Real-time adjustment method and system for low-voltage side distributed resources of power distribution network

Abstract

The invention provides a real-time adjustment method and system for low-voltage side distributed resources of a power distribution network. The adjustment method comprises the following steps: acquiring and preprocessing historical operation data of low-voltage side distributed power equipment of the power distribution network; determining a station belonging relation of the power equipment and a topological structure between the power equipment; establishing a distributed optimization platform based on the topological structure, and calculating a voltage risk-approaching coefficient of the low-voltage side of the power distribution network; acquiring a first voltage risk-approaching coefficient of the adjusting node and corresponding single-time adjusting cost of the photovoltaic power equipment and the energy storage power equipment; acquiring a charge state when the voltage of the low-voltage side of the power distribution network exceeds the limit, determining a second voltage risk-approaching coefficient corresponding to the adjusting node when the voltage exceeds the limit based on the cost limit boundary constraint, and determining power equipment for dispatching the voltage of the system according to the ratio of the two voltage risk-approaching coefficients; according to the adjustment method provided by the invention, the dynamic scheduling and optimal control of the distributed resources are realized, and the operation efficiency and reliability of the power distribution network are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and particularly relates to a method and system for real-time adjustment of distributed resources on the low-voltage side of a distribution network. Background Art

[0002] With the development of new power systems, a large number of distributed resources have been connected to the low-voltage side of the distribution network, such as distributed photovoltaic power generation, energy storage devices, electric vehicles, etc. The access of these distributed resources makes the operation state of the distribution network more complex and changeable, and traditional sensing systems are difficult to meet the requirements of real-time and accurate sensing of the state of distributed resources.

[0003] Due to the access of distributed resources such as photovoltaic power generation and energy storage devices to the power grid, the randomness and intermittency of distributed power sources will cause voltage and frequency fluctuations, affecting the stable operation of the power grid and bringing negative impacts to equipment safety and grid economic operation. How to accurately identify the voltage state in the distribution network, make perceptual judgments, and then adjust the power output of distributed power equipment to ensure power supply stability and reliability through coordinated actions has always been a hot research issue. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a method and system for real-time adjustment of distributed resources on the low-voltage side of a distribution network to solve the technical problems existing in the prior art.

[0005] The present invention proposes a method for real-time adjustment of distributed resources on the low-voltage side of a distribution network, including: Obtain the historical operation data of distributed power equipment on the low-voltage side of the distribution network, and perform standardization and feature dimensionality reduction processing on the obtained historical operation data; Perform relationship identification on the historical operation data after dimensionality reduction processing to determine the station affiliation relationship of the power equipment, perform phase analysis on the power equipment with the same station affiliation relationship, and determine the topological structure between the distributed power equipment on the low-voltage side of the power grid according to the phase analysis; Based on the topological structure, establish a distributed optimization platform, obtain the voltage data of each power equipment in real time through the optimization platform, use the voltage offset and voltage fluctuation in the voltage data as the inputs of the fuzzy control system on the low-voltage side of the distribution network for fuzzy processing, and obtain the voltage risk coefficient on the low-voltage side of the distribution network; Define the nodes where the photovoltaic power equipment and energy storage power equipment on the low-voltage side of the distribution network are located as adjustment nodes, obtain the first voltage risk coefficient of the adjustment nodes, as well as the corresponding single adjustment cost of the photovoltaic power equipment and energy storage power equipment; Obtain the charge state when the voltage on the low-voltage side of the distribution network exceeds the limit, determine the second voltage risk coefficient corresponding to the adjustment node when the voltage exceeds the limit based on the cost limit boundary constraint, and determine the voltage control of the power equipment according to the ratio of the first voltage risk coefficient and the second voltage risk coefficient.

[0006] Preferably, the steps of performing relationship recognition on the historical operation data after dimensionality reduction to determine the station affiliation relationship of power equipment, performing phase analysis on power equipment with the same station affiliation relationship, and determining the topological structure between power equipment distributed on the low-voltage side of the power grid according to the phase analysis include: Construct an adjacency matrix based on the historical operation data after dimensionality reduction, calculate the sum of weights between all power equipment according to the adjacency matrix to obtain a degree matrix, and obtain a cluster matrix on the low-voltage side of the distribution network according to the adjacency matrix and the degree matrix; Calculate the eigenvalues of the cluster matrix and sort them, select the vectors corresponding to the preset eigenvalues to construct a vector matrix, and perform clustering processing on the row elements of the vector matrix to obtain the station affiliation relationship corresponding to the distributed power equipment; Perform equivalent modeling on the power grid lines corresponding to the power equipment belonging to the same station class, obtain the voltage data of each electronic device at different times in the power grid line, and represent it with a time series to obtain a voltage data curve sample; Obtain the turning points in the voltage data curve sample, perform importance marking based on a hierarchical method, segment the voltage data curve sample according to the importance marking result, and determine the upstream and downstream phase relationships between power equipment based on the phase recognition correlation coefficient; Determine the topological structure of the low-voltage side of the distribution network according to the upstream and downstream phase relationships between power equipment.

[0007] Preferably, the expression of the cluster matrix is:

[0008] In the formula, represents the cluster matrix, represents the degree matrix, , represents the degree of the th power equipment, represents the adjacency matrix, represents the th power equipment to the th power equipment weight;

[0009] In the formula, and respectively represent the th power equipment and the th power equipment, and The weight value between them satisfies a Gaussian distribution, represents the second-order norm, represents the standard deviation corresponding to the Gaussian distribution satisfied by the weight value, respectively represent the neighborhood of and the expression of the phase recognition correlation coefficient is:

[0010] In the formula, represents the voltage data matrix corresponding to the th power equipment, represents the voltage data matrix corresponding to the th power equipment, represents the covariance between the voltage matrices of the th power equipment and the th power equipment, respectively represent the th power equipment and the th power equipment corresponding standard deviations.

[0011] Preferably, the step of obtaining the voltage data of each power equipment in real time through the optimization platform includes: Obtain the historical voltage data and prediction credibility of the power equipment, and determine the first prediction model according to the historical voltage data and prediction credibility; Perform the first prediction on the voltage data of the power equipment according to the first prediction model, and exchange the first prediction value of the line voltage according to the line connection relationship of the power equipment; Process the first prediction value according to the node voltage correlation prediction model to obtain the voltage data corresponding to each power equipment.

[0012] Preferably, the expression of the first prediction model is:

[0013] In the formula, represents the first prediction value, represents the hyperparameter of the first prediction model, represents the insensitive loss function, represents the relaxation factor corresponding to the th historical voltage data sample, represents the number of samples, represents the prediction credibility of the first prediction model, represents the first-order norm; The expression of the node voltage correlation prediction model is:

[0014] In the formula, represents the voltage prediction data, 、 respectively represent the voltage measurement value and credibility of the low-voltage side of the distribution network, 、 respectively represent the voltage measurement value and credibility of the line layer where the power equipment is connected to the distribution network, respectively represent the voltage measurement value and credibility of the line layer where the power equipment is connected to the user side.

[0015] Preferably, the expression for the single adjustment cost corresponding to the photovoltaic power equipment is:

[0016] In the formula, represents the single adjustment cost corresponding to the photovoltaic power equipment, represents the equivalent input cost of a single adjustment of the photovoltaic power equipment, which is related to the input cost and the number of adjustment life times of the photovoltaic power equipment, represents the compensation electricity price per unit active power of the photovoltaic, represents the photovoltaic curtailment penalty coefficient, represents the expected photovoltaic power generation; The expression for the single adjustment cost corresponding to the energy storage power equipment is:

[0017] In the formula, represents the single adjustment cost corresponding to the energy storage power equipment, represents the equivalent input cost of a single adjustment of the energy storage power equipment, which is related to the input cost and the number of adjustment life times of the energy storage power equipment, represents the coefficient of change in the state of charge, respectively represent the energy storage power equipment at time and time of the state of charge, represents the energy storage power curtailment penalty coefficient, represents the active power output of the energy storage.

[0018] Preferably, the expression for the cost limit boundary constraint is:

[0019] The steps of determining the voltage control of the power equipment according to the ratio of the first voltage risk coefficient and the second voltage risk coefficient include: If the first voltage risk coefficient is greater than the second voltage risk coefficient, select the energy storage power equipment for system voltage control; If the first voltage risk coefficient is less than or equal to the second voltage risk coefficient, select the photovoltaic power equipment for system voltage control.

[0020] The present invention also provides a real-time adjustment system for distributed resources on the low-voltage side of a distribution network, including; A dimensionality reduction processing module, configured to obtain historical operation data of power equipment distributed on the low-voltage side of the distribution network, and perform standardization and feature dimensionality reduction processing on the obtained historical operation data; An identification module, configured to perform relationship identification on the historical operation data after dimensionality reduction processing to determine the station affiliation relationship of the power equipment, perform phase analysis on the power equipment with the same station affiliation relationship, and determine the topological structure between the power equipment distributed on the low-voltage side of the power grid according to the phase analysis; A fuzzy processing module, configured to establish a distributed optimization platform based on the topological structure, obtain voltage data of each power equipment in real time through the optimization platform, use the voltage offset and voltage fluctuation in the voltage data as the inputs of the fuzzy control system on the low-voltage side of the distribution network for fuzzy processing, and obtain the voltage risk coefficient on the low-voltage side of the distribution network; A calculation module, configured to define the nodes where the photovoltaic power equipment and energy storage power equipment on the low-voltage side of the distribution network are located as adjustment nodes, obtain the first voltage risk coefficient of the adjustment nodes and the corresponding single adjustment cost of the photovoltaic power equipment and energy storage power equipment; A scheduling module, configured to obtain the charge state when the voltage on the low-voltage side of the distribution network exceeds the limit, determine the second voltage risk coefficient corresponding to the adjustment node when the voltage exceeds the limit based on the cost limit boundary constraint, and determine the voltage control of the power equipment according to the ratio of the first voltage risk coefficient and the second voltage risk coefficient.

[0021] Preferably, the identification module includes: A construction unit, configured to construct an adjacency matrix according to the historical operation data after dimensionality reduction processing, calculate the sum of weights between all power equipment according to the adjacency matrix to obtain a degree matrix, and obtain a cluster matrix on the low-voltage side of the distribution network according to the adjacency matrix and the degree matrix; A clustering unit, configured to calculate the eigenvalues of the cluster matrix and sort them, select the vectors corresponding to the preset eigenvalues to construct a vector matrix, perform clustering processing on the row elements of the vector matrix, and obtain the station affiliation relationship corresponding to the distributed power equipment; An equivalent unit, configured to perform equivalent modeling on the power grid lines corresponding to the power equipment belonging to the same station type, obtain the voltage data of each electronic device at different times in the power grid line, and represent it with a time series to obtain a voltage data curve sample; A marking unit, configured to obtain the turning points in the voltage data curve sample, perform importance marking based on a grading method, segment the voltage data curve sample according to the importance marking result, and determine the upstream and downstream phase relationships between the power equipment based on the phase identification correlation coefficient; A determination unit, configured to determine the topological structure on the low-voltage side of the distribution network according to the upstream and downstream phase relationships between the power equipment.

[0022] Preferably, in the recognition module, The expression of the cluster matrix is:

[0023] In the formula, represents the cluster matrix, represents the degree matrix, , represents the degree of the th power equipment, represents the adjacency matrix, represents the th power equipment to the

[0024] In the formula, and respectively represent the th power equipment and the th power equipment, and The weight value between them satisfies the Gaussian distribution, represents the second-order norm, represents the standard deviation corresponding to the Gaussian distribution satisfied by the weight value, respectively represent the neighborhood of and the neighborhood of The expression of the phase recognition correlation coefficient is:

[0025] In the formula, represents the voltage data matrix corresponding to the th power equipment, represents the voltage data matrix corresponding to the th power equipment, represents the covariance between the voltage matrices of the th power equipment and the th power equipment, respectively represent the th power equipment and the th power equipment corresponding standard deviations.

[0026] The beneficial effects of the present invention compared with the prior art are as follows: The real-time adjustment method for distributed resources on the low-voltage side of the distribution network provided by this application first obtains the historical operation data of the power equipment distributed on the low-voltage side of the distribution network, identifies the relationships in the historical operation data to determine the station affiliation relationships of the power equipment, conducts phase analysis on the power equipment with the same station affiliation relationship, and determines the topological structure among the power equipment distributed on the low-voltage side of the grid according to the phase analysis; the topological relationship between power equipment is an important guarantee for carrying out operations such as distribution line parameter identification, operation data analysis, and substation operation planning; then, a distributed optimization platform is established based on the topological structure, and the voltage data of each power equipment is obtained in real time through the optimization platform. The voltage offset and voltage fluctuation in the voltage data are used as inputs to the fuzzy control system on the low-voltage side of the distribution network for fuzzy processing to obtain the voltage risk coefficient on the low-voltage side of the distribution network. The single adjustment cost of the adjustment node is obtained according to the voltage risk coefficient, the charge state when the voltage on the low-voltage side of the distribution network exceeds the limit is obtained, the second voltage risk coefficient corresponding to the adjustment node when the voltage exceeds the limit is determined based on the cost limit boundary constraint, and the voltage control of the power equipment is determined according to the ratio of the first voltage risk coefficient and the second voltage risk coefficient; the real-time adjustment method for distributed resources on the low-voltage side of the distribution network disclosed in this application can sense the voltage conditions on the low-voltage side of the distribution network in real time and perform corresponding voltage scheduling to ensure the voltage stability of the system, optimize the operation of the distribution network, and improve power supply reliability and power quality.

[0027] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a flowchart of the real-time adjustment method for distributed resources on the low-voltage side of the distribution network in the first embodiment of the present invention; Figure 2 is a structural block diagram of a computer in the fourth embodiment of the present invention.

[0029] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. SPECIFIC EMBODIMENTS

[0030] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs. The terms used in the specification of this invention are for the purpose of describing specific embodiments only and are not intended to limit the invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0032] Embodiment 1 Please refer to Figure 1 , which shows the real-time adjustment method for distributed resources on the low-voltage side of the distribution network in the first embodiment of the present invention. Specifically, the real-time adjustment method for distributed resources on the low-voltage side of the distribution network specifically includes steps S10 to S50: S10. Obtain the historical operation data of the power equipment distributed on the low-voltage side of the distribution network, and perform standardization and feature dimension reduction processing on the obtained historical operation data; Optionally, the operation data can be collected by a data automatic acquisition device. The collected operation data includes parameters such as voltage, current, power, and temperature. Conducting an overall analysis of the data will greatly increase the analysis time and computational complexity, as many similar data are reused while useful data cannot be distinguished for key attention. Therefore, it is first necessary to perform standardization processing and feature dimension reduction processing on the collected data to remove duplicate data, etc. The low-dimensional data can represent most of the features of the original data, and analyzing the low-dimensional data can obtain the desired results; reducing the amount of data analysis.

[0033] S20. Perform relationship recognition on the historical operation data after dimension reduction processing to determine the equipment belonging relationship of the power equipment, perform phase analysis on the power equipment with the same equipment belonging relationship, and determine the topological structure between the power equipment distributed on the low-voltage side of the power grid according to the phase analysis; The step of performing relationship recognition on the historical operation data after dimension reduction processing to determine the equipment belonging relationship of the power equipment, performing phase analysis on the power equipment with the same equipment belonging relationship, and determining the topological structure between the power equipment distributed on the low-voltage side of the power grid includes: Construct an adjacency matrix based on the historical operation data after dimension reduction processing, calculate the sum of weights between all power equipment according to the adjacency matrix to obtain a degree matrix, and obtain a cluster matrix on the low-voltage side of the distribution network according to the adjacency matrix and the degree matrix; Calculate the eigenvalues of the cluster matrix and sort them, select the vectors corresponding to the preset eigenvalues to construct a vector matrix, and perform clustering processing on the row elements of the vector matrix to obtain the equipment belonging relationship corresponding to the distributed power equipment; Perform equivalent modeling on the power grid lines corresponding to the power equipment belonging to the same equipment type, obtain the voltage data of each electronic device at different times in the power grid line, and represent it with a time series to obtain a voltage data curve sample; Obtain the turning points in the voltage data curve sample, mark the importance based on a hierarchical method, segment the voltage data curve sample by time according to the importance marking result, and determine the upstream and downstream phase relationships between power equipment based on the phase recognition correlation coefficient; Determine the topological structure of the low-voltage side of the distribution network according to the upstream and downstream phase relationships between power equipment.

[0034] The expression of the cluster matrix is:

[0035] In the formula, represents the cluster matrix, represents the degree matrix, , represents the degree of the th power equipment, represents the adjacency matrix, represents the th power equipment's weight for the

[0036] In the formula, and respectively represent the th power equipment and the th power equipment, and the weight value between them satisfies a Gaussian distribution, represents the second-order norm, represents the standard deviation corresponding to the Gaussian distribution satisfied by the weight value, respectively represent 's neighborhood and 's neighborhood; The expression of the phase recognition correlation coefficient is:

[0037] In the formula, represents the voltage data matrix corresponding to the th power equipment, represents the voltage data matrix corresponding to the th power equipment, represents the covariance between the voltage matrices of the th power equipment and the th power equipment, respectively represent the standard deviations corresponding to the th power equipment and the th power equipment.

[0038] Optionally, consider the data in the distributed power equipment as a data set, and the points in the data set as points in space. Statistically analyze the weights between different power equipment and other power equipment and construct an adjacency matrix. The elements of the adjacency matrix reflect all the weight relationships between each power equipment. The degree matrix is a diagonal matrix, and each element is the sum of the weights of a power equipment and the remaining power equipment. Through clustering operations, the power equipment can be divided into different distribution areas, such as belonging to the same park, community, or charging station, etc.; perform phase analysis on the power equipment on the distribution line belonging to the same distribution area, analyze the influence relationship of voltage fluctuations of upstream and downstream power equipment on the current power equipment, and combine the topological information of GIS to obtain the topological relationship of the power equipment within the distribution area; the topological relationship between power equipment is an important guarantee for carrying out business operations such as distribution line parameter identification, operation data analysis, and distribution area operation planning.

[0039] S30. Based on the topological structure, establish a distributed optimization platform. Through the optimization platform, obtain the voltage data of each power equipment in real time, and use the voltage offset and voltage fluctuation in the voltage data as the inputs of the fuzzy control system on the low-voltage side of the distribution network for fuzzy processing to obtain the voltage risk coefficient on the low-voltage side of the distribution network. The step of obtaining the voltage data of each power equipment in real time through the optimization platform includes: Obtain the historical voltage data and prediction credibility of the power equipment, and determine the first prediction model according to the historical voltage data and prediction credibility. Perform a first prediction on the voltage data of the power equipment according to the first prediction model, and exchange the first prediction values of the line voltages according to the line connection relationship of the power equipment. Process the first prediction value according to the node voltage correlation prediction model to obtain the voltage data corresponding to each power equipment.

[0040] The expression of the first prediction model is:

[0041] In the formula, represents the first prediction value, represents the hyperparameter of the first prediction model, represents the insensitive loss function, represents the th relaxation factor corresponding to the historical voltage data sample, represents the number of samples, represents the prediction credibility of the first prediction model, represents the first-order norm; The expression of the node voltage correlation prediction model is:

[0042] In the formula, Indicates voltage prediction data, , respectively represent the voltage measurement value and reliability of the low-voltage side of the distribution network, , respectively represent the voltage measurement value and reliability of the line layer where the power equipment is connected to the distribution network, respectively represent the voltage measurement value and reliability of the line layer where the power equipment is connected to the user side.

[0043] Optionally, building an optimization platform includes platform function analysis, hardware architecture, conditional constraints, software implementation, etc.; Since the distributed power equipment on the low-voltage side of the distribution network may be in the upper and lower layer power grids at the same time, it may act as both a load in the upper layer power grid and a power source in the lower layer power grid. Schematically, the distributed power equipment may act as both a load of the distribution network and a power source on the user side; Therefore, obtaining the voltage data of each power equipment needs to consider the influence of the upper and lower layer power grid lines at the same time to improve the accuracy of voltage data acquisition. The node voltage correlation prediction model has both distributed and information interaction characteristics and is suitable for application on a distributed optimization platform.

[0044] S40, Define the nodes where the photovoltaic power equipment and energy storage power equipment on the low-voltage side of the distribution network are located as adjustment nodes, and obtain the first voltage risk coefficient of the adjustment nodes and the corresponding single adjustment cost of the photovoltaic power equipment and energy storage power equipment; The expression for the single adjustment cost corresponding to the photovoltaic power equipment is:

[0045] In the formula, represents the single adjustment cost corresponding to the photovoltaic power equipment, represents the equivalent input cost of the single adjustment of the photovoltaic power equipment, which is related to the input cost and adjustment life times of the photovoltaic power equipment, represents the compensation electricity price per unit active power of the photovoltaic, represents the photovoltaic curtailment penalty coefficient, represents the expected photovoltaic power generation; The expression for the single adjustment cost corresponding to the energy storage power equipment is:

[0046] In the formula, represents the single adjustment cost corresponding to the energy storage power equipment, represents the equivalent input cost of the single adjustment of the energy storage power equipment, which is related to the input cost and adjustment life times of the energy storage power equipment, represents the state of charge change coefficient, respectively represent the energy storage power equipment at time and time of the state of charge, represents the energy storage power curtailment penalty factor, represents the active power output of the energy storage.

[0047] S50, obtain the charge state when the low-voltage side voltage of the distribution network exceeds the limit, determine the second voltage crisis coefficient corresponding to the regulation node when the voltage exceeds the limit based on the cost limit boundary constraint, and determine the voltage control of the power equipment according to the ratio of the first voltage crisis coefficient and the second voltage crisis coefficient; The expression of the cost limit boundary constraint is:

[0048] The steps of determining the voltage control of the power equipment according to the ratio of the first voltage crisis coefficient and the second voltage crisis coefficient include: If the first voltage crisis coefficient is greater than the second voltage crisis coefficient, select the energy storage power equipment for system voltage control; If the first voltage crisis coefficient is less than or equal to the second voltage crisis coefficient, select the photovoltaic power equipment for system voltage control.

[0049] Optionally, in this embodiment, the steps of system voltage control are: Determine the objective function and construct a mathematical model based on the optimal stability, minimum voltage deviation, and minimum system power consumption of the low-voltage side distribution network, and determine the objective constraints; Introduce intermediate variables to process the objective constraints, and convert the problem of solving the objective function under the objective constraints into a linear dimension solution under the second-order cone model; Perform a relaxation transformation on the second-order cone model to obtain a convex feasible operation domain corresponding to the second-order cone model, and convert the solution of the second-order cone model into a multi-dimensional space planning problem solution in the convex feasible operation domain, so as to obtain the control voltage corresponding to the output of the power equipment.

[0050] Optionally, the expression of the objective function is:

[0051] In the formula, respectively represent the weight factors, represents the preset voltage control time, represents the number of voltage nodes in the system, respectively represent the voltage nodes and voltage node at moment, represents the reference voltage, represents the voltage node and voltage node phase angle difference between, represents any preset time period.

[0052] The target constraints at least include economic benefit constraints, charge constraints, voltage response delay constraints, etc.; the main function of introducing intermediate variables is to simplify the constraint conditions, transform them into a mathematical solution model in a linear dimension, improve the solution efficiency, facilitate the analysis and operation of the voltage adjustment effect, and the main function of the relaxation transformation is to convert the operation effect of the second-order cone model to a convex feasible operation domain, and then in the convex feasible operation domain, the conventional " - relaxation" method can be used for rapid solution. represents the slack variable, and the smaller the slack variable, the higher the accuracy of the output voltage.

[0053] In summary, the real-time adjustment method for distributed resources on the low-voltage side of the distribution network provided by this application first obtains the historical operation data of the power equipment distributed on the low-voltage side of the distribution network, identifies the relationships in the historical operation data to determine the belonging relationships of the power equipment, conducts phase analysis on the power equipment with the same belonging relationship, and determines the topological structure between the power equipment distributed on the low-voltage side of the power grid according to the phase analysis; the topological relationship between power equipment is an important guarantee for carrying out operations such as distribution line parameter identification, operation data analysis, and substation area operation planning; then a distributed optimization platform is established based on the topological structure, the voltage data of each power equipment is obtained in real time through the optimization platform, the voltage offset and voltage fluctuation in the voltage data are used as the inputs of the fuzzy control system on the low-voltage side of the distribution network for fuzzy processing to obtain the voltage risk coefficient on the low-voltage side of the distribution network, the single adjustment cost of the adjustment node is obtained according to the voltage risk coefficient, the charge state when the voltage on the low-voltage side of the distribution network exceeds the limit is obtained, the second voltage risk coefficient corresponding to the adjustment node when the voltage exceeds the limit is determined based on the cost limit boundary constraint, and the voltage control of the power equipment is determined according to the ratio of the first voltage risk coefficient and the second voltage risk coefficient; the real-time adjustment method for distributed resources on the low-voltage side of the distribution network disclosed in this application can sense the voltage situation on the low-voltage side of the distribution network in real time, and perform corresponding voltage scheduling to ensure the voltage stability of the system, optimize the operation of the distribution network, and improve the power supply reliability and power quality.

[0054] Embodiment 2 This embodiment provides a real-time adjustment system for distributed resources on the low-voltage side of a distribution network, including: A dimensionality reduction processing module, configured to obtain the historical operation data of the power equipment distributed on the low-voltage side of the distribution network, and perform standardization and feature dimensionality reduction processing on the obtained historical operation data; An identification module, configured to perform relationship identification on the historical operation data after dimensionality reduction processing to determine the belonging relationships of the power equipment, conduct phase analysis on the power equipment with the same belonging relationship, and determine the topological structure between the power equipment distributed on the low-voltage side of the power grid according to the phase analysis; The blurring processing module is used to establish a distributed optimization platform based on the topological structure, obtain the voltage data of each power device in real time through the optimization platform, and use the voltage offset and voltage fluctuation in the voltage data as the inputs of the fuzzy control system on the low-voltage side of the distribution network for blurring processing to obtain the voltage risk coefficient on the low-voltage side of the distribution network; The calculation module is used to define the nodes where the photovoltaic power devices and energy storage power devices are located on the low-voltage side of the distribution network as adjustment nodes, obtain the first voltage risk coefficient of the adjustment nodes, as well as the corresponding single adjustment cost of the photovoltaic power devices and energy storage power devices; The scheduling module is used to obtain the charge state when the voltage on the low-voltage side of the distribution network exceeds the limit, determine the second voltage risk coefficient corresponding to the adjustment node when the voltage exceeds the limit based on the cost limit boundary constraint, and determine the voltage control of the power device according to the ratio of the first voltage risk coefficient and the second voltage risk coefficient.

[0055] Preferably, the steps of performing relationship recognition on the dimension-reduced historical operation data to determine the station affiliation relationship of power devices, performing phase analysis on power devices with the same station affiliation relationship, and determining the topological structure between the distributed power devices on the low-voltage side of the power grid according to the phase analysis include: Construct an adjacency matrix based on the dimension-reduced historical operation data, calculate the sum of weights between all power devices according to the adjacency matrix to obtain the degree matrix, and obtain the cluster matrix on the low-voltage side of the distribution network according to the adjacency matrix and the degree matrix; Calculate the eigenvalues of the cluster matrix and sort them, select the vectors corresponding to the preset eigenvalues to construct a vector matrix, and perform clustering processing on the row elements of the vector matrix to obtain the station affiliation relationship corresponding to the distributed power devices; Perform equivalent modeling on the power grid lines corresponding to the power devices belonging to the same station class, obtain the voltage data of each electronic device at different times in the power grid line, and represent it with a time series to obtain the voltage data curve sample; Obtain the turning points in the voltage data curve sample, perform importance marking based on a grading method, segment the voltage data curve sample according to the importance marking result, and determine the upstream and downstream phase relationships between power devices based on the phase recognition correlation coefficient; Determine the topological structure on the low-voltage side of the distribution network according to the upstream and downstream phase relationships between power devices.

[0056] Preferably, the expression of the cluster matrix is:

[0057] In the formula, represents the cluster matrix, represents the degree matrix, , represents the Degree of a power equipment Represents an adjacency matrix Represents the th power equipment's weight for the th power equipment;

[0058] In the formula, and respectively represent the th power equipment and the th power equipment, and The weight value between them satisfies a Gaussian distribution, Represents the second-order norm, Represents the standard deviation corresponding to the Gaussian distribution satisfied by the weight value, respectively represent 's neighborhood and 's neighborhood; The expression of the phase identification correlation coefficient is:

[0059] In the formula, Represents the voltage data matrix corresponding to the th power equipment, Represents the voltage data matrix corresponding to the th power equipment, Represents the covariance between the th power equipment and the voltage matrix of the th power equipment, respectively represent the th power equipment and the th power equipment's corresponding standard deviation.

[0060] Preferably, the steps of obtaining the voltage data of each power equipment in real time through the optimization platform include: Obtain the historical voltage data and prediction credibility of the power equipment, and determine the first prediction model according to the historical voltage data and prediction credibility; Perform the first prediction on the voltage data of the power equipment according to the first prediction model, and exchange the first predicted value of the line voltage according to the line connection relationship of the power equipment; Process the first predicted value according to the node voltage association prediction model to obtain the voltage data corresponding to each power equipment.

[0061] Preferably, the expression of the first prediction model is:

[0062] In the formula, Represents the first predicted value, Represents the hyperparameters of the first prediction model, Represents the insensitive loss function, Represents the relaxation factor corresponding to the th historical voltage data sample, Represents the prediction confidence of the first prediction model, Represents the first-order norm; The expression of the node voltage correlation prediction model is:

[0063] In the formula, Represents the voltage prediction data, , respectively represent the voltage measurement value and confidence on the low-voltage side of the distribution network, , respectively represent the voltage measurement value and confidence of the line layer where the power equipment is connected to the distribution network, respectively represent the voltage measurement value and confidence of the line layer where the power equipment is connected to the user side.

[0064] Preferably, the expression of the single adjustment cost corresponding to the photovoltaic power equipment is:

[0065] In the formula, Represents the single adjustment cost corresponding to the photovoltaic power equipment, Represents the equivalent input cost of a single adjustment of the photovoltaic power equipment, which is related to the input cost and the number of adjustment life times of the photovoltaic power equipment, Represents the compensation electricity price per unit active power of the photovoltaic, Represents the photovoltaic curtailment penalty coefficient, Represents the expected photovoltaic power generation; The expression of the single adjustment cost corresponding to the energy storage power equipment is:

[0066] In the formula, Represents the single adjustment cost corresponding to the energy storage power equipment, Represents the equivalent input cost of a single adjustment of the energy storage power equipment, which is related to the input cost and the number of adjustment life times of the energy storage power equipment, Represents the coefficient of change in the state of charge, respectively represent the moment and moment of the state of charge of the energy storage power equipment, Represents the energy storage power curtailment penalty coefficient, Represents the active power output of the energy storage.

[0067] Preferably, the expression of the cost limit boundary constraint is:

[0068] The steps of determining voltage control of the power equipment according to the ratio of the first voltage danger coefficient and the second voltage danger coefficient include: If the first voltage danger coefficient is greater than the second voltage danger coefficient, select the energy storage power equipment for system voltage control; If the first voltage danger coefficient is less than or equal to the second voltage danger coefficient, select the photovoltaic power equipment for system voltage control.

[0069] Embodiment III This embodiment provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the real-time adjustment method of distributed resources on the low-voltage side of the distribution network as described above.

[0070] Embodiment IV The present invention also provides a computer. Please refer to Figure 2 , as shown in the computer in the embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored on the memory 10 and operable on the processor 20. When the processor 20 executes the computer program 30, it implements the above-mentioned real-time adjustment method of distributed resources on the low-voltage side of the distribution network.

[0071] Among them, the memory 10 includes at least one type of storage medium, and the storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disc, etc. The memory 10 can be an internal storage unit of the computer in some embodiments, such as the hard disk of the computer. The memory 10 can also be an external storage device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 10 can also include both an internal storage unit and an external storage device of the computer. The memory 10 can be used not only to store application software and various types of data installed in the computer, but also to temporarily store data that has been output or will be output.

[0072] Among them, in some embodiments, the processor 20 may be an Electronic Control Unit (ECU, also known as the vehicle computer), a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips, which are used to run the program code stored in the memory 10 or process data, such as executing an access restriction program and the like.

[0073] It should be noted that Figure 2 The structure shown does not constitute a limitation on the computer. In other embodiments, the computer may include fewer or more components than shown in the figure, or combine certain components, or have different component arrangements.

[0074] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a predefined sequence list of executable instructions for implementing logical functions, which can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0075] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part (electronic device) having one or more wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0076] It should be understood that each part of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques well known in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0077] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope described in this specification.

[0078] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A real-time adjustment method for distributed resources on the low-voltage side of a distribution network, characterized in that, Including: Obtain the historical operation data of the distributed power equipment on the low-voltage side of the distribution network, and perform standardization and feature dimension reduction processing on the obtained historical operation data; Perform relationship recognition on the historical operation data after dimension reduction processing to determine the station affiliation relationship of the power equipment, perform phase analysis on the power equipment with the same station affiliation relationship, and determine the topological structure between the distributed power equipment on the low-voltage side of the power grid according to the phase analysis; Based on the topological structure, establish a distributed optimization platform, obtain the voltage data of each power equipment in real time through the optimization platform, and use the voltage offset and voltage fluctuation in the voltage data as the input of the fuzzy control system on the low-voltage side of the distribution network for fuzzy processing to obtain the voltage risk coefficient on the low-voltage side of the distribution network; Define the nodes where the photovoltaic power equipment and energy storage power equipment on the low-voltage side of the distribution network are located as adjustment nodes, obtain the first voltage risk coefficient of the adjustment nodes and the corresponding single adjustment cost of the photovoltaic power equipment and energy storage power equipment; Obtain the charge state when the voltage on the low-voltage side of the distribution network exceeds the limit, determine the second voltage risk coefficient corresponding to the adjustment node when the voltage exceeds the limit based on the cost limit boundary constraint, and determine the voltage control of the power equipment according to the ratio of the first voltage risk coefficient and the second voltage risk coefficient; 2. The real-time adjustment method for distributed resources on the low-voltage side of a distribution network according to claim 1, wherein The step of performing relationship recognition on the historical operation data after dimension reduction processing to determine the station affiliation relationship of the power equipment, performing phase analysis on the power equipment with the same station affiliation relationship, and determining the topological structure between the distributed power equipment on the low-voltage side of the power grid includes: Construct an adjacency matrix according to the historical operation data after dimension reduction processing, calculate the sum of weights between all power equipment according to the adjacency matrix to obtain a degree matrix, and obtain a cluster matrix on the low-voltage side of the distribution network according to the adjacency matrix and the degree matrix; Calculate the eigenvalues of the cluster matrix and sort them, select the vectors corresponding to the preset eigenvalues to construct a vector matrix, and perform clustering processing on the row elements of the vector matrix to obtain the station affiliation relationship corresponding to the distributed power equipment; Perform equivalent modeling on the power grid lines corresponding to the power equipment belonging to the same station class, obtain the voltage data of each electronic equipment at different times in the power grid line, and represent it with a time series to obtain a voltage data curve sample; Obtain the turning points in the voltage data curve sample, perform importance marking based on a hierarchical method, segment the voltage data curve sample according to the importance marking result, and determine the upstream and downstream phase relationships between the power equipment based on the phase recognition correlation coefficient; Determine the topological structure on the low-voltage side of the distribution network according to the upstream and downstream phase relationships between the power equipment; 3. The real-time adjustment method for distributed resources on the low-voltage side of the distribution network according to claim 2, characterized in that The expression of the cluster matrix is: In the formula, represents the cluster matrix, represents the degree matrix, , represents the degree of the th power equipment, represents the adjacency matrix, represents the weight of the th power equipment to the th power equipment; Wherein, and respectively represent the th power equipment and the th power equipment, and The weight value between them satisfies a Gaussian distribution, represents the second-order norm, represents the standard deviation corresponding to the Gaussian distribution satisfied by the weight value, respectively represent 's neighborhood and 's neighborhood; The expression of the phase recognition correlation coefficient is: Wherein, represents the voltage data matrix corresponding to the th power equipment, represents the voltage data matrix corresponding to the th power equipment, represents the covariance between the voltage matrices of the th power equipment and the th power equipment, respectively represent the standard deviations corresponding to the th power equipment and the th power equipment.

4. The real-time adjustment method for distributed resources on the low-voltage side of a distribution network according to claim 1, characterized in that, The step of obtaining the voltage data of each power equipment in real time through the optimization platform includes: Obtain the historical voltage data and prediction credibility of the power equipment, and determine the first prediction model according to the historical voltage data and prediction credibility; Perform the first prediction on the voltage data of the power equipment according to the first prediction model, and exchange the first predicted value of the line voltage according to the line connection relationship of the power equipment. Process the first predicted value according to the node voltage correlation prediction model to obtain the voltage data corresponding to each power equipment.

5. The real-time adjustment method for distributed resources on the low-voltage side of a distribution network according to claim 4, wherein The expression of the first prediction model is: In the formula, represents the first predicted value, represents the hyperparameter of the first prediction model, represents the insensitive loss function, represents the relaxation factor corresponding to the th historical voltage data sample, represents the prediction confidence of the first prediction model, represents the first-order norm; The expression of the node voltage correlation prediction model is: In the formula, represents the voltage prediction data, , respectively represent the voltage measurement value and the credibility of the low-voltage side of the distribution network, , respectively represent the voltage measurement value and the credibility of the line layer connecting the power equipment to the distribution network, respectively represent the voltage measurement value and the credibility of the line layer connecting the power equipment to the user side.

6. The real-time adjustment method for distributed resources on the low-voltage side of a distribution network according to claim 1, wherein The expression of the single adjustment cost corresponding to the photovoltaic power equipment is: Wherein, represents the single adjustment cost corresponding to the photovoltaic power equipment, represents the equivalent input cost of a single adjustment of the photovoltaic power equipment, which is related to the input cost and the number of adjustment life times of the photovoltaic power equipment, represents the compensation electricity price per unit active power of photovoltaic, represents the photovoltaic curtailment penalty coefficient, represents the expected photovoltaic power generation; The expression of the single adjustment cost corresponding to the energy storage power equipment is: In the formula, represents the single - adjustment cost corresponding to the energy - storage power equipment, represents the equivalent input cost of a single adjustment of the energy - storage power equipment, which is related to the input cost and the number of adjustment life times of the energy - storage power equipment, represents the coefficient of charge - quantity change, respectively represent the charge - quantities of the energy - storage power equipment at moment and moment, represents the penalty coefficient for energy - storage power curtailment, represents the active power output of the energy - storage.

7. The real-time adjustment method for distributed resources on the low-voltage side of a distribution network according to claim 6, wherein The expression of the cost limit boundary constraint is: The step of determining voltage control of the power equipment according to the ratio of the first voltage danger coefficient and the second voltage danger coefficient includes: If the first voltage danger coefficient is greater than the second voltage danger coefficient, select the energy storage power equipment for system voltage control; If the first voltage danger coefficient is less than or equal to the second voltage danger coefficient, select the photovoltaic power equipment for system voltage control.

8. A real-time adjustment system for distributed resources on the low-voltage side of a distribution network, characterized in that, Including; A dimensionality reduction processing module, configured to obtain the historical operation data of the power equipment distributed on the low-voltage side of the distribution network, and perform standardization and feature dimensionality reduction processing on the obtained historical operation data; An identification module, configured to perform relationship identification on the historical operation data after dimensionality reduction processing to determine the station affiliation relationship of the power equipment, perform phase analysis on the power equipment with the same station affiliation relationship, and determine the topological structure between the power equipment distributed on the low-voltage side of the power grid according to the phase analysis; A fuzzy processing module, configured to establish a distributed optimization platform based on the topological structure, obtain the voltage data of each power equipment in real time through the optimization platform, and use the voltage offset and voltage fluctuation in the voltage data as the inputs of the fuzzy control system on the low-voltage side of the distribution network for fuzzy processing to obtain the voltage danger coefficient on the low-voltage side of the distribution network; A calculation module, configured to define the nodes where the photovoltaic power equipment and the energy storage power equipment on the low-voltage side of the distribution network are located as adjustment nodes, obtain the first voltage danger coefficient of the adjustment nodes and the corresponding single adjustment costs of the photovoltaic power equipment and the energy storage power equipment; A scheduling module, configured to obtain the charge state when the voltage on the low-voltage side of the distribution network exceeds the limit, determine the second voltage danger coefficient corresponding to the adjustment node when the voltage exceeds the limit based on the cost limit boundary constraint, and determine voltage control of the power equipment according to the ratio of the first voltage danger coefficient and the second voltage danger coefficient.

9. The real-time adjustment system for distributed resources on the low-voltage side of the distribution network according to claim 8, wherein The identification module includes: A construction unit, configured to construct an adjacency matrix according to the historical operation data after dimensionality reduction processing, calculate the sum of weights between all power equipment according to the adjacency matrix to obtain a degree matrix, and obtain a cluster matrix on the low-voltage side of the distribution network according to the adjacency matrix and the degree matrix; A cluster unit, which is used to calculate the eigenvalues of a cluster matrix, sort them, select vectors corresponding to preset eigenvalues to construct a vector matrix, and perform clustering processing on the row elements of the vector matrix to obtain the station affiliation relationships corresponding to distributed power equipment; An equivalent unit, which is used to perform equivalent modeling on the power grid lines corresponding to power equipment belonging to the same station type, obtain voltage data of each electronic device at different times in the power grid lines, and represent them with time series to obtain voltage data curve samples; A marking unit, which is used to obtain turning points in the voltage data curve samples, perform importance marking based on a ranking method, segment the voltage data curve samples according to the importance marking results, and determine the upstream and downstream phase relationships between power equipment based on the phase recognition correlation coefficient; A determination unit, which is used to determine the topological structure of the low-voltage side of the distribution network according to the upstream and downstream phase relationships between power equipment.

10. The real-time adjustment system for distributed resources on the low-voltage side of a distribution network according to claim 9, wherein In the recognition module, The expression of the cluster matrix is: In the formula, represents the cluster matrix, represents the degree matrix, , represents the degree of the th power equipment, represents the adjacency matrix, represents the weight of the th power equipment on the th power equipment; Wherein, and respectively represent the th power equipment and the th power equipment, and The weight value between them satisfies a Gaussian distribution, represents the second-order norm, represents the standard deviation corresponding to the Gaussian distribution satisfied by the weight value, respectively represent 's neighborhood and 's neighborhood; The expression of the phase recognition correlation coefficient is: In the formula, represents the voltage data matrix corresponding to the th power equipment, represents the voltage data matrix corresponding to the th power equipment, represents the covariance between the voltage matrices of the th power equipment and the th power equipment, respectively represent the standard deviations corresponding to the th power equipment and the th power equipment.

Images