A method and system for analyzing factors influencing the capacity of a distribution network carrying distributed resources

Abstract

The present invention discloses a method and system for analyzing factors affecting the ability of a distribution network to carry distributed resources, which relates to the technical field of distribution network carrying capacity assessment, including: performing a first preprocessing on first target data of the distribution network to obtain second target data; performing a first screening on the second target data to obtain a first influencing factor of the distribution network carrying capacity; presetting a first causal graph structure of the first influencing factor to analyze the causal effect of the first influencing factor on the distribution network carrying capacity; and constructing a structural causal model based on the causal effect and the first causal graph structure to evaluate the impact of different intervention strategies on the distribution network carrying capacity. The present invention achieves an in-depth understanding of the mechanism affecting the distribution network carrying capacity, can provide strong support for distribution network planning and operation decisions, and help improve the distribution network's ability to carry distributed resources.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution network carrying capacity evaluation, and particularly relates to a power distribution network carrying distributed resource capacity influence factor analysis method and system. BACKGROUND

[0002] With large-scale access of distributed energy, electric vehicles and other new types of loads, the carrying capacity of the power distribution network is facing severe challenges. The traditional carrying capacity evaluation method is mainly based on static power flow analysis and probability statistical model, which is difficult to fully capture the complex interaction between influence factors and cannot accurately quantify the influence degree of each factor on the carrying capacity. In addition, the existing method often ignores the time series characteristics and dynamic change law, and is difficult to cope with the rapid change of the operation state of the power distribution network. SUMMARY

[0003] This section aims to summarize some aspects of the embodiments of the present application and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of the specification to avoid obscuring the purpose of this section, abstract and title, and such simplifications or omissions cannot be used to limit the scope of the present application.

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a power distribution network carrying distributed resource capacity influence factor analysis method and system to solve the problems mentioned in the background art.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the embodiments of the present application provide a power distribution network carrying distributed resource capacity influence factor analysis method, comprising: performing first preprocessing on first target data of the power distribution network to obtain second target data;

[0008] Performing first screening on the second target data to obtain first influence factors of the power distribution network carrying capacity;

[0009] Pre-setting a first causal diagram structure of the first influence factors, and analyzing the causal effect of the first influence factors on the power distribution network carrying capacity;

[0010] Based on the causal effect and the first causal diagram structure, a structural causal model is constructed to evaluate the influence of different intervention strategies on the carrying capacity of the power distribution network.

[0011] As a preferred scheme of the power distribution network carrying distributed resource capacity influence factor analysis method, the first causal diagram structure comprises a first graph structure.

[0012] The first influence factor is used to test the first graph structure to delete redundant edges.

[0013] The remaining edges are oriented to obtain a second graph structure.

[0014] As a preferred scheme of the power distribution network carrying distributed resource capacity influence factor analysis method, wherein: the analysis of the causal effect of the first influence factor on the carrying capacity of the power distribution network comprises: constructing a first prediction model and a second prediction model of any influence factor;

[0015] The first prediction model is used to predict the key influence factor;

[0016] The second prediction model is used to predict the carrying capacity of the power distribution network.

[0017] As a preferred scheme of the power distribution network carrying distributed resource capacity influence factor analysis method, wherein: further comprising: the first prediction model and the second prediction model are based on the result prediction of other influence factors except any influence factor.

[0018] As a preferred scheme of the power distribution network carrying distributed resource capacity influence factor analysis method, wherein: further comprising: based on the predicted key influence factor and the carrying capacity of the power distribution network to calculate the causal effect estimate value.

[0019] As a preferred scheme of the power distribution network carrying distributed resource capacity influence factor analysis method, wherein: based on the causal effect and the first causal graph structure to construct a structural causal model to evaluate the influence of different intervention strategies on the carrying capacity of the power distribution network comprises:

[0020] The target intervention strategy of the structural causal model is preset, and the key influence factor in the structural causal model is set as a target influence factor;

[0021] The intervention effect is calculated to evaluate the influence of the target intervention strategy on the carrying capacity of the power distribution network.

[0022] As a preferred scheme of the power distribution network carrying distributed resource capacity influence factor analysis method, wherein: the calculation of the intervention effect to evaluate the influence of the target intervention strategy on the carrying capacity of the power distribution network further comprises: the intervention effect is the difference between the expected value of the target influence factor under the target intervention strategy and the expected value under the non-intervention condition;

[0023] The structural causal model updates the target influence factor according to the intervention strategy to calculate the carrying capacity of the power distribution network;

[0024] The distribution of the carrying capacity of the power distribution network after intervention is obtained by traversing different intervention strategies, and the average value or expectation value of the distribution is calculated as an estimate of the intervention effect to analyze the influence mechanism of the carrying capacity of the power distribution network.

[0025] In a second aspect, the present application provides a power distribution network carrying distributed resource capacity influence factor analysis system, comprising:

[0026] A data acquisition unit is configured to perform first preprocessing on the first target data of the power distribution network to obtain second target data.

[0027] A screening module is configured to perform first screening on the second target data to obtain first influence factors of the carrying capacity of the power distribution network.

[0028] An analysis module is configured to preset a first causal diagram structure of the first influence factors and analyze the causal effect of the first influence factors on the carrying capacity of the power distribution network.

[0029] An evaluation module is configured to construct a structural causal model based on the causal effect and the first causal diagram structure to evaluate the influence of different intervention strategies on the carrying capacity of the power distribution network.

[0030] In a third aspect, the present application provides an electronic device, comprising:

[0031] A memory and a processor.

[0032] The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, which realize the steps of the power distribution network carrying distributed resource capacity influence factor analysis method.

[0033] In a fourth aspect, the present application provides a computer readable storage medium storing computer executable instructions, which realize the steps of the power distribution network carrying distributed resource capacity influence factor analysis method when executed by a processor.

[0034] Compared with the prior art, the present application has the following beneficial effects: the first target data of the power distribution network is preprocessed to obtain the second target data, the first influence factors of the carrying capacity of the power distribution network are obtained by first screening the second target data, the first causal diagram structure of the first influence factors is preset, the causal effect of the first influence factors on the carrying capacity of the power distribution network is analyzed, the structural causal model is constructed based on the causal effect and the first causal diagram structure to evaluate the influence of different intervention strategies on the carrying capacity of the power distribution network, the carrying capacity influence mechanism of the power distribution network is deeply understood, the power distribution network planning and operation decision-making are strongly supported, and the carrying capacity of the power distribution network distributed resources is improved. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only represent some of the embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort based on these drawings. Among them:

[0036] Figure 1 The method flowchart of the power distribution network carrying distributed resource capability influence factor analysis method and system according to an embodiment of the present application. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings in the specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort should be within the protection scope of the present application.

[0038] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the spirit of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0039] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. The "in one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0040] The present application is described in detail in conjunction with the schematic diagram. In the detailed description of the embodiments of the present application, the cross-sectional view of the device structure will be partially enlarged without the general proportion for the convenience of description, and the schematic diagram is only an example, which should not limit the scope of protection of the present application herein. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in actual manufacturing.

[0041] Meanwhile, in the description of the present application, it should be noted that the terms "up, down, in and out" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first, second or third" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance.

[0042] Unless otherwise defined, the terms "mounting, connecting, associating" in the present application should be interpreted broadly, for example: it can be fixed connection, detachable connection or integral connection; it can also be mechanical connection, electrical connection or direct connection, it can also be indirectly connected through intermediate medium, or it can be the internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0043] Embodiment 1

[0044] Reference Figure 1 For an embodiment of the present application, the embodiment provides a power distribution network carrying distributed resource capacity influencing factor analysis method, comprising:

[0045] S100: first preprocessing the first target data of the power distribution network to obtain the second target data;

[0046] S200: first screening the second target data to obtain the first influencing factor of the carrying capacity of the power distribution network;

[0047] S300: presetting the first causal diagram structure of the first influencing factor, and analyzing the causal effect of the first influencing factor on the carrying capacity of the power distribution network;

[0048] S400: constructing a structural causal model based on the causal effect and the first causal diagram structure to evaluate the influence of different intervention strategies on the carrying capacity of the power distribution network.

[0049] It should be noted that with the large-scale access of new types of loads such as distributed energy and electric vehicles, the carrying capacity of the power distribution network is facing severe challenges. Since the traditional carrying capacity evaluation method is difficult to fully capture the complex interaction between influencing factors, it is also difficult to accurately quantify the influence degree of each factor on the carrying capacity. In addition, the existing method also ignores the time series characteristics and dynamic change law, and it is difficult to cope with the rapid change of the operation state of the power distribution network. Through the above steps S100-S400, the embodiment of the present application accurately quantifies the causal effect of each influencing factor on the carrying capacity of the power distribution network by constructing a causal relationship network covering multiple dimensions of factors such as physical characteristics, operation state and external environment of the power distribution network. Through the integration of multi-source heterogeneous data, combined with machine learning and statistical inference technology, the influence mechanism of the carrying capacity of the power distribution network is analyzed in depth.

[0050] Embodiment 2

[0051] Reference Figure 1 For an embodiment of the present application, based on the previous embodiment, a power distribution network carrying distributed resource capacity influencing factor analysis method is provided, comprising:

[0052] In the embodiment of the present application, the first causal diagram structure comprises: a first graph structure;

[0053] The first influence factor is used to test the first graph structure to delete redundant edges;

[0054] The remaining edges are oriented to obtain a second graph structure.

[0055] In an optional embodiment, the first causal graph structure can be constructed by a fast causal inference method;

[0056] In another optional embodiment, the first causal graph structure can also be constructed by a Bayesian network structure learning method;

[0057] In a preferred embodiment, the present application adopts the Peter-Clark algorithm to construct a preliminary causal graph structure. The algorithm belongs to a constraint-based method, which mainly infers the causal relationship between variables by testing marginal and conditional independence. The basic principle of the Peter-Clark algorithm is to delete the edges between variables step by step through conditional independence test, and finally obtain a directed acyclic graph.

[0058] In an optional embodiment, the first graph structure is a complete undirected graph, and the second graph structure is a directed acyclic graph.

[0059] In an optional embodiment, the edges between variables are deleted step by step through conditional independence test, and finally a directed acyclic graph is obtained, which specifically includes steps A1-A3:

[0060] A1: Construct a complete undirected graph, in which all variables are connected by edges.

[0061] A2: For any two connected variables X and Y, test whether X and Y are independent given a subset S of other variables. If so, delete the edge between X and Y.

[0062] A3: Orient the remaining edges to obtain a directed acyclic graph.

[0063] For example, the partial correlation coefficient is used as the statistic of conditional independence test. Assuming that X and Y are to be tested for independence given Z, the calculation formula of the partial correlation coefficient is:

[0064]

[0065] Where ρ XY ,ρ XZ ,ρ YZ are the correlation coefficients between X and Y, X and Z, and Y and Z, respectively.

[0066] It should be noted that in the embodiments of the present application, the first influencing factor is obtained by first screening the second target data, wherein the second target data is obtained by first preprocessing the power distribution network first target data.

[0067] In the embodiments of the present application, the first target data is original data collected for analyzing the influencing factors of the power distribution network carrying capacity of distributed resources, and these original data can come from multiple aspects. The present application integrates multi-source heterogeneous data, and combines machine learning and statistical inference technology to realize in-depth analysis of the influencing mechanism of the power distribution network carrying capacity.

[0068] In an optional embodiment, the first preprocessing of the power distribution network first target data can include preprocessing methods such as outlier detection and missing value filling;

[0069] In another optional embodiment, the first preprocessing of the power distribution network first target data can also include preprocessing methods such as data standardization processing, data cleaning and data integration, so as to obtain clean, complete and unified format second target data for subsequent analysis and modeling, which is not limited in the present application.

[0070] For example, for missing load data, a time series interpolation method can be used for filling; for abnormal voltage data, expert knowledge and statistical methods can be combined for correction.

[0071] In the embodiments of the present application, the first influencing factor obtained by first screening the second target data is based on expert knowledge and statistical analysis to preliminarily screen factors that may affect the carrying capacity of the power distribution network.

[0072] In an optional embodiment, the first influencing factor can be obtained from the power distribution network topology structure and device parameters and operating state data;

[0073] In another optional embodiment, the first influencing factor can also be obtained from distributed resource data and environmental factor data.

[0074] For example, the power distribution network topology structure and device parameters include transformer capacity, line impedance, switch state and other data;

[0075] For example, the operating state data includes node voltage, line power flow, load demand and other data;

[0076] For example, the distributed resource data includes the access capacity and output characteristics of photovoltaic, wind power and other distributed power sources;

[0077] For example, the environmental factor data includes temperature, humidity, sunshine intensity and other meteorological information data.

[0078] In an optional embodiment, the variables selected as the first influencing factors include:

[0079] X1: Transformer capacity utilization rate

[0080] X2: Line load rate

[0081] X3: Photovoltaic penetration rate

[0082] X4: Wind power access capacity

[0083] X5: Electric vehicle charging load proportion

[0084] X6: Ambient temperature

[0085] X7: Power supply radius

[0086] X8: Load density

[0087] Y: Power distribution network carrying capacity (characterized by maximum accessible distributed resource capacity)

[0088] In the embodiments of the present application, analyzing the causal effect of the first influencing factor on the carrying capacity of the power distribution network includes: constructing a first prediction model and a second prediction model of any influencing factor;

[0089] The first prediction model is used to predict the key influencing factor;

[0090] The second prediction model is used to predict the carrying capacity of the power distribution network.

[0091] In the embodiments of the present application, the first prediction model and the second prediction model are result predictions based on other influencing factors other than any influencing factor.

[0092] In the embodiments of the present application, the causal effect estimation value is calculated based on the predicted key influencing factor and the carrying capacity of the power distribution network.

[0093] It should be noted that in the embodiments of the present application, the causal effect estimation problem is decomposed into two prediction problems to reduce the influence of model error on the estimation result.

[0094] In a preferred embodiment, a double machine learning method is used to estimate the causal effect of each factor on the carrying capacity, specifically including steps B1-B3:

[0095] B1: For each processing variable X i , two prediction models are constructed:

[0096] The first prediction model: uses other variables to predict Xi

[0097] The second prediction model: uses other variables to predict the result variable Y

[0098] B2: Calculate the residual error:

[0099]

[0100] ε Y = Y - E[Y|X -i ]

[0101] where X -i represents all variables except X i .

[0102] B3: Estimate the causal effect using the residual error ε Y ,

[0103]

[0104] where Cov represents covariance and Var represents variance.

[0105] In an optional embodiment, the prediction model can employ a variety of other machine learning and statistical models that can be used for prediction tasks, such as support vector machines, convolutional neural networks, gradient boosting trees, etc.

[0106] In a preferred embodiment, a random forest can be employed as the prediction model for estimating the causal effect of the first influencing factors on the carrying capacity of the power distribution network.

[0107] For example, the causal effect estimation of photovoltaic penetration rate (X3) on carrying capacity (Y) includes steps C1-C5:

[0108] C1: Construct a random forest model RF1 to predict X3 using X1, X2, X4, X5, X6, X7, and X8;

[0109] C2: Construct a random forest model RF2 to predict Y using X1, X2, X4, X5, X6, X7, and X8;

[0110] C3: Calculate the residual error:

[0111]

[0112] ε Y = Y - RF2 * predict(X1, X2, X4, X5, X6, X7, X8)

[0113] C4: Estimate the causal effect:

[0114]

[0115] C5: Repeat steps C1-C4 to obtain the causal effect estimation of all factors on the carrying capacity. ​

[0116] In the embodiments of the present application, the structural causal model is constructed based on the causal effect and the first causal graph structure to evaluate the influence of different intervention strategies on the carrying capacity of the power distribution network, which includes:

[0117] The target intervention strategy of the preset structural causal model is set as the target influencing factor in the structural causal model;

[0118] The intervention effect is calculated to evaluate the influence of the target intervention strategy on the carrying capacity of the power distribution network.

[0119] In the embodiments of the present application, the intervention effect is calculated to evaluate the influence of the target intervention strategy on the carrying capacity of the power distribution network, which further includes that the intervention effect is the difference between the expected value of the target influencing factor under the target intervention strategy and the expected value under the non-intervention condition;

[0120] The structural causal model updates the target influencing factor according to the intervention strategy to calculate the carrying capacity of the power distribution network;

[0121] Different intervention strategies are traversed to obtain the distribution of the carrying capacity of the power distribution network after intervention, and the mean or expected value of the distribution is calculated as an estimate of the intervention effect to analyze the influence mechanism of the carrying capacity of the power distribution network.

[0122] It should be noted that the present application reveals the essential mechanism of influencing the carrying capacity of the power distribution network through causal reasoning, overcoming the limitations of traditional correlation analysis methods.

[0123] In an optional embodiment, the structural causal model for evaluating the influence of different intervention strategies on the carrying capacity of the power distribution network can estimate the causal effect through the Bayesian framework, naturally handle uncertainty, and make inferences through methods such as Markov Chain Monte Carlo.

[0124] In another optional embodiment, the structural causal model for evaluating the influence of different intervention strategies on the carrying capacity of the power distribution network can estimate the causal effect by assigning a weight to each observation value through inverse probability weighting, so that the distribution of confounding factors between the treatment group and the control group becomes similar.

[0125] In a preferred embodiment, the potential influence of different intervention strategies on the carrying capacity is evaluated through counterfactual reasoning, which specifically includes steps D1-D3:

[0126] D1: Construct a structural causal model:

[0127] X i =f i (PA i ,U i ),i=1,...,8

[0128] Y=f(X1,...X8,UY )

[0129] where PA i represents the parent node set of X i , U i and U Y represent exogenous random variables.

[0130] D2: define intervention operation do(X i =x), which means setting X i to a specific value x.

[0131] D3: calculate intervention effect E[Ydo(X i =x)]-E[Y], which means the average causal effect of changing X i from the current value to x on Y.

[0132] Exemplary, taking the example of evaluating the impact of increasing transformer capacity on carrying capacity, specifically including steps E1-E3:

[0133] E1: based on the obtained causal graph and estimated causal effect, construct SCM:

[0134] X1=f1(U1)

[0135] X1=f2(X1,U2) ...

[0137] Y=f(X1,...,X8,U Y )

[0138] E2: define intervention operation do(X i =x1'), where x1' represents the increased transformer capacity utilization rate.

[0139] E3: calculate intervention effect:

[0140] ΔY=E[Ydo(X i =x1')]-E[Y]

[0141] The above expectation values are estimated by Monte Carlo simulation method, and multiple experiments are repeated to obtain stable results. Based on the above analysis, the following main conclusions are obtained:

[0142] Transformer capacity utilization rate (X1), line load rate (X2) and photovoltaic penetration rate (X3) are the three most important factors affecting the carrying capacity of distribution network, and their causal effect estimates are θ1=-0.42, θ2=-0.38, θ3=0.31, respectively.

[0143] By counterfactual analysis, it is found that reducing the transformer capacity utilization rate from the current 75% to 65% can increase the carrying capacity of the distribution network by about 12%.

[0144] The negative impact of the power supply radius (X7) on the carrying capacity (θ7=-0.25) is greater than expected, indicating that optimizing the network topology is important for improving the carrying capacity.

[0145] Based on the above analysis results, the following suggestions for improving the carrying capacity of the distribution network are proposed:

[0146] Prioritize increasing transformer capacity or reducing transformer load rate, such as by adding new transformers or load transfer measures.

[0147] Strengthen the distribution network line reconstruction, improve the line current carrying capacity, and reduce the line load rate.

[0148] Reasonably plan the access location and capacity of photovoltaic power generation, and fully utilize the positive impact of photovoltaic power generation.

[0149] Optimize the distribution network structure, appropriately shorten the power supply radius, and improve the network carrying capacity.

[0150] It should be noted that the present application combines machine learning and statistical inference techniques to improve the accuracy and reliability of causal effect estimation. By introducing counterfactual analysis, the potential effects of different intervention strategies can be evaluated, providing strong support for decision-making.

[0151] It should also be noted that the present application first collects and pre-processes multi-source heterogeneous data, determines potential influencing factors through variable selection, uses the Peter-Clark algorithm for causal discovery, and constructs a preliminary causal graph structure. On this basis, a double machine learning method is used to estimate the causal effects of each factor. Finally, through counterfactual analysis, the potential impact of different intervention strategies is evaluated, achieving a deep understanding of the impact mechanism of the carrying capacity of the distribution network, providing strong support for distribution network planning and operation decisions, and helping to improve the carrying capacity of the distribution network for distributed resources.

[0152] Embodiment 3

[0153] The above is a schematic scheme of the method for analyzing the factors affecting the carrying capacity of the distribution network for distributed resources. It should be noted that the technical scheme of the system for analyzing the factors affecting the carrying capacity of the distribution network for distributed resources is the same as the technical scheme of the method for analyzing the factors affecting the carrying capacity of the distribution network for distributed resources described above. The technical scheme of the system for analyzing the factors affecting the carrying capacity of the distribution network for distributed resources in this embodiment is not described in detail, and can be referred to the description of the technical scheme of the method for analyzing the factors affecting the carrying capacity of the distribution network for distributed resources.

[0154] The power distribution network carrying distributed resource capacity influencing factor analysis system in the embodiment comprises:

[0155] The data acquisition unit is configured to perform first preprocessing on the first target data of the power distribution network and acquire second target data.

[0156] The screening module is configured to perform first screening on the second target data to obtain first influencing factors of the power distribution network carrying capacity.

[0157] The analysis module is configured to preset a first causal diagram structure of the first influencing factors and analyze causal effects of the first influencing factors on the power distribution network carrying capacity.

[0158] The evaluation module is configured to construct a structural causal model based on the causal effects and the first causal diagram structure to evaluate influences of different intervention strategies on the power distribution network carrying capacity.

[0159] The embodiment further provides an electronic device suitable for the power distribution network carrying distributed resource capacity influencing factor analysis method, which comprises:

[0160] The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement the power distribution network carrying distributed resource capacity influencing factor analysis method.

[0161] The embodiment further provides a storage medium having a computer program stored thereon, and the program is executed by a processor to implement the power distribution network carrying distributed resource capacity influencing factor analysis method.

[0162] The storage medium proposed in the embodiment and the power distribution network carrying distributed resource capacity influencing factor analysis method proposed in the above embodiment belong to the same inventive concept, and the technical details not described in the embodiment can be referred to the above embodiment, and the embodiment has the same beneficial effects as the above embodiment.

[0163] Those skilled in the art can clearly understand the present application by the description of the above embodiments. The present application can be realized by software and necessary general hardware, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a FLASH, a hard disk, or an optical disc, and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the method of each embodiment of the present application.

[0164] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A method for analyzing factors affecting the ability of a distribution network to carry distributed resources, characterized in that: include: Performing a first preprocessing on first target data of the distribution network to obtain second target data, where the first target data is raw data collected to analyze factors affecting the ability of the distribution network to carry distributed resources; Performing a first screening on the second target data to obtain a first influencing factor of the distribution network carrying capacity; Presetting a first causal graph structure of the first influencing factor, and analyzing the causal effect of the first influencing factor on the carrying capacity of the distribution network, including: constructing a first prediction model and a second prediction model for any influencing factor; The first prediction model is used to predict key influencing factors; The second prediction model is used to predict the carrying capacity of the distribution network; The first prediction model and the second prediction model are based on the result prediction of other influencing factors other than any one influencing factor; Based on the predicted key influencing factors and the distribution network carrying capacity, a dual machine learning method is used to estimate the causal effect of each factor on the carrying capacity, and the causal effect estimate is calculated, which specifically includes steps B1-B3: B1: For each treatment variable X i , build two prediction models: First prediction model: predict X using other variables i ; Second prediction model: Use other variables to predict the outcome variable Y; B2: Calculate the residual: e Y =Y-E[Y|X -i ] Among them, X -i Indicates division by X i All variables except B3: Use residual ε Y , Estimating causal effects: Among them, Cov represents covariance and Var represents variance; A structural causal model is constructed based on the causal effect and the first causal graph structure to evaluate the impact of different intervention strategies on the carrying capacity of the distribution network, including: Presetting a target intervention strategy for the structural causal model, and setting key influencing factors in the structural causal model as target influencing factors; Calculate intervention effects and evaluate the impact of target intervention strategies on the carrying capacity of the distribution network; The calculating of the intervention effect and evaluating the impact of the target intervention strategy on the distribution network carrying capacity further includes: the intervention effect is the difference between the expected value of the target influencing factor under the target intervention strategy and the expected value under no intervention conditions; The structural causal model updates the target influencing factors according to the intervention strategy to calculate the distribution network carrying capacity; Traverse different intervention strategies, obtain the distribution of distribution network carrying capacity after intervention, calculate the average value or expected value of the distribution, and use it as an estimate of the intervention effect to analyze the impact mechanism of distribution network carrying capacity.

2. The method for analyzing factors affecting the ability of a distribution network to carry distributed resources according to claim 1, wherein: The first causal graph structure includes: a first graph structure; The first influencing factor is used to test the first graph structure to delete redundant edges; Orient the remaining edges to obtain the second graph structure.

3. A system for analyzing factors affecting the ability of a distribution network to carry distributed resources, applied to the method according to any one of claims 1-2, characterized in that: include: a data acquisition unit, configured to perform a first preprocessing on the first target data of the distribution network to acquire second target data; a screening module, configured to perform a first screening on the second target data to obtain a first influencing factor of the distribution network carrying capacity; An analysis module, configured to preset a first causal graph structure of the first influencing factor and analyze a causal effect of the first influencing factor on the carrying capacity of the distribution network; An evaluation module is used to construct a structural causal model based on the causal effect and the first causal graph structure to evaluate the impact of different intervention strategies on the carrying capacity of the distribution network.

4. An electronic device comprising: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for analyzing factors affecting the distribution network's ability to carry distributed resources as described in any one of claims 1 to 2 are implemented.

5. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for analyzing factors affecting the ability of a distribution network to carry distributed resources as described in any one of claims 1 to 2.

Images