initial context.

[0069] In this embodiment, physical connection refers to the relationship between devices that are directly connected through physical media such as cables and wires. Identifying physical connections is the basis for building microgrid device portraits, which ensures that the actual path of energy transmission between devices is accurately recorded; logical connections refer to the functional associations between devices, such as control signals, data communications, etc. The identification of logical connections helps to understand the collaborative working mechanism between devices; by taking the physical and logical connections between devices as the first initial context, a network diagram that reflects the relationship between devices can be constructed. This network diagram not only shows the connection relationship between devices, but also implies the relative position of devices in geographic space; combined with the geographic coordinates of the devices, the network diagram can be mapped to the actual geographic space, thereby determining the grid space, the two-dimensional mapping area of ​​the grid space on the geographic coordinates, and its regional outline naturally forms the initial boundary of each regional grid. This mapping method ensures the close integration of device portraits and geographic information, which is not only intuitive, but also easy to integrate with the GIS system to achieve visual display of device portraits.

[0070] Secondly, this application takes into account the mutual coupling between the devices in each regional network, and needs to identify the physical and logical connections between the devices between the regional grids, ensuring that the device portrait can fully reflect the overall structure and operation logic of the microgrid system. Based on the first initial context (the connection relationship between the devices in the regional grid), the initial boundary (the geographical scope of the regional grid), and the second initial context (the connection relationship between the devices between the regional grids), a microgrid device portrait can be constructed. This portrait not only contains detailed information about the equipment (such as type, status, location, etc.), but also shows the connection relationship and collaborative working mechanism between the devices; the process of constructing the device portrait is a process of data integration and knowledge extraction. Through the above means, massive amounts of device data can be converted into structured information that is easy to understand and manage, providing strong support for the operation and maintenance management of the microgrid system.

[0071] S2. Obtain the device variables corresponding to the regional grid to construct a triple matrix, and determine the boundary correction factor and the context correction factor according to the state transition path of each device variable in the triple matrix.

[0072] Specifically, the step of acquiring device variables corresponding to the regional grid and constructing a triple matrix includes the following steps:

[0073] S201, acquiring state variable data, control variable data and clock variable data in the microgrid system to construct a triplet of each device;

[0074] S202, constructing a triplet matrix according to the triplet of each device in the regional grid on the time section;

[0075] Wherein, the state variable data at least includes voltage data and current data;

[0076] The control variable data at least includes switch state data and parameter adjustment data;

[0077] The clock variable data at least includes timestamp data and state duration data.

[0078] In this embodiment, the microgrid system includes multiple devices, such as generators, transformers, energy storage devices and loads. Different devices correspond to different state variable data, control variable data and clock variable data; state variable data include: voltage data: such as the output voltage of the generator, the input / output voltage of the transformer, etc.; current data: such as the output current of the generator, the current of the load, etc.; temperature data: such as the oil temperature of the transformer, the winding temperature of the generator, etc.; power data: such as the output power of the generator, the power consumption of the load, etc. Control variable data include: switch state data: such as the start and stop state of the generator, the opening and closing state of the circuit breaker, etc.; parameter adjustment data: such as the excitation adjustment of the generator, the tap adjustment of the transformer, etc.; clock variable data include: timestamp data: record the specific time point of data sampling or event occurrence; state duration data: record the duration of the device in a specific state. For each device, first select a time section (for example, a time point every minute or every hour), and collect the above three types of data to form a triplet of the device at the time section. The general form of the triplet can be expressed as: {state variable, control variable, clock variable}.

[0079] In order to intuitively and vividly display the triplet, a specific example is: for the generator G1, the triplet at a certain time section t may be as follows: triplet G1t = {(voltage: 230V, current: 100A, temperature: 65℃, power: 50kW), (switch state: open, excitation regulation: 80%), (timestamp: 2023-04-01 12:00:00, state duration: 30 minutes)}.

[0080] Furthermore, after obtaining the triplets of all devices at each time section, these triplets are arranged in the order of devices and time sections to construct a triple matrix. The rows of the matrix represent devices, the columns represent time sections, and the elements in the matrix are the triplets of the corresponding devices and time sections; assuming three devices (G1, T1, L1) and two time sections (t1, t2), the triple matrix is ​​shown in Table 1 below. After constructing the triple matrix, the operating state changes of the equipment, the adjustment of the control strategy, and the influence of time factors can be analyzed according to the state transition path of each device variable in the matrix.

[0081] Table 1. Triplet matrix

[0082]

[0083] Specifically, the boundary correction factor and the context correction factor are determined according to the state transition path of each device variable in the triple matrix; the steps include:

[0084] S211, setting a state threshold of a state variable corresponding to each device, and when it is detected that the state variable exceeds the set state threshold, determining a faulty device and determining a state transition direction according to a correlation matrix corresponding to the faulty device.

[0085] Specifically, the step of determining the faulty device and determining the state transition direction according to the correlation matrix corresponding to the faulty device includes the following steps:

[0086] Determine the relevance of each device to the faulty device based on the functional similarity and the fault coupling degree, and then determine the relevance matrix;

[0087] Determine the faulty device and obtain the cluster center corresponding to the faulty device, and determine the functional similarity based on the ratio of the distance from each faulty device to the cluster center and the distance from the remaining devices to the cluster center in the regional grid;

[0088] Determine the fault coupling degree based on the state change rate of each device when the faulty device fails in the historical time section;

[0089] The correlation value of each device relative to the faulty device is obtained by weighted summation according to the functional similarity, fault coupling degree and their corresponding weight factors, and the correlation matrix corresponding to the faulty device is constructed based on the correlation value; the element with the largest value in the correlation matrix is ​​taken as the state transition direction.

[0090] In this embodiment, for each device, according to its operating characteristics and safety requirements, the state threshold of the state variable, such as the current threshold, the voltage threshold, etc., is set; the state variables of each device are detected in real time through the monitoring system, and when the state variable of a certain device is found to exceed the threshold, the device is determined to be a faulty device; a correlation matrix is ​​constructed based on the functional similarity and fault coupling, wherein the functional similarity is calculated based on the ratio of the distance from the device to the cluster center, and the fault coupling is calculated based on the state change rate of each device when the faulty device fails on the historical time section. Then, the correlation value of each device relative to the faulty device is obtained by weighted summation, and the correlation matrix corresponding to the faulty device is constructed based on the correlation value. The element with the largest value in the correlation matrix is ​​used as the state transition direction. Among them, the calculation formula of functional similarity is: , For equipment i Faulty equipment j The distance to the cluster center, For faulty equipment iDistance to cluster center; Fault coupling degree: ,in Yes Equipment j On the device i The rate of state change when a fault occurs; is the maximum state change rate; the correlation value at this time is: ,in and is the weight factor. The weight factor is determined based on the device type and device failure. Generally, , .

[0091] S212: Determine a target transition device according to the state transition direction, and determine the transition content according to the state change of the target transition device.

[0092] In this embodiment, the target transition device is determined according to the state transition direction, and the state change of the target transition device is extracted as the transition content. The transition content includes parameter changes corresponding to changes in physical and logical connections, as well as the moment and duration of the transition change.

[0093] S213, determining a state callback factor according to the transition content and transition direction of each device in the regional grid, and determining a state transition path on each time section of the regional grid according to the state callback factor, specifically, comprising the following steps:

[0094] If the transition direction points to a device in the regional grid, the transition content includes the parameter change of the first initial context corresponding to the change of the physical connection and the logical connection in the first initial context, as well as the time and duration of determining the transition change, and the change parameter in the transition content is extracted as the first state callback factor; wherein the physical connection and the logical connection between each device in the regional grid are taken as the first initial context;

[0095] If the transition direction points to the device between the regional grids, the transition content includes the change of the physical connection and the logical connection in the second initial context corresponding to the parameter change of the second initial context and the time and duration of the transition change, and the change parameter in the transition content is extracted as the second state callback factor; wherein the physical connection and the logical connection of each device between the regional grids are determined as the second initial context;

[0096] The adjustment direction, adjustment content, and adjustment time of each metadata in the triple matrix are determined according to the first state callback factor and / or the second state callback factor; the state transition path of each time section of the regional grid is determined according to the adjustment direction, adjustment content, and adjustment time state corresponding to the devices within and between the regional grids.

[0097] In this embodiment, when the transition direction points to the device in the regional grid, the present application focuses on the changes in the first initial context (i.e., the physical connection and logical connection between the devices in the regional grid). These changes include changes in physical connections (such as the connection status of cables and lines) and logical connections (such as control logic, signal transmission, etc. between devices), as well as parameter changes corresponding to these changes (such as the change in voltage and current). At the same time, the moment and duration of the transition change are further determined. These information together constitute the transition content and extract the change parameters as the first state callback factor. When the transition direction points to the device between the regional grids, the present application focuses on the changes in the second initial context (i.e., the physical connection and logical connection of the devices between the regional grids). The parameter changes corresponding to these changes, the moment and duration of the transition change are extracted as the second state callback factor. The extracted first state callback factor and the second state callback factor are used to determine the adjustment direction, adjustment content and adjustment time of each metadata in the triple matrix. By introducing the state callback factor and the triple matrix, the state changes of the devices in the regional grid and between the regional grids can be accurately tracked and managed, so that the system can better adapt to the dynamically changing environment and needs.

[0098] In order to facilitate the intuitive understanding of the technical solution of this application, the above technical means are further explained in combination with specific forms. For the device transition within the regional grid, the first state callback factor R 1 can be expressed as a set of parameters for changes in physical and logical connections in the transition content, namely ,in and Respectively represent the change parameters of physical connection and logical connection, ts 1 indicates the start time of the transition change, td1 Indicates the duration of the duration. For device transitions between regional grids, the second state callback factor R 2 is similarly expressed as , where the meaning of each symbol is the same as R 1 is similar, but refers to the connection and transition characteristics between regional grids; the triple matrix T Can be defined as a The matrix of m represents the number of time slices, n Indicates the number of devices or connections (depending on the specific application scenario). Each element It is a triplet, including adjustment direction, adjustment content, and adjustment time. R 1 and R 2. You can update the triple matrix T Specifically, for each time slice and each device or connection i, according to R 1 or R2 to determine the adjustment direction, content, and time. Once the triple matrix T Once updated, the state transition path at each time section of the regional grid can be determined by traversing the elements in the matrix; specifically, for each time section, the state adjustment information of all devices or connections can be viewed and combined to form a state transition path. The state transition path can be formally represented as a sequence , where each Indicated in t The set of states at a time section.

[0099] S214: taking each device and its connection in the state transition path as a context correction factor, and taking each device and its geographical coordinates in the state transition path as a boundary correction factor.

[0100] Specifically, the method of using each device and its connection in the state transition path as a context correction factor includes the following steps:

[0101] Each device and its connection in the grid space is determined through the state transition path as the first initial context correction factor; each device and its connection between grid spaces is determined through the state transition path as the second initial context correction factor.

[0102] Each device and its connection in the grid space is determined through the state transition path as the first initial context correction factor; each device and its connection between grid spaces is determined through the state transition path as the second initial context correction factor.

[0103] In this embodiment, the context correction factor refers to the changes in the states of each device and its connection in the state transition path, wherein the first initial context correction factor standard is the changes in the devices and their connections in the grid space; the second initial context correction factor standard is the changes in the devices and their connections between the grid spaces; it reflects the dynamic adjustment of the physical connection and logical connection within or between the regional grids; physical connection changes: for example, the physical line between device A and device B is rewired, or a device adds a new physical interface to support the connection with other devices. These changes can be quantified by connection state parameters (such as connection strength, bandwidth, delay, etc.). Logical connection changes: for example, the communication protocol between device A and device B is upgraded, or the position of a device in the network topology has changed (such as from an edge node to a core node). It can be quantified by logical connection parameters (such as communication protocol version, network address, routing information, etc.). Timestamp and duration: For each change in connection state, it is also necessary to record the timestamp and duration of its occurrence in order to track the time dynamics in the state transition path. The boundary correction factor refers to the changes in the devices and their geographic coordinates in the state transition path, which reflect the dynamic adjustment of the spatial distribution of devices in the regional grid. Changes in geographic coordinates: For example, if device A fails, in order to ensure the stable operation of the system, the function of A needs to be transferred to device B, resulting in changes in the boundaries of a regional grid (such as expansion or contraction). These changes can be quantified by the latitude and longitude coordinates of the device or the location information relative to a reference point. The geographic location of device A has changed when it is transferred to device B, or the distance between a device and the boundary of the regional grid has changed. These changes can be quantified by calculating the straight-line distance, Euclidean distance or other spatial measurement indicators between devices. Timestamp and duration: Similarly, for each change in geographic coordinates, it is also necessary to record the timestamp and duration of its occurrence in order to track the spatial dynamics in the state transition path. By introducing context correction factors and boundary correction factors, changes in device states and their spatial distribution in the regional grid can be more accurately described and managed, thereby improving the accuracy of state management.

[0104] S3, in response to the boundary correction factor and the context correction factor, respectively correcting the initial boundary and the initial context to reconstruct the microgrid device portrait; specifically, comprising the following steps:

[0105] S31, correcting the initial boundary of each grid space according to the boundary correction factor to obtain an updated boundary;

[0106] Synchronously, the first initial context in each grid space is corrected according to the first initial context correction factor to obtain a first updated context;

[0107] Synchronously, the second initial context between the grid spaces is corrected according to the second initial context correction factor to obtain a second updated context;

[0108] S32. Reconstruct the microgrid device portrait according to the first update context, the second update context, and the update boundary.

[0109] In this embodiment, the initial boundary of each grid space is corrected according to the boundary correction factor (i.e., the change of the device geographic coordinates and the change of the grid space boundary), and the updated boundary will more accurately define the scope of each grid space. According to the first initial context correction factor (i.e., the change of the device connection status in the grid space), the first initial context in each grid space is corrected. Including updating the connection status, communication protocol, bandwidth, delay and other information between devices to reflect the actual interaction relationship between devices. According to the second initial context correction factor (i.e., the change of the device connection status between grid spaces), the second initial context between grid spaces is corrected. It involves updates in cross-grid communication links, data flow, resource sharing, etc. to ensure that the interaction relationship between grid spaces is accurately described. Then, the updated boundary, the first updated context and the second updated context are integrated to form a complete network model containing all grid spaces, devices and their connection relationships; then, based on this network model, the location, status, function of each device and its interaction relationship with other devices are described in detail to form a new microgrid device portrait. Finally, advanced visualization technologies (such as GIS, virtual reality, etc.) are used to present the microgrid equipment portrait in an intuitive and interactive way, which is convenient for operators to monitor, analyze and make decisions. This application can obtain accurate, intuitive and flexible microgrid equipment portraits by updating boundary correction factors and context correction factors in real time, and correcting and reconstructing the initial boundaries and initial contexts, providing strong support for microgrid operation management, resource allocation, fault recovery, etc.

[0110] Embodiment 2: A technical solution also provided in the embodiment of the present invention is a system for constructing a dynamic portrait of a microgrid device, such as Figure 2 The system shown includes:

[0111] Initial construction module 001: cluster analysis of all element labels of the microgrid and construct regional grids of the microgrid system according to functional attributes, determine the initial boundaries and initial context of the regional grid to construct a microgrid equipment portrait;

[0112] Correction module 002: Obtain the device variables corresponding to the regional grid to construct a triple matrix, and determine the boundary correction factor and the vein correction factor according to the state transition path of each device variable in the triple matrix;

[0113] Reconstruction module 003: Responding to the boundary correction factor and the context correction factor, respectively correcting the initial boundary and the initial context to reconstruct the microgrid device portrait.

[0114] In this embodiment, through the cluster analysis of all-factor labels, scientific classification and regional grid division of microgrid equipment are achieved, and the initial boundaries and initial context of the regional grid are determined, which provides an initial framework for the construction of microgrid equipment portraits, helps to fully capture the association relationship between devices, and provides a solid foundation for the subsequent dynamic portrait construction; further, by constructing a triple matrix to fully capture the changes in equipment status, data support is provided for the analysis of state transition paths; through the analysis of state transition paths, abnormal changes in equipment status can be discovered in time, and timely and effective preventive measures can be formulated based on abnormal changes. By obtaining correction factors, a basis is provided for subsequent dynamic corrections, and real-time updates of microgrid equipment portraits are achieved, ensuring the accuracy and timeliness of the portraits. Through portrait reconstruction, the association relationship and state changes between devices can be more clearly displayed, providing strong support for the optimized operation and fault handling of microgrids.

[0115] Embodiment three: An optional embodiment also provided in the embodiments of the present invention is: an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, it implements the steps of a method for constructing a dynamic portrait of a microgrid device based on full-factor tags.

[0116] Embodiment 4: An optional embodiment also provided in the embodiments of the present invention is: a storage medium, in which computer executable instructions are stored, and when the computer executable instructions are loaded and executed by a processor, the steps of a method for constructing a dynamic portrait of a microgrid device based on full-factor tags are implemented.

[0117] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the specific device can be divided into different functional modules to complete all or part of the functions described above.

[0118] In the embodiments provided in the present application, it should be understood that the disclosed structures and methods can be implemented in other ways. For example, the embodiments of the structure described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another structure, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, structures or units, which can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0120] In addition, each functional unit in the embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0121] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0122] The specific implementation described above is a preferred implementation of the method and system for constructing a dynamic portrait of microgrid equipment based on full-element tags of the present invention, but it is not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to this specific implementation. All equivalent changes made in accordance with the shape and structure of the present invention are within the protection scope of the present invention.

Claims

1. A method for constructing a dynamic portrait of microgrid equipment based on full-factor tags, characterized by: The steps include: S1. Perform cluster analysis on all element labels of the microgrid and construct the regional grid of the microgrid system according to the functional attributes, determine the initial boundary and initial context of the regional grid to construct the microgrid equipment portrait; S2, obtaining the device variables corresponding to the regional grid to construct a triple matrix, and determining the boundary correction factor and the vein correction factor according to the state transition path of each device variable in the triple matrix; S3, in response to the boundary correction factor and the context correction factor, respectively correcting the initial boundary and the initial context to reconstruct the microgrid device portrait; Determining the initial boundary and initial context of the regional grid to construct a microgrid device portrait includes the following steps: S111, taking the physical connection and logical connection between each device in the regional grid as the first initial context, and determining the grid space according to the first initial context and the geographical coordinates of the device; taking the regional outline of the two-dimensional mapping area of ​​the grid space on the geographical coordinates corresponding to the regional grid as the initial boundary of each regional grid; S122, determining the physical connection and logical connection of each device between the regional grids as the second initial context; constructing a microgrid device portrait according to the first initial context, the initial boundary and the second initial context; Determining the boundary correction factor and the context correction factor according to the state transition path of each device variable in the triple matrix; The steps include: S211, setting a state threshold of a state variable corresponding to each device, and when it is detected that the state variable exceeds the set state threshold, determining a faulty device and determining a state transition direction according to a correlation matrix corresponding to the faulty device; S212, determining a target transition device according to a state transition direction, and determining transition content according to a state change of the target transition device; S213, determining a state callback factor according to the transition content and transition direction of each device in the regional grid, and determining a state transition path on each time section of the regional grid according to the state callback factor; S214: taking each device and its connection in the state transition path as a context correction factor, and taking each device and its geographical coordinates in the state transition path as a boundary correction factor.

2. The method for constructing a dynamic portrait of a microgrid device based on full-factor tags according to claim 1 is characterized in that: The cluster analysis of all element labels of the microgrid and construction of a regional grid of the microgrid system according to functional attributes includes the following steps: S101, obtaining all-factor information of the area covered by the microgrid system, wherein the all-factor information includes equipment structure topology data, equipment real-time status data, and equipment historical maintenance data; S102, performing cluster analysis on all factor information according to functional attributes combined with a clustering algorithm to obtain a device set, and using the geographical attributes of the devices in the device set as grid units to determine a regional grid.

3. The method for constructing a dynamic portrait of a microgrid device based on full-factor tags according to claim 1 is characterized in that: The step of obtaining device variables corresponding to the regional grid and constructing a triple matrix includes the following steps: S201, acquiring state variable data, control variable data and clock variable data in the microgrid system to construct a triplet of each device; S202, constructing a triplet matrix according to the triplet of each device in the regional grid on the time section; Wherein, the state variable data at least includes voltage data and current data; The control variable data at least includes switch state data and parameter adjustment data; The clock variable data at least includes timestamp data and state duration data.

4. The method for constructing a dynamic portrait of a microgrid device based on full-factor tags according to claim 1 is characterized in that: The method of determining the faulty device and determining the state transition direction according to the association matrix corresponding to the faulty device comprises the following steps: Determine the relevance of each device to the faulty device based on the functional similarity and the fault coupling degree, and then determine the relevance matrix; Determine the faulty device and obtain the cluster center corresponding to the faulty device, and determine the functional similarity based on the ratio of the distance from the faulty device to the cluster center to the distance from the remaining devices to the cluster center in the regional grid; Determine the fault coupling degree based on the state change rate of each device when the faulty device fails in the historical time section; The correlation value of each device relative to the faulty device is obtained by weighted summing according to the functional similarity, fault coupling degree and their corresponding weight factors, and a correlation matrix corresponding to the faulty device is constructed based on the correlation value; The element with the largest value in the correlation matrix is ​​taken as the state transition direction.

5. The method for constructing a dynamic portrait of a microgrid device based on full-factor tags according to claim 1 is characterized in that: The method of determining the state callback factor according to the transition content and transition direction of each device in the regional grid, and determining the state transition path on each time section of the regional grid according to the state callback factor comprises the following steps: If the transition direction points to a device in the regional grid, the transition content includes the parameter change of the first initial context corresponding to the change of the physical connection and the logical connection in the first initial context, as well as the time and duration of determining the transition change, and the change parameter in the transition content is extracted as the first state callback factor; wherein the physical connection and the logical connection between each device in the regional grid are taken as the first initial context; If the transition direction points to the device between the regional grids, the transition content includes the change of the physical connection and the logical connection in the second initial context corresponding to the parameter change of the second initial context and the time and duration of the transition change, and the change parameter in the transition content is extracted as the second state callback factor; wherein the physical connection and the logical connection of each device between the regional grids are determined as the second initial context; The adjustment direction, adjustment content, and adjustment time of each metadata in the triple matrix are determined according to the first state callback factor and / or the second state callback factor; the state transition path of each time section of the regional grid is determined according to the adjustment direction, adjustment content, and adjustment time corresponding to the devices within and between the regional grids.

6. The method for constructing a dynamic portrait of a microgrid device based on full-factor tags according to claim 5 is characterized in that: In S214, the process of using each device and its connection in the state transition path as a context correction factor includes the following steps: Each device and its connection in the grid space is determined through the state transition path as the first initial context correction factor; each device and its connection between grid spaces is determined through the state transition path as the second initial context correction factor.

7. The method for constructing a dynamic portrait of a microgrid device based on full-factor tags according to claim 6 is characterized in that: The step of correcting the initial boundary and the initial context in response to the boundary correction factor and the context correction factor and reconstructing the microgrid device portrait comprises the following steps: S31, correcting the initial boundary of each grid space according to the boundary correction factor to obtain an updated boundary; Synchronously, the first initial context in each grid space is corrected according to the first initial context correction factor to obtain a first updated context; Synchronously, the second initial context between the grid spaces is corrected according to the second initial context correction factor to obtain a second updated context; S32. Reconstruct the microgrid device portrait according to the first update context, the second update context, and the update boundary.

8. A system for constructing a dynamic portrait of a microgrid device, applicable to the method for constructing a dynamic portrait of a microgrid device based on full-element tags as claimed in any one of claims 1 to 7, characterized in that: include: Initial construction module: cluster analysis is performed on all element labels of the microgrid and the regional grid of the microgrid system is constructed according to the functional attributes. The initial boundary and initial context of the regional grid are determined to construct the microgrid equipment portrait. Correction module: obtain the device variables corresponding to the regional grid to construct a triple matrix, and determine the boundary correction factor and the vein correction factor according to the state transition path of each device variable in the triple matrix; Reconstruction module: in response to the boundary correction factor and the context correction factor, respectively correct the initial boundary and the initial context to reconstruct the microgrid device portrait.

9. An electronic device, characterized in that: It includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of the method for constructing a dynamic portrait of a microgrid device based on full-element tags as described in any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: The storage medium stores computer executable instructions, which, when loaded and executed by the processor, implement the steps of the method for constructing a dynamic portrait of a microgrid device based on full-factor tags as described in any one of claims 1 to 7.

Images