Load characteristic driven power balance adjusting method

Abstract

The invention discloses an electric power balance adjustment method driven by load characteristics, relates to the technical field related to electric power distribution, and determines K electric power sub-regions by obtaining installation information and repair records of a user and combining line planning information to divide a target region. The method comprises the following steps: acquiring transformer operation data, performing fluctuation coefficient analysis, determining K transformer fluctuation coefficient sets, performing transformer centralized fluctuation analysis, determining K centralized fluctuation coefficients, and determining K common regulatory factors; traversing the K power sub-regions to collect power consumption data of the users to obtain a power consumption data set of the K users, performing load fluctuation stability analysis, and determining a regulation factor set of the K users; and obtaining a power supply data set, and performing power balance adjustment scheme configuration in combination with the K common adjustment factors and the K user adjustment factor sets to obtain a target power balance adjustment scheme. The technical problems of low adjustment precision and poor stability of an electric power balance adjustment method in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the technical field related to power distribution, and specifically to a power balance adjustment method driven by load characteristics. Background Art

[0002] The operating conditions of transformers and load fluctuations in the power system are important factors affecting power balance regulation. In the prior art, power companies mainly rely on users' repair records, installation information and basic line planning information to maintain and manage regional power supply. However, due to the lack of effective fluctuation analysis tools and user load stability analysis mechanisms, the prior art is insufficient in terms of accuracy and stability of power balance regulation.

[0003] Therefore, the power balance adjustment method in the prior art has technical problems of low adjustment accuracy and poor stability. Summary of the invention

[0004] This application solves the technical problems of low regulation accuracy and poor stability in the existing power balance regulation methods by providing a load characteristic driven power balance regulation method. By accurately dividing the power sub-areas and analyzing the transformer fluctuation coefficient, the concentrated fluctuation coefficient and common regulation factor of each area are determined, and then the power balance regulation scheme is optimized, the stability of the power grid and the power supply reliability are improved, and the technical effect of completing power balance regulation efficiently and accurately is achieved.

[0005] The present application provides a load characteristic driven power balance adjustment method, the method comprising: obtaining user registration information and repair records of a target area, dividing the target area into sub-areas in combination with the line planning information of the target area, and determining K power sub-areas, wherein K is an integer greater than or equal to 1. Collecting transformer operation data of the K power sub-areas within a preset time window, and performing fluctuation coefficient analysis on the obtained K transformer operation data sets according to a preset fluctuation index set, and determining K transformer fluctuation coefficient sets. Traversing the K transformer fluctuation coefficient sets to perform transformer concentrated fluctuation analysis, determine K concentrated fluctuation coefficients, and determine K public adjustment factors based on the K concentrated fluctuation coefficients. Traversing the K power sub-areas to collect user power consumption data, obtain K user power consumption data sets, perform user load fluctuation stability analysis on the K user power consumption data sets, and determine K user adjustment factor sets. Obtaining the power supply data set of the target area within the preset adjustment window, configuring a power balance adjustment scheme in combination with the K public adjustment factors and the K user adjustment factor sets, and obtaining a target power balance adjustment scheme.

[0006] In an implementation, the preset fluctuation index set includes voltage deviation, grid frequency deviation and voltage operation fluctuation.

[0007] In the implementation, the transformer operation data of the K power sub-areas within the preset time window are collected, and the fluctuation coefficient analysis is performed on the obtained K transformer operation data sets according to the preset fluctuation index set to determine the K transformer fluctuation coefficient sets, including: searching the K transformer operation data sets according to the preset fluctuation index set to determine K voltage deviation mean sets, K grid frequency deviation mean sets and K voltage operation fluctuation mean sets. A transformer fluctuation identifier is constructed, and the transformer fluctuation identifier is used to perform transformer fluctuation identification on the K voltage deviation mean sets, the K grid frequency deviation mean sets and the K voltage operation fluctuation mean sets respectively to obtain the K transformer fluctuation coefficient sets.

[0008] In the implementation method, the K transformer fluctuation coefficient sets are traversed to perform transformer concentrated fluctuation analysis, K concentrated fluctuation coefficients are determined, and K common adjustment factors are determined based on the K concentrated fluctuation coefficients, including: constructing K fluctuation analysis spaces based on the K transformer fluctuation coefficient sets, wherein the K fluctuation analysis spaces include K fluctuation particle sets, and each fluctuation particle corresponds to a transformer fluctuation coefficient. Extracting K spatial center particles of the K fluctuation analysis spaces, taking the K spatial center particles as the starting point, iterating in the K fluctuation analysis spaces according to a preset fluctuation iteration step until the preset number of iterations is met, and obtaining K target fluctuation particles. Taking the K target fluctuation particles as the sphere center and the preset fluctuation iteration step as the sphere radius, constructing K target fluctuation spherical subspaces, and performing mean processing on the transformer fluctuation coefficients contained in the K target fluctuation spherical subspaces, and obtaining K concentrated fluctuation coefficients.

[0009] In the implementation, extracting K spatial center particles of the K fluctuation analysis spaces, taking the K spatial center particles as the starting point, iterating in the K fluctuation analysis spaces according to a preset fluctuation iteration step length until a preset number of iterations is met, and obtaining K target fluctuation particles, includes: taking the K spatial center particles as the starting point, iterating in the K fluctuation analysis spaces according to a preset fluctuation iteration step length, and obtaining K iterative fluctuation particles. When the particle aggregation density of the K iterative fluctuation particles is greater than or equal to the particle aggregation density of the K spatial center particles, updating the K iterative fluctuation particles as the starting point, continuing to iterate according to the preset fluctuation iteration step length until a preset number of iterations is met, and taking the K iterative fluctuation particles corresponding to the maximum value of the particle aggregation density during the iteration as the K target fluctuation particles.

[0010] In the implementation method, when the particle aggregation density of the K iterative fluctuating particles is less than the particle aggregation density of the K space center particles, the K iterative fluctuating particles are updated as the starting point according to the preset acceptance probability, and the iteration is continued according to the preset fluctuation iteration step until the preset number of iterations is met, and the K iterative fluctuating particles corresponding to the maximum value of the particle aggregation density during the iteration process are respectively used as K target fluctuating particles.

[0011] In the implementation method, the ratios of the K concentrated fluctuation coefficients to the sum of the K concentrated fluctuation coefficients are calculated respectively, and the K common adjustment factors are obtained according to the calculation results.

[0012] In the implementation, the power supply data of the target area and the K power output data sets of the K power sub-areas at the current moment are obtained, and the power balance adjustment scheme is optimized in combination with the K public adjustment factors and the K user adjustment factor sets to obtain the target power balance adjustment scheme, including: performing stability authentication on the power supply data set, and obtaining an adjustment instruction if the authentication passes. A scheme configurator is called according to the adjustment instruction, and the scheme configurator is used to perform scheme analysis on the power supply data set, the K public adjustment factors and the K user adjustment factor sets to determine the target power balance adjustment scheme.

[0013] The load characteristic driven power balance adjustment method proposed in this application is proposed to obtain the user registration information and repair record of the target area, and divide the target area into sub-areas in combination with the line planning information of the target area, and determine K power sub-areas, where K is an integer greater than or equal to 1. Collect the transformer operation data of the K power sub-areas within the preset time window, and perform fluctuation coefficient analysis on the obtained K transformer operation data sets according to the preset fluctuation index set to determine K transformer fluctuation coefficient sets. Traverse the K transformer fluctuation coefficient sets to perform transformer concentrated fluctuation analysis, determine K concentrated fluctuation coefficients, and determine K public adjustment factors based on the K concentrated fluctuation coefficients. Traverse the K power sub-areas to collect user power consumption data, obtain K user power consumption data sets, perform user load fluctuation stability analysis on the K user power consumption data sets, and determine K user adjustment factor sets. Obtain the power supply data set of the target area within the preset adjustment window, and configure the power balance adjustment scheme in combination with the K public adjustment factors and the K user adjustment factor sets to obtain the target power balance adjustment scheme. The technical problems of low regulation accuracy and poor stability in the existing power balance regulation method are solved. By accurately dividing the power sub-areas and analyzing the transformer fluctuation coefficient, the concentrated fluctuation coefficient and common regulation factor of each area are determined, and then the power balance regulation scheme is optimized, the stability of the power grid and the power supply reliability are improved, and the technical effect of completing power balance regulation efficiently and accurately is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of a flow chart of a load characteristic driven power balance adjustment method provided in an embodiment of the present application; Figure 2 A schematic diagram of a flow chart of obtaining a set of K transformer fluctuation coefficients by a load characteristic driven power balance adjustment method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0017] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0018] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0019] The present application provides a load characteristic driven power balance adjustment method, such as Figure 1 As shown, the method includes: Obtain user installation information and repair records in the target area, divide the target area into sub-areas in combination with the line planning information of the target area, and determine K power sub-areas, where K is an integer greater than or equal to 1. Collect transformer operation data of the K power sub-areas within a preset time window, and perform fluctuation coefficient analysis on the obtained K transformer operation data sets according to a preset fluctuation index set to determine K transformer fluctuation coefficient sets. Traverse the K transformer fluctuation coefficient sets to perform transformer concentrated fluctuation analysis, determine K concentrated fluctuation coefficients, and determine K common adjustment factors based on the K concentrated fluctuation coefficients.

[0020] The user registration information and repair records of the target area are obtained. The user registration information is the equipment installation information submitted by the user to the power company. The power supply plan is executed according to the actual situation of the target area to complete the final registration node, including the equipment installation location, type, etc. The user repair record refers to the repair information submitted by the user in the target area that needs to perform power balance adjustment to the power company due to power failure or abnormality, including the fault time, location, type, etc. The target area is divided into sub-areas in combination with the line planning information of the target area. When dividing the sub-areas, according to the line planning, a division is performed according to the area covered by the main line, and the coverage area is divided into multiple independent minimum power supply division areas. There is only one transformer in each minimum power supply division area. Then, according to the user registration information and repair record, the result of the first division is divided twice according to the actual user registration capacity and the number of repairs. If the user registration capacity and the number of repairs in a segment area are small, it can be combined with other segment areas to form a larger sub-area. If the user registration capacity and the number of repairs in the segment area are large, then it is taken as a separate sub-area to determine K power sub-areas, where K is a constant. For example, during the secondary division, by setting the reported capacity division threshold and the repair number division threshold, multiple adjacent areas that do not meet the reported capacity division threshold and the repair number division threshold are combined to obtain a combined area that meets the reported capacity division threshold and the repair number division threshold. The area that meets the reported capacity division threshold and the repair number division threshold is treated as a separate area.

[0021] Subsequently, the transformer operation data of the K power sub-areas within a preset time window are collected at a fixed sampling frequency. The preset time window is a preset time interval such as a week, a day or a month and a sampling frequency. The transformer operation data includes real-time operation parameters such as voltage, current, power, and temperature. The K transformer operation data sets obtained are subjected to fluctuation coefficient analysis according to a preset fluctuation index set to determine K transformer fluctuation coefficient sets. Among them, the preset fluctuation index set includes voltage deviation, grid frequency deviation, and voltage operation fluctuation. Further, the K transformer fluctuation coefficient sets are traversed to perform transformer concentrated fluctuation analysis, determine K concentrated fluctuation coefficients, and determine K common adjustment factors based on the K concentrated fluctuation coefficients.

[0022] like Figure 2As shown, the method provided in the embodiment of the present application also includes: searching the K transformer operation data sets according to the preset fluctuation index set to determine K voltage deviation mean sets, K grid frequency deviation mean sets and K voltage operation fluctuation mean sets. Constructing a transformer fluctuation identifier, using the transformer fluctuation identifier to perform transformer fluctuation identification on the K voltage deviation mean sets, the K grid frequency deviation mean sets and the K voltage operation fluctuation mean sets respectively, and obtaining the K transformer fluctuation coefficient sets.

[0023] The transformer operation data of the K power sub-areas within the preset time window are collected, and the fluctuation coefficient analysis is performed on the obtained K transformer operation data sets according to the preset fluctuation index set to determine the K transformer fluctuation coefficient sets, including: searching the K transformer operation data sets according to the preset fluctuation index set to determine K voltage deviation mean value sets, K grid frequency deviation mean value sets and K voltage operation fluctuation mean value sets. The voltage deviation mean value is the average value of the difference between the actual voltage and the rated voltage within the preset time window, the transformer voltage deviation mean values ​​in multiple same areas form a voltage deviation mean value set, the grid frequency deviation mean value is the average value of the difference between the actual frequency and the standard frequency (such as 50Hz) within the preset time window, and the transformer grid frequency deviation mean values ​​in multiple same areas form a grid frequency deviation mean value set. The voltage operation fluctuation mean value is the variance value of the transformer voltage fluctuation within the preset time window, and the transformer voltage operation fluctuation mean values ​​in multiple same areas form a voltage operation fluctuation mean value set.

[0024] Furthermore, a transformer fluctuation identifier is constructed, and the transformer fluctuation identifier is used to perform transformer fluctuation identification on a set of data in the K voltage deviation mean value sets, the K grid frequency deviation mean value sets, and the K voltage operation fluctuation mean value sets, respectively, wherein a set of data includes a voltage deviation mean value, a grid frequency deviation mean value, and a voltage operation fluctuation mean value. The K transformer fluctuation coefficient sets are obtained, wherein each transformer fluctuation coefficient corresponds to a transformer in a power sub-area.

[0025] Exemplarily, data of a transformer is randomly extracted from the K voltage deviation mean sets, the K grid frequency deviation mean sets, and the K voltage operation fluctuation mean sets to obtain a first voltage deviation mean set, a first grid frequency deviation mean set, and a first voltage operation fluctuation mean set, forming a first fluctuation data matrix of the first transformer within a preset time window, such as: ; in, is the first wave data matrix, is the total number of samples collected by the first transformer within the preset time window, is an integer greater than or equal to 1, For the The first voltage deviation mean value of the first transformer during the first acquisition, For the The first grid frequency deviation mean of the first transformer during the first acquisition, For the The first voltage operation fluctuation mean of the first transformer during the first acquisition, and each column vector represents the fluctuation vector of the first transformer during the first acquisition.

[0026] The expression of the transformer fluctuation identifier is: ; in, The length is No. A set of transformer fluctuation coefficients, is a weight vector pre-set by a person skilled in the art, For the The fluctuation data matrix of the transformer, is less than or equal to A positive integer.

[0027] The first fluctuation data matrix is ​​input into the transformer fluctuation identifier for analysis to obtain a first transformer fluctuation coefficient set of the first transformer, wherein the first transformer fluctuation coefficient set is = .

[0028] Based on the same principle as obtaining the first transformer fluctuation coefficient set, the K transformer fluctuation coefficient sets are obtained, specifically: , is an integer greater than or equal to 1, where The set of transformer fluctuation coefficients is described as = ,in, is less than or equal to A positive integer.

[0029] Among them, when constructing the transformer fluctuation identifier, historical fluctuation identification data is obtained, and the historical fluctuation identification data includes multiple voltage deviation means, multiple grid frequency deviation means, multiple voltage operation fluctuation means, and corresponding transformer fluctuation coefficients. Multiple voltage deviation means, multiple grid frequency deviation means, and multiple voltage operation fluctuation means are used as training data, and the corresponding transformer fluctuation coefficients are used as supervision data to perform supervised training on the neural network model until the output accuracy of the model meets the requirements, and then the trained model is obtained to obtain the transformer fluctuation identifier.

[0030] The method provided in the embodiment of the present application also includes: constructing K fluctuation analysis spaces based on the K transformer fluctuation coefficient sets, wherein the K fluctuation analysis spaces include K fluctuation particle sets, and each fluctuation particle corresponds to a transformer fluctuation coefficient. Extracting the K spatial center particles of the K fluctuation analysis spaces, taking the K spatial center particles as the starting point, iterating in the K fluctuation analysis spaces according to a preset fluctuation iteration step until the preset number of iterations is met, and obtaining K target fluctuation particles. Taking the K target fluctuation particles as the sphere center and the preset fluctuation iteration step as the sphere radius, constructing K target fluctuation spherical subspaces, and performing mean processing on the transformer fluctuation coefficients contained in the K target fluctuation spherical subspaces, and obtaining K concentrated fluctuation coefficients.

[0031] In one possible embodiment, a fluctuation analysis space is constructed for each transformer fluctuation coefficient set, which is described as: ,in, To express the A set of transformer fluctuation coefficients, that is, The relevant analysis space, represents a wave particle in the wave analysis space, The wave particle is The vector represented by .

[0032] Preferably, in any wave analysis space, when the particles iterate according to the preset wave iteration step, the following formula is satisfied: ,in, is the spatial center particle of the ith wave analysis space, is the target wave particle after iteration of the spatial center particle of the i-th wave analysis space, It is an iterative movement vector of a random direction constructed based on the length of the preset wave iteration step at each iteration. The one-to-one mapping relationship between the transformer fluctuation coefficient and The corresponding transformer fluctuation coefficient is taken as the concentrated fluctuation coefficient .

[0033] Traversing the K transformer fluctuation coefficient sets to perform transformer concentrated fluctuation analysis, determining K concentrated fluctuation coefficients, and determining K common adjustment factors based on the K concentrated fluctuation coefficients, including: constructing K fluctuation analysis spaces based on the K transformer fluctuation coefficient sets, wherein the K fluctuation analysis spaces include K fluctuation particle sets, and each fluctuation particle corresponds to a transformer fluctuation coefficient. Extracting K spatial center particles of the K fluctuation analysis spaces, the spatial center particles are the center positions of the fluctuation particles, that is, the parameters closest to the parameter mean in the transformer fluctuation coefficient set. Taking the K spatial center particles as the starting point, iterating in the K fluctuation analysis spaces according to the preset fluctuation iteration step length, the preset fluctuation iteration step length is the parameter traversal step length of the preset fluctuation analysis space. Until the preset number of iterations is met, K target fluctuation particles are obtained. Finally, taking the K target fluctuation particles as the sphere center and the preset fluctuation iteration step length as the sphere radius, K target fluctuation spherical subspaces are constructed, that is, obtaining the area with the target fluctuation particle as the center and the preset fluctuation iteration step length as the radius, and obtaining the target fluctuation spherical subspace. The transformer fluctuation coefficients contained in the K target fluctuation ball subspaces are averaged, the average of each target fluctuation ball subspace is obtained, and K concentrated fluctuation coefficients are obtained.

[0034] Preferably, the process of determining K common adjustment factors according to the K concentrated fluctuation coefficients is described as follows: ; in, is the common adjustment factor corresponding to the i-th transformer, is the concentrated fluctuation coefficient corresponding to the i-th transformer, and K is the total number of transformers.

[0035] The method provided by the embodiment of the present application also includes: starting from the K spatial center particles, iterating in the K fluctuation analysis spaces according to a preset fluctuation iteration step length to obtain K iterative fluctuation particles. When the particle aggregation density of the K iterative fluctuation particles is greater than or equal to the particle aggregation density of the K spatial center particles, the K iterative fluctuation particles are updated as the starting point, and the iterative step length is continued to be iterated until the preset number of iterations is met, and the K iterative fluctuation particles corresponding to the maximum value of the particle aggregation density during the iteration are respectively used as K target fluctuation particles.

[0036] Extracting K spatial center particles of the K fluctuation analysis spaces, taking the K spatial center particles as the starting point, iterating in the K fluctuation analysis spaces according to the preset fluctuation iteration step, until the preset number of iterations is met, and obtaining K target fluctuation particles, including: taking the K spatial center particles as the starting point, iterating in the K fluctuation analysis spaces according to the preset fluctuation iteration step, obtaining K iterative fluctuation particles, wherein the iterative fluctuation particle is a random iterative fluctuation particle at the preset fluctuation iteration step. Constructing a region with the iterative fluctuation particle as the center and the preset fluctuation iteration step as the radius, obtaining all particles in the region, and calculating the particle aggregation density of the iterative fluctuation particle. The particle aggregation density is the ratio of the number of particles in the region to the area. Calculating the particle aggregation density of the spatial center particle, the particle aggregation density of the spatial center particle is to construct a region with the spatial center particle as the center and the preset fluctuation iteration step as the radius, obtaining all particles in the region, and calculating the particle aggregation density of the spatial center particle. When the particle aggregation density of the K iterative wave particles is greater than or equal to the particle aggregation density of the K spatial center particles, the K iterative wave particles are updated as the starting point, and the iteration is continued according to the preset fluctuation iteration step until the preset number of iterations is met, and the K iterative wave particles corresponding to the maximum value of the particle aggregation density during the iteration are respectively used as K target fluctuation particles. When the particle aggregation density of the K iterative wave particles is less than the particle aggregation density of the K spatial center particles, the K iterative wave particles are updated as the starting point according to the preset acceptance probability, and the preset acceptance probability is 60%, that is, there is a certain probability of non-acceptance. If not accepted, the iteration is stopped and the spatial center particle is used as the target fluctuation particle. If the K iterative wave particles are accepted to be updated as the starting point, the iteration is continued according to the preset fluctuation iteration step until the preset number of iterations is met, and the K iterative wave particles corresponding to the maximum value of the particle aggregation density during the iteration are respectively used as K target fluctuation particles.

[0037] Traverse the K power sub-areas to collect user power consumption data, obtain K user power consumption data sets, perform user load fluctuation stability analysis on the K user power consumption data sets, and determine K user adjustment factor sets. Obtain the power supply data set of the target area within the preset adjustment window, combine the K public adjustment factors and the K user adjustment factor sets to configure the power balance adjustment plan, and obtain the target power balance adjustment plan.

[0038] Traverse the K power sub-areas to collect user power consumption data, obtain the power consumption data of users in each power sub-area, and obtain K user power consumption data sets, each user power consumption data set contains the power consumption data of multiple users in the corresponding area obtained based on a fixed sampling interval in a preset time interval, and the power consumption data includes load data, power consumption, etc. Further, perform user load fluctuation stability analysis on the K user power consumption data sets, calculate the variance of the load data of each user, obtain the user adjustment factor set of the area, and then determine the K user adjustment factor sets. Finally, obtain the power supply data set of the target area within the preset adjustment window, and the power supply data set includes power supply reliability, power supply, etc. The power balance adjustment scheme is configured in combination with the K public adjustment factors and the K user adjustment factor sets to obtain a target power balance adjustment scheme, wherein when obtaining the K public adjustment factors, the ratio of the K concentrated fluctuation coefficients to the sum of the K concentrated fluctuation coefficients is calculated respectively, and the K public adjustment factors are obtained according to the calculation results. The larger the fluctuation coefficient, the larger the public adjustment factor, indicating that the area is unstable, so a larger redundancy amplitude should be used during adjustment to meet regional needs. The technical problems of low adjustment accuracy and poor stability in the power balance adjustment method in the prior art are solved. By accurately dividing the power sub-areas and analyzing the transformer fluctuation coefficient, the concentrated fluctuation coefficient and public adjustment factor of each area are determined, and then the power balance adjustment scheme is optimized, the stability of the power grid and the power supply reliability are improved, and the technical effect of completing power balance adjustment efficiently and accurately is achieved.

[0039] The method provided in the embodiment of the present application further includes: performing stability authentication on the power supply data set, and obtaining an adjustment instruction if the authentication passes. Calling a scheme configurator according to the adjustment instruction, using the scheme configurator to perform scheme analysis on the power supply data set, the K public adjustment factors, and the K user adjustment factor sets, and determining the target power balance adjustment scheme.

[0040] Extract the power supply reliability rate from the power supply data set, perform stability certification on the power supply reliability rate, and if the certification passes, that is, the power supply reliability rate meets the requirements, obtain the adjustment instruction. If the certification fails, that is, the power supply reliability rate does not meet the requirements, power supply feedback is performed. After obtaining the adjustment instruction, call the scheme configurator according to the adjustment instruction, and use the scheme configurator to perform scheme analysis on the power supply data set, the K public adjustment factors, and the K user adjustment factor sets to determine the target power balance adjustment scheme. The power balance adjustment scheme contains specific adjustment parameters for power grid generation, voltage, and power grid frequency. The scheme configurator is constructed based on a neural network model, and multiple historical power balance adjustment schemes and multiple adjustment scenarios corresponding to the adjustment schemes are obtained, including power supply data, public adjustment factors, and user adjustment factors. The multiple historical power balance adjustment schemes and the corresponding multiple adjustment scenarios are used as training data to supervise the neural network model for training, until the power balance adjustment scheme output by the model meets the preset accuracy requirements, the training is completed, and the scheme configurator is obtained.

[0041] The technical solution provided by the embodiment of the present invention obtains the user installation information and repair record of the target area, divides the target area into sub-areas in combination with the line planning information of the target area, and determines K power sub-areas, where K is an integer greater than or equal to 1. The transformer operation data of the K power sub-areas in the preset time window is collected, and the K transformer operation data sets obtained are analyzed for fluctuation coefficients according to the preset fluctuation index set to determine K transformer fluctuation coefficient sets. The K transformer fluctuation coefficient sets are traversed to perform transformer concentrated fluctuation analysis, determine K concentrated fluctuation coefficients, and determine K public adjustment factors based on the K concentrated fluctuation coefficients. The K power sub-areas are traversed to collect user power consumption data, obtain K user power consumption data sets, perform user load fluctuation stability analysis on the K user power consumption data sets, and determine K user adjustment factor sets. The power supply data set of the target area in the preset adjustment window is obtained, and the power balance adjustment scheme is configured in combination with the K public adjustment factors and the K user adjustment factor sets to obtain the target power balance adjustment scheme. The technical problems of low adjustment accuracy and poor stability in the power balance adjustment method in the prior art are solved. By accurately dividing the power sub-areas and analyzing the transformer fluctuation coefficient, the concentrated fluctuation coefficient and common regulation factor of each area are determined, and then the power balance regulation plan is optimized, the stability of the power grid and the power supply reliability are improved, and the technical effect of completing the power balance regulation efficiently and accurately is achieved.

[0042] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A load characteristic driven power balance adjustment method, characterized in that: The method comprises: Obtain user installation information and repair records in the target area, divide the target area into sub-areas based on the line planning information of the target area, and determine K power sub-areas, where K is an integer greater than or equal to 1; Collecting transformer operation data of the K power sub-areas within a preset time window, and performing fluctuation coefficient analysis on the obtained K transformer operation data sets according to a preset fluctuation index set to determine K transformer fluctuation coefficient sets; Traversing the K transformer fluctuation coefficient sets to perform transformer concentrated fluctuation analysis, determine K concentrated fluctuation coefficients, and determine K common adjustment factors based on the K concentrated fluctuation coefficients; Traversing the K power sub-areas to collect user power consumption data, obtaining K user power consumption data sets, performing user load fluctuation stability analysis on the K user power consumption data sets, and determining K user adjustment factor sets; A power supply data set of the target area within a preset adjustment window is obtained, and a power balance adjustment scheme is configured in combination with the K public adjustment factors and the K user adjustment factor sets to obtain a target power balance adjustment scheme.

2. The load characteristic driven power balance adjustment method according to claim 1, characterized in that: The preset fluctuation index set includes voltage deviation, grid frequency deviation and voltage operation fluctuation.

3. The load characteristic driven power balance adjustment method according to claim 2, characterized in that: Collecting transformer operation data of the K power sub-areas within a preset time window, and performing fluctuation coefficient analysis on the obtained K transformer operation data sets according to a preset fluctuation index set, and determining K transformer fluctuation coefficient sets, including: Retrieving the K transformer operation data sets according to the preset fluctuation index set to determine K voltage deviation mean value sets, K grid frequency deviation mean value sets and K voltage operation fluctuation mean value sets; A transformer fluctuation identifier is constructed, and the transformer fluctuation identifier is used to respectively identify transformer fluctuations on the K voltage deviation mean sets, the K grid frequency deviation mean sets, and the K voltage operation fluctuation mean sets, to obtain the K transformer fluctuation coefficient sets.

4. The load characteristic driven power balance adjustment method according to claim 1, characterized in that: Traversing the K transformer fluctuation coefficient sets to perform transformer concentrated fluctuation analysis, determining K concentrated fluctuation coefficients, and determining K common adjustment factors based on the K concentrated fluctuation coefficients, including: Constructing K fluctuation analysis spaces based on the K transformer fluctuation coefficient sets, wherein the K fluctuation analysis spaces include K fluctuation particle sets, and each fluctuation particle corresponds to a transformer fluctuation coefficient; Extracting K spatial center particles of the K fluctuation analysis spaces, taking the K spatial center particles as the starting point, iterating in the K fluctuation analysis spaces according to a preset fluctuation iteration step length until a preset number of iterations is met, and obtaining K target fluctuation particles; Taking the K target fluctuation particles as the sphere center and the preset fluctuation iteration step as the sphere radius, K target fluctuation spherical subspaces are constructed, and the transformer fluctuation coefficients contained in the K target fluctuation spherical subspaces are averaged to obtain K concentrated fluctuation coefficients.

5. The load characteristic driven power balance adjustment method according to claim 4, characterized in that: Extracting K spatial center particles of the K fluctuation analysis spaces, taking the K spatial center particles as the starting point, iterating in the K fluctuation analysis spaces according to a preset fluctuation iteration step length until a preset number of iterations is met, and obtaining K target fluctuation particles, including: Taking the K spatial center particles as the starting point, iterating in the K wave analysis spaces according to a preset wave iteration step length to obtain K iterative wave particles; When the particle aggregation density of the K iterative wave particles is greater than or equal to the particle aggregation density of the K space center particles, the K iterative wave particles are updated as the starting point, and the iteration is continued according to the preset fluctuation iteration step until the preset number of iterations is met, and the K iterative wave particles corresponding to the maximum value of the particle aggregation density during the iteration process are respectively used as K target wave particles.

6. The load characteristic driven power balance adjustment method according to claim 5, characterized in that: When the particle aggregation density of the K iterative fluctuating particles is less than the particle aggregation density of the K spatial center particles, the K iterative fluctuating particles are updated as the starting point according to the preset acceptance probability, and the iteration is continued according to the preset fluctuation iteration step until the preset number of iterations is met, and the K iterative fluctuating particles corresponding to the maximum value of the particle aggregation density during the iteration process are respectively used as the K target fluctuating particles.

7. The load characteristic driven power balance adjustment method according to claim 4, characterized in that: The ratios of the K concentrated fluctuation coefficients to the sum of the K concentrated fluctuation coefficients are calculated respectively, and the K common adjustment factors are obtained according to the calculation results.

8. The load characteristic driven power balance adjustment method according to claim 1, characterized in that: Acquiring the power supply data of the target area at the current moment and the K power output data sets of the K power sub-areas, optimizing the power balance adjustment scheme in combination with the K public adjustment factors and the K user adjustment factor sets, and obtaining a target power balance adjustment scheme, including: Performing stability authentication on the power supply data set, and obtaining an adjustment instruction if the authentication passes; A scheme configurator is called according to the adjustment instruction, and the scheme configurator is used to perform scheme analysis on the power supply data set, the K public adjustment factors and the K user adjustment factor sets to determine the target power balance adjustment scheme.

Images