Power distribution network flood risk assessment method and device, electronic equipment and storage medium

Abstract

The invention discloses a power distribution network flood risk assessment method and device, electronic equipment and a storage medium, and the method comprises the steps: dividing a target region corresponding to a target power distribution network into n water collection regions, determining a power distribution network risk value corresponding to each water collection region in the n water collection regions according to a determination mode in the following steps S1-S3, obtaining n power distribution network risk values, the method specifically comprises the following steps of S1, determining flood monitoring data of a first catchment area in a historical time period to obtain target flood monitoring data, S2, determining a power distribution network equipment failure probability corresponding to the first catchment area based on x pieces of marked data, y pieces of unmarked data and a preset Gaussian mixture model, and S3, determining a power distribution network risk value corresponding to the first water collection area based on the power distribution network equipment failure probability, and finally determining a target power distribution network risk value of the target area based on the n power distribution network risk values. By adopting the embodiment of the invention, the accuracy of risk assessment of flood brought to the power distribution network is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network risk assessment, and in particular to a distribution network flood risk assessment method, device, electronic equipment and storage medium. Background Art

[0002] The distribution network is an important facility to ensure the safety of urban power supply. If the distribution network equipment is flooded or even submerged, it will seriously affect the safety of power supply. Some equipment in the distribution network cannot work normally after being damaged, resulting in a reduction in the power supply range and causing great inconvenience to people's lives. Accurately assessing the risks of floods to the distribution network can allow the power department to take rescue measures in advance. At present, the risks brought by floods to the distribution network can be assessed, but the accuracy of the assessment is not high. Summary of the invention

[0003] The embodiment of the present application provides a method for assessing flood risk in a distribution network, which improves the accuracy of risk assessment on the distribution network brought by floods by determining a target distribution network risk value of a target area corresponding to the target distribution network.

[0004] In a first aspect, an embodiment of the present application provides a method for assessing flood risk in a distribution network, the method comprising:

[0005] The target area corresponding to the target distribution network is divided into n catchment areas; n is an integer greater than 1;

[0006] According to the determination method in the following steps S1-S3, the distribution network risk value corresponding to each of the n watershed areas is determined to obtain n distribution network risk values, which is specifically the following steps:

[0007] S1. Determine the flood monitoring data of the first watershed in the historical time period to obtain target flood monitoring data; the first watershed is any one of the n watersheds; the target flood monitoring data includes x labeled data and y unlabeled data; x is a positive integer, and y is a positive integer;

[0008] S2, determining the failure probability of the distribution network equipment corresponding to the first catchment area based on x labeled data, y unlabeled data, and a preset Gaussian mixture model;

[0009] S3. Determine the distribution network risk value corresponding to the first catchment area based on the failure probability of the distribution network equipment;

[0010] A target distribution network risk value of a target area is determined based on the n distribution network risk values.

[0011] In a second aspect, an embodiment of the present application provides a distribution network flood risk assessment device, the device comprising: a division unit and a processing unit;

[0012] A division unit, used to divide the target area corresponding to the target distribution network into n catchment areas; n is an integer greater than 1;

[0013] The processing unit is used to determine the distribution network risk value corresponding to each of the n watershed areas according to the determination method in the following steps S1-S3 to obtain n distribution network risk values, specifically the following steps:

[0014] S1. Determine the flood monitoring data of the first watershed in the historical time period to obtain target flood monitoring data; the first watershed is any one of the n watersheds; the target flood monitoring data includes x labeled data and y unlabeled data; x is a positive integer, and y is a positive integer;

[0015] S2, determining the failure probability of the distribution network equipment corresponding to the first catchment area based on x labeled data, y unlabeled data, and a preset Gaussian mixture model;

[0016] S3. Determine the distribution network risk value corresponding to the first catchment area based on the failure probability of the distribution network equipment;

[0017] A target distribution network risk value of a target area is determined based on the n distribution network risk values.

[0018] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor so that the electronic device executes the method of the first aspect.

[0019] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0020] In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, so that a computer executes the method of the first aspect.

[0021] The implementation of the present invention has the following beneficial effects:

[0022] It can be seen that the distribution network flood risk assessment method described in the implementation mode of the present invention first divides the target area corresponding to the target distribution network into n catchment areas, and then determines the distribution network risk value corresponding to each of the n catchment areas according to the determination method in the following steps S1-S3, and obtains n distribution network risk values, which are specifically the following steps: S1, determining the flood monitoring data of the first catchment area in the historical time period to obtain target flood monitoring data; the first catchment area is any one of the n catchment areas; the target flood monitoring data includes x labeled data and y unlabeled data; x is a positive integer, and y is a positive integer; S2, determining the failure probability of the distribution network equipment corresponding to the first catchment area based on the x labeled data, y unlabeled data, and a preset Gaussian mixture model; S3, determining the distribution network risk value corresponding to the first catchment area based on the failure probability of the distribution network equipment, and finally determining the target distribution network risk value of the target area based on the n distribution network risk values, thereby improving the accuracy of the risk assessment of the distribution network brought by floods. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the implementation methods of the present application or the background technology, the drawings required for use in the implementation methods of the present application or the background technology will be described below.

[0024] Figure 1 It is a flow chart of a method for assessing flood risk in a distribution network provided by an embodiment of the present application;

[0025] Figure 2 It is a flow chart for determining the failure probability of distribution network equipment provided by an embodiment of the present application;

[0026] Figure 3 It is a structural schematic diagram of a distribution network flood risk assessment device provided in an embodiment of the present application;

[0027] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the implementation mode of the present application will be clearly and completely described below in conjunction with the drawings in the implementation mode of the present application. Obviously, the described implementation mode is only a part of the implementation mode of the present application, not all the implementation modes. Based on the implementation mode in the present application, all other implementation modes obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0029] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0030] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0031] See also Figure 1 , Figure 1 This is a flow chart of a method for assessing flood risk in a distribution network provided by an embodiment of the present application, including but not limited to the following steps:

[0032] S101: Divide a target area corresponding to a target distribution network into n catchment areas.

[0033] In this embodiment, n is an integer greater than 1. Since the area corresponding to the distribution network is large and the situation is complex, a large and complex area can be decomposed into relatively smaller and more homogeneous parts. Exemplarily, the target area corresponding to the target distribution network is divided into p unit areas, where p is an integer greater than or equal to n. Specifically, the target area can be regarded as a plane figure and divided into squares of the same size according to the set rules. The unit areas can also be divided according to fixed distance intervals, or according to urban rivers and rivers. It can also be divided according to geographical meteorological data, such as elevation data and precipitation data, and can also be divided according to the geographical location data of the substation, or it can be divided according to street view data, which is not limited here. Exemplarily, the accumulated amount of water flow corresponding to each unit area in p unit areas is determined to obtain p accumulated amounts of water flow. Specifically, the accumulated amount of water flow corresponding to each unit area can be determined by determining the change in the water level corresponding to each unit area. The change in the water level can be determined by a water level meter. Exemplarily, based on p water flow accumulations, p unit areas are combined to obtain n watersheds, wherein each of the n watersheds corresponds to at least one unit area, and if the number corresponding to at least one unit area is greater than 1, at least one unit area corresponding to each watershed is an adjacent unit area, and the water flow accumulation corresponding to each watershed is greater than or equal to the water flow accumulation threshold. Specifically, each watershed is composed of one or more unit areas, and there may be a watershed that contains only one unit area, or a watershed that is composed of multiple unit areas. When a watershed is composed of multiple unit areas, these unit areas must be adjacent in space. It can ensure the continuity and rationality of the catchment area in space. If non-adjacent unit areas are combined into one catchment area, it may bring difficulties in management and analysis in practical applications. For example, when considering the natural flow of water and the planning of water conservancy facilities in the catchment area, adjacent unit areas are more in line with the actual situation. For each catchment area finally formed, there is a requirement for the cumulative amount of water flow. The cumulative amount of water flow in this catchment area must reach or exceed a pre-set threshold of cumulative amount of water flow. The setting of this threshold may be based on actual needs, such as the design requirements of water conservancy projects, the goals of water resources management, etc. Only the catchment area that meets this condition is considered to meet specific requirements. By dividing the unit area and determining the cumulative amount of water flow, the distribution of water resources in the target area can be more accurately understood. The division of the catchment area based on the cumulative amount of water flow can clearly understand the water collection situation of each catchment area. The provisions of the adjacent unit areas forming the catchment area are conducive to effective control of floods in space.

[0034] It can be seen that subdividing a large area into smaller unit areas and dividing the catchment area based on the accumulated water flow can more accurately analyze and understand the distribution and flow of water resources in the target area, and provide more accurate data support for subsequent water conservancy planning and management. Accurate division and analysis can reduce the uncertainty in risk assessment and management of distribution network equipment and improve the ability to predict risks.

[0035] S102: Determine the flood monitoring data of the first catchment area in a historical time period to obtain target flood monitoring data.

[0036] In this embodiment, the first catchment area is any one of the n catchment areas, wherein the target flood monitoring data includes x labeled data and y unlabeled data, where x is a positive integer and y is a positive integer. Specifically, the flood monitoring data includes: geographic meteorological data, such as elevation data and precipitation data; power grid parameter data, such as electrical equipment data and substation geographic location data; rainstorm or flood process monitoring data; urban terrain data and street view data; urban drainage network data; urban river and river terrain data; substation network data including the ground elevation of each substation, cable joint elevation data, station network data, etc.

[0037] It needs to be explained that labeled data means that each sample in the data set has a clear category label or target value. In the context of flood monitoring data, for example, for water level data, if it has been clearly marked that a certain water level value corresponds to a category such as "flood occurrence" or "normal water level", this is labeled data. Labeled data is the basis of supervised learning and also plays a key guiding role in semi-supervised learning. Unlabeled data means that the samples in the data set do not have a pre-given category label or target value. In the flood monitoring scenario, a large amount of water level change data, rainfall data, etc. may be collected, but these data are not labeled as floods or not. This is unlabeled data.

[0038] It can be seen that the explicit information of labeled data is fully utilized to guide learning and analysis, while a large amount of unlabeled data is not wasted. The potential patterns and information in unlabeled data are mined through methods such as semi-supervised learning, thereby making more comprehensive use of the collected data.

[0039] S103: Determine the failure probability of distribution network equipment corresponding to the first catchment area based on x labeled data, y unlabeled data, and a preset Gaussian mixture model.

[0040] In this implementation, see Figure 2 , Figure 2 A flowchart for determining the failure probability of distribution network equipment provided by an embodiment of the present application includes but is not limited to the following steps:

[0041] S201: Determine k Gaussian components corresponding to a preset Gaussian mixture model.

[0042] In this embodiment, each Gaussian component is related to the monitoring data of floods, and k is a positive integer. The Gaussian mixture model is a probability model composed of multiple Gaussian distributions (normal distributions). Here, k Gaussian components in this model need to be determined. k is a positive integer, which represents the number of Gaussian distributions. These Gaussian components are related to flood monitoring data, which means that each Gaussian distribution may represent a typical state in flood monitoring data. For example, one Gaussian component may represent the state of normal water level and flow, and another Gaussian component may represent the water level and flow state during mild floods. The remaining Gaussian components represent different states, which will not be repeated here.

[0043] S202: Determine the failure probability of distribution network equipment corresponding to each Gaussian component in k Gaussian components based on x labeled data, and obtain k first distribution network equipment failure probabilities.

[0044] In this embodiment, first, x labeled data are classified into different categories related to k Gaussian components according to the labels, and then the number of data points that cause the failure of the distribution network equipment and the number of data points that do not cause the failure are counted under the flood state represented by each Gaussian component. Then, the failure probability of the distribution network equipment corresponding to each Gaussian component (the first distribution network equipment failure probability) can be calculated by the ratio of the number of data points that cause the failure to the total number of data points in the Gaussian component (failed plus non-failed), which can be calculated specifically according to the following formula: Among them, P i is the failure probability of the first distribution network equipment corresponding to the i-th Gaussian component, n i is the number of data points that cause the failure of distribution network equipment in the i-th Gaussian component, m i is the number of data points that do not cause distribution network equipment failure in the i-th Gaussian component.

[0045] It can be seen that through a clear calculation method, the failure probability of distribution network equipment corresponding to each Gaussian component can be obtained more accurately, which provides an accurate quantitative basis for subsequent risk assessment and decision-making. By classifying the labeled data into flood states represented by different Gaussian components, the failure probability in each state can be calculated separately, thereby more carefully analyzing the impact of different degrees of floods on distribution network equipment.

[0046] S203: Input y unlabeled data into a preset Gaussian mixture model to obtain y·k probability density values.

[0047] In this embodiment, each of the y unlabeled data corresponds to k probability density values. Each of the y unlabeled data corresponds to k probability density values. Specifically, each of the y unlabeled data is input into a preset Gaussian mixture model to obtain a probability density value corresponding to each data, and each data corresponds to k probability density values. By inputting y unlabeled data, y·k probability density values ​​are obtained.

[0048] S204: Determine the failure probability of the distribution network equipment corresponding to each unlabeled data in the y unlabeled data based on the k first distribution network equipment failure probabilities and y·k probability density values, and obtain y second distribution network equipment failure probabilities.

[0049] In this embodiment, the k first distribution network equipment failure probabilities represent the distribution network equipment failure probability corresponding to each Gaussian component in the k Gaussian components, and the y·k probability density values ​​represent the probability distribution of y unlabeled data under the k Gaussian components. Then, the k probability density values ​​corresponding to each unlabeled data in the y unlabeled data are multiplied by the k first distribution network equipment failure probabilities to obtain the second distribution network equipment failure probability corresponding to each unlabeled data in the y unlabeled data, that is, the y second distribution network equipment failure probabilities.

[0050] S205: Determine the failure probability of the distribution network equipment corresponding to each labeled data in the x labeled data, and obtain x second distribution network equipment failure probabilities.

[0051] In this embodiment, the tag content of the marked data includes information related to the failure probability of the distribution network equipment, and these probabilities can be directly extracted as the failure probability of the distribution network equipment corresponding to each marked data. For example, the format of the marked data is (flood monitoring data value, distribution network equipment failure probability), then the failure probability of the distribution network equipment corresponding to each data point can be directly extracted to obtain x second distribution network equipment failure probabilities.

[0052] It can be seen that the failure probability of distribution network equipment is determined by combining labeled data and unlabeled data, which makes full use of all available data resources and avoids incomplete information caused by relying solely on labeled data. The failure probability of distribution network equipment is calculated in a variety of ways, combining the characteristics and advantages of different data, which can more accurately estimate the failure probability and reduce errors. For a large amount of unlabeled data, the information about the failure of distribution network equipment hidden in it is mined by combining it with the Gaussian mixture model and the existing failure probability, which increases the utilization value of the data, enables the model to better adapt to different data distributions and complex actual situations, improves the versatility and reliability of the model in different scenarios, and also helps to more completely evaluate the risks of distribution networks under flood conditions.

[0053] S206: Determine the failure probability of the distribution network equipment corresponding to the first catchment area based on the x failure probabilities of the second distribution network equipment and the y failure probabilities of the second distribution network equipment.

[0054] In this embodiment, the average value of the failure probabilities of x second distribution network equipment is first determined to obtain the first reference distribution network equipment failure probability, and then the average value of the failure probabilities of y second distribution network equipment is determined to obtain the second reference distribution network equipment failure probability, and then the first weight corresponding to the first reference distribution network equipment failure probability and the second weight corresponding to the second reference distribution network equipment failure probability are determined. The first weight and the second weight can be determined according to the quality, reliability or amount of data. For example, if the accuracy of the labeled data is very high, the first weight can be set to a larger value. If the amount of unlabeled data is large and can provide more information, the second weight can be increased accordingly. The weights can also be determined by cross-validation or other model evaluation methods to make the final distribution network equipment failure probability estimate more accurate. Exemplarily, the failure probability of the distribution network equipment corresponding to the first catchment area is determined based on the first weight, the second weight, the failure probability of the first reference distribution network equipment, and the failure probability of the second reference distribution network equipment. Specifically, as the number of isolated points increases, the operating state of the distribution network becomes more complex and unstable, and the power grid environment around the equipment corresponding to the unlabeled data changes, and the corresponding failure probability is associated with the number of isolated points. Therefore, the number of isolated points in the first catchment area is first obtained, and then the target adjustment coefficient corresponding to the number of isolated points is determined, which can be a preset mapping relationship between the number of isolated points and the adjustment coefficient. Based on the mapping relationship, the target adjustment coefficient corresponding to the number of isolated points can be determined. Then, the second weight is adjusted based on the target adjustment coefficient to obtain the second target weight. The specific calculation formula is as follows: second target weight = second weight × (1 + target adjustment coefficient); the second target weight can be obtained according to the above formula. Then, the first weight is adjusted based on the second target weight to obtain the first target weight. Specifically, since the sum of the first weight and the second weight is 1, after the second weight is adjusted to the second target weight, the first weight is also adjusted accordingly to obtain the first target weight, so that the sum of the first target weight and the second target weight is 1. Exemplarily, the failure probability of the distribution network equipment corresponding to the first catchment area is determined based on the first target weight, the second target weight, the first reference distribution network equipment failure probability, and the second reference distribution network equipment failure probability. Specifically, the failure probability of the distribution network equipment corresponding to the first catchment area is calculated according to the following formula:

[0055] F=a×α+b×β

[0056] Among them, F is the failure probability of distribution network equipment, a is the first reference distribution network equipment failure probability, b is the second reference distribution network equipment failure probability, α is the first target weight, and β is the second target weight.

[0057] It can be seen that the reference failure probability calculated by combining labeled data and unlabeled data makes full use of the information contained in different types of data to make the final failure probability estimation more comprehensive and accurate. By assigning different weights to the reference failure probabilities calculated by labeled data and unlabeled data, they can be flexibly adjusted according to the quality, reliability, and quantity of the data to better reflect their importance in the failure probability estimation. The introduction of the target adjustment coefficient corresponding to the number of isolated points can reflect the influence of the complexity and instability of the distribution network operation state on the failure probability, making the calculation results more in line with the actual situation.

[0058] S104: Determine a distribution network risk value corresponding to the first catchment area based on the failure probability of distribution network equipment.

[0059] In this embodiment, the failure probability of distribution network equipment can be input into a preset risk assessment model to obtain the distribution network risk value corresponding to the first catchment area. It can also be a mapping relationship between the preset failure probability of distribution network equipment and the distribution network risk value. Based on this mapping relationship, the distribution network risk value corresponding to the first catchment area can be determined.

[0060] It can be seen that through the preset model or mapping relationship, the distribution network risk value can be quickly and directly derived from the failure probability of distribution network equipment, saving a lot of computing time and resources. The preset method can ensure the consistency of evaluation under different circumstances, reduce the impact of human factors and random errors on the results, and improve the accuracy of the evaluation.

[0061] S105: Determine a target distribution network risk value of a target area based on the n distribution network risk values.

[0062] In this embodiment, the method for determining the distribution network risk value corresponding to any one of the n watersheds is the same as the method for determining the distribution network risk value corresponding to the first watershed. Therefore, the distribution network risk value corresponding to each of the n watersheds can be determined according to the above-mentioned method of determining the distribution network risk value corresponding to the first watershed, and n distribution network risk values ​​can be obtained.

[0063] After determining the risk values ​​of n distribution networks, the load importance value corresponding to each of the n catchment areas is determined to obtain n load importance values. The load importance value corresponding to the first catchment area is first determined. Specifically, the critical load, important load and general load of the distribution network equipment in the first catchment area are first determined. Critical loads usually refer to those loads that are crucial to social operation, people's life safety or the normal operation of important facilities, and once a power outage occurs, extremely serious consequences will be caused, such as hospital operating rooms, emergency command centers, etc. Important loads refer to loads that will cause greater losses or impacts due to power outages, but the consequences are slightly lighter than critical loads, such as production lines in large factories, trading systems of financial institutions, etc. General loads refer to loads that are relatively less affected by power outages, such as daily electricity consumption of ordinary residents and lighting of general commercial stores. Exemplarily, the first weight corresponding to the critical load, the second weight corresponding to the important load, and the third weight corresponding to the general load are determined, wherein the first weight is greater than the second weight, the second weight is greater than the third weight, and the sum of the first weight, the second weight and the third weight is 1. Specifically, since the critical load is of the highest importance, its corresponding first weight is the largest, the importance of the important load is second, and its corresponding second weight is second. The importance of the general load is relatively low, and the corresponding third weight is the smallest. The sum of the three weights is 1 to ensure the normalization of the weights, that is, they together constitute a complete measure of the importance of the load. Exemplarily, the corresponding target load in the first catchment area is determined based on the critical load, the important load, the general load, the first weight, the second weight and the third weight. Specifically, by multiplying and summing different types of loads with their corresponding weights, a target load value that comprehensively considers the importance of various types of loads can be obtained. This target load value can more comprehensively reflect the overall importance and characteristics of the loads in the catchment area. Exemplarily, the load importance value corresponding to the target load is determined, wherein the target load is positively correlated with the load importance value, and the load importance value is positively correlated with the load importance. Specifically, it can be a mapping relationship between a preset load and a load importance value. Based on the mapping relationship, the load importance value corresponding to the target load can be determined. The larger the target load, the higher the load importance value, which means that the importance of the load in the watershed is stronger. Exemplarily, the risk weight corresponding to each of the n watersheds is determined based on n load importance values ​​to obtain n risk weights, wherein the load importance value is positively correlated with the risk weight. Specifically, for the load importance value calculated for each watershed, a corresponding risk weight will be determined for the watershed accordingly. If the load importance value of a watershed is high, it means that the importance of its load is large, and the risk weight allocated to it will also be large. Conversely, if the load importance value is low, the corresponding risk weight is small. Therefore, the risk weight corresponding to each of the n watersheds is determined based on the n load importance values, and n risk weights can be obtained.

[0064] Exemplarily, the target distribution network risk value of the target area is determined based on n distribution network risk values ​​and n risk weights. Specifically, the reference distribution network risk value is first determined based on the n distribution network risk values ​​and n risk weights. Since each watershed area has its own independently calculated distribution network risk value, the distribution network risk values ​​of the n watershed areas are then weighted and comprehensively calculated based on the risk weight of each watershed area obtained previously. That is, the distribution network risk value of each watershed area is multiplied by its corresponding risk weight, and then the weighted results of all watershed areas are added together, and the obtained sum is the reference distribution network risk value of the target area. When the maximum load loss increases, it means that when the distribution network faces a fault or abnormal situation, more power loads may not be supplied, which will lead to more extensive and serious power outages. From an economic perspective, more loads losing power will cause larger-scale production interruptions, stagnation of commercial activities and inconvenience in residents' lives, thereby bringing huge economic losses. The longer the power outage and the more users and industries involved, the greater the economic losses, and the higher the risk value of the distribution network. From the perspective of recovery cost, a larger load loss may cause more equipment to be damaged, increase the cost of repairing and replacing equipment, and the manpower and material investment required to restore power supply, thereby increasing the risk value of the distribution network. Therefore, the maximum load loss of the target distribution network in the historical time period is obtained, and the first impact coefficient corresponding to the maximum load loss is determined. It can be a mapping relationship between the preset maximum load loss and the first impact coefficient. Based on this mapping relationship, the first impact coefficient corresponding to the maximum load loss can be determined. If the voltage exceeds the threshold for a long time, the long-term overvoltage may cause the power equipment (such as transformers, capacitors, cables, etc.) to bear excessive voltage stress, accelerate the aging and damage of the equipment, and increase the probability of equipment failure, thereby leading to an increase in maintenance and replacement costs. Overvoltage for too long may cause safety accidents such as electrical fires, threatening the safety of life and property. Due to the increase in equipment failures and safety issues, the number of power outages may increase and the power outage time may be extended, reducing the power supply reliability of the distribution network. Therefore, the longer the voltage of the target distribution network exceeds the threshold, the greater the impact on the normal operation of the distribution network and users, and the higher the risk value of the distribution network. Therefore, the time when the voltage corresponding to the target distribution network exceeds the voltage threshold in the historical time period is obtained to obtain the target time, and then determine the second influence coefficient corresponding to the target time. It can be a mapping relationship between the time when the voltage corresponding to the target distribution network exceeds the voltage threshold in the historical time period and the influence coefficient. Based on the mapping relationship, the second influence coefficient corresponding to the target time can be determined. Exemplarily, the reference distribution network risk value is adjusted according to the first influence coefficient and the second influence coefficient to obtain the target distribution network risk value. The specific calculation formula is as follows: target distribution network risk value = reference distribution network risk value × (1 + first influence coefficient) × (1 + second influence coefficient); The target distribution network risk value can be obtained according to the above formula.

[0065] It can be seen that it covers many factors such as the failure risk of distribution network equipment in the catchment area, the importance of load, the maximum load loss and the voltage exceeding the threshold time, which can comprehensively and integratedly evaluate the distribution network risk in the target area, avoid the one-sidedness of single factor evaluation, and carry out detailed classification and weight allocation of loads in the catchment area, which more accurately reflects the importance and impact of different loads. By determining the distribution network risk value, load importance value, risk weight, etc. of the catchment area, and considering the adjustment of the reference risk value with multiple influencing coefficients, the accuracy and reliability of the final distribution network risk assessment can be significantly improved, which can adapt to the characteristics and differences of different catchment areas, as well as various complex situations in the operation of the distribution network, making the evaluation results more accurate.

[0066] In summary, the implementation of the present invention has the following beneficial effects:

[0067] It can be seen that the distribution network flood risk assessment method described in the implementation mode of the present invention first divides the target area corresponding to the target distribution network into n catchment areas, and then determines the distribution network risk value corresponding to each of the n catchment areas according to the determination method in the following steps S1-S3, and obtains n distribution network risk values, which are specifically the following steps: S1, determining the flood monitoring data of the first catchment area in the historical time period to obtain target flood monitoring data; the first catchment area is any one of the n catchment areas; the target flood monitoring data includes x labeled data and y unlabeled data; x is a positive integer, and y is a positive integer; S2, determining the failure probability of the distribution network equipment corresponding to the first catchment area based on the x labeled data, y unlabeled data, and a preset Gaussian mixture model; S3, determining the distribution network risk value corresponding to the first catchment area based on the failure probability of the distribution network equipment, and finally determining the target distribution network risk value of the target area based on the n distribution network risk values, thereby improving the accuracy of the risk assessment of the distribution network brought by floods.

[0068] See also Figure 3 , Figure 3 It is a structural diagram of a distribution network flood risk assessment device provided in an embodiment of the present application. The distribution network flood risk assessment device 300 includes: a division unit 301 and a processing unit 302;

[0069] A division unit 301 is used to divide the target area corresponding to the target distribution network into n catchment areas; n is an integer greater than 1;

[0070] The processing unit 302 is used to determine the distribution network risk value corresponding to each of the n watershed areas according to the determination method in the following steps S1-S3 to obtain n distribution network risk values, which is specifically the following steps:

[0071] S1. Determine the flood monitoring data of the first watershed in the historical time period to obtain target flood monitoring data; the first watershed is any one of the n watersheds; the target flood monitoring data includes x labeled data and y unlabeled data; x is a positive integer, and y is a positive integer;

[0072] S2, determining the failure probability of the distribution network equipment corresponding to the first catchment area based on x labeled data, y unlabeled data, and a preset Gaussian mixture model;

[0073] S3. Determine the distribution network risk value corresponding to the first catchment area based on the failure probability of the distribution network equipment;

[0074] A target distribution network risk value of a target area is determined based on the n distribution network risk values.

[0075] In some possible implementations, in determining the failure probability of the distribution network equipment corresponding to the first catchment area based on the x labeled data, the y unlabeled data, and the preset Gaussian mixture model, the processing unit 302 is specifically configured to:

[0076] Determine k Gaussian components corresponding to the preset Gaussian mixture model; each Gaussian component is related to the monitoring data of flood; k is a positive integer;

[0077] Based on x labeled data, determine the failure probability of distribution network equipment corresponding to each Gaussian component in k Gaussian components, and obtain k first distribution network equipment failure probabilities;

[0078] Input y unlabeled data into the preset Gaussian mixture model to obtain y k probability density values; each of the y unlabeled data corresponds to k probability density values;

[0079] Determine the failure probability of the distribution network equipment corresponding to each unlabeled data in the y unlabeled data based on the k first distribution network equipment failure probabilities and the y k probability density values, and obtain y second distribution network equipment failure probabilities;

[0080] Determine the failure probability of the distribution network equipment corresponding to each of the x labeled data, and obtain x second distribution network equipment failure probabilities;

[0081] The failure probability of the distribution network equipment corresponding to the first catchment area is determined based on the x failure probabilities of the second distribution network equipment and the y failure probabilities of the second distribution network equipment.

[0082] In some possible implementations, in determining the failure probability of the distribution network equipment corresponding to the first catchment area based on the x second distribution network equipment failure probabilities and the y second distribution network equipment failure probabilities, the processing unit 302 is specifically configured to:

[0083] Determine an average value of the x second distribution network equipment failure probabilities to obtain a first reference distribution network equipment failure probability;

[0084] Determine an average value of y second distribution network equipment failure probabilities to obtain a second reference distribution network equipment failure probability;

[0085] Determine a first weight corresponding to a first reference distribution network equipment failure probability and a second weight corresponding to a second reference distribution network equipment failure probability;

[0086] The failure probability of the distribution network equipment corresponding to the first catchment area is determined based on the first weight, the second weight, the first reference failure probability of the distribution network equipment, and the second reference failure probability of the distribution network equipment.

[0087] In some possible implementations, in determining the failure probability of the distribution network equipment corresponding to the first catchment area based on the first weight, the second weight, the first reference distribution network equipment failure probability, and the second reference distribution network equipment failure probability, the processing unit 302 is specifically configured to:

[0088] Get the number of isolated points in the first catchment area;

[0089] Determine the target adjustment coefficient corresponding to the number of isolated points;

[0090] Adjust the second weight based on the target adjustment coefficient to obtain a second target weight;

[0091] Adjust the first weight based on the second target weight to obtain the first target weight;

[0092] The failure probability of the distribution network equipment corresponding to the first catchment area is determined based on the first target weight, the second target weight, the first reference distribution network equipment failure probability, and the second reference distribution network equipment failure probability.

[0093] In some possible implementations, in determining the target distribution network risk value of the target area based on the n distribution network risk values, the processing unit 302 is specifically configured to:

[0094] According to the determination method in the following steps A1-A4, the load importance value corresponding to each of the n watershed areas is determined to obtain n load importance values, which is specifically the following steps:

[0095] A1. Determine the critical load, important load and general load of the distribution network equipment in the first catchment area;

[0096] A2. Determine the first weight corresponding to the critical load, the second weight corresponding to the important load, and the third weight corresponding to the general load; the first weight is greater than the second weight, the second weight is greater than the third weight, and the sum of the first weight, the second weight and the third weight is 1;

[0097] A3. Determine the corresponding target load in the first catchment area based on the critical load, the important load, the general load, the first weight, the second weight, and the third weight;

[0098] A4. Determine the load importance value corresponding to the target load; the target load is positively correlated with the load importance value, and the load importance value is positively correlated with the load importance;

[0099] Based on n load importance values, the risk weight corresponding to each of the n catchment areas is determined to obtain n risk weights; the load importance value is positively correlated with the risk weight;

[0100] The target distribution network risk value of the target area is determined based on n distribution network risk values ​​and n risk weights.

[0101] In some possible implementations, in determining the target distribution network risk value of the target area based on the n distribution network risk values ​​and the n risk weights, the processing unit 302 is specifically configured to:

[0102] Determine a reference distribution network risk value based on n distribution network risk values ​​and n risk weights;

[0103] Obtain the maximum load loss of the target distribution network in the historical time period;

[0104] determining a first influence coefficient corresponding to a maximum load loss;

[0105] Obtain the time when the voltage corresponding to the target distribution network exceeds the voltage threshold in the historical time period to obtain the target time;

[0106] determining a second influence coefficient corresponding to the target time;

[0107] The reference distribution network risk value is adjusted according to the first influence coefficient and the second influence coefficient to obtain the target distribution network risk value.

[0108] In some possible implementations, in terms of dividing the target area corresponding to the target distribution network into n catchment areas, the processing unit 302 is specifically configured to:

[0109] The target area corresponding to the target distribution network is divided into p unit areas; p is an integer greater than or equal to n;

[0110] Determine the water flow accumulation corresponding to each unit area in p unit areas, and obtain p water flow accumulations;

[0111] Based on p water flow accumulations, p unit areas are combined to obtain n watersheds; each of the n watersheds corresponds to at least one unit area; if the number corresponding to at least one unit area is greater than 1, at least one unit area corresponding to each watershed is an adjacent unit area; the water flow accumulation corresponding to each watershed is greater than or equal to the water flow accumulation threshold.

[0112] See also Figure 4 , Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, the electronic device 400 includes a transceiver 401, a processor 402 and a memory 403. They are connected via a bus 404. The memory 403 is used to store computer programs and data, and the transceiver 401 can transmit the data stored in the memory 403 to the processor 402. The above program includes instructions for executing the following steps:

[0113] The target area corresponding to the target distribution network is divided into n catchment areas; n is an integer greater than 1;

[0114] According to the determination method in the following steps S1-S3, the distribution network risk value corresponding to each of the n watershed areas is determined to obtain n distribution network risk values, which is specifically the following steps:

[0115] S1. Determine the flood monitoring data of the first watershed in the historical time period to obtain target flood monitoring data; the first watershed is any one of the n watersheds; the target flood monitoring data includes x labeled data and y unlabeled data; x is a positive integer, and y is a positive integer;

[0116] S2, determining the failure probability of the distribution network equipment corresponding to the first catchment area based on x labeled data, y unlabeled data, and a preset Gaussian mixture model;

[0117] S3. Determine the distribution network risk value corresponding to the first catchment area based on the failure probability of the distribution network equipment;

[0118] A target distribution network risk value of a target area is determined based on the n distribution network risk values.

[0119] In some possible implementations, in terms of determining the failure probability of distribution network equipment corresponding to the first catchment area based on x labeled data, y unlabeled data, and a preset Gaussian mixture model, the program includes instructions for performing the following steps:

[0120] Determine k Gaussian components corresponding to the preset Gaussian mixture model; each Gaussian component is related to the monitoring data of flood; k is a positive integer;

[0121] Based on x labeled data, determine the failure probability of distribution network equipment corresponding to each Gaussian component in k Gaussian components, and obtain k first distribution network equipment failure probabilities;

[0122] Input y unlabeled data into the preset Gaussian mixture model to obtain y k probability density values; each of the y unlabeled data corresponds to k probability density values;

[0123] Determine the failure probability of the distribution network equipment corresponding to each unlabeled data in the y unlabeled data based on the k first distribution network equipment failure probabilities and the y k probability density values, and obtain y second distribution network equipment failure probabilities;

[0124] Determine the failure probability of the distribution network equipment corresponding to each of the x labeled data, and obtain x second distribution network equipment failure probabilities;

[0125] The failure probability of the distribution network equipment corresponding to the first catchment area is determined based on the x failure probabilities of the second distribution network equipment and the y failure probabilities of the second distribution network equipment.

[0126] In some possible implementations, in terms of determining the failure probability of the distribution network equipment corresponding to the first catchment area based on the x second distribution network equipment failure probabilities and the y second distribution network equipment failure probabilities, the above program includes instructions for performing the following steps:

[0127] Determine an average value of the x second distribution network equipment failure probabilities to obtain a first reference distribution network equipment failure probability;

[0128] Determine an average value of y second distribution network equipment failure probabilities to obtain a second reference distribution network equipment failure probability;

[0129] Determine a first weight corresponding to a first reference distribution network equipment failure probability and a second weight corresponding to a second reference distribution network equipment failure probability;

[0130] The failure probability of the distribution network equipment corresponding to the first catchment area is determined based on the first weight, the second weight, the first reference failure probability of the distribution network equipment, and the second reference failure probability of the distribution network equipment.

[0131] In some possible implementations, in terms of determining the failure probability of the distribution network equipment corresponding to the first catchment area based on the first weight, the second weight, the first reference distribution network equipment failure probability, and the second reference distribution network equipment failure probability, the above program includes instructions for performing the following steps:

[0132] Get the number of isolated points in the first catchment area;

[0133] Determine the target adjustment coefficient corresponding to the number of isolated points;

[0134] Adjust the second weight based on the target adjustment coefficient to obtain a second target weight;

[0135] Adjust the first weight based on the second target weight to obtain the first target weight;

[0136] The failure probability of the distribution network equipment corresponding to the first catchment area is determined based on the first target weight, the second target weight, the first reference distribution network equipment failure probability, and the second reference distribution network equipment failure probability.

[0137] In some possible implementations, in determining a target distribution network risk value of a target area based on n distribution network risk values, the program includes instructions for performing the following steps:

[0138] According to the determination method in the following steps A1-A4, the load importance value corresponding to each of the n watershed areas is determined to obtain n load importance values, which is specifically the following steps:

[0139] A1. Determine the critical load, important load and general load of the distribution network equipment in the first catchment area;

[0140] A2. Determine the first weight corresponding to the critical load, the second weight corresponding to the important load, and the third weight corresponding to the general load; the first weight is greater than the second weight, the second weight is greater than the third weight, and the sum of the first weight, the second weight and the third weight is 1;

[0141] A3. Determine the corresponding target load in the first catchment area based on the critical load, the important load, the general load, the first weight, the second weight, and the third weight;

[0142] A4. Determine the load importance value corresponding to the target load; the target load is positively correlated with the load importance value, and the load importance value is positively correlated with the load importance;

[0143] Based on n load importance values, the risk weight corresponding to each of the n catchment areas is determined to obtain n risk weights; the load importance value is positively correlated with the risk weight;

[0144] The target distribution network risk value of the target area is determined based on n distribution network risk values ​​and n risk weights.

[0145] In some possible implementations, in determining a target distribution network risk value of a target area based on n distribution network risk values ​​and n risk weights, the program includes instructions for performing the following steps:

[0146] Determine a reference distribution network risk value based on n distribution network risk values ​​and n risk weights;

[0147] Obtain the maximum load loss of the target distribution network in the historical time period;

[0148] determining a first influence coefficient corresponding to a maximum load loss;

[0149] Obtain the time when the voltage corresponding to the target distribution network exceeds the voltage threshold in the historical time period to obtain the target time;

[0150] determining a second influence coefficient corresponding to the target time;

[0151] The reference distribution network risk value is adjusted according to the first influence coefficient and the second influence coefficient to obtain the target distribution network risk value.

[0152] In some possible implementations, in terms of dividing the target area corresponding to the target distribution network into n catchment areas, the above program includes instructions for performing the following steps:

[0153] The target area corresponding to the target distribution network is divided into p unit areas; p is an integer greater than or equal to n;

[0154] Determine the water flow accumulation corresponding to each unit area in p unit areas, and obtain p water flow accumulations;

[0155] Based on p water flow accumulations, p unit areas are combined to obtain n watersheds; each of the n watersheds corresponds to at least one unit area; if the number corresponding to at least one unit area is greater than 1, at least one unit area corresponding to each watershed is an adjacent unit area; the water flow accumulation corresponding to each watershed is greater than or equal to the water flow accumulation threshold.

[0156] It should be understood that the electronic devices in this application may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptops, mobile Internet devices MID (Mobile Internet Devices, MID for short) or wearable devices or servers, edge computing nodes, etc. The above electronic devices are only examples, not exhaustive, and include but are not limited to the above electronic devices.

[0157] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement part or all of the steps of any distribution network flood risk assessment method recorded in the above method implementation.

[0158] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any distribution network flood risk assessment method recorded in the above method implementation.

[0159] It should be noted that, for the above-mentioned various method implementations, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the implementations described in the specification are all optional implementations, and the actions and modules involved are not necessarily required by this application.

[0160] In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0161] In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device implementation described above is only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0163] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0164] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of each implementation method of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0165] A person skilled in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0166] The above is a detailed introduction to the implementation methods of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above implementation methods is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for assessing flood risk in a distribution network, characterized in that: include: Divide the target area corresponding to the target distribution network into n catchment areas; n is an integer greater than 1; According to the determination method in the following steps S1-S3, the distribution network risk value corresponding to each of the n watershed areas is determined to obtain n distribution network risk values, which is specifically the following steps: S1. Determine flood monitoring data of a first watershed in a historical period to obtain target flood monitoring data; the first watershed is any one of the n watersheds; the target flood monitoring data includes x labeled data and y unlabeled data; x is a positive integer, and y is a positive integer; S2. Determine the failure probability of the distribution network equipment corresponding to the first catchment area based on the x labeled data, the y unlabeled data, and a preset Gaussian mixture model; S3. Determine the distribution network risk value corresponding to the first catchment area based on the failure probability of the distribution network equipment; A target distribution network risk value of the target area is determined based on the n distribution network risk values.

2. The method according to claim 1, characterized in that The determining the failure probability of the distribution network equipment corresponding to the first catchment area based on the x labeled data, the y unlabeled data, and a preset Gaussian mixture model includes: Determine k Gaussian components corresponding to the preset Gaussian mixture model; each Gaussian component is related to the monitoring data of flood; k is a positive integer; Determine the failure probability of the distribution network equipment corresponding to each Gaussian component of the k Gaussian components based on the x labeled data, and obtain k first distribution network equipment failure probabilities; Inputting the y unlabeled data into the preset Gaussian mixture model to obtain y·k probability density values; each unlabeled data in the y unlabeled data corresponds to k probability density values; Determine the failure probability of the distribution network equipment corresponding to each unlabeled data in the y unlabeled data based on the k first distribution network equipment failure probabilities and the y·k probability density values, and obtain y second distribution network equipment failure probabilities; Determine the failure probability of the distribution network equipment corresponding to each of the x labeled data, and obtain x second distribution network equipment failure probabilities; The failure probability of the distribution network equipment corresponding to the first water collection area is determined based on the x second distribution network equipment failure probabilities and the y second distribution network equipment failure probabilities.

3. The method according to claim 2, characterized in that The determining the failure probability of the distribution network equipment corresponding to the first water catchment area based on the x second distribution network equipment failure probabilities and the y second distribution network equipment failure probabilities includes: Determine an average value of the x second distribution network equipment failure probabilities to obtain a first reference distribution network equipment failure probability; Determine an average value of the y second distribution network equipment failure probabilities to obtain a second reference distribution network equipment failure probability; Determine a first weight corresponding to the first reference distribution network equipment failure probability and a second weight corresponding to the second reference distribution network equipment failure probability; The failure probability of the distribution network equipment corresponding to the first catchment area is determined based on the first weight, the second weight, the first reference failure probability of the distribution network equipment, and the second reference failure probability of the distribution network equipment.

4. The method according to claim 3, characterized in that The determining the failure probability of the distribution network equipment corresponding to the first catchment area based on the first weight, the second weight, the first reference failure probability of the distribution network equipment, and the second reference failure probability of the distribution network equipment includes: Obtaining the number of isolated points in the first catchment area; Determining a target adjustment coefficient corresponding to the number of isolated points; Adjust the second weight based on the target adjustment coefficient to obtain a second target weight; Adjust the first weight based on the second target weight to obtain a first target weight; The failure probability of the distribution network equipment corresponding to the first catchment area is determined based on the first target weight, the second target weight, the first reference distribution network equipment failure probability, and the second reference distribution network equipment failure probability.

5. The method according to any one of claims 1 to 4, characterized in that: The determining the target distribution network risk value of the target area based on the n distribution network risk values ​​includes: According to the determination method in the following steps A1-A4, the load importance value corresponding to each of the n watershed areas is determined to obtain n load importance values, which is specifically the following steps: A1. Determine the critical load, important load and general load of the distribution network equipment in the first catchment area; A2. Determine a first weight corresponding to the critical load, a second weight corresponding to the important load, and a third weight corresponding to the general load; the first weight is greater than the second weight, the second weight is greater than the third weight, and the sum of the first weight, the second weight and the third weight is 1; A3. Determine the corresponding target load in the first catchment area based on the critical load, the important load, the general load, the first weight, the second weight and the third weight; A4. Determine the load importance value corresponding to the target load; the target load is positively correlated with the load importance value, and the load importance value is positively correlated with the load importance; Determine the risk weight corresponding to each of the n watershed areas based on the n load importance values, and obtain n risk weights; the load importance value is positively correlated with the risk weight; The target distribution network risk value of the target area is determined based on the n distribution network risk values ​​and the n risk weights.

6. The method according to claim 5, characterized in that The determining the target distribution network risk value of the target area based on the n distribution network risk values ​​and the n risk weights includes: Determining a reference distribution network risk value based on the n distribution network risk values ​​and the n risk weights; Obtaining a maximum load loss amount of the target distribution network within the historical time period; determining a first influence coefficient corresponding to the maximum load loss; Obtain the time at which the voltage corresponding to the target distribution network exceeds the voltage threshold within the historical time period to obtain the target time; determining a second influence coefficient corresponding to the target time; The reference distribution network risk value is adjusted according to the first influence coefficient and the second influence coefficient to obtain the target distribution network risk value.

7. The method according to claim 1, characterized in that The target area corresponding to the target distribution network is divided into n catchment areas, including: Dividing the target area corresponding to the target distribution network into p unit areas; p is an integer greater than or equal to n; Determine the water flow accumulation amount corresponding to each unit area in the p unit areas to obtain p water flow accumulation amounts; The p unit areas are combined based on the p water flow accumulation amounts to obtain the n watershed areas; each of the n watershed areas corresponds to at least one of the unit areas; if the number corresponding to the at least one unit area is greater than 1, the at least one unit area corresponding to each watershed area is an adjacent unit area; the water flow accumulation amount corresponding to each watershed area is greater than or equal to the water flow accumulation amount threshold.

8. A distribution network flood risk assessment device, characterized in that: The device comprises: a dividing unit and a processing unit; The division unit is used to divide the target area corresponding to the target distribution network into n catchment areas; n is an integer greater than 1; The processing unit is used to determine the distribution network risk value corresponding to each of the n watershed areas according to the determination method in the following steps S1-S3 to obtain n distribution network risk values, specifically the following steps: S1. Determine flood monitoring data of a first watershed in a historical period to obtain target flood monitoring data; the first watershed is any one of the n watersheds; the target flood monitoring data includes x labeled data and y unlabeled data; x is a positive integer, and y is a positive integer; S2. Determine the failure probability of the distribution network equipment corresponding to the first catchment area based on the x labeled data, the y unlabeled data, and a preset Gaussian mixture model; S3. Determine the distribution network risk value corresponding to the first catchment area based on the failure probability of the distribution network equipment; A target distribution network risk value of the target area is determined based on the n distribution network risk values.

9. An electronic device, characterized in that: The method comprises a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for executing the steps in the method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images