Photovoltaic access capacity allocation method and system

Abstract

The present invention discloses a photovoltaic access capacity allocation method and system, the method comprising: collecting historical photovoltaic power generation data, historical load data and user voltage data of each user in each time period of each substation on all medium and low voltage lines, obtaining the photovoltaic access scenario of the target medium and low voltage lines, and predicting the corresponding line photovoltaic access capacity; performing a first nonlinear mapping association process on each substation and the line photovoltaic access capacity to obtain the substation photovoltaic access capacity allocation value of each substation; performing a second nonlinear mapping association process on the substation photovoltaic access capacity allocation value of each substation and the user voltage data of all users in each substation to obtain the user photovoltaic access capacity allocation value of each user. A photovoltaic access capacity allocation method and system provided by an embodiment of the present invention improves the allocation accuracy of photovoltaic access capacity.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic access capacity allocation, and in particular to a photovoltaic access capacity allocation method and system. Background Art

[0002] Photovoltaic power generation, as a clean and renewable form of energy, is of great significance to promoting green and low-carbon development. With the rapid development of distributed photovoltaic power generation, the access of distribution networks to photovoltaic capacity faces challenges such as voltage fluctuations and grid stability. By accurately assessing the photovoltaic access capacity, it can ensure that the grid will not exceed its carrying capacity when accepting photovoltaic power, thereby avoiding safety issues such as grid overload and voltage fluctuations, which helps to maintain the stable operation of the grid and ensure the reliability of power supply.

[0003] However, due to the technical barriers of existing allocation methods, existing PV access capacity allocation methods can only perform rough allocation, resulting in low allocation accuracy of PV access capacity.

[0004] It can be seen that how to improve the allocation accuracy of photovoltaic access capacity has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention

[0005] The present invention provides a photovoltaic access capacity allocation method and system to solve the technical problem that the existing photovoltaic access capacity allocation method can only perform rough allocation, resulting in low allocation accuracy of the photovoltaic access capacity.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a photovoltaic access capacity allocation method.

[0007] Collect historical photovoltaic power generation data, historical load data and user voltage data of each user in each time period for each substation on all medium and low voltage lines;

[0008] Performing feature extraction on all the historical photovoltaic power generation data and all the historical load data of each of the substations in each of the time periods to obtain a feature vector of each of the substations in each of the time periods;

[0009] Performing cluster analysis on all the medium and low voltage lines using all the feature vectors to obtain photovoltaic access scenarios of target medium and low voltage lines, and predicting the corresponding photovoltaic access capacity of the lines based on the photovoltaic access scenarios of the target medium and low voltage lines;

[0010] A first nonlinear mapping association process is performed on each of the substations and the photovoltaic access capacity of the line to obtain a substation photovoltaic access capacity allocation value for each of the substations; the first nonlinear mapping association process is designed to allocate the photovoltaic access capacity of the line according to a first allocation standard formed by the historical photovoltaic power generation data and the historical load data;

[0011] A second nonlinear mapping association process is performed on the photovoltaic access capacity allocation value of each of the substations and the user voltage data of all the users in each of the substations to obtain a user photovoltaic access capacity allocation value for each of the users; the second nonlinear mapping association process is designed to allocate the photovoltaic access capacity allocation value of the corresponding substation according to a second allocation standard formed by the user voltage data.

[0012] As one of the preferred solutions, after obtaining the photovoltaic access capacity allocation value of each of the substations, the method further includes:

[0013] Constructing a secondary chaotic polynomial agent model for each substation according to the historical photovoltaic power generation data and the historical load data of each substation in all the time periods;

[0014] The substation secondary chaotic polynomial agent model is used to process the substation photovoltaic access capacity allocation value of each substation, and the first voltage amplitude of each substation is output;

[0015] If the first voltage amplitude of all the substations does not meet the voltage constraint of the target medium and low voltage lines, the product of the photovoltaic access capacity of the line and the preset first reduction coefficient is used as the updated photovoltaic access capacity of the line, and the first nonlinear mapping association processing is performed on each of the substations and the updated photovoltaic access capacity of the line, so as to optimize the photovoltaic access capacity allocation value of each substation;

[0016] If the first voltage amplitudes of all the substations meet the voltage constraints of the target medium and low voltage lines, the substation photovoltaic access capacity allocation value of each substation is output.

[0017] As one of the preferred solutions, the step of constructing a secondary chaotic polynomial agent model for each substation according to the historical photovoltaic power generation data and the historical load data in all the time periods includes:

[0018] According to the historical photovoltaic power generation data and the historical load data of each substation in all the time periods, the key basis functions and regression coefficients of the chaotic polynomial expansion agent model are optimized and analyzed using the minimum angle regression algorithm to obtain a primary chaotic polynomial agent model of the substation;

[0019] The substation data fitting residuals of the first-level chaotic polynomial proxy model of the substation at all truncation orders are calculated according to the historical photovoltaic power generation data and the historical load data of each substation in all the time periods, and the substation second-level chaotic polynomial proxy model is obtained based on the sorting results of all the substation data fitting residuals.

[0020] As one of the preferred solutions, the first nonlinear mapping association processing is performed on each of the substations and the photovoltaic access capacity of the line to obtain the photovoltaic access capacity allocation value of each substation, including:

[0021] Counting the nighttime load data of each of the substations, and calculating the voltage quality index of each of the substations;

[0022] Performing weighted summation on the nighttime load data of each of the substations and the corresponding voltage quality index to calculate a comprehensive weighted score for each of the substations; normalizing the comprehensive weighted scores of all the substations to obtain a normalized photovoltaic access ratio for each of the substations;

[0023] The product of the normalized photovoltaic access ratio of each substation and the photovoltaic access capacity of the line is used as the substation photovoltaic access capacity allocation value of each substation.

[0024] As one preferred solution, after obtaining the user photovoltaic access capacity allocation value of each user, the method further includes:

[0025] Constructing a user secondary chaotic polynomial agent model according to the user voltage data of all the users in each of the substations;

[0026] The user secondary chaotic polynomial agent model is used to process the user photovoltaic access capacity allocation value of each user, and output a second voltage amplitude of each user;

[0027] If the second voltage amplitude of all the users does not meet the voltage constraint of the corresponding substation, the product of the substation photovoltaic access capacity allocation value of each substation and the preset second reduction coefficient is used as the updated substation photovoltaic access capacity allocation value of each substation, and the second nonlinear mapping association processing is performed on the updated substation photovoltaic access capacity allocation value of each substation and the user voltage data of all the users in each substation, so as to optimize the user photovoltaic access capacity allocation value of each user;

[0028] If the second voltage amplitudes of all the users meet the voltage constraints of the corresponding substations, the user photovoltaic access capacity allocation value of each user is output.

[0029] As one of the preferred solutions, the user secondary chaotic polynomial agent model is constructed according to the user voltage data of all the users in each of the substations, including:

[0030] According to the user voltage data of all the users in each of the substations, a minimum angle regression algorithm is used to optimize and analyze the key basis functions and regression coefficients of the chaotic polynomial expansion agent model to obtain a user first-level chaotic polynomial agent model;

[0031] The user data fitting residuals of the user first-level chaotic polynomial proxy model at all truncation orders are calculated according to the user voltage data of all the users in each of the substations, and the user second-level chaotic polynomial proxy model is obtained based on the sorting results of all the user data fitting residuals.

[0032] As one of the preferred solutions, the photovoltaic access capacity allocation value of each of the substations and the user voltage data of all the users in each of the substations are subjected to a second nonlinear mapping association process to obtain the user photovoltaic access capacity allocation value of each of the users, including:

[0033] Normalizing the user voltage data of each user to obtain a normalized photovoltaic access ratio of each user;

[0034] The product of the normalized photovoltaic access ratio of each user and the corresponding photovoltaic access capacity allocation value of the substation is used as the user photovoltaic access capacity allocation value of each user.

[0035] As one of the preferred solutions, the characteristic vector includes the photovoltaic power generation fluctuation amplitude, the photovoltaic power generation mean, the photovoltaic load ratio, the load fluctuation amplitude and the load mean;

[0036] The feature extraction of all the historical photovoltaic power generation data and all the historical load data of each substation in each time period to obtain the feature vector of each substation in each time period includes:

[0037] The difference between the maximum value and the corresponding minimum value of all the historical photovoltaic power generation data of each of the stations in each of the time periods is used as the photovoltaic power generation fluctuation amplitude of each of the stations in each of the time periods;

[0038] Taking the average value of all the historical photovoltaic power generation data of each of the stations in each of the time periods as the average photovoltaic power generation value of each of the stations in each of the time periods;

[0039] Taking the difference between the maximum value and the corresponding minimum value of all the historical load data of each substation in each time period as the load fluctuation amplitude of each substation in each time period;

[0040] Taking the average value of all the historical load data of each substation in each time period as the load mean value of each substation in each time period;

[0041] The ratio of the photovoltaic power generation average value to the corresponding load average value is used as the photovoltaic load ratio of each of the substations in each of the time periods.

[0042] As one of the preferred solutions, the photovoltaic access scenarios include high-load and high-fluctuation scenarios, low-load and low-fluctuation scenarios, photovoltaic-intensive scenarios and high-load and low-fluctuation scenarios.

[0043] Another embodiment of the present invention provides a photovoltaic access capacity allocation system, the system comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements a photovoltaic access capacity allocation method as described above when executing the computer program.

[0044] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0045] (1) Collect historical photovoltaic power generation data, historical load data and user voltage data of each user in each time period of each substation on all medium and low voltage lines, perform feature extraction on all historical photovoltaic power generation data and all historical load data of each substation in each time period, and obtain the feature vector of each substation in each time period to evaluate the photovoltaic power generation characteristics and load characteristics of each substation;

[0046] (2) Considering that the characteristics of photovoltaic power generation and load vary significantly depending on the region, time and conditions, all medium and low voltage lines are clustered and analyzed with all feature vectors to obtain the photovoltaic access scenarios of the target medium and low voltage lines. The corresponding photovoltaic access capacity of the lines is predicted based on the photovoltaic access scenarios of the target medium and low voltage lines. All medium and low voltage lines are divided into different photovoltaic access scenarios through clustering, and the corresponding photovoltaic access capacity of the lines is predicted according to the photovoltaic access scenarios to which the target medium and low voltage lines belong, thereby improving the accuracy of the allocation of photovoltaic access capacity.

[0047] (3) Performing a first nonlinear mapping association process on the photovoltaic access capacity of each substation and line to obtain the substation photovoltaic access capacity allocation value of each substation, and the first nonlinear mapping association process is designed to allocate the line photovoltaic access capacity according to the first allocation standard formed by historical photovoltaic power generation data and historical load data; performing a second nonlinear mapping association process on the substation photovoltaic access capacity allocation value of each substation and the user voltage data of all users in each substation to obtain the user photovoltaic access capacity allocation value of each user, and the second nonlinear mapping association process is designed to allocate the corresponding substation photovoltaic access capacity allocation value according to the second allocation standard formed by the user voltage data; using a double-layer allocation method to allocate the line photovoltaic access capacity layer by layer to the substation and the end user, ensuring that the upper limit of the photovoltaic access capacity of each node is reasonably allocated, thereby improving the allocation accuracy of the photovoltaic access capacity;

[0048] (4) The PV access scenarios are divided by clustering method, and targeted quantitative analysis is carried out according to the characteristics of the PV access scenarios to which the target medium and low voltage lines belong. The PV access capacity of the lines is allocated layer by layer to the substations and end users in combination with the two-layer allocation method, so as to more accurately evaluate the PV access capacity and comprehensively improve the allocation accuracy of the PV access capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flowchart of a photovoltaic access capacity allocation method in one embodiment of the present invention;

[0050] Figure 2 The figure is a schematic diagram of obtaining the photovoltaic access capacity allocation value of a user in one embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0053] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0054] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0055] An embodiment of the present invention provides a photovoltaic access capacity allocation method. For details, see Figure 1~Figure 2 , Figure 1 FIG. 1 is a flow chart of a photovoltaic access capacity allocation method in one embodiment of the present invention. Figure 2 The figure shows a schematic diagram of obtaining the user's photovoltaic access capacity allocation value in one embodiment of the present invention.

[0056] A flowchart of a photovoltaic access capacity allocation method in one embodiment of the present invention includes the following steps S1 to S5, which are specifically as follows:

[0057] Step S1: Collect historical photovoltaic power generation data, historical load data and user voltage data of each user in each time period for each substation on all medium and low voltage lines.

[0058] It should be noted that when allocating photovoltaic access capacity, by analyzing historical photovoltaic power generation data and load data, the photovoltaic access capacity of each substation in different time periods can be evaluated, and by analyzing user voltage data, the impact of photovoltaic power access on user voltage can be evaluated.

[0059] Specifically, the historical photovoltaic power generation data, historical load data and user voltage data of each user in each time period of each substation on all medium and low voltage lines are collected, and data cleaning and outlier processing are performed on all collected data.

[0060] Step S2: extract features from all historical photovoltaic power generation data and all historical load data of each substation in each time period to obtain a feature vector of each substation in each time period.

[0061] It should be noted that the characteristic vector includes the fluctuation amplitude of photovoltaic power generation, the mean value of photovoltaic power generation, the photovoltaic load ratio, the load fluctuation amplitude and the load mean value.

[0062] Specifically, the difference between the maximum value and the corresponding minimum value of all historical photovoltaic power generation data of each substation in each time period is taken as the photovoltaic power generation fluctuation amplitude of each substation in each time period, and the average value of all historical photovoltaic power generation data of each substation in each time period is taken as the mean photovoltaic power generation of each substation in each time period.

[0063] The difference between the maximum value and the corresponding minimum value of all historical load data of each substation in each time period is taken as the load fluctuation amplitude of each substation in each time period, and the average value of all historical load data of each substation in each time period is taken as the load mean of each substation in each time period.

[0064] The ratio of the average photovoltaic power generation to the corresponding average load is taken as the photovoltaic load ratio of each substation in each time period.

[0065] Step S3: Perform cluster analysis on all medium and low voltage lines using all feature vectors to obtain photovoltaic access scenarios of target medium and low voltage lines, and predict the corresponding photovoltaic access capacity of the lines based on the photovoltaic access scenarios of target medium and low voltage lines.

[0066] It should be noted that, considering that photovoltaic power generation and load characteristics vary significantly depending on the region, time and conditions, in order to conduct targeted analysis of the target medium and low voltage lines to improve the accuracy of the allocation of photovoltaic access capacity, a cluster analysis is performed on all medium and low voltage lines to obtain the photovoltaic access scenarios of the target medium and low voltage lines.

[0067] Specifically, all feature vectors of all medium and low voltage lines are used as the input of the spectral clustering algorithm, and the spectral clustering algorithm is used to divide the photovoltaic access scenarios of all medium and low voltage lines into four typical photovoltaic access scenarios: high load and high fluctuation scenario, low load and low fluctuation scenario, photovoltaic intensive scenario and high load and low fluctuation scenario.

[0068] It should be noted that the spectral clustering algorithm is based on graph theory. The spectral clustering algorithm converts the clustering problem into a graph partitioning problem. The spectral clustering algorithm has significant advantages over the traditional clustering algorithm. The spectral clustering algorithm is a well-known technology and will not be described in detail in this embodiment. The high-load and high-fluctuation scenario represents a scenario where the load fluctuates greatly and the photovoltaic power fluctuates frequently; the low-load and low-fluctuation scenario represents a scenario where the photovoltaic power fluctuates less and the load is relatively stable; the photovoltaic-intensive scenario represents a scenario where the photovoltaic power is high, but the load is relatively stable and the voltage fluctuates greatly; the high-load and low-fluctuation scenario represents a scenario where the load is continuously high and the voltage fluctuates less.

[0069] As an embodiment of the present application, based on the photovoltaic access scenario of the target medium and low voltage lines, a long short-term memory network model is used to predict the line photovoltaic access capacity of the target medium and low voltage lines.

[0070] It should be noted that the long short-term memory network model is a special recurrent neural network structure that can capture long-term dependencies in time series, thereby making accurate predictions. The long short-term memory network model is a well-known technology and will not be described in detail in this embodiment.

[0071] Step S4: Perform a first nonlinear mapping association process on each substation and line photovoltaic access capacity to obtain a substation photovoltaic access capacity allocation value for each substation.

[0072] It should be noted that the first nonlinear mapping association process is designed to allocate the photovoltaic access capacity of the line according to the first allocation standard formed by the historical photovoltaic power generation data and the historical load data.

[0073] Specifically, the nighttime load data of each substation is counted and the voltage quality index of each substation is calculated; the nighttime load data of each substation and the corresponding voltage quality index are weighted and summed to obtain the comprehensive weighted score of each substation; the comprehensive weighted scores of all substations are normalized to obtain the normalized photovoltaic access ratio of each substation; the product of the normalized photovoltaic access ratio of each substation and the photovoltaic access capacity of the line is used as the substation photovoltaic access capacity allocation value of each substation.

[0074] Furthermore, after obtaining the photovoltaic access capacity allocation value of each substation, the photovoltaic access capacity allocation value of each substation is optimized.

[0075] Specifically, a secondary chaotic polynomial agent model of each substation is constructed according to the historical photovoltaic power generation data and historical load data of each substation in all time periods; the secondary chaotic polynomial agent model of the substation is used to process the photovoltaic access capacity allocation value of each substation, and output the first voltage amplitude of each substation.

[0076] If the first voltage amplitude of all substations does not meet the voltage constraint of the target medium and low voltage lines, the product of the line photovoltaic access capacity and the preset first reduction coefficient is used as the updated line photovoltaic access capacity, and the first nonlinear mapping association processing is performed on each substation and the updated line photovoltaic access capacity to optimize the substation photovoltaic access capacity allocation value of each substation; if the first voltage amplitude of all substations meets the voltage constraint of the target medium and low voltage lines, the substation photovoltaic access capacity allocation value of each substation is output.

[0077] In this step, the specific method for constructing a secondary chaotic polynomial agent model for the substation based on the historical photovoltaic power generation data and historical load data of each substation in all time periods is as follows: based on the historical photovoltaic power generation data and historical load data of each substation in all time periods, the minimum angle regression algorithm is used to optimize and analyze the key basis functions and regression coefficients of the chaotic polynomial expansion agent model to obtain the primary chaotic polynomial agent model for the substation; based on the historical photovoltaic power generation data and historical load data of each substation in all time periods, the substation data fitting residuals of the primary chaotic polynomial agent model for the substation at all truncation orders are calculated, and the secondary chaotic polynomial agent model for the substation is obtained based on the sorting results of the data fitting residuals of all substations.

[0078] It should be noted that the chaotic polynomial expansion agent model is based on the orthogonal polynomial theory. The core idea of ​​the chaotic polynomial expansion agent model is to use the excellent performance of orthogonal polynomials to establish an agent model through the mapping process of random variable input to response. The chaotic polynomial expansion agent model is a well-known technology and will not be described in detail in this embodiment. By adopting a data-driven chaotic polynomial expansion agent model, the dependence of traditional photovoltaic capacity allocation methods on power system topology and load models is avoided, and the complexity of photovoltaic access scenarios can be better adapted.

[0079] Step S5: performing a second nonlinear mapping association process on the photovoltaic access capacity allocation value of each substation and the user voltage data of all users in each substation to obtain the photovoltaic access capacity allocation value of each user.

[0080] It should be noted that the second nonlinear mapping association process is designed to allocate the corresponding photovoltaic access capacity allocation value of the substation according to the second allocation standard formed by the user voltage data.

[0081] Specifically, the user voltage data of each user is normalized to obtain the normalized photovoltaic access ratio of each user; the product of the normalized photovoltaic access ratio of each user and the corresponding photovoltaic access capacity allocation value of the substation is used as the user photovoltaic access capacity allocation value of each user.

[0082] Furthermore, after obtaining the user photovoltaic access capacity allocation value of each user, the user photovoltaic access capacity allocation value of each user is optimized.

[0083] Specifically, a user secondary chaotic polynomial agent model is constructed according to the user voltage data of all users in each substation; the user secondary chaotic polynomial agent model is used to process the user photovoltaic access capacity allocation value of each user, and the second voltage amplitude of each user is output.

[0084] If the second voltage amplitude of all users does not meet the voltage constraint of the corresponding substation, the product of the substation photovoltaic access capacity allocation value of each substation and the preset second reduction coefficient is used as the updated substation photovoltaic access capacity allocation value of each substation, and the updated substation photovoltaic access capacity allocation value of each substation and the user voltage data of all users in each substation are subjected to a second nonlinear mapping association process to optimize the user photovoltaic access capacity allocation value of each user; if the second voltage amplitude of all users meets the voltage constraint of the corresponding substation, the user photovoltaic access capacity allocation value of each user is output.

[0085] In this step, the specific method for constructing a user-secondary chaotic polynomial agent model based on the user voltage data of all users in each substation is as follows: based on the user voltage data of all users in each substation, the minimum angle regression algorithm is used to optimize and analyze the key basis functions and regression coefficients of the chaotic polynomial expansion agent model to obtain a user-first-level chaotic polynomial agent model; based on the user voltage data of all users in each substation, the user data fitting residuals of the user-first-level chaotic polynomial agent model at all truncation orders are calculated, and the user-secondary chaotic polynomial agent model is obtained based on the sorting results of the fitting residuals of all user data.

[0086] Another embodiment of the present invention provides a photovoltaic access capacity allocation system, the system comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements a photovoltaic access capacity allocation method as described above when executing the computer program.

[0087] A photovoltaic access capacity allocation method and system provided by an embodiment of the present invention has the following beneficial effects compared with the prior art:

[0088] (1) Collect historical photovoltaic power generation data, historical load data and user voltage data of each user in each time period of each substation on all medium and low voltage lines, perform feature extraction on all historical photovoltaic power generation data and all historical load data of each substation in each time period, and obtain the feature vector of each substation in each time period to evaluate the photovoltaic power generation characteristics and load characteristics of each substation;

[0089] (2) Considering that the characteristics of photovoltaic power generation and load vary significantly depending on the region, time and conditions, all medium and low voltage lines are clustered and analyzed with all feature vectors to obtain the photovoltaic access scenarios of the target medium and low voltage lines. The corresponding photovoltaic access capacity of the lines is predicted based on the photovoltaic access scenarios of the target medium and low voltage lines. All medium and low voltage lines are divided into different photovoltaic access scenarios through clustering, and the corresponding photovoltaic access capacity of the lines is predicted according to the photovoltaic access scenarios to which the target medium and low voltage lines belong, thereby improving the accuracy of the allocation of photovoltaic access capacity.

[0090] (3) Performing a first nonlinear mapping association process on the photovoltaic access capacity of each substation and line to obtain the substation photovoltaic access capacity allocation value of each substation, and the first nonlinear mapping association process is designed to allocate the line photovoltaic access capacity according to the first allocation standard formed by historical photovoltaic power generation data and historical load data; performing a second nonlinear mapping association process on the substation photovoltaic access capacity allocation value of each substation and the user voltage data of all users in each substation to obtain the user photovoltaic access capacity allocation value of each user, and the second nonlinear mapping association process is designed to allocate the corresponding substation photovoltaic access capacity allocation value according to the second allocation standard formed by the user voltage data; using a double-layer allocation method to allocate the line photovoltaic access capacity layer by layer to the substation and the end user, ensuring that the upper limit of the photovoltaic access capacity of each node is reasonably allocated, thereby improving the allocation accuracy of the photovoltaic access capacity;

[0091] (4) The PV access scenarios are divided by clustering method, and targeted quantitative analysis is carried out according to the characteristics of the PV access scenarios to which the target medium and low voltage lines belong. The PV access capacity of the lines is allocated layer by layer to the substations and end users in combination with the two-layer allocation method, so as to more accurately evaluate the PV access capacity and comprehensively improve the allocation accuracy of the PV access capacity.

[0092] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A photovoltaic access capacity allocation method, characterized in that: The method comprises: Collect historical photovoltaic power generation data, historical load data and user voltage data of each user in each time period for each substation on all medium and low voltage lines; Performing feature extraction on all the historical photovoltaic power generation data and all the historical load data of each of the substations in each of the time periods to obtain a feature vector of each of the substations in each of the time periods; Performing cluster analysis on all the medium and low voltage lines using all the feature vectors to obtain photovoltaic access scenarios of target medium and low voltage lines, and predicting the corresponding photovoltaic access capacity of the lines based on the photovoltaic access scenarios of the target medium and low voltage lines; A first nonlinear mapping association process is performed on each of the substations and the photovoltaic access capacity of the line to obtain a substation photovoltaic access capacity allocation value for each of the substations; the first nonlinear mapping association process is designed to allocate the photovoltaic access capacity of the line according to a first allocation standard formed by the historical photovoltaic power generation data and the historical load data; A second nonlinear mapping association process is performed on the photovoltaic access capacity allocation value of each of the substations and the user voltage data of all the users in each of the substations to obtain a user photovoltaic access capacity allocation value for each of the users; the second nonlinear mapping association process is designed to allocate the photovoltaic access capacity allocation value of the corresponding substation according to a second allocation standard formed by the user voltage data.

2. A photovoltaic access capacity allocation method according to claim 1, characterized in that: After obtaining the photovoltaic access capacity allocation value of each of the substations, the method further includes: Constructing a secondary chaotic polynomial agent model for each substation according to the historical photovoltaic power generation data and the historical load data of each substation in all the time periods; The substation secondary chaotic polynomial agent model is used to process the substation photovoltaic access capacity allocation value of each substation, and the first voltage amplitude of each substation is output; If the first voltage amplitude of all the substations does not meet the voltage constraint of the target medium and low voltage lines, the product of the photovoltaic access capacity of the line and the preset first reduction coefficient is used as the updated photovoltaic access capacity of the line, and the first nonlinear mapping association processing is performed on each of the substations and the updated photovoltaic access capacity of the line, so as to optimize the photovoltaic access capacity allocation value of each substation; If the first voltage amplitudes of all the substations meet the voltage constraints of the target medium and low voltage lines, the substation photovoltaic access capacity allocation value of each substation is output.

3. A photovoltaic access capacity allocation method according to claim 2, characterized in that: The step of constructing a secondary chaotic polynomial agent model for each substation according to the historical photovoltaic power generation data and the historical load data in all the time periods includes: According to the historical photovoltaic power generation data and the historical load data of each substation in all the time periods, the key basis functions and regression coefficients of the chaotic polynomial expansion agent model are optimized and analyzed using the minimum angle regression algorithm to obtain a primary chaotic polynomial agent model of the substation; The substation data fitting residuals of the first-level chaotic polynomial proxy model of the substation at all truncation orders are calculated according to the historical photovoltaic power generation data and the historical load data of each substation in all the time periods, and the substation second-level chaotic polynomial proxy model is obtained based on the sorting results of all the substation data fitting residuals.

4. A photovoltaic access capacity allocation method according to claim 1, characterized in that: The step of performing a first nonlinear mapping association process on each of the substations and the photovoltaic access capacity of the line to obtain a substation photovoltaic access capacity allocation value for each of the substations includes: Counting the nighttime load data of each of the substations, and calculating the voltage quality index of each of the substations; Performing weighted summation on the nighttime load data of each of the substations and the corresponding voltage quality index to calculate a comprehensive weighted score for each of the substations; normalizing the comprehensive weighted scores of all the substations to obtain a normalized photovoltaic access ratio for each of the substations; The product of the normalized photovoltaic access ratio of each substation and the photovoltaic access capacity of the line is used as the substation photovoltaic access capacity allocation value of each substation.

5. A photovoltaic access capacity allocation method according to claim 1, characterized in that: After obtaining the user photovoltaic access capacity allocation value of each user, the method further includes: Constructing a user secondary chaotic polynomial agent model according to the user voltage data of all the users in each of the substations; The user secondary chaotic polynomial agent model is used to process the user photovoltaic access capacity allocation value of each user, and output a second voltage amplitude of each user; If the second voltage amplitude of all the users does not meet the voltage constraint of the corresponding substation, the product of the substation photovoltaic access capacity allocation value of each substation and the preset second reduction coefficient is used as the updated substation photovoltaic access capacity allocation value of each substation, and the second nonlinear mapping association processing is performed on the updated substation photovoltaic access capacity allocation value of each substation and the user voltage data of all the users in each substation, so as to optimize the user photovoltaic access capacity allocation value of each user; If the second voltage amplitudes of all the users meet the voltage constraints of the corresponding substations, the user photovoltaic access capacity allocation value of each user is output.

6. A photovoltaic access capacity allocation method according to claim 5, characterized in that: The step of constructing a user secondary chaotic polynomial agent model based on the user voltage data of all the users in each of the substations comprises: According to the user voltage data of all the users in each of the substations, a minimum angle regression algorithm is used to optimize and analyze the key basis functions and regression coefficients of the chaotic polynomial expansion agent model to obtain a user first-level chaotic polynomial agent model; The user data fitting residuals of the user first-level chaotic polynomial proxy model at all truncation orders are calculated according to the user voltage data of all the users in each of the substations, and the user second-level chaotic polynomial proxy model is obtained based on the sorting results of all the user data fitting residuals.

7. A photovoltaic access capacity allocation method according to claim 1, characterized in that: The step of performing a second nonlinear mapping association process on the photovoltaic access capacity allocation value of each of the substations and the user voltage data of all the users in each of the substations to obtain the photovoltaic access capacity allocation value of each of the users includes: Normalizing the user voltage data of each user to obtain a normalized photovoltaic access ratio of each user; The product of the normalized photovoltaic access ratio of each user and the corresponding photovoltaic access capacity allocation value of the substation is used as the user photovoltaic access capacity allocation value of each user.

8. A photovoltaic access capacity allocation method according to claim 1, characterized in that: The characteristic vectors include the photovoltaic power generation fluctuation amplitude, the photovoltaic power generation mean value, the photovoltaic load ratio, the load fluctuation amplitude and the load mean value; The feature extraction of all the historical photovoltaic power generation data and all the historical load data of each substation in each time period to obtain the feature vector of each substation in each time period includes: The difference between the maximum value and the corresponding minimum value of all the historical photovoltaic power generation data of each of the stations in each of the time periods is used as the photovoltaic power generation fluctuation amplitude of each of the stations in each of the time periods; Taking the average value of all the historical photovoltaic power generation data of each of the stations in each of the time periods as the average photovoltaic power generation value of each of the stations in each of the time periods; Taking the difference between the maximum value and the corresponding minimum value of all the historical load data of each substation in each time period as the load fluctuation amplitude of each substation in each time period; Taking the average value of all the historical load data of each substation in each time period as the load mean value of each substation in each time period; The ratio of the photovoltaic power generation average value to the corresponding load average value is used as the photovoltaic load ratio of each of the substations in each of the time periods.

9. A photovoltaic access capacity allocation method according to claim 1, characterized in that: The photovoltaic access scenarios include high-load and high-fluctuation scenarios, low-load and low-fluctuation scenarios, photovoltaic-intensive scenarios, and high-load and low-fluctuation scenarios.

10. A photovoltaic access capacity allocation system, characterized in that: The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, a photovoltaic access capacity allocation method as described in any one of claims 1 to 9 is implemented.

Images