A method for dynamically evaluating operation risk of distribution network photovoltaic facilities under heavy rain conditions

Abstract

The application is suitable for the technical field of new energy safety evaluation, and provides a dynamic evaluation method for operation risk of distribution network photovoltaic facilities under rainstorm conditions. In the embodiment, for the photovoltaic facilities to be evaluated, the multi-dimensional evaluation indexes including meteorological dimension, equipment dimension and operation dimension and the weight values of the indexes are determined; then the real-time risk evaluation data corresponding to the risk evaluation indexes are input into a risk grade comprehensive evaluation model to obtain a comprehensive evaluation vector of the photovoltaic facilities, and finally the final estimated risk grade and the corresponding processing method are determined through the comprehensive evaluation vector. In the embodiment, the three-dimensional data of meteorology-equipment-operation are processed, so that the evaluation result output by the risk grade comprehensive evaluation model of the application has high accuracy and comprehensiveness, thereby the fault early warning probability can be improved and the accidents can be reduced.

Description

Technical Field

[0001] This application relates to the field of new energy safety assessment technology, and in particular to a method for dynamic evaluation of the operational risks of photovoltaic facilities in power distribution networks under heavy rain conditions. Background Technology

[0002] As the global energy structure transformation accelerates, photovoltaic power generation, as an important component of clean energy, continues to increase its share in the power system. However, the operational safety of photovoltaic power plants faces numerous threats from meteorological disasters, such as typhoons, heavy rains, and blizzards.

[0003] Traditional risk assessment methods have several limitations: First, existing research largely focuses on the impact analysis of single meteorological factors, failing to fully consider the multi-path impact mechanisms of meteorological disasters. Taking heavy rain as an example, most literature only considers rainfall amount as an input variable, neglecting the synergistic destructive effects of accompanying factors such as high humidity and strong winds on photovoltaic modules and support systems. Especially in coastal areas, heavy rain is often accompanied by salt spray corrosion, and this multi-factor coupling effect can significantly accelerate the aging process of equipment.

[0004] Secondly, the poor correlation between on-site operational data and meteorological factors results in low-quality input data for the risk assessment model. Because photovoltaic power plant monitoring systems and meteorological monitoring systems typically operate independently, differences exist in data acquisition frequency, timestamp alignment, and other aspects, making it difficult to establish accurate correlations. This leads to the current...

[0005] In addition, the lack of effective monitoring methods for some key parameters, such as component backsheet temperature and support foundation settlement, further restricts the accuracy of the evaluation model.

[0006] Therefore, photovoltaic facilities have significant shortcomings in terms of data correlation, dynamic adaptability, and engineering applicability under severe weather conditions, resulting in an incomplete and inaccurate risk assessment method for the equipment. Summary of the Invention

[0007] In view of this, this application provides a dynamic risk assessment method for the operation of photovoltaic facilities in distribution networks under rainstorm conditions, so as to improve the accuracy and comprehensiveness of risk assessment for photovoltaic facilities operating under severe weather conditions, thereby increasing the probability of fault early warning and reducing the occurrence of accidents.

[0008] The first aspect of this application provides a method for dynamic evaluation of the operational risk of photovoltaic facilities in a distribution network under heavy rain conditions, the method comprising: The risk assessment indicators for the target photovoltaic facility and the corresponding sample data for each indicator are determined. The entropy value of each indicator in the risk assessment indicators is determined, and the objective weight of each indicator is determined by the entropy value. The risk assessment indicators include meteorological dimension indicators, equipment dimension indicators and historical operation dimension indicators. The real-time risk assessment data corresponding to the risk assessment indicators is obtained. The membership vector of each physical value of the risk assessment data is determined by the risk level membership function in the pre-constructed risk level comprehensive evaluation model. Then, the comprehensive evaluation vector of the risk assessment data is determined by the membership vector and the objective weight of the indicators. The risk level membership function contains several different risk levels, and the comprehensive evaluation vector contains the membership value of each risk level. The estimated risk level of the risk assessment data is determined based on the comprehensive evaluation vector, and then the corresponding processing method is determined based on the estimated risk level.

[0009] Optionally, determining the entropy value of each indicator in the risk assessment indicators, and then determining the objective weight of each indicator using the entropy value, includes: The sampling quantity n of the target photovoltaic facility and the number m of the indicators in the risk assessment indicators are determined by formula. Determine the entropy value of each indicator, and then use the formula. Determine the objective weights of the indicators, among which, , Let j be the entropy value of the j-th index. Let j be the objective weight of the indicator. Let be the characteristic weight of the j-th indicator for the i-th target photovoltaic facility, where i≤n and j≤m.

[0010] Optionally, the process of constructing the risk level membership function includes: Four key parameters a, b, c, d are defined for the trapezoidal membership function for each risk level, where a is the lower limit of the risk level, b and c are the stable intervals of the risk level, and d is the upper limit of the risk level. Determine the membership function of the index as follows Then, the risk level membership function is determined based on the index membership function. Where level represents the number of risk levels.

[0011] Optionally, determining the estimated risk level of each indicator's physical value based on the comprehensive evaluation vector includes: The risk level corresponding to the largest membership value in the comprehensive evaluation vector is determined as the estimated risk level of the physical value of the indicator.

[0012] Optionally, determining the estimated risk level of each indicator's physical value based on the comprehensive evaluation vector includes: Determine the difference between the largest membership value and other membership values ​​in the comprehensive evaluation vector, and compare the difference with a preset difference threshold to determine whether there is a target membership value whose difference is less than or equal to the difference threshold; When it does not exist, the first risk level corresponding to the largest membership value is determined as the estimated risk level of the physical value of the indicator; When it exists, determine the second risk level corresponding to the target membership value, and determine the risk level with the higher level between the first risk level and the second risk level as the estimated risk level.

[0013] A second aspect of this application provides a dynamic risk assessment device for the operation of photovoltaic facilities in a power distribution network under heavy rain conditions, the device comprising: The indicator weight determination unit is used to determine the risk assessment indicators of the target photovoltaic facility and the sample data corresponding to each indicator, determine the entropy value of each indicator in the risk assessment indicators, and then determine the objective weight of each indicator through the entropy value. The risk assessment indicators include meteorological dimension indicators, equipment dimension indicators and historical operation dimension indicators. The evaluation vector determination unit is used to acquire real-time risk assessment data corresponding to the risk assessment indicators, determine the membership vector of each physical value of the indicator in the risk assessment data through the risk level membership function in the pre-constructed risk level comprehensive evaluation model, and then determine the comprehensive evaluation vector of the risk assessment data through the membership vector and the objective weight of the indicator. The risk level membership function contains several different risk levels, and the comprehensive evaluation vector contains the membership value of each risk level. The risk level prediction unit is used to determine the predicted risk level of the risk assessment data based on the comprehensive evaluation vector, and then determine the corresponding processing method based on the predicted risk level.

[0014] Optionally, the indicator weight determination unit is used to determine the sampling quantity n of the target photovoltaic facility and the number m of indicators in the risk assessment indicators, using the formula... Determine the entropy value of each indicator, and then use the formula. Determine the objective weights of the indicators, among which, , Let j be the entropy value of the j-th index. Let j be the objective weight of the indicator. Let be the characteristic weight of the j-th indicator for the i-th target photovoltaic facility, where i≤n and j≤m.

[0015] Optionally, the process of constructing the risk level membership function in the membership vector determination unit includes: Four key parameters a, b, c, d are defined for the trapezoidal membership function for each risk level, where a is the lower limit of the risk level, b and c are the stable intervals of the risk level, and d is the upper limit of the risk level. Determine the membership function of the index as follows Then, the risk level membership function is determined based on the index membership function. Where level represents the number of risk levels.

[0016] Optionally, the risk level prediction unit, which determines the predicted risk level of each indicator's physical value based on the comprehensive evaluation vector, includes: The risk level corresponding to the largest membership value in the comprehensive evaluation vector is determined as the estimated risk level of the physical value of the indicator.

[0017] Optionally, the risk level prediction unit, which determines the predicted risk level of each indicator's physical value based on the comprehensive evaluation vector, includes: Determine the difference between the largest membership value and other membership values ​​in the comprehensive evaluation vector, and compare the difference with a preset difference threshold to determine whether there is a target membership value whose difference is less than or equal to the difference threshold; When it does not exist, the first risk level corresponding to the largest membership value is determined as the estimated risk level of the physical value of the indicator; When it exists, determine the second risk level corresponding to the target membership value, and determine the risk level with the higher level between the first risk level and the second risk level as the estimated risk level.

[0018] In the embodiments provided in this application, for photovoltaic facilities requiring evaluation, firstly, multi-dimensional evaluation indicators, including meteorological, equipment, and operational dimensions, and the weight values ​​of each indicator are determined; then, real-time risk assessment data corresponding to the risk assessment indicators are input into the comprehensive risk level evaluation model to obtain the comprehensive evaluation vector of the photovoltaic facility; finally, the final estimated risk level and corresponding handling method are determined through this comprehensive evaluation vector. This embodiment processes data in three dimensions—meteorology, equipment, and operation—ensuring that the evaluation results output by the comprehensive risk level evaluation model of this application have high accuracy and comprehensiveness, thereby improving the probability of fault warning and reducing the occurrence of accidents. Attached Figure Description

[0019] Figure 1 A flowchart illustrating the method provided in this application embodiment; Figure 2 This is a structural diagram of the device provided in the embodiments of this application; Figure 3 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0020] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0021] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0022] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0023] This application provides a method for dynamic risk assessment of photovoltaic facilities operating in power distribution networks under heavy rain conditions, so as to improve the accuracy and comprehensiveness of risk assessment of photovoltaic facilities operating under severe weather conditions.

[0024] The technical solutions of this application will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0025] like Figure 1 The diagram shown is a flowchart of the dynamic risk assessment method for the operation of photovoltaic facilities in a distribution network under heavy rain conditions provided in this application. The process may include the following steps: Step S101: Determine the risk assessment indicators of the target photovoltaic facility and the sample data corresponding to each indicator, determine the entropy value of each indicator in the risk assessment indicators, and then determine the objective weight of each indicator through the entropy value.

[0026] In this embodiment, the aforementioned risk assessment indicators include meteorological indicators, equipment indicators, and historical operational indicators. Meteorological indicators may include rainfall intensity, typhoon level, duration, etc., and can be obtained through meteorological monitoring equipment. Equipment indicators may include PID attenuation rate, inverter failure rate, equipment usage time, etc., and can be obtained through a SCADA system (Supervisory and Data Acquisition System). Historical operational indicators may include power generation efficiency reduction, system availability, etc., and can be obtained through historical data of the target photovoltaic facility or similar photovoltaic facilities.

[0027] After determining the various risk assessment indicators, the weight of each indicator is then determined. The specific process is as follows: First, determine the entropy value of each indicator. This process requires determining three parameters: the number of sample data points, i.e., the number of target photovoltaic facilities n used for sampling; the total number of indicators m in the risk assessment indicators; and the feature weight P of each indicator. Obtaining n and m is simple; it only requires statistical analysis of the target photovoltaic facilities and indicator data. The determination process for the feature weight P is as follows: (1) Standardize the original collected sample data to obtain the standardized matrix: in For fuzzy synthesis operators, a weighted average type is adopted. algorithm.

[0028] (2) Determine the feature weight by calculating the contribution of the i-th sample value under the j-th indicator. The calculation formula is as follows: This value reflects the weight proportion of the i-th evaluation object (power station / time point) under the j-th indicator. The information entropy of this indicator is extracted by calculating the distribution of all samples under this indicator. After determining the above three parameters, the formula can be used... To determine the entropy value of each indicator, in this formula, After determining the entropy value, the difference coefficient of each indicator is determined by the difference coefficient = 1 - entropy value. Then, the difference coefficients of all indicators are normalized, and the resulting ratio is the objective weight of that indicator.

[0029] Step S102: Obtain the real-time risk assessment data corresponding to the risk assessment indicators, determine the membership vector of each indicator physical value in the risk assessment data through the risk level membership function in the pre-constructed risk level comprehensive evaluation model, and then determine the comprehensive evaluation vector of the risk assessment data through the membership vector and the objective weight of the indicators.

[0030] In this embodiment, the risk level membership function includes several different risk levels, and the comprehensive evaluation vector includes the membership values ​​of each risk level. Real-time risk assessment data can be obtained through the same process as acquiring sample data in step S101. For example, real-time meteorological dimension data can be obtained through real-time monitoring of meteorological monitoring equipment, real-time equipment dimension data can be obtained through real-time monitoring of a SCADA system, and real-time operational dimension data can be obtained through real-time monitoring of the target photovoltaic facility.

[0031] After acquiring real-time risk assessment data, it is input into the risk level comprehensive evaluation model to determine the corresponding comprehensive evaluation vector. The specific process is as follows: First, all real-time risk assessment data are standardized to a uniform magnitude (between 0 and 1) to eliminate the influence of different units. The process involves dividing the real-time risk assessment data into benefit-type indicators (positive indicators) and cost / risk-type indicators (negative indicators). For positive indicators, [further steps are needed]. Transformation is performed. For negative indicators, through... The transformation process is then performed. In the formula above, max and min represent the maximum and minimum values ​​for each indicator, respectively. Through this process, the real-time risk assessment data for all indicators can be transformed to a range of 0-1.

[0032] The second step is to determine the number of risk levels and define the corresponding trapezoidal membership function for each risk level. The risk level membership function is composed of various trapezoidal membership functions. In this formula, x is the real-time risk assessment data after standardization, a is the lower limit of the risk level, b and c are the stable intervals of the risk level, and d is the upper limit of the risk level.

[0033] The values ​​of parameters a, b, c, and d are determined based on industry-recognized standards and the physical operating limits of the equipment, specifically as follows: (1) Industry / National Standard Basis: The parameter range of meteorological dimension indicators (such as rainstorm intensity) refers to the national meteorological department's classification standard for rainstorm intensity. For example, a 24-hour rainfall of 50 mm (or short-term heavy rainfall level) is used as the core reference for classifying "medium risk" and "high risk", and the standards are set accordingly. and The stable interval of the level is [b,c]. (2) Equipment physical characteristics: Equipment dimensional indicators (such as inverter status) are determined based on the physical limits of the components. For example, for the inverter operating environment, when the temperature reaches 75℃ (the critical point of sharp efficiency reduction) or the insulation resistance is lower than the safety threshold, it is taken as the risk starting point a or the saturation zone starting point b to ensure that the assessment results are consistent with the physical failure mechanism; (3) Level Connection Logic: The parameter settings for each risk level follow the principle of interval overlap (i.e., By cross-mapping standards with physical characteristics, the continuity and dynamism of risk assessment can be achieved.

[0034] Taking four risk levels—low risk, medium risk, high risk, and extremely high risk—as an example, the membership function for this risk level is: Example (using "Rainstorm Intensity" as an example, unit: mm / h): To achieve accurate determination, different levels are configured with different parameters: (1) Low risk The parameters for a, b, c, and d are [0, 0, 10, 25], which means that speeds below 10 mm / h are absolutely safe, and speeds above 25 mm / h are no longer considered low-risk. (2) Medium risk ): [15,25,40,50] -- overlaps with low risk in the 15-25 range, reflecting the increasing risk; (3) High risk [45,55,70,80] -- Corresponds to the intensification phase of heavy rain, triggering differentiated inspections; (4) Extremely high risk [75,85,95,100] -- Approaching the physical limit, preparing to activate the protection linkage.

[0035] The third step is to substitute real-time risk assessment data (such as a rainfall intensity of 63 mm / h) into the trapezoidal membership function defined for each risk level, and calculate the membership values ​​of the data belonging to the four risk levels respectively. This yields the row vector of the indicator: .

[0036] Reconstruct the fuzzy relation matrix : The membership vector of the m indicators in the above risk assessment indicators Arranged by row, forming a fuzzy relation matrix: .

[0037] Finally, the objective weights of the indicators obtained in step S101 are combined with the fuzzy relation matrix R through a fuzzy synthesis operation. This yields a comprehensive evaluation vector for each real-time risk assessment data point, where b1, b2, b3, and b4 represent the membership values ​​for the four risk levels: low risk, medium risk, high risk, and extremely high risk, respectively.

[0038] Step S103: Determine the estimated risk level of the risk assessment data based on the comprehensive evaluation vector, and then determine the corresponding processing method based on the estimated risk level.

[0039] In this embodiment, the maximum membership principle or the centroid method can be used to analyze the vector. Defuzzification is performed to determine the estimated risk level. The maximum membership method takes the level corresponding to the maximum value in vector B as the final risk level. For example, the membership degree of the real-time risk assessment data {rainfall intensity: 63mm / h} is [0, 0.3, 0.7, 0], and the membership degree of the real-time risk assessment data {PID attenuation rate: 4.8%} is [0.2, 0.6, 0.2, 0]. Through weighted calculation, the comprehensive evaluation vector B = [0.072, 0.356, 0.482, 0.090] is obtained, and 0.482 is the maximum value. Therefore, the high risk corresponding to 0.482 is determined as the estimated risk level of the real-time risk assessment data {rainfall intensity: 63mm / h; PID attenuation rate: 4.8%}.

[0040] This embodiment can set corresponding handling methods according to different risk levels. For example, in the case of low risk, the corresponding handling method is to take no action. In the case of medium risk, the handling method is to notify the relevant maintenance personnel by phone. In the case of high risk, the emergency plan is activated, such as activating the PID protection device; maintenance personnel complete the drainage system inspection within 2 hours, etc. In the case of extremely high risk, the highest level of physical protection actions are automatically executed, such as emergency power cut-off of equipment, activation of redundant cooling system, closure of key valves, or opening of all pressure relief devices.

[0041] In another embodiment, determining the estimated risk level of each indicator's physical value based on the comprehensive evaluation vector includes: Determine the difference between the largest membership value and other membership values ​​in the comprehensive evaluation vector, and compare the difference with a preset difference threshold to determine whether there is a target membership value whose difference is less than or equal to the difference threshold; When it does not exist, the first risk level corresponding to the largest membership value is determined as the estimated risk level of the physical value of the indicator; When it exists, determine the second risk level corresponding to the target membership value, and determine the risk level with the higher level between the first risk level and the second risk level as the estimated risk level.

[0042] Because the membership values ​​of various risk levels can be too close, this embodiment pre-sets a threshold for the difference in membership values, such as 5%. Then, it compares the highest membership value in the comprehensive evaluation vector with other membership values. If the difference between the two membership values ​​is less than 5%, a higher-level risk warning is automatically triggered. For example, if the membership value for the medium-risk level is the highest, and the membership value for the high-risk level is lower than that for the medium-risk level, but the difference between the two is less than 5%, then the estimated risk level is determined to be high risk, not medium risk.

[0043] Furthermore, if there are other risk levels with higher risk grades whose membership values ​​differ from the highest membership value by less than 5%, then the highest risk grade is determined as the estimated risk grade. For example, if the membership value for medium risk is the highest, the membership value for high risk is the second highest, and the membership value for very high risk is the third highest, and the difference between the membership value for very high risk and the membership value for medium risk is less than 5%, then very high risk is determined as the estimated risk grade.

[0044] It should be noted that in this embodiment, the largest membership value in the comprehensive evaluation vector can also be directly compared with the second largest membership value to reduce the amount of calculation.

[0045] This concludes the process. Figure 1 The process is shown below.

[0046] In this embodiment, for photovoltaic facilities requiring evaluation, multi-dimensional data including meteorological, equipment, and operational dimensions is first acquired for risk assessment. Then, the weight value of each indicator in the data is determined. Finally, a comprehensive evaluation vector for the photovoltaic facility is determined using a comprehensive risk level evaluation model and these weight values. The final estimated risk level is then determined using this comprehensive evaluation vector. This embodiment processes data across three dimensions—meteorology, equipment, and operation—ensuring the evaluation results output by the comprehensive risk level evaluation model have high accuracy and comprehensiveness, thereby improving the probability of fault warning and reducing the occurrence of accidents.

[0047] This application also provides a dynamic risk assessment device for the operation of photovoltaic facilities in power distribution networks under heavy rain conditions, such as... Figure 2 As shown, the device includes: The indicator weight determination unit 201 is used to determine the risk assessment indicators of the target photovoltaic facility and the sample data corresponding to each indicator, determine the entropy value of each indicator in the risk assessment indicators, and then determine the objective weight of each indicator through the entropy value. The risk assessment indicators include meteorological dimension indicators, equipment dimension indicators and historical operation dimension indicators. The evaluation vector determination unit 202 is used to obtain real-time risk assessment data corresponding to the risk assessment indicators, determine the membership vector of each physical value of the indicator in the risk assessment data through the risk level membership function in the pre-constructed risk level comprehensive evaluation model, and then determine the comprehensive evaluation vector of the risk assessment data through the membership vector and the objective weight of the indicator. The risk level membership function contains several different risk levels, and the comprehensive evaluation vector contains the membership value of each risk level. The risk level prediction unit 203 is used to determine the predicted risk level of the risk assessment data based on the comprehensive evaluation vector, and then determine the corresponding processing method based on the predicted risk level.

[0048] In another embodiment, the indicator weight determination unit is used to determine the sampling quantity n of the target photovoltaic facility and the number m of indicators in the risk assessment indicators, using the formula... Determine the entropy value of each indicator, and then use the formula. Determine the objective weights of the indicators, among which, , Let j be the entropy value of the j-th index. Let j be the objective weight of the indicator. Let be the characteristic weight of the j-th indicator for the i-th target photovoltaic facility, where i≤n and j≤m.

[0049] In another embodiment, the process of constructing the risk level membership function in the membership vector determination unit includes: Four key parameters a, b, c, d are defined for the trapezoidal membership function for each risk level, where a is the lower limit of the risk level, b and c are the stable intervals of the risk level, and d is the upper limit of the risk level. Determine the membership function of the index as follows Then, the risk level membership function is determined based on the index membership function. Where level represents the number of risk levels.

[0050] In another embodiment, the risk level prediction unit, which determines the predicted risk level of each indicator's physical value based on the comprehensive evaluation vector, includes: The risk level corresponding to the largest membership value in the comprehensive evaluation vector is determined as the estimated risk level of the physical value of the indicator.

[0051] In another embodiment, the risk level prediction unit, which determines the predicted risk level of each indicator's physical value based on the comprehensive evaluation vector, includes: Determine the difference between the largest membership value and other membership values ​​in the comprehensive evaluation vector, and compare the difference with a preset difference threshold to determine whether there is a target membership value whose difference is less than or equal to the difference threshold; When it does not exist, the first risk level corresponding to the largest membership value is determined as the estimated risk level of the physical value of the indicator; When it exists, determine the second risk level corresponding to the target membership value, and determine the risk level with the higher level between the first risk level and the second risk level as the estimated risk level.

[0052] The above embodiments of the present invention provide a method for dynamic evaluation of the operational risk of photovoltaic facilities in distribution networks under heavy rain conditions, and based on the method, a device for dynamic evaluation of the operational risk of photovoltaic facilities in distribution networks under heavy rain conditions. Through the above method and device, the accuracy and comprehensiveness of risk assessment of photovoltaic facilities operating under severe weather conditions can be improved, thereby increasing the probability of fault early warning and reducing the occurrence of accidents.

[0053] This embodiment also discloses a computer device, such as... Figure 3 As shown, the computer device includes a processor and a memory, the memory storing at least one instruction, which is loaded and executed by the processor to implement the dynamic risk assessment method for the operation of distribution network photovoltaic facilities under rainstorm conditions as described above.

[0054] Furthermore, in the above-described implementation of the dynamic risk assessment device for the operation of photovoltaic facilities under heavy rain conditions, the logical division of each program module is merely illustrative. In actual applications, the above functions can be assigned to different program modules as needed, for example, for the sake of corresponding hardware configuration requirements or the convenience of software implementation. That is, the internal structure of the dynamic risk assessment device for the operation of photovoltaic facilities can be divided into different program modules to complete all or part of the functions described above.

[0055] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for dynamic evaluation of the operational risk of photovoltaic facilities in power distribution networks under heavy rain conditions, characterized in that, The method includes: The risk assessment indicators for the target photovoltaic facility and the corresponding sample data for each indicator are determined. The entropy value of each indicator in the risk assessment indicators is determined, and the objective weight of each indicator is determined by the entropy value. The risk assessment indicators include meteorological dimension indicators, equipment dimension indicators and historical operation dimension indicators. The real-time risk assessment data corresponding to the risk assessment indicators is obtained. The membership vector of each physical value of the risk assessment data is determined by the risk level membership function in the pre-constructed risk level comprehensive evaluation model. Then, the comprehensive evaluation vector of the risk assessment data is determined by the membership vector and the objective weight of the indicators. The risk level membership function contains several different risk levels, and the comprehensive evaluation vector contains the membership value of each risk level. The estimated risk level of the risk assessment data is determined based on the comprehensive evaluation vector, and then the corresponding processing method is determined based on the estimated risk level.

2. The method according to claim 1, characterized in that, The process of determining the entropy value of each indicator in the risk assessment indicators, and then determining the objective weight of each indicator using the entropy value, includes: The sampling quantity n of the target photovoltaic facility and the number m of the indicators in the risk assessment indicators are determined by formula. Determine the entropy value of each indicator, and then use the formula. Determine the objective weights of the indicators, among which, , Let j be the entropy value of the j-th index. Let j be the objective weight of the indicator. Let be the characteristic weight of the j-th indicator for the i-th target photovoltaic facility, where i≤n and j≤m.

3. The method according to claim 1, characterized in that, The process of constructing the risk level membership function includes: Four key parameters a, b, c, d are defined for the trapezoidal membership function for each risk level, where a is the lower limit of the risk level, b and c are the stable intervals of the risk level, and d is the upper limit of the risk level. Determine the membership function of the index as follows Then, the risk level membership function is determined based on the index membership function. Where level represents the number of risk levels.

4. The method according to claim 1, characterized in that, The process of determining the estimated risk level of each indicator's physical value based on the comprehensive evaluation vector includes: The risk level corresponding to the largest membership value in the comprehensive evaluation vector is determined as the estimated risk level of the physical value of the indicator.

5. The method according to claim 1, characterized in that, The process of determining the estimated risk level of each indicator's physical value based on the comprehensive evaluation vector includes: Determine the difference between the largest membership value and other membership values ​​in the comprehensive evaluation vector, and compare the difference with a preset difference threshold to determine whether there is a target membership value whose difference is less than or equal to the difference threshold; When it does not exist, the first risk level corresponding to the largest membership value is determined as the estimated risk level of the physical value of the indicator; When it exists, determine the second risk level corresponding to the target membership value, and determine the risk level with the higher level between the first risk level and the second risk level as the estimated risk level.

6. A dynamic risk assessment device for the operation of photovoltaic facilities in a power distribution network under heavy rain conditions, characterized in that, The device includes: The indicator weight determination unit is used to determine the risk assessment indicators of the target photovoltaic facility and the sample data corresponding to each indicator, determine the entropy value of each indicator in the risk assessment indicators, and then determine the objective weight of each indicator through the entropy value. The risk assessment indicators include meteorological dimension indicators, equipment dimension indicators and historical operation dimension indicators. The evaluation vector determination unit is used to acquire real-time risk assessment data corresponding to the risk assessment indicators, determine the membership vector of each physical value of the indicator in the risk assessment data through the risk level membership function in the pre-constructed risk level comprehensive evaluation model, and then determine the comprehensive evaluation vector of the risk assessment data through the membership vector and the objective weight of the indicator. The risk level membership function contains several different risk levels, and the comprehensive evaluation vector contains the membership value of each risk level. The risk level prediction unit is used to determine the predicted risk level of the risk assessment data based on the comprehensive evaluation vector, and then determine the corresponding processing method based on the predicted risk level.

7. The apparatus according to claim 6, characterized in that, The indicator weight determination unit is used to determine the sampling quantity n of the target photovoltaic facility and the number m of indicators in the risk assessment indicators, through the formula... Determine the entropy value of each indicator, and then use the formula. Determine the objective weights of the indicators, among which, , Let j be the entropy value of the j-th index. Let j be the objective weight of the indicator. Let be the characteristic weight of the j-th indicator for the i-th target photovoltaic facility, where i≤n and j≤m.

8. The apparatus according to claim 6, characterized in that, The process of constructing the risk level membership function in the membership vector determination unit includes: Four key parameters a, b, c, d are defined for the trapezoidal membership function for each risk level, where a is the lower limit of the risk level, b and c are the stable intervals of the risk level, and d is the upper limit of the risk level. Determine the membership function of the index as follows Then, the risk level membership function is determined based on the index membership function. Where level represents the number of risk levels.

9. The apparatus according to claim 6, characterized in that, The risk level prediction unit, which determines the predicted risk level of each indicator's physical value based on the comprehensive evaluation vector, includes: The risk level corresponding to the largest membership value in the comprehensive evaluation vector is determined as the estimated risk level of the physical value of the indicator.

10. The apparatus according to claim 6, characterized in that, The risk level prediction unit, which determines the predicted risk level of each indicator's physical value based on the comprehensive evaluation vector, includes: Determine the difference between the largest membership value and other membership values ​​in the comprehensive evaluation vector, and compare the difference with a preset difference threshold to determine whether there is a target membership value whose difference is less than or equal to the difference threshold; When it does not exist, the first risk level corresponding to the largest membership value is determined as the estimated risk level of the physical value of the indicator; When it exists, determine the second risk level corresponding to the target membership value, and determine the risk level with the higher level between the first risk level and the second risk level as the estimated risk level.

Images