Power distribution network operation state division method, device, equipment, medium and product

Abstract

The invention discloses a power distribution network operation state division method, device, equipment, medium and product in the technical field of power distribution networks, and the method comprises the steps: building an evaluation index system of the operation state of a power distribution network based on the operation characteristics of the power distribution network; basic parameters of the power system are obtained, and index values of all indexes in the evaluation index system are calculated; dividing the index value of each index in proportion to generate a sample set and a test set; label information of the running state is added to the index value of each index in the sample set; dividing the sample set into a pairwise constraint set and a non-pairwise constraint set based on the label information; based on the pairwise constraint set and the non-pairwise constraint set, adopting a k-means clustering algorithm to perform clustering analysis on the index value of each index in the sample set to obtain a clustering center; performing operation state division on the index value of each index in the test set according to the clustering center; according to the method, the running state of the power distribution network can be comprehensively evaluated, so that accurate running state division is carried out.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network, and in particular to a method, device, equipment, medium and product for dividing the operating status of a distribution network. Background Art

[0002] The distribution network is directly connected to the user side and is an important link in providing high-quality electricity and ensuring the safety of users' electricity use. The evaluation of the distribution network operation status is the basis for the continuous and stable operation of the distribution network. Through the evaluation, the weak links in the operation of the distribution network can be accurately perceived and the operation control of the distribution network can be strengthened. There are various types of distributed resources in the new distribution network, and the integration forms are different. The traditional distribution network operation status evaluation method does not have a clear definition of the operation status of each indicator, and the evaluation object is single, which is difficult to solve the evaluation problem of the distribution network after the large-scale access of distributed new energy. Through the comprehensive analysis of the distribution network operation data, the indicator model affecting the distribution network operation status is determined, and a scientific and standardized distribution network operation status evaluation mechanism is established, which not only protects the interests of users and maintains social harmony and stability, but also helps to discover the weak links in the operation of the distribution network, improve the maintenance capacity of the distribution network, and further realize the lean operation and maintenance level of the distribution network. Therefore, it is of great significance to carry out research on the evaluation of the distribution network operation status. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method, device, equipment, medium and product for dividing the operating status of a distribution network, verify the rationality of the evaluation index system through correlation and collinearity, solve the index operating status division through semi-supervised learning, and solve the technical problem of distribution network operating status evaluation.

[0004] To achieve the above object, the present invention is implemented by adopting the following technical solutions: In a first aspect, the present invention provides a method for dividing the operation status of a distribution network, comprising: Based on the operating characteristics of the distribution network, an evaluation index system for the operating status of the distribution network is established; Obtaining basic parameters of the power system and calculating the index value of each index in the evaluation index system; Divide the index values ​​of each of the indicators in proportion to generate a sample set and a test set; Adding label information of the running status to the indicator value of each indicator in the sample set; Dividing the sample set into a pairwise constraint set and an unpairwise constraint set based on the label information; Based on the paired constraint set and the unpaired constraint set, a k-means clustering algorithm is used to perform cluster analysis on the indicator values ​​of each of the indicators in the sample set to obtain a cluster center; The indicator values ​​of each indicator in the test set are divided into operating states according to the cluster center.

[0005] Optionally, the evaluation index system for the distribution network operation status includes: Power safety criteria layer indicators, used to measure the ability of the distribution network to cope with future risks; Power quality criterion layer indicators are used to measure the power supply quality level of distribution network voltage and frequency; The power supply margin criterion layer indicator is used to measure the ability of the distribution network to cope with load fluctuations while meeting load demand; Power reliability criterion layer indicators are used to measure the handling capacity of the distribution network when a fault occurs; Operational reliability criterion layer indicators are used to measure the actual controllability of distributed resources and loads in the distribution network; The independent operation quasi-measurement layer indicator is used to measure the ability of the distribution network to disconnect the interconnection switch after a major incident occurs and to meet the power demand without the support of external power supply.

[0006] Optionally, the power safety criteria layer indicators include short-circuit capacity and failure risk rate; The power quality criterion layer indicators include voltage deviation and frequency deviation; The power supply margin criterion layer indicators include load rate and load offset rate; The power reliability criterion layer indicators include fault self-healing rate and power transfer rate; The indicators of the operation reliability criterion layer include the proportion of controllable distributed resources and the proportion of controllable load; The independent operation quasi-measurement layer indicators include the independent operation time ratio and the load power supply guarantee ratio.

[0007] Optionally, the establishment of an evaluation index system for the distribution network operation status further includes: Obtaining basic parameters of the power system and calculating the index value of each index in the evaluation index system; Calculate the correlation between the two indicators based on the indicator values, and delete or replace one of the two indicators whose correlation is greater than a preset correlation threshold with a newly defined new indicator; The collinearity between each of the indicators and other indicators is calculated based on the indicator value, and the indicators with collinearity greater than a preset collinearity threshold and other indicators are merged into a new indicator or replaced with a redefined new indicator.

[0008] Optionally, the label information of the operating status includes an operating state, a warning state, and a fault state.

[0009] Optionally, dividing the sample set into a pairwise constraint set and an unpairwise constraint set based on the label information includes: If the label information of two indicator values ​​of the same indicator in the sample set is the same, the two indicator values ​​are divided into a paired constraint set; if the label information of two indicator values ​​of the same indicator in the sample set is different, the two indicator values ​​are divided into a non-paired constraint set.

[0010] Optionally, based on the pair constraint set and the unpair constraint set, using a k-means clustering algorithm to perform cluster analysis on the indicator values ​​of each of the indicators in the sample set to obtain the cluster center includes: Repeat the following steps until the cluster center remains unchanged or the maximum number of iterations is reached: Using k-means clustering algorithm to perform cluster analysis on the indicator values ​​of each indicator in the sample set; For a pair of indicator values ​​in the pairwise constraint set and , if in the clustering result, the index value and Belong to different clusters, then calculate the index value and The distance to its cluster center and ; like , then the indicator value and Divide into index values In the corresponding cluster; if , then the indicator value and Divide into index values In the corresponding cluster; For a pair of index values ​​in the non-paired constraint set and , if in the clustering result, the index value and Belong to the same cluster, then calculate the index value and The distance to its cluster center and ; like , then the index value Re-clustering can never match the index value In the same cluster, if , then the index value Re-clustering, it can never be consistent with the index value are in the same cluster.

[0011] Optionally, the using a k-means clustering algorithm to perform cluster analysis on the indicator values ​​of each of the indicators in the sample set further includes: Calculating the k nearest neighbors of the indicator value of each of the indicators in the sample set, and determining the predicted label of the indicator value; If the value of any indicator If the predicted label of is different from its label information, then determine whether the following formula is satisfied: ; In the formula, The predicted label corresponds to the cluster The number of indicator values, For the index value The number of neighbors of , is the total number of indicator values ​​of the indicator, is a constant parameter; If satisfied, the indicator value is extracted from the sample set.

[0012] In a second aspect, the present invention provides a device for dividing a distribution network operation state threshold interval, comprising: An indicator system establishment module is configured to establish an evaluation indicator system for the operation status of the distribution network based on the operation characteristics of the distribution network; An index value calculation module is configured to obtain basic parameters of the power system and calculate the index value of each index in the evaluation index system; An indicator value division module is configured to divide the indicator value of each indicator in proportion to generate a sample set and a test set; A label information adding module, configured to add label information of the running status to the indicator value of each indicator in the sample set; An indicator pairwise division module, configured to divide the sample set into a pairwise constraint set and a non-pairwise constraint set based on the label information; An indicator clustering calculation module is configured to perform cluster analysis on the indicator values ​​of each of the indicators in the sample set based on the paired constraint set and the unpaired constraint set using a k-means clustering algorithm to obtain a cluster center; The indicator value division module is configured to divide the operating status of the indicator value of each indicator in the test set according to the cluster center.

[0013] In a third aspect, the present invention provides an electronic device, including a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps according to the above method.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when executed by a processor.

[0015] In a fifth aspect, the present invention provides a computer program product, comprising a computer program / instruction, which implements the steps of the above method when executed by a processor.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a method, device, equipment, medium and product for dividing the operating status of a distribution network. The method can comprehensively evaluate the operating status of the distribution network. Compared with the traditional evaluation method that can only comprehensively evaluate the distribution network, the present invention can obtain the operating status of each evaluation indicator and provide more effective information for the distribution network evaluation. In addition, the present invention can adjust the distribution network operating status division interval based on the existing prior information to improve the evaluation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a method for dividing the operation status of a distribution network provided by an embodiment of the present invention; Figure 2 Schematic diagram of the composition of the evaluation index system for the operation status of the distribution network provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of an actual power distribution network in a certain place provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0019] Embodiment 1:

[0020] like Figure 1 As shown, an embodiment of the present invention provides a method for dividing the operation status of a distribution network, comprising the following steps: Step S1: Based on the operating characteristics of the distribution network, an evaluation index system for the operating status of the distribution network is established.

[0021] like Figure 2 As shown, specifically in this embodiment, the evaluation index system of the distribution network operation status includes: Power safety criteria layer indicators, used to measure the ability of the distribution network to cope with future risks; Power quality criterion layer indicators are used to measure the power supply quality level of distribution network voltage and frequency; The power supply margin criterion layer indicator is used to measure the ability of the distribution network to cope with load fluctuations while meeting load demand; Power reliability criterion layer indicators are used to measure the handling capacity of the distribution network when a fault occurs; Operational reliability criterion layer indicators are used to measure the actual controllability of distributed resources and loads in the distribution network; The independent operation quasi-measurement layer indicator is used to measure the ability of the distribution network to disconnect the interconnection switch after a major incident occurs and to meet the power demand without the support of external power supply.

[0022] (1) The indicators of the power safety criteria layer include short-circuit capacity and fault risk rate. The short-circuit capacity is used to measure the distribution network's ability to handle large-scale short-circuit faults, and the fault risk rate is used to measure the probability of fault risk in the distribution network under the influence of the working environment temperature. The short-circuit capacity can be obtained by: When a three-phase short circuit occurs in the distribution network, the short circuit voltage and current are obtained, and the short circuit capacity is calculated. : ; In the formula, is the short-circuit capacity, It is the short-circuit voltage and short-circuit current when a three-phase fault occurs in the distribution network. is the maximum short-circuit voltage and maximum short-circuit current of the distribution network; The failure risk rate can be obtained by: The working environment temperature of the main transformer in the distribution network is obtained by random sampling method, and the aging degree of the main transformer is calculated : ; ; In the formula, For the The aging degree, time interval and working environment temperature corresponding to each sampling point; According to the aging degree of the main transformer Calculate the service life of the main transformer under the influence of the working environment temperature : ; ; In the formula, , For the The service life and loss life of the main transformer under the influence of the working environment temperature at each moment; For service life , using the Weibull distribution model to quantify the failure risk rate : ; In the formula, is the rated service life of the main transformer, is the Weibull distribution parameter.

[0023] (2) The power quality criterion layer indicators include voltage deviation and frequency deviation, which are used to measure the power supply quality level of distribution network voltage and frequency; Voltage deviation for: ; In the formula, It is the maximum operating voltage and rated operating voltage of the main transformer in the distribution network; Frequency Deviation for: ; In the formula, It is the maximum operating frequency and standard operating frequency of the distribution network.

[0024] (3) The indicators of the power supply margin criterion layer include load rate and load deviation rate. The load rate is used to measure the actual carrying capacity of the distribution network, and the load deviation rate is used to measure the load fluctuation trend of the distribution network. Load factor for: ; In the formula, The load active power of the distribution network and the rated active power of the main transformer; The load offset rate can be obtained by: Load offset rate for: ; ; In the formula, For a set time Neidi The active power of the distribution network load and the maximum active power of the distribution network at a certain moment, For a set time Average active power of internal distribution network load, For a set time Maximum active power of the internal distribution network.

[0025] (4) The indicators of the power reliability criterion layer include fault self-healing rate and power transfer rate. The fault self-healing rate is used to measure the distribution network's ability to respond to risky faults, and the power transfer rate is used to measure the distribution network's power supply capacity in response to power consumption events. Fault self-healing rate for: ; In the formula, is the number of distribution network failures and self-healing events, is the number of distribution network failure events; Transfer rate for: ; In the formula, The distribution network receives the active power provided by other distribution networks and the active power of the distribution network load.

[0026] (5) The indicators of the operation reliability criterion layer include the proportion of controllable distributed resources and the proportion of controllable loads. The proportion of controllable distributed resources is used to measure the actual controllability of distributed resources in the distribution network, and the proportion of controllable loads is used to measure the actual controllability of loads in the distribution network. Controllable distributed resource ratio for: ; In the formula, is the active power of controllable distributed resources and distributed resources in the distribution network; Controllable load ratio for: ; In the formula, It is the active power of controllable load and load in the distribution network.

[0027] (6) Independent operation quasi-measurement layer indicators include independent operation time ratio and load power supply guarantee ratio. for: ; In the formula, is the actual independent operation time of the distribution network, Require time for distribution network standards; Ensure load power supply ratio : ; In the formula, It is the active power when the distribution network operates independently. The load demand of the distribution network is the active power.

[0028] In other optional implementations, the criterion layer indicators may be set according to actual needs to adapt to corresponding application scenarios.

[0029] In order to further optimize the criteria layer indicators, the evaluation indicator system for the distribution network operation status also includes: Obtain the basic parameters of the power system and calculate the index values ​​of each index in the evaluation index system; Calculate the correlation between two indicators based on the indicator values, and delete or replace one of the two indicators whose correlation is greater than a preset correlation threshold with a newly defined new indicator; If the correlation coefficient between indicators is greater than 0.9, it means that there is a strong positive correlation between the two indicators, and the information overlap between the two is extremely high; when it is less than -0.9, it means that there is a strong negative correlation between the two indicators, which also means that the information overlap between the two is extremely high. Therefore, after solving the correlation coefficient between the indicators, 0.9 is usually set as the critical value. When it is less than 0.9, it means that the correlation between the two indicators is weak, the information between the two cannot be fully expressed by the other party, and the indicators have strong independence.

[0030] The collinearity between each indicator and other indicators is calculated based on the indicator value, and the indicators with collinearity greater than a preset collinearity threshold are merged with other indicators into a new indicator or replaced with a redefined new indicator.

[0031] Correlation analysis of two indicators can often only reflect the information overlap between the two indicators. However, even if the correlation between the two indicators is not strong, there may be a situation where a linear combination of n indicators (n>2) can express a certain indicator, that is, most of the information it contains can also be expressed by the linear combination of other indicators. Therefore, it is necessary to perform a collinearity test on the indicators, calculate the variance inflation factor of each indicator, and determine whether it exceeds the threshold. If the variance inflation factor is greater than 10, it is considered that the indicator can be formed by a linear combination of multiple other indicators, with a strong degree of information overlap, and a new indicator needs to be proposed.

[0032] Step S2: Obtain basic parameters of the power system and calculate the index value of each index in the evaluation index system.

[0033] Step S3: Divide the indicator value of each indicator in proportion to generate a sample set and a test set.

[0034] Specifically in this embodiment, the ratio of the index values ​​of the sample set and the test set is 1:9.

[0035] Step S4: Add label information of the running status to the indicator value of each indicator in the sample set.

[0036] Specifically in this embodiment, the label information of the operating state includes an operating state, a warning state, and a fault state.

[0037] Step S5: Divide the sample set into a pairwise constraint set and an unpairwise constraint set based on the label information.

[0038] Dividing the sample set into a pairwise constraint set and an unpaired constraint set based on label information includes: If the label information of two indicator values ​​of the same indicator in the sample set is the same, the two indicator values ​​are divided into a pair constraint set. If the label information of two indicator values ​​of the same indicator in the sample set is different, the two indicator values ​​are divided into a non-pair constraint set.

[0039] Step S6: Based on the paired constraint set and the unpaired constraint set, a k-means clustering algorithm is used to perform cluster analysis on the indicator values ​​of each indicator in the sample set to obtain the cluster center.

[0040] The k-means clustering algorithm is used to perform cluster analysis on the indicator values ​​of each indicator in the sample set, and the following steps are also included: Calculate the k nearest neighbors of the indicator value of each indicator in the sample set and determine the predicted label of the indicator value; If the value of any indicator If the predicted label of is different from its label information, then determine whether the following formula is satisfied: ; In the formula, The predicted label corresponds to the cluster The number of indicator values, For the index value The number of neighbors of , is the total number of indicator values ​​of the indicator, is a constant parameter; If satisfied, the indicator value Proposed from the sample set. By proposing indicator values ​​that do not meet the requirements Reduce the amount of calculation.

[0041] Get the cluster center, including: Repeat the following steps until the cluster center remains unchanged or the maximum number of iterations is reached: The k-means clustering algorithm is used to perform cluster analysis on the indicator values ​​of each indicator in the sample set; For a pair of indicator values ​​in a pairwise constraint set and , if in the clustering result, the index value and Belong to different clusters, then calculate the index value and The distance to its cluster center and ; like , then the indicator value and Divide into index values In the corresponding cluster; if , then the indicator value and Divide into index values In the corresponding cluster; For a pair of index values ​​in a non-paired constraint set and , if in the clustering result, the index value and Belong to the same cluster, then calculate the index value and The distance to its cluster center and ; like , then the index value Re-clustering can never match the index value In the same cluster, if , then the index value Re-clustering can never match the index value are in the same cluster.

[0042] Step S7: divide the operating status of the indicator value of each indicator in the test set according to the cluster center.

[0043] The system of this embodiment is based on the actual distribution network structure of a certain place, such as Figure 3 As shown in the figure, the distribution network has 149 nodes, a load capacity of 115MVA, and a photovoltaic capacity of 14.825MVA. The main lines include 10kV and 20kV.

[0044] The correlation test results of the evaluation index system proposed in this embodiment are shown in Table 1. Due to space limitations, the names of the indicators are Figure 2 The alphanumeric characters after the name of each indicator are used to represent the indicators in the table below. The same is true for the indicators in the table below.

[0045] Table 1: Correlation test results

[0046] Obviously, although there is a certain degree of information overlap between the indicators, the correlation coefficient between the indicators does not exceed the threshold of 0.9. Therefore, it can be considered that the degree of information duplication between the indicators is within a reasonable range, and each indicator still contains a large amount of independently stored information.

[0047] The collinearity test results of the evaluation index system proposed in this embodiment are shown in Table 2.

[0048] Table 2: Collinearity test results

[0049] Based on the k-means clustering results, the center values ​​of each indicator cluster are output as the operation status division interval, as shown in Table 3.

[0050] Table 3: Cluster center values ​​of each state of indicators

[0051] This implementation method establishes a distribution network operation status evaluation index system; considers the correlation test between single indicators and the diagnosis of collinearity between multiple indicators to verify the rationality of establishing the evaluation index system; initializes the distribution network operation status evaluation index interval value; establishes a pair constraint set and a sample set based on the must-connect constraint and the do-not-connect constraint to learn the existing prior knowledge; based on the prior information, establishes an improved k-means algorithm to adjust the original operation status threshold interval of each evaluation index. The method proposed in the present invention achieves a balance between prior information and machine learning, and provides a new calculation idea for the distribution network operation status evaluation.

[0052] Embodiment 2: An embodiment of the present invention provides a device for dividing a distribution network operation state threshold interval, comprising: An indicator system establishment module is configured to establish an evaluation indicator system for the operation status of the distribution network based on the operation characteristics of the distribution network; An index value calculation module is configured to obtain basic parameters of the power system and calculate the index value of each index in the evaluation index system; An indicator value division module is configured to divide the indicator value of each indicator in proportion to generate a sample set and a test set; A label information adding module is configured to add label information of the running status to the indicator value of each indicator in the sample set; An indicator pairwise partitioning module is configured to partition a sample set into a pairwise constraint set and a non-pairwise constraint set based on label information; The indicator clustering calculation module is configured to perform cluster analysis on the indicator values ​​of each indicator in the sample set based on the paired constraint set and the unpaired constraint set using the k-means clustering algorithm to obtain the cluster center; The indicator value division module is configured to divide the operating status of the indicator value of each indicator in the test set according to the cluster center.

[0053] Embodiment three:

[0054] Based on the first embodiment, the embodiment of the present invention provides an electronic device, including a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps according to the above method.

[0055] Embodiment 4:

[0056] Based on the first embodiment, the embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented.

[0057] Embodiment five:

[0058] Based on the first embodiment, the embodiment of the present invention provides a computer program product, including a computer program / instruction, which implements the steps of the above method when executed by a processor.

[0059] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0060] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0061] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0062] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0063] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for dividing the operating status of a distribution network, characterized in that: include: Based on the operating characteristics of the distribution network, an evaluation index system for the operating status of the distribution network is established; Obtaining basic parameters of the power system and calculating the index value of each index in the evaluation index system; Divide the index values ​​of each of the indicators in proportion to generate a sample set and a test set; Adding label information of the running status to the indicator value of each indicator in the sample set; Dividing the sample set into a pairwise constraint set and an unpairwise constraint set based on the label information; Based on the paired constraint set and the unpaired constraint set, a k-means clustering algorithm is used to perform cluster analysis on the indicator values ​​of each of the indicators in the sample set to obtain a cluster center; The indicator values ​​of each indicator in the test set are divided into operating states according to the cluster center.

2. The method for dividing the distribution network operation status threshold interval according to claim 1 is characterized in that: The evaluation index system of the distribution network operation status includes: Power safety criteria layer indicators, used to measure the ability of the distribution network to cope with future risks; Power quality criterion layer indicators are used to measure the power supply quality level of distribution network voltage and frequency; The power supply margin criterion layer indicator is used to measure the ability of the distribution network to cope with load fluctuations while meeting load demand; Power reliability criterion layer indicators are used to measure the handling capacity of the distribution network when a fault occurs; Operational reliability criterion layer indicators are used to measure the actual controllability of distributed resources and loads in the distribution network; The independent operation quasi-measurement layer indicator is used to measure the ability of the distribution network to disconnect the interconnection switch after a major incident occurs and to meet the power demand without the support of external power supply.

3. The method for dividing the distribution network operation status threshold interval according to claim 2 is characterized in that: The power safety criteria layer indicators include short-circuit capacity and failure risk rate; The power quality criterion layer indicators include voltage deviation and frequency deviation; The power supply margin criterion layer indicators include load rate and load offset rate; The power reliability criterion layer indicators include fault self-healing rate and power transfer rate; The indicators of the operation reliability criterion layer include the proportion of controllable distributed resources and the proportion of controllable load; The independent operation quasi-measurement layer indicators include the independent operation time ratio and the load power supply guarantee ratio.

4. The method for dividing the threshold interval of the distribution network operation status according to claim 1 is characterized in that: The evaluation index system for establishing the distribution network operation status also includes: Obtaining basic parameters of the power system and calculating the index value of each index in the evaluation index system; Calculate the correlation between the two indicators based on the indicator values, and delete or replace one of the two indicators whose correlation is greater than a preset correlation threshold with a newly defined new indicator; The collinearity between each of the indicators and other indicators is calculated based on the indicator value, and the indicators with collinearity greater than a preset collinearity threshold and other indicators are merged into a new indicator or replaced with a redefined new indicator.

5. The method for dividing the threshold interval of the distribution network operation status according to claim 1 is characterized in that: The label information of the operating status includes operating state, warning state and fault state.

6. The method for dividing the threshold interval of the distribution network operation status according to claim 1 is characterized in that: The dividing the sample set into a pairwise constraint set and an unpairwise constraint set based on the label information comprises: If the label information of two indicator values ​​of the same indicator in the sample set is the same, the two indicator values ​​are divided into a paired constraint set; if the label information of two indicator values ​​of the same indicator in the sample set is different, the two indicator values ​​are divided into a non-paired constraint set.

7. The method for dividing the threshold interval of the distribution network operation status according to claim 6 is characterized in that: The step of performing cluster analysis on the indicator values ​​of each indicator in the sample set based on the pair constraint set and the unpair constraint set using a k-means clustering algorithm to obtain a cluster center includes: Repeat the following steps until the cluster center remains unchanged or the maximum number of iterations is reached: Using k-means clustering algorithm to perform cluster analysis on the indicator values ​​of each indicator in the sample set; For a pair of indicator values ​​in the pairwise constraint set and , if in the clustering result, the index value and Belong to different clusters, then calculate the index value and The distance to its cluster center and ; like , then the indicator value and Divide into index values In the corresponding cluster; if , then the indicator value and Divide into index values In the corresponding cluster; For a pair of index values ​​in the non-paired constraint set and , if in the clustering result, the index value and Belong to the same cluster, then calculate the index value and The distance to its cluster center and ; like , then the index value Re-clustering, it can never be consistent with the index value In the same cluster, if , then the index value Re-clustering can never match the index value are in the same cluster.

8. The method for dividing the threshold interval of the distribution network operation status according to claim 1 is characterized in that: The adopting k-means clustering algorithm to perform cluster analysis on the indicator values ​​of each of the indicators in the sample set also includes: Calculate the k nearest neighbors of the indicator value of each indicator in the sample set, and determine the predicted label of the indicator value; If the value of any indicator If the predicted label of is different from its label information, then determine whether the following formula is satisfied: ； In the formula, The predicted label corresponds to the cluster The number of indicator values, For the index value The number of neighbors of , is the total number of indicator values ​​of the indicator, is a constant parameter; If satisfied, the indicator value is extracted from the sample set.

9. A device for dividing the threshold interval of the operation status of a distribution network, characterized in that: include: An indicator system establishment module is configured to establish an evaluation indicator system for the operation status of the distribution network based on the operation characteristics of the distribution network; An index value calculation module is configured to obtain basic parameters of the power system and calculate the index value of each index in the evaluation index system; An indicator value division module is configured to divide the indicator value of each indicator in proportion to generate a sample set and a test set; A label information adding module, configured to add label information of the running status to the indicator value of each indicator in the sample set; An indicator pairwise division module, configured to divide the sample set into a pairwise constraint set and a non-pairwise constraint set based on the label information; An indicator clustering calculation module is configured to perform cluster analysis on the indicator values ​​of each of the indicators in the sample set based on the paired constraint set and the unpaired constraint set using a k-means clustering algorithm to obtain a cluster center; The indicator value division module is configured to divide the operating status of the indicator value of each indicator in the test set according to the cluster center.

10. An electronic device, characterized in that: including processor and storage medium; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images