Method and device for evaluating reliability of power distribution network

Abstract

The invention belongs to the technical field of power grid systems, and particularly discloses a power distribution network reliability evaluation method and device. According to the method, one or more pieces of reliability index data highly related to the reliability of the power distribution network in the current time period are obtained, and the entropy value and the weight data corresponding to the one or more pieces of reliability index data are obtained through the entropy value method; and applying a back propagation neural network to the obtained entropy and weight to calculate a reliability evaluation result of the power distribution network in a future time period, thereby realizing accurate prediction of the reliability of the power distribution network, and improving the reliability of the power distribution network under the development of distributed power generation.

Description

Technical Field

[0001] The present application belongs to the technical field of power grid systems, and more specifically, to a distribution network reliability assessment method and device. Background Art

[0002] The rapid development of distributed power sources has achieved energy conservation and consumption reduction for the whole society, but the development of distributed generation affects the reliable operation of the distribution network. Distributed generation can provide short-term, continuous power for isolated loads in the event of a failure in the upstream distribution network. Therefore, the large-scale development of distributed generation can improve the reliability of the distribution network. However, due to climate and environmental reasons, distributed generation exhibits strong randomness. The reliability of the distribution network system is closely related to the operating environment and system operation planning. The relationship between influencing factors and reliability criteria is often a complex, dynamic, high-dimensional, nonlinear relationship.

[0003] The traditional system reliability derivation method based on component reliability requires a large amount of historical statistical data and a relatively stable system structure to ensure the accuracy of random variable correlation and derivation model structure. However, due to the large amount of distributed power being allocated to the distribution network, the traditional system structure has changed rapidly. The traditional reliability prediction method based on statistical reasoning is difficult to accurately handle the reliability prediction problem of distributed generation distribution networks. Summary of the invention

[0004] In view of the defects of the prior art, the purpose of this application is to provide a distribution network reliability assessment method and device, aiming to solve the problem that the reliability prediction method based on statistical reasoning in the prior art cannot accurately handle the reliability prediction of the distribution network under the development of distributed power generation.

[0005] To achieve the above objectives, in a first aspect, the present application provides a distribution network reliability assessment method, comprising:

[0006] Obtain at least one reliability indicator data strongly related to the reliability of the distribution network in the current period;

[0007] Obtaining a first entropy value and a first weight respectively corresponding to at least one reliability indicator data;

[0008] The first entropy value and the first weight are input into the target back propagation neural network to obtain the reliability assessment result of the distribution network in the future period.

[0009] In some embodiments, obtaining at least one reliability indicator data strongly related to the reliability of the power distribution network in the current period includes:

[0010] A principal component analysis is performed on a plurality of reliability index data that affect the reliability of the distribution network in the current period to obtain at least one reliability index data that is strongly correlated with the reliability of the distribution network in the current period.

[0011] In some embodiments, a method for acquiring a target back propagation neural network includes:

[0012] Obtain a second entropy value and a second weight respectively corresponding to at least one reliability indicator data strongly related to the reliability of the distribution network in a historical period;

[0013] Inputting the second entropy value and the second weight into the back propagation neural network for training until the back propagation neural network converges;

[0014] The converged back-propagation neural network is used as the target back-propagation neural network.

[0015] In some embodiments, obtaining a first entropy value and a first weight respectively corresponding to at least one reliability indicator data includes:

[0016] Normalize multiple reliability index data that affect the reliability of the distribution network in the current period, and obtain standard data corresponding to each reliability index data in the current period;

[0017] According to the standard data, a first entropy value is obtained;

[0018] A first weight is obtained according to the first entropy value.

[0019] In some embodiments, the method further comprises:

[0020] Based on any one of the standard back-propagation algorithm, the elastic back-propagation algorithm, the conjugate gradient algorithm and the Levenberg-Marquardt algorithm, the parameters of the back-propagation neural network are adjusted.

[0021] In some embodiments, multiple reliability indicator data affecting the reliability of the distribution network include:

[0022] The average frequency of system outages, the average duration of system outages, the average power supply availability, the total system power shortage, the average length of overhead lines, the average length of cables, the average number of distribution substations, the wiring rate and the cycle rate.

[0023] In a second aspect, the present application provides a distribution network reliability assessment device, comprising:

[0024] A first acquisition module is used to acquire at least one reliability index data strongly related to the reliability of the distribution network in the current period;

[0025] A second acquisition module is used to acquire a first entropy value and a first weight respectively corresponding to at least one reliability indicator data;

[0026] The evaluation module is used to input the first entropy value and the first weight into the target back propagation neural network to obtain the distribution network reliability evaluation result in the future period.

[0027] In a third aspect, the present application provides an electronic device comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the programs stored in the memory are executed, the processor is used to execute the distribution network reliability assessment method described in the first aspect or any embodiments of the first aspect.

[0028] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the distribution network reliability assessment method described in the first aspect or any embodiments of the first aspect.

[0029] In a fifth aspect, the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the distribution network reliability assessment method described in the first aspect or any embodiments of the first aspect.

[0030] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the prior art:

[0031] The distribution network reliability assessment method and device provided in the present application obtain one or more reliability index data that are strongly related to the reliability of the distribution network in the current time period, and obtain the entropy value and weight data corresponding to the above one or more reliability index data through the entropy method, and apply the back propagation neural network to the obtained entropy value and weight to calculate the distribution network reliability assessment result in the future time period, so as to achieve accurate prediction of the distribution network reliability and improve the reliability of the distribution network under the development of distributed power generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a flow chart of a distribution network reliability assessment method provided in an embodiment of the present application;

[0033] Figure 2 It is a schematic diagram of the structure of the back propagation neural network provided in the embodiment of the present application;

[0034] Figure 3 It is a schematic diagram of the training process of the back propagation neural network provided in the embodiment of the present application;

[0035] Figure 4 is a structural schematic diagram of a distribution network reliability assessment device provided in an embodiment of the present application;

[0036] Figure 5 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0038] The term "and / or" in this article is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The symbol " / " in this article indicates that the associated objects are in an or relationship, for example, A / B means A or B.

[0039] The terms "first" and "second" in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of objects. For example, a first entropy value and a second entropy value are used to distinguish different entropy values ​​rather than to describe a specific order of entropy values.

[0040] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0041] In the description of the embodiments of the present application, unless otherwise specified, the meaning of "multiple" refers to two or more than two. For example, multiple reliability indicator data refers to two or more reliability indicator data, etc.

[0042] Among the related technologies, artificial intelligence algorithms have obvious advantages in simulating the internal laws of things, determining the complex relationship between input and output, and dealing with uncertain parameter problems. Therefore, many studies on the reliability of distribution networks are based on artificial intelligence algorithms.

[0043] Based on this, the present application provides a distribution network reliability assessment method and device, which uses principal component analysis, entropy method and back propagation neural network architecture to process and analyze the data of the distribution network, so as to predict the reliability of the distributed power generation distribution network. The prediction of the distribution network reliability can determine the reliability indicators such as the average power outage time of the system, the total power shortage degree of the system, the average number of distribution stations and substations, and the impact on the power supply reliability.

[0044] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application.

[0045] See also Figure 1, an embodiment of the present application provides a distribution network reliability assessment method, including: step 110, step 120 and step 130.

[0046] Step 110 obtains at least one reliability index data strongly related to the reliability of the distribution network in the current period;

[0047] Step 120 obtains a first entropy value and a first weight respectively corresponding to at least one reliability indicator data;

[0048] Step 130 inputs the first entropy value and the first weight into the target back propagation neural network to obtain the distribution network reliability assessment result in the future period.

[0049] In the embodiment of the present application, the distribution network may be a distributed power generation distribution network.

[0050] Furthermore, in some embodiments, the multiple reliability index data affecting the reliability of the distribution network may include:

[0051] The average frequency of system outages, the average duration of system outages, the average power supply availability, the total system power shortage, the average length of overhead lines, the average length of cables, the average number of distribution stations, the wiring rate and the cycle rate.

[0052] In the embodiments of the present application, there are many reliability index data that affect the reliability of the distributed power generation distribution network, such as the average power outage frequency of the system, the average power outage duration of the system, the average power supply availability, the total power shortage degree of the system, the average length of the overhead line, the average length of the cable, the average number of distribution stations (including distribution substations and substations), the wiring rate and the cycle rate.

[0053] Although there are many reliability index data that affect the reliability of the distribution network, the degree of influence of each reliability index data on the reliability of the distribution network is different. Some reliability index data have a stronger influence on the reliability of the distribution network, while some reliability index data have a weaker influence on the reliability of the distribution network. In the embodiment of the present application, one or more reliability index data with a stronger influence on the reliability of the distribution network (i.e., strongly related to the reliability of the distribution network) are selected from the above reliability index data in the current period as an important criterion for evaluating the reliability of the distribution network.

[0054] Based on the entropy method, the one or more reliability index data that are strongly related to the reliability of the distribution network are processed, and the entropy values ​​and weights corresponding to the one or more reliability index data that are strongly related to the reliability of the distribution network in the current period are calculated. The entropy value is the first entropy value, and the weight is the first weight.

[0055] The importance of reliability index data can be expressed by the change of reliability index data. The smaller the entropy value of a reliability index data, the greater the change of the reliability index data, the more information it provides, the more valuable it is, and the greater the weight of the reliability index data. Otherwise, the weight of the reliability index data is small.

[0056] Based on the entropy method, the first entropy value and the first weight of the important criteria affecting the reliability of the distributed generation distribution network are determined. Finally, the back propagation neural network architecture is used, such as Figure 2 As shown, the objective function of the framework is the square error between the actual output value and the expected output value. The back propagation neural network consists of three layers: input layer, hidden layer and output layer. The neurons in each layer are connected to each other through connection weights. The neurons in the same layer are independent of each other. The input signal (A1, A2, ..., An, n is the number of input nodes) is first transmitted from the input layer to the hidden layer, and then processed layer by layer to the output layer, and the output layer outputs the reliability assessment result X1 of the distribution network in the future period. If the required output is not obtained in the output layer, the back propagation process is started. The error signal is returned from the initially connected channel and eliminated by automatically correcting the weight of each neuron. In the embodiment of the present application, the hidden layer has 3 neurons, and the outputs are H1, H2, and H3.

[0057] In the embodiment of the present application, the target back propagation neural network is obtained after training the above-mentioned back propagation neural network. The first entropy value and the first weight corresponding to the one or more reliability index data strongly related to the reliability of the distribution network in the current period obtained above are input as input signals into the target back propagation neural network, and the reliability evaluation result of the distribution network in the future period is output through the output layer of the target back propagation neural network.

[0058] The distribution network reliability assessment method provided in the embodiment of the present application obtains one or more reliability index data that are strongly related to the reliability of the distribution network in the current time period, and obtains the entropy value and weight data corresponding to the one or more reliability index data through the entropy method, and applies the back propagation neural network to the obtained entropy value and weight to calculate the distribution network reliability assessment result in the future time period, so as to achieve accurate prediction of the distribution network reliability and improve the reliability of the distribution network under the development of distributed power generation.

[0059] Further, in some embodiments, in step 110, obtaining at least one reliability index data strongly related to the reliability of the distribution network in the current period may include:

[0060] A principal component analysis is performed on a plurality of reliability index data that affect the reliability of the distribution network in the current period to obtain at least one reliability index data that is strongly correlated with the reliability of the distribution network in the current period.

[0061] In the embodiment of the present application, by collating the reliability index data related to the reliability of the distributed generation and distribution network in the current period, analyzing the factors affecting the reliability of the distributed generation and distribution network in the current period, for example, the average power outage frequency of the system, the average power outage duration of the system, the average power supply availability, the total power shortage degree of the system, the average length of the overhead line, the average length of the cable, the average number of distribution stations, the wiring rate and the cycle rate are selected as basic criteria to form a preliminary evaluation index system.

[0062] The principal component analysis (PCA) is performed on the above basic criteria to simplify the variable dimension, ensure the independence of the variables, extract one or more reliability index data that are strongly related to the reliability of the distributed generation and distribution network, and use them as important factors affecting the reliability of the distributed generation and distribution network. A large amount of high-dimensional data is converted into low-dimensional data to reflect the main characteristics of all data.

[0063] The distribution network reliability assessment method provided in the embodiment of the present application performs principal component analysis on multiple reliability index data that affect the reliability of the distribution network, obtains one or more reliability index data that are strongly correlated with the reliability of the distribution network in the current time period, and obtains entropy values ​​and weight data corresponding to the one or more reliability index data through an entropy method, and applies a back propagation neural network to the obtained entropy values ​​and weights to calculate the distribution network reliability assessment results in the future time period, thereby achieving accurate prediction of the distribution network reliability and improving the reliability of the distribution network under the development of distributed power generation.

[0064] Furthermore, in some embodiments, in the above steps, the method of obtaining the target back propagation neural network may include:

[0065] Obtain a second entropy value and a second weight respectively corresponding to at least one reliability indicator data strongly related to the reliability of the distribution network in a historical period;

[0066] Inputting the second entropy value and the second weight into the back propagation neural network for training until the back propagation neural network converges;

[0067] The converged back-propagation neural network is used as the target back-propagation neural network.

[0068] In an embodiment of the present application, it is assumed that the multiple reliability index data affecting the reliability of the distributed power generation distribution network acquired in the historical period (2013-2019) are: system average power outage frequency, system average power outage duration, average power supply availability, system total power shortage degree, average length of overhead lines, average length of cables, average number of distribution stations (including distribution stations and substations), wiring rate and cycle rate, as shown in Table 1. Table 1 is the reliability index data of the urban distribution network of a certain city from 2013 to 2019. It is assumed that C1-C9 represent the system average power outage frequency, system average power outage duration, average power supply availability, system total power shortage degree, average length of overhead lines, average length of cables, average number of distribution stations, wiring rate and cycle rate, respectively.

[0069] Table 1

[0070]

[0071]

[0072] SPSS22.0 software was used to standardize C1 to C9 in Table 1. Then, the principal component analysis method was used to analyze C1 to C9, and the important criteria that were strongly related to the reliability of the distribution network were selected. After calculation, it can be seen that the test statistic (KMO) is 0.773, which is greater than the minimum standard of 0.6. The P value of the Bartlett spherical test is 0.000, which is less than 0.001.

[0073] In the embodiment of the present application, two principal components with a cumulative variance contribution rate of 98.6% were extracted. Among them, C1, C5, C9, C2, C3, C7 and C6 belong to principal component 1, and C8 and C4 belong to principal component 2. The variance contribution of principal component 1 is 89.853%, which means that this factor contains nearly 90% of the data information. Finally, the important criteria belonging to principal component 1 are taken as the basic standards, including C1, C2, C3, C5, C6, C7 and C9.

[0074] Among them, the principal component matrix of C1 to C9 is shown in Table 2:

[0075] Table 2

[0076]

[0077] According to the characteristics of each important criterion, it is divided into distribution system factors and distribution equipment factors, where the distribution system factors are C1 to C3, and the distribution equipment factors are C5, C6, C7 and C9. Based on the entropy method, the entropy values ​​and weights corresponding to C1, C2, C3, C5, C6, C7 and C9 can be obtained. The entropy value is the second entropy value, and the weight is the second weight.

[0078] The basic criteria in the historical period are normalized by formula (1) or formula (2), as follows:

[0079]

[0080] In the formula, is the standard data after normalization, u ij is the element in the i-th row and j-th column of the matrix u, i = 1, 2, ..., m, j = 1, 2, ..., n, m is the number of basic criteria, n is the number of periods included in the historical period, minu ij is the minimum value of the elements in the i-th row and j-th column of matrix u, maxu ij is the maximum value of the elements in the i-th row and j-th column of the matrix u, and the matrix u is determined according to the basic criteria in the historical period. In the embodiment of the present application, m=9, n=7.

[0081] The second entropy values ​​corresponding to the important criteria C1, C2, C3, C5, C6, C7 and C9 that are strongly related to the reliability of the distribution network in the historical period are calculated based on the following formula:

[0082]

[0083] in, h i is the entropy value of the basic criterion corresponding to the i-th row. When i=1,2,3,5,6,7,9, h1,h2,h3,h5,h6,h7,h9 are the second entropy values ​​corresponding to the important criteria C1, C2, C3, C5, C6, C7 and C9 respectively.

[0084] According to formula (3), the weights corresponding to the entropy values ​​of each basic criterion can be calculated as follows:

[0085]

[0086] In the formula, ω i is the weight corresponding to the entropy value of the basic criterion corresponding to the i-th row. When i=1,2,3,5,6,7,9, the obtained ω1,ω2,ω3,ω5,ω6,ω7,ω9 are the second weights corresponding to the important criteria C1, C2, C3, C5, C6, C7 and C9 respectively.

[0087] After calculation, the second entropy values ​​and second weights corresponding to the important criteria are shown in Table 3:

[0088] Table 3

[0089]

[0090] The second entropy values ​​and second weights corresponding to the important criteria from 2013 to 2018 are selected as training samples of the back propagation neural network to evaluate the reliability of the distribution network in 2019. The true values ​​of the reliability of the distribution network from 2013 to 2018 are shown in Table 4:

[0091] Table 4

[0092]

[0093] The training samples (i.e., the second entropy value and the second weight obtained above) are normalized and reduced to two dimensions: distribution system factors and distribution equipment factors. The back propagation neural network is trained until the back propagation neural network converges, and the converged back propagation neural network is used as the target back propagation neural network.

[0094] During the training process of the back propagation neural network, the square error between the actual output value of the reliability of the distribution network in 2019 output by the back propagation neural network and the true value of the reliability of the distribution network in 2019 can be used as the objective function, and the back propagation neural network can be continuously trained until the objective function becomes stable.

[0095] Please see further Figure 3 , the training process of the back propagation neural network can specifically include:

[0096] Based on the principal component analysis method, one or more reliability index data that are strongly related to the reliability of the distribution network in the historical period are obtained;

[0097] Calculate the second entropy value and the second weight respectively corresponding to one or more reliability index data in the historical period based on the entropy method;

[0098] Set the initial weights and initial thresholds of the back-propagation neural network;

[0099] Taking the second entropy value and the second weight as input data, output data is given;

[0100] Calculate the output of each hidden layer neuron node;

[0101] Calculate the output of the output layer neuron nodes;

[0102] Calculate the square error between the predicted value of distribution network reliability output by the output layer and the true value of distribution network reliability;

[0103] Determine whether the error meets the requirements, such as being smaller than a preset value or tending to be stable;

[0104] If it is not satisfied, the hidden layer error is calculated;

[0105] Solve for error gradient;

[0106] Adjust the initial weights and initial thresholds according to the learning function, and repeat the above process until the error meets the requirements.

[0107] Furthermore, in some embodiments, the above method may further include:

[0108] Based on any one of the standard back-propagation algorithm, the elastic back-propagation algorithm, the conjugate gradient algorithm and the Levenberg-Marquardt algorithm, the parameters of the back-propagation neural network are adjusted.

[0109] In the embodiment of the present application, in the process of training the above-mentioned back propagation neural network, common neural network training methods such as standard back propagation algorithm, elastic back propagation algorithm, conjugate gradient and Levenberg-Marquardt algorithm are used for training. The comparison of reliability evaluation results, average relative error and response time is shown in Table 5.

[0110] Table 5

[0111]

[0112] It can be seen from Table 5 that the minimum mean relative error can be obtained by training the back propagation neural network using the Levenberg-Marquardt algorithm. Therefore, in the embodiment of the present application, in order to further improve the accuracy of the distribution network reliability assessment, the Levenberg-Marquardt algorithm can be used to train the back propagation neural network.

[0113] In order to improve the reliability of the distribution network under the development of distributed generation, this application firstly applies the principal component analysis method to select the basic criteria. Then the entropy method is used to calculate the weights of the basic criteria to avoid the subjectivity of human decision-making. Finally, the back propagation neural network is introduced for reliability assessment. The effectiveness of the model is verified by example analysis. Compared with other algorithms, the Levenberg-Marquardt method has the smallest average relative error.

[0114] Further, in some embodiments, in step 120, obtaining a first entropy value and a first weight respectively corresponding to at least one reliability indicator data may include:

[0115] Normalize multiple reliability index data that affect the reliability of the distribution network in the current period, and obtain standard data corresponding to each reliability index data in the current period;

[0116] According to the standard data, a first entropy value is obtained;

[0117] A first weight is obtained according to the first entropy value.

[0118] In the embodiment of the present application, multiple reliability index data affecting the reliability of the distribution network in the current period are obtained, for example, including the average power outage frequency of the system, the average power outage duration of the system, the average power supply availability, the total power shortage degree of the system, the average length of the overhead line, the average length of the cable, the average number of distribution transformer stations, the wiring rate and the cycle rate. Based on formula (1) and formula (2), multiple reliability index data affecting the reliability of the distribution network in the current period are normalized to obtain the standard data corresponding to each reliability index data in the current period.

[0119] The principal component analysis method is used to perform principal component analysis on the multiple reliability index data in the current period obtained above, and one or more reliability index data that are strongly related to the reliability of the distribution network in the current period are obtained, which are assumed to be: system average power outage frequency, system average power outage duration, average power supply availability, average length of overhead lines, average length of cables, average number of distribution substations and cycle rate.

[0120] Based on formulas (3) to (5) and the standard data corresponding to each reliability index data in the current period, the first entropy value and the first weight corresponding to one or more reliability index data strongly related to the reliability of the distribution network in the current period can be calculated.

[0121] The distribution network reliability assessment device provided in the present application is described below. The distribution network reliability assessment device described below and the distribution network reliability assessment method described above can be referenced to each other.

[0122] See also Figure 4 , an embodiment of the present application provides a distribution network reliability assessment device, which may include: a first acquisition module 410 , a second acquisition module 420 and an assessment module 430 .

[0123] A first acquisition module 410 is used to acquire at least one reliability index data strongly related to the reliability of the distribution network in the current period;

[0124] A second acquisition module 420 is used to obtain a first entropy value and a first weight respectively corresponding to at least one reliability indicator data;

[0125] The evaluation module 430 is used to input the first entropy value and the first weight into the target back propagation neural network to obtain the distribution network reliability evaluation result in the future period.

[0126] The distribution network reliability assessment device provided in the embodiment of the present application obtains one or more reliability index data that are strongly related to the reliability of the distribution network in the current time period, and obtains the entropy value and weight data corresponding to the one or more reliability index data through the entropy method, and applies the back propagation neural network to the obtained entropy value and weight to calculate the distribution network reliability assessment result in the future time period, thereby realizing accurate prediction of the distribution network reliability and improving the reliability of the distribution network under the development of distributed power generation.

[0127] It can be understood that the detailed functional implementation of each of the above-mentioned units / modules can be found in the introduction of the aforementioned method embodiment, and will not be repeated here.

[0128] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.

[0129] Based on the method in the above embodiment, the present application embodiment provides an electronic device, see Figure 5 The electronic device may include: a processor (Processor) 510, a communication interface (CommunicationsInterface) 520, a memory (Memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the method in the above embodiment.

[0130] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0131] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0132] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0133] It is understandable that the processor in the embodiment of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0134] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0135] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0136] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0137] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A distribution network reliability assessment method, characterized in that: include: Obtain at least one reliability indicator data strongly related to the reliability of the distribution network in the current period; Obtaining a first entropy value and a first weight respectively corresponding to the at least one reliability indicator data; The first entropy value and the first weight are input into a target back propagation neural network to obtain a distribution network reliability assessment result in a future period.

2. The distribution network reliability assessment method according to claim 1, characterized in that: The obtaining of at least one reliability index data strongly related to the reliability of the distribution network in the current period includes: A principal component analysis is performed on a plurality of reliability index data affecting the reliability of the distribution network in the current period to obtain at least one reliability index data strongly correlated with the reliability of the distribution network in the current period.

3. The distribution network reliability assessment method according to claim 1, characterized in that: The method for acquiring the target back propagation neural network includes: Obtain a second entropy value and a second weight respectively corresponding to at least one reliability indicator data strongly related to the reliability of the distribution network in a historical period; Inputting the second entropy value and the second weight into a back propagation neural network for training until the back propagation neural network converges; The converged back-propagation neural network is used as the target back-propagation neural network.

4. The distribution network reliability assessment method according to claim 1, characterized in that: The obtaining of the first entropy value and the first weight respectively corresponding to the at least one reliability indicator data comprises: Normalize multiple reliability index data that affect the reliability of the distribution network in the current period, and obtain standard data corresponding to each reliability index data in the current period; According to the standard data, obtaining the first entropy value; The first weight is obtained according to the first entropy value.

5. The distribution network reliability assessment method according to claim 3, characterized in that: The method further comprises: Based on any one of a standard back propagation algorithm, a resilient back propagation algorithm, a conjugate gradient algorithm and a Levenberg-Marquardt algorithm, the parameters of the back propagation neural network are adjusted.

6. The distribution network reliability assessment method according to claim 2, characterized in that: The multiple reliability index data affecting the reliability of the distribution network include: The average frequency of system outages, the average duration of system outages, the average power supply availability, the total system power shortage, the average length of overhead lines, the average length of cables, the average number of distribution substations, the wiring rate and the cycle rate.

7. A distribution network reliability assessment device, characterized in that: include: A first acquisition module is used to acquire at least one reliability index data strongly related to the reliability of the distribution network in the current period; A second acquisition module is used to acquire a first entropy value and a first weight respectively corresponding to the at least one reliability indicator data; An evaluation module is used to input the first entropy value and the first weight into a target back propagation neural network to obtain a distribution network reliability evaluation result in a future period.

8. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the distribution network reliability assessment method as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program runs on a processor, the processor is enabled to execute the distribution network reliability assessment method according to any one of claims 1 to 6.

10. A computer program product, characterized in that When the computer program product runs on a processor, the processor is enabled to execute the distribution network reliability assessment method according to any one of claims 1 to 6.

Images