Data set construction method and system for integrated energy system

Abstract

The application provides a data set construction method and system of an integrated energy system. The implementation scheme is as follows: based on first QS file data of the integrated energy system, a first network topology is determined, a plurality of power transmission lines in the network topology are interrupted, and a second network topology is obtained; based on the switching state of each power transmission line and the voltage of each node in the second network topology, a connected path from a first node with the highest voltage to other nodes is searched in the second network topology according to the principle that the voltage is from high to low, and a target network topology is obtained; based on the target network topology, the empty charging line and the transformer equivalent model in the first QS file data are processed, and are mapped to a power flow calculation model, and then power flow calculation is performed, based on the power flow calculation result, the first QS file data is updated, and target QS file data is obtained. Therefore, the data set of the integrated energy system can be quickly and accurately obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and particularly relates to a data set construction method and system of an integrated energy system. BACKGROUND

[0002] With the development of energy transformation and smart grid technology, integrated energy system (IES) has become an important research direction in the field of energy. In order to realize the effective management and operation of IES, the modeling and simulation analysis of the system become particularly important.

[0003] In the modeling and simulation of IES, deep learning technology shows great potential due to its strong feature learning ability and prediction ability. However, the training of deep learning model requires a large amount of labeled data, and the complexity and dynamics of integrated energy system make it very difficult to obtain and label data. In the dispatch D5000 system, the QS data model contains all the power flow section data at a time point, considering the fluctuation characteristics of time and climate, it is necessary to generate diverse integrated energy system operation scenarios based on a QS file to ensure timely adjustments in various situations.

[0004] Therefore, how to process the existing system operation history data to obtain the corresponding data set is very important for guaranteeing the safe and efficient operation of the integrated energy system. SUMMARY

[0005] The present application provides a data set construction method and system of an integrated energy system, which can solve at least one of the above technical problems.

[0006] According to an aspect of the present application, a data set construction method of an integrated energy system is provided, comprising:

[0007] obtaining first QS file data of the integrated energy system, wherein the first QS file data includes relevant power data of each node and each transmission line in the integrated energy system;

[0008] determining a first network topology of the integrated energy system based on the first QS file data;

[0009] interrupting a plurality of transmission lines in the first network topology of the integrated energy system to obtain a second network topology;

[0010] Based on the switching status of each transmission line in the second network topology and the voltage of each node, the connection path from the first node with the highest voltage to other nodes is searched in the second network topology according to the principle of voltage from high to low, so as to obtain the target network topology.

[0011] Based on the target network topology, the equivalent models of the empty charging line and transformer in the first QS file data are processed to obtain the second QS file data.

[0012] The second QS file data is mapped into the power flow calculation model, and power flow calculation is performed on the mapped power flow calculation model to obtain the power flow calculation result;

[0013] Based on the power flow calculation results, the first QS file data is updated to obtain the target QS file data;

[0014] Based on the target QS file data, the dataset of the integrated energy system is determined.

[0015] According to another aspect of the present invention, a dataset construction apparatus for an integrated energy system is provided, comprising:

[0016] The file data acquisition module is used to acquire the first QS file data of the integrated energy system, wherein the first QS file data includes the relevant power data of each node and each transmission line in the integrated energy system;

[0017] The first topology determination module is used to determine the first network topology of the integrated energy system based on the first QS file data.

[0018] The second topology determination module is used to interrupt multiple transmission lines in the first network topology of the integrated energy system to obtain a second network topology;

[0019] The third topology determination module is used to search for connected paths from the first node with the highest voltage to other nodes in the second network topology based on the switching status of each transmission line and the voltage of each node, in accordance with the principle of voltage from high to low, to obtain the target network topology.

[0020] The data processing module is used to process the equivalent models of the empty charging line and transformer in the first QS file data based on the target network topology to obtain the second QS file data;

[0021] The power flow calculation module is used to map the second QS file data to the power flow calculation model, and perform power flow calculation on the mapped power flow calculation model to obtain the power flow calculation result;

[0022] The file data update module is used to update the first QS file data based on the power flow calculation results to obtain the target QS file data;

[0023] The dataset determination module is used to determine the dataset of the integrated energy system based on the target QS file data.

[0024] This invention employs a method to interrupt lines in the network topology of the QS file data of an integrated energy system, thereby modifying the network topology and forming a new network topology for the integrated energy system. Since new islands appear in the new network topology, by analyzing the switching status of each transmission line and the voltage of each node in the second network topology, a connection path is searched from the first node with the highest voltage to other nodes according to the principle of voltage decreasing. The resulting target network topology eliminates islands. Thus, the impact of islands can be eliminated when calculating the power flow of the integrated energy system. Using the power flow calculation results after eliminating island effects, the original QS file data is updated, allowing for the rapid generation of new QS file data. Repeating these steps allows for the rapid and accurate generation of a dataset of the integrated energy system that eliminates island effects. Subsequently, this dataset can be used to construct models related to the integrated energy system.

[0025] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0026] The accompanying drawings are provided for a better understanding of this solution and do not constitute a limitation of the invention. Wherein:

[0027] Figure 1 This is a flowchart of a method for constructing a dataset for an integrated energy system according to an embodiment of the present invention;

[0028] Figure 2 This is a schematic diagram of a network topology according to an embodiment of the present invention;

[0029] Figure 3 This is a schematic diagram illustrating the mapping relationship between the QS file and the power flow calculation module according to an embodiment of the present invention;

[0030] Figure 4 This is a schematic diagram of a network topology search process according to an embodiment of the present invention;

[0031] Figure 5 This is a structural block diagram of a dataset construction device for an integrated energy system according to an embodiment of the present invention;

[0032] Figure 6This is a block diagram of an electronic device used to implement the methods of embodiments of the present invention. Detailed Implementation

[0033] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0034] Figure 1 This is a flowchart of a method for constructing a dataset for an integrated energy system according to an embodiment of the present invention.

[0035] like Figure 1 As shown, the method for constructing the dataset of this integrated energy system may include:

[0036] S110, Obtain the first QS file data of the integrated energy system, wherein the first QS file data includes the relevant power data of each node and each transmission line in the integrated energy system;

[0037] S120, Based on the first QS file data, determine the first network topology of the integrated energy system;

[0038] S130, interrupt multiple transmission lines in the first network topology of the integrated energy system to obtain the second network topology;

[0039] S140, Based on the switching status of each transmission line in the second network topology and the voltage of each node, in the second network topology, starting from the first node with the highest voltage, search for the connected paths from the first node to other nodes according to the principle of voltage from high to low, and obtain the target network topology.

[0040] S150, based on the target network topology, process the equivalent models of empty charging lines and transformers in the first QS file data to obtain the second QS file data;

[0041] S160, Map the data from the second QS file to the power flow calculation model, and perform power flow calculation on the mapped power flow calculation model to obtain the power flow calculation results;

[0042] S170, based on the power flow calculation results, update the first QS file data to obtain the target QS file data;

[0043] S180, based on the target QS file data, determines the dataset of the integrated energy system.

[0044] Exemplarily, the QS file data can also be referred to as the QS data model of the integrated energy system. This model includes multiple models, and the models related to power flow calculation include TopoNode, Unit, Load, compensator_P, compensator_S, ACline, and Transformer modules. Each module in the QS model file has a starting tag, such as <BaseValue: test network type=full number> and < / BaseValue: test network>. Through these starting tags, the corresponding module data can be extracted from the QS model.

[0045] Exemplarily, the QS file data remembers the relevant power data of each node and each transmission line in the integrated energy system. This power data can include node type, line type, transformer, load, and generator, etc.

[0046] Exemplarily, based on the first QS file data, data sampling is performed on the integrated energy system, including the load, output power, and output voltage of each node, etc.

[0047] Exemplarily, multiple transmission lines in the first network topology of the integrated energy system are randomly interrupted to obtain a second network topology. The number of interrupted transmission lines can also be randomly determined, for example, a number is randomly determined between 5 and 10.

[0048] Exemplarily, using the sampled data, the failure rate and the faulty lines of the first network topology recorded in the first QS file data are determined. Using this information, the topology modification method of the integrated energy system is determined. Based on this topology modification method, multiple transmission lines in the first network topology of the integrated energy system are interrupted to obtain a second network topology. For example, the interrupted lines are the faulty lines. In this way, the fault situation of the system can be simulated to obtain the corresponding fault data. Subsequently, these data sets can be used to construct a power fault prediction model.

[0049] In this example, since new islands will be generated in the newly generated second network topology and the original first QS file data does not record the information of these new islands, it is necessary to exclude the islands in the newly generated second network topology to obtain the target network topology before performing power flow calculation on the target network topology to exclude the influence of the islands on the power flow calculation result and improve the accuracy of the power flow calculation result.

[0050] For example, a network topology diagram is formed based on the switching states of each transmission line in the second network topology and the voltage of each node. In the network topology diagram, starting from the first node with the highest voltage, connected paths from the first node to other nodes are searched according to the principle of voltage decreasing from high to low. The searched connected paths are then used to form the target network topology. Nodes in the second network topology that are not part of the target network topology are considered island nodes.

[0051] For example, such as Figure 2 As shown, this is the target network topology after excluding isolated nodes.

[0052] For example, a graph depth-first search (DFS) algorithm can also be used to eliminate isolated nodes. For instance, the network topology graph is input into the DFS algorithm, which, based on the voltage of each node and the state of the connections between them, starts from the node with the highest voltage and searches for connected paths to other nodes according to the principle of decreasing voltage. In this way, the target network topology can be quickly obtained.

[0053] For example, after determining the target network topology, the topology is modified in the first QS file data, and the equivalent models of empty charging lines and transformers in the modified network topology are processed to obtain the second QS file data.

[0054] Understandably, the empty charging line to be simulated is a line without islands on either side. Therefore, in this example, islands in the network topology are excluded before processing the equivalent models of the empty charging line and transformer. This eliminates the need for island detection on both sides of the line to be simulated before performing the empty charging line model simulation, improving the efficiency of the simulation.

[0055] Understandably, in QS file data, transformers are generally depicted as two-winding or three-winding transformers. These transformers need to be equivalently processed to facilitate subsequent power flow calculations.

[0056] For example, a two-winding transformer is modeled as a 'T'-type equivalent model, and a three-winding transformer is modeled as a 'Y'-type equivalent model.

[0057] For example, the second QS file data is mapped to a power flow calculation model, which can be, for instance, a pandpower model file in Python programming software, such as... Figure 3 As shown, the details are as follows:

[0058] Based on the fields of each node in the TopoNode module of the second QS file data, generate the node data table bus of pandapower;

[0059] Based on the fields of each parallel compensation device in the Compensator_P module of the second QS file data, generate the pandapower parallel compensation device data table shunt;

[0060] Based on the load fields of the Load module in the second QS file data, generate the load data table load of pandapower;

[0061] Based on the generator unit fields in the Unit module of the second QS file data, generate the generator data table gen of pandapower;

[0062] Based on the fields of each transmission line in the Compensator_S module and ACline module in the second QS file data, as well as the fields of each series compensation device, the pandapower branch data table line is generated.

[0063] Based on the fields of each transformer in the Transformer module of the second QS file data, generate the transformer data tables trafo and trafo3w for pandapower.

[0064] Therefore, the PandPower model file includes the node data table bus, the parallel compensation device data table shunt, the load data table load, the generator data table gen, the branch data table line, and the transformer data tables trafo and trafo3w.

[0065] In this way, the newly generated pandpower model file can be used to perform power flow calculations to obtain the power flow calculation results of the target network topology.

[0066] For example, the power flow calculation results of the target network topology are used to replace the corresponding fields in the first QS file data to obtain new QS file data, namely the target QS file data.

[0067] For example, the “Ue” and “ang” values ​​of each node in the net.res_bus data table in the power flow calculation results are used to replace the “Ue” and “ang” values ​​of the corresponding nodes in the first QS file data.

[0068] Based on the "Ue", "ang", "P" and "Q" values ​​of each node in the net.res_gen data table in the power flow results, replace the "Ue", "ang", "P" and "Q" values ​​of the corresponding nodes in the Unit field information of the first QS file data.

[0069] Based on the "P" and "Q" values ​​of each node in the net.res_gen data table in the power flow results, replace the 'P' and 'Q' values ​​of the corresponding nodes in the Load field information of the first QS file data.

[0070] Based on the "Q" value of each node in the net.res_gen data table in the power flow results, replace the 'Q' value of the corresponding node in the Compensator_P field information of the first QS file data.

[0071] Similarly, for the switching status of lines and transformer status, the status information of lines and transformers in the corresponding fields of the first QS file data can be replaced with the information recorded in the net.res_line, net.res_trao, and net.res_trao3w data tables in the power flow results.

[0072] Thus, the first QS file data after replacing the field information becomes the target QS file data. Furthermore, new QS file data can be generated quickly using the method described above.

[0073] For example, steps S110 to S170 can be repeated multiple times, thereby generating multiple different QS file data to construct the dataset of step S180.

[0074] According to the above implementation method, the lines in the network topology of the integrated energy system's QS file data are interrupted to modify the network topology and form a new network topology for the integrated energy system. Since new islands appear in the new network topology, by using the switching status of each transmission line in the second network topology and the voltage of each node, a connection path from the first node with the highest voltage to other nodes is searched in the second network topology according to the principle of voltage from high to low. The resulting target network topology can eliminate islands. Thus, the impact of islands can be eliminated when calculating the power flow of the integrated energy system. Using the power flow calculation results that eliminate the impact of islands, the original QS file data is updated, and new QS file data can be quickly generated. Repeating the above steps, a dataset of the integrated energy system that eliminates the impact of islands can be quickly and accurately generated. Subsequently, this dataset can be used to construct a model related to the integrated energy system, and this model is unaffected by islands.

[0075] In one implementation, multiple transmission lines in a first network topology of an integrated energy system are interrupted to obtain a second network topology, including: determining the line failure rate of the first network topology based on first QS file data; determining the number of interrupted transmission lines based on the line failure rate of the first network topology and the total number of transmission lines in the first network topology; and interrupting the corresponding number of transmission lines in the first network topology of the integrated energy system based on the number of interrupted transmission lines to obtain the second network topology.

[0076] For example, based on the power information such as load, output power and output voltage of each node and each line recorded in the first QS file data, the power verification or simulation verification of the first network topology is performed to obtain the line failure rate of the first network topology.

[0077] For example, the number of interrupted transmission lines is obtained by multiplying the line failure rate of the first network topology by the total number of transmission lines in the first network topology. In this way, the network topology can be modified according to the failure rate.

[0078] For example, based on the number of interrupted transmission lines, a second network topology is obtained by randomly interrupting a corresponding number of transmission lines in the first network topology of the integrated energy system or by interrupting designated transmission lines. Here, the corresponding number is understood to be the same as or similar to the number of interrupted transmission lines.

[0079] According to the above implementation method, by modifying the network topology according to the failure rate, it is possible to simulate failure conditions to perform power flow calculations, and subsequently obtain a dataset of the integrated energy system under failure conditions.

[0080] In one implementation, a second network topology is obtained by interrupting a corresponding number of transmission lines in the first network topology of the integrated energy system based on the number of interrupted transmission lines. This includes: updating the number of interrupted transmission lines based on the number of islands in the first network topology; and randomly interrupting a corresponding number and location of transmission lines in the first network topology of the integrated energy system based on the updated number of interrupted transmission lines and the location of islands in the first network topology, thereby obtaining the second network topology.

[0081] For example, if the number of islands in the first network topology is greater than a preset threshold, the number of interrupted transmission lines is increased; if the number of islands in the first network topology is less than the preset threshold, the number of interrupted transmission lines remains unchanged.

[0082] For example, the corresponding number can be understood as the same as or similar to the updated number of interrupted transmission lines.

[0083] For example, the transmission line at the corresponding location can be understood as a transmission line that is more than a specified distance away from the location of an island in the first network topology. This specified distance can be a distance determined by the distance distribution between each line and the island.

[0084] According to the above implementation method, by considering the number and location of isolated islands and their impact on faulty lines, and excluding the influence of this information, and only considering line faults caused by other factors, the network topology can be modified, which can improve the accuracy of subsequent fault prediction model construction.

[0085] In one implementation, based on the switching states of each transmission line in the second network topology and the voltage of each node, the system searches for connected paths from the first node with the highest voltage to other nodes in the second network topology according to the principle of voltage from high to low, to obtain the target network topology. This includes: constructing a network topology graph based on the switching states of each transmission line in the second network topology and the voltage of each node, wherein the network topology graph includes the switching states of the two ends of each transmission line, the switching states of each transmission line, and the voltage of each node; inputting the network topology graph into a graph depth search algorithm to obtain the target network topology output by the graph depth search algorithm, wherein the graph depth search algorithm is used to search for connected paths from the first node with the highest voltage to other nodes in the network topology graph according to the principle of voltage from high to low, and to form the target network topology from the connected paths.

[0086] For example, in a network topology diagram, the state of each branch ij can be represented by the switching states of its two endpoints, topology nodes i and j. When their sum is 0, the branch is connected; if it is greater than 0, the branch is disconnected. Specifically, this can be expressed as:

[0087] if If, then branch ij is in a closed state; if If , then branch ij is in an open state. Indicates the switch state of terminal i. This indicates the switch state of terminal j.

[0088] For example, such as Figure 4 As shown, this illustrates the path search process. The shaded areas represent the valid nodes in the progressively generated target network topology.

[0089] For example, the depth-first search algorithm is a recursive algorithm because the same operation is performed for each node, as shown in the following equation:

[0090] .

[0091] If a depth-first search is performed starting from node A, the path from node A to node B is explored first. At node B, all unvisited neighbor nodes are searched, revealing two paths: B to D and B to E and then to F. After completing the search for the path from A to B, the search returns to the starting node A. Then, the search for the second path, A to C, begins from A. At node C, a depth-first search is performed, visiting its only neighbor node F. In this way, the search process prioritizes exploring new paths at each node, and once all paths at a given node have been explored, the search backtracks to the previous node to continue.

[0092] According to the above implementation method, the network topology is first encapsulated into a topology graph, and then a graph depth-first search algorithm is used to perform a graph search to eliminate isolated nodes and obtain the final target network topology. In this way, the network topology after eliminating isolated nodes can be obtained quickly.

[0093] In one implementation, based on the target network topology, the equivalent models of the empty charging lines and transformers in the first QS file data are processed to obtain the second QS file data, including:

[0094] Based on the target network topology, determine the valid lines and valid transformer branches in the first QS file data;

[0095] In the first QS file data, for any valid line, when the first side of the valid line is in operation and the second side is in shutdown, a first node without load and generator is added to the second side; and the switch of the second side is set at the first node, and the parameters of the first line from the first side to the first node are set to be the same as the parameters of the second line from the first side to the second side, so that the switches at both ends of the first line are closed and the second line is opened at the same time to simulate an empty charging line.

[0096] In the first QS file data, for any effective transformer branch, the two-winding transformer in the effective transformer branch is equivalent to a T-type equivalent model to obtain the short-circuit impedance and magnetization admittance of the T-type equivalent model, and the three-winding transformer in the effective transformer branch is equivalent to a Y-type equivalent model to obtain the short-circuit impedance and magnetization admittance of the Y-type equivalent model.

[0097] Based on the first QS file data after the simulation of the empty charging line and the equivalent transformation of the transformer, the second QS file data is determined.

[0098] Understandably, a valid line is one where there are no dead islands on either side. A valid transformer branch is a branch that includes a transformer and where there are no dead islands on either side.

[0099] For example, since the target network topology has excluded islands, any line within it is a valid line, and any branch that includes a transformer is a valid transformer branch.

[0100] For example, in the case of line I being in operation and line J being out of operation, a new node K without load and generator is added on line J. The switch on line J is switched to K. The parameters of line IK are the same as those of line IJ, so that the switches at both ends of line I-K are closed, and the original line IJ is disconnected, thereby simulating the line charging without load.

[0101] For example, in the case of line I being out of service and line J being in operation, a new node K is added to line I. The switch on line I is switched to K. The parameters of line JK are the same as those of line IJ, so that the switches at both ends of line JK are closed, while the original line IJ is disconnected to simulate the line being charged without power.

[0102] For example, for a T-type equivalent model, its short-circuit impedance can be calculated from the short-circuit voltage percentage, the system reference capacity, and the transformer's rated capacity. Specifically:

[0103] ;

[0104] ;

[0105] ;

[0106] ;

[0107] in, This represents the short-circuit impedance amplitude of the transformer. This represents the percentage of the transformer's short-circuit voltage. As the system's baseline capacity, This refers to the rated capacity of the transformer. This represents the real part of the transformer's short-circuit impedance. This represents the percentage of the real part of the transformer short-circuit voltage. This represents the imaginary part of the transformer short-circuit voltage. This is the short-circuit impedance of the transformer.

[0108] For example, for the T-type equivalent model, its magnetization admittance can be calculated from the no-load loss, iron loss, system reference capacity, and transformer capacity. Specifically:

[0109] ;

[0110] ;

[0111] ;

[0112] ;

[0113] in, This represents the amplitude of the transformer's magnetization admittance. For transformer no-load loss, For transformer iron loss, This is the real part of the transformer's magnetization admittance. This is the imaginary part of the transformer's magnetization admittance. This is the magnetization admittance of the transformer.

[0114] For example, the short-circuit impedance and magnetization admittance of the transformer calculated based on the above example are relative to the transformer's rated values. Therefore, they are then converted to the rated values ​​of the network topology, as follows:

[0115] ;

[0116] ;

[0117] ;

[0118] ;

[0119] in, This refers to the voltage at the low-voltage side connection node of the transformer. Rated apparent power, This refers to the low-voltage side voltage of the transformer. The equivalent branch impedance of the transformer. It is the equivalent branch admittance of the transformer.

[0120] In one implementation, updating the first QS file data based on the power flow calculation results to obtain the target QS file data includes: updating the relevant power data of the corresponding node and the corresponding transmission line in the first QS file data based on the relevant power data of each node and each transmission line in the power flow calculation results to obtain the target QS file data.

[0121] For example, the power flow calculation results of the target network topology are used to replace the corresponding fields in the first QS file data to obtain new QS file data, namely the target QS file data.

[0122] For example, the “Ue” and “ang” values ​​of each node in the net.res_bus data table in the power flow calculation results are used to replace the “Ue” and “ang” values ​​of the corresponding nodes in the first QS file data.

[0123] Based on the "Ue", "ang", "P" and "Q" values ​​of each node in the net.res_gen data table in the power flow results, replace the "Ue", "ang", "P" and "Q" values ​​of the corresponding nodes in the Unit field information of the first QS file data.

[0124] Based on the "P" and "Q" values ​​of each node in the net.res_gen data table in the power flow results, replace the 'P' and 'Q' values ​​of the corresponding nodes in the Load field information of the first QS file data.

[0125] Based on the "Q" value of each node in the net.res_gen data table in the power flow results, replace the 'Q' value of the corresponding node in the Compensator_P field information of the first QS file data.

[0126] Similarly, for the switching status of lines and transformer status, the status information of lines and transformers in the corresponding fields of the first QS file data can be replaced with the information recorded in the net.res_line, net.res_trao, and net.res_trao3w data tables in the power flow results.

[0127] Thus, the first QS file data after replacing the field information becomes the target QS file data. Furthermore, new QS file data can be generated quickly using the method described above.

[0128] According to the above implementation method, new QS file data is generated by reverse mapping based on the power flow calculation results. In this way, multiple QS file data can be generated quickly and accurately to obtain a dataset.

[0129] Figure 5 This is a structural block diagram of a dataset construction device for an integrated energy system according to an embodiment of the present invention.

[0130] like Figure 5 As shown, the dataset construction device for the integrated energy system may include:

[0131] The file data acquisition module 510 is used to acquire the first QS file data of the integrated energy system, wherein the first QS file data includes the relevant power data of each node and each transmission line in the integrated energy system.

[0132] The first topology determination module 520 is used to determine the first network topology of the integrated energy system based on the first QS file data.

[0133] The second topology determination module 530 is used to interrupt multiple transmission lines in the first network topology of the integrated energy system to obtain a second network topology;

[0134] The third topology determination module 540 is used to search for connected paths from the first node with the highest voltage to other nodes in the second network topology based on the switching status of each transmission line and the voltage of each node, in accordance with the principle of voltage from high to low, to obtain the target network topology.

[0135] Data processing module 550 is used to process the equivalent models of empty charging lines and transformers in the first QS file data based on the target network topology to obtain the second QS file data;

[0136] The power flow calculation module 560 is used to map the second QS file data into the power flow calculation model, and to perform power flow calculation on the mapped power flow calculation model to obtain the power flow calculation result;

[0137] The file data update module 570 is used to update the first QS file data based on the power flow calculation result to obtain the target QS file data;

[0138] The dataset determination module 580 is used to determine the dataset of the integrated energy system based on the target QS file data.

[0139] In one embodiment, the second topology determination module 530 includes:

[0140] The failure rate determination unit is used to determine the line failure rate of the first network topology based on the first QS file data.

[0141] The line number determination unit is used to determine the number of interrupted transmission lines based on the line failure rate of the first network topology and the total number of transmission lines in the first network topology.

[0142] The network topology determination unit is used to randomly interrupt a corresponding number of transmission lines in the first network topology of the integrated energy system based on the number of interrupted transmission lines, to obtain a second network topology.

[0143] In one embodiment, the network topology determination unit is specifically used for:

[0144] The number of interrupted power transmission lines is updated based on the number of islands in the first network topology.

[0145] Based on the updated number of interrupted transmission lines and the location of islands in the first network topology, the corresponding number and location of transmission lines in the first network topology of the integrated energy system are randomly interrupted to obtain the second network topology.

[0146] In one embodiment, the third topology determination module 540 includes:

[0147] The topology graph construction unit is used to construct a network topology graph based on the switching status of each transmission line in the second network topology and the voltage of each node. The network topology graph includes the switching status of the two end nodes of each transmission line, the switching status of each transmission line, and the voltage of each node.

[0148] The graph depth search unit is used to input the network topology graph into the graph depth search algorithm to obtain the target network topology output by the graph depth search algorithm. The graph depth search algorithm is used to search for each connected path from the first node to other nodes in the network topology graph, starting from the first node with the highest voltage, according to the principle of voltage from high to low, and to form the target network topology by each connected path.

[0149] In one embodiment, the data processing module 550 includes:

[0150] The effective line determination unit is used to determine the effective lines and effective transformer branches in the first QS file data based on the target network topology.

[0151] An empty-charge simulation unit is used to, in the first QS file data, for any of the effective lines, when the first side of the effective line is in operation and the second side is in shutdown state, add a first node without load and generator on the second side; set the switch of the second side to the first node, set the parameters of the first line from the first side to the first node to be the same as the parameters of the second line from the first side to the second side, so that the switches at both ends of the first line are closed and the second line is opened at the same time to simulate an empty-charge line;

[0152] The transformer processing unit is configured to, in the first QS file data, for any of the effective transformer branches, convert the two-winding transformer in the effective transformer branch into a T-type equivalent model to obtain the short-circuit impedance and magnetization admittance of the T-type equivalent model, and convert the three-winding transformer in the effective transformer branch into a Y-type equivalent model to obtain the short-circuit impedance and magnetization admittance of the Y-type equivalent model;

[0153] The file determination unit is used to determine the second QS file data based on the first QS file data after the empty charging line simulation and the transformer equivalent conversion.

[0154] In one embodiment, the file data update module 570 is specifically used for:

[0155] Based on the relevant power data of each node and each transmission line in the power flow calculation results, update the relevant power data of the corresponding node and the corresponding transmission line in the QS file data to obtain the target QS file data.

[0156] The specific functions and examples of each module and submodule of the system in this embodiment of the invention can be found in the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0157] The acquisition, storage, and application of user personal information involved in the technical solution of this invention all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0158] According to embodiments of the present invention, the present invention also provides a system and a readable storage medium.

[0159] Figure 6 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0160] like Figure 6 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0161] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0162] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the integrated energy system dataset construction method. For example, in some embodiments, the integrated energy system dataset construction method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the integrated energy system dataset construction method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the integrated energy system dataset construction method by any other suitable means (e.g., by means of firmware).

[0163] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0164] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0165] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0166] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0167] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0168] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0169] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0170] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for constructing a dataset for an integrated energy system, characterized in that, include: Obtain the first QS file data of the integrated energy system, wherein the first QS file data includes the relevant power data of each node and each transmission line in the integrated energy system; Based on the data in the first QS file, the first network topology of the integrated energy system is determined; Repeat the following steps to obtain multiple target QS file data: To obtain a second network topology by interrupting multiple transmission lines in the first network topology of the integrated energy system, the method includes: determining the line failure rate of the first network topology based on the first QS file data; determining the number of interrupted transmission lines based on the line failure rate of the first network topology and the total number of transmission lines in the first network topology; updating the number of interrupted transmission lines based on the number of islands in the first network topology, including: increasing the number of interrupted transmission lines if the number of islands in the first network topology is greater than a preset threshold, and keeping the number of interrupted transmission lines unchanged if the number of islands in the first network topology is less than the preset threshold; and randomly interrupting the corresponding number and position of transmission lines in the first network topology of the integrated energy system based on the updated number of interrupted transmission lines and the position of the islands in the first network topology to obtain the second network topology, wherein the transmission lines at the corresponding positions are transmission lines whose positions are more than a specified distance away from the positions of the islands in the first network topology. Based on the switching status of each transmission line in the second network topology and the voltage of each node, the connection path from the first node with the highest voltage to other nodes is searched in the second network topology according to the principle of voltage from high to low, so as to obtain the target network topology. Based on the target network topology, the equivalent models of the empty charging line and transformer in the first QS file data are processed to obtain the second QS file data. The second QS file data is mapped into the power flow calculation model, and power flow calculation is performed on the mapped power flow calculation model to obtain the power flow calculation result; Based on the power flow calculation results, the first QS file data is updated to obtain the target QS file data; After obtaining the multiple target QS file data, the dataset of the integrated energy system is determined based on the multiple target QS file data.

2. The method according to claim 1, characterized in that, Based on the switching states of each transmission line and the voltage of each node in the second network topology, the method searches for connected paths from the first node with the highest voltage to other nodes according to the principle of voltage from high to low in the second network topology, to obtain the target network topology, including: Based on the switching status of each transmission line in the second network topology and the voltage of each node, a network topology diagram is constructed, wherein the network topology diagram includes the switching status of the two ends of each transmission line, the switching status of each transmission line, and the voltage of each node. The network topology graph is input into a graph depth search algorithm to obtain the target network topology output by the graph depth search algorithm. The graph depth search algorithm is used to search for each connected path from the first node to other nodes in the network topology graph, starting from the first node with the highest voltage, according to the principle of voltage from high to low, and to form the target network topology from each connected path.

3. The method according to claim 1, characterized in that, The step of processing the equivalent models of the empty charging line and transformer in the first QS file data based on the target network topology to obtain the second QS file data includes: Based on the target network topology, determine the valid lines and valid transformer branches in the first QS file data; In the first QS file data, for any of the effective lines, when the first side of the effective line is in operation and the second side is in shutdown, a first node without load and generator is added to the second side; and the switch of the second side is set at the first node, and the parameters of the first line from the first side to the first node are set to be the same as the parameters of the second line from the first side to the second side, so that the switches at both ends of the first line are closed, and the second line is disconnected to simulate an empty charging line; In the first QS file data, for any of the effective transformer branches, the two-winding transformer in the effective transformer branch is equivalent to a T-type equivalent model to obtain the short-circuit impedance and magnetization admittance of the T-type equivalent model, and the three-winding transformer in the effective transformer branch is equivalent to a Y-type equivalent model to obtain the short-circuit impedance and magnetization admittance of the Y-type equivalent model. The second QS file data is determined based on the first QS file data after the empty charging line simulation and the transformer equivalent transformation.

4. The method according to claim 1, characterized in that, The step of updating the first QS file data based on the power flow calculation results to obtain the target QS file data includes: Based on the relevant power data of each node and each transmission line in the power flow calculation results, update the relevant power data of the corresponding node and the corresponding transmission line in the QS file data to obtain the target QS file data.

5. A dataset construction device for an integrated energy system, characterized in that, include: The file data acquisition module is used to acquire the first QS file data of the integrated energy system, wherein the first QS file data includes the relevant power data of each node and each transmission line in the integrated energy system; This module is used to obtain multiple target QS file data obtained by repeatedly executing the first topology determination module, the second topology determination module, the third topology determination module, the data processing module, the power flow calculation module, and the file data update module: The first topology determination module is used to determine the first network topology of the integrated energy system based on the first QS file data. The second topology determination module is used to interrupt multiple transmission lines in the first network topology of the integrated energy system to obtain a second network topology; The third topology determination module is used to search for connected paths from the first node with the highest voltage to other nodes in the second network topology based on the switching status of each transmission line and the voltage of each node, in accordance with the principle of voltage from high to low, to obtain the target network topology. The data processing module is used to process the equivalent models of the empty charging line and transformer in the first QS file data based on the target network topology to obtain the second QS file data; The power flow calculation module is used to map the second QS file data to the power flow calculation model, and perform power flow calculation on the mapped power flow calculation model to obtain the power flow calculation result; The file data update module is used to update the first QS file data based on the power flow calculation result to obtain the target QS file data; The dataset determination module is used to determine the dataset of the integrated energy system based on the multiple target QS file data after obtaining the multiple target QS file data; The second topology determination module includes: The failure rate determination unit is used to determine the line failure rate of the first network topology based on the first QS file data. The line number determination unit is used to determine the number of interrupted transmission lines based on the line failure rate of the first network topology and the total number of transmission lines in the first network topology. A network topology determination unit is used to update the number of interrupted transmission lines based on the number of islands in the first network topology, including: if the number of islands in the first network topology is greater than a preset threshold, then increasing the number of interrupted transmission lines; if the number of islands in the first network topology is less than the preset threshold, then keeping the number of interrupted transmission lines unchanged; based on the updated number of interrupted transmission lines and the positions of the islands in the first network topology, randomly interrupting the corresponding number and corresponding positions of transmission lines in the first network topology of the integrated energy system to obtain a second network topology, wherein the transmission lines at the corresponding positions are transmission lines whose positions are more than a specified distance away from the positions of the islands in the first network topology.

6. A dataset construction system for an integrated energy system, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

7. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-4.

Images