Power distribution network locating and sizing method and device and computer equipment

Abstract

The invention is suitable for the technical field of power systems, and particularly relates to a power distribution network locating and sizing method and device and computer equipment. The method comprises the following steps: acquiring historical data of a wind turbine set and a photovoltaic set in a to-be-evaluated power distribution network to construct an output probability function and a joint output probability function of the wind turbine set and the photovoltaic set to obtain a joint output probability function, sampling in each time period, and calculating to obtain the output of the corresponding time period according to the sampling result of each time period and the joint output probability function. And according to the obtained network loss function, the node voltage fluctuation function and the optimal capacity target function, constructing a total target function of the to-be-evaluated power distribution network, obtaining charging historical data and an energy storage model of the charging station, and determining an optimal capacity and an optimal position by combining a preset neural network model and taking the total target function as a target. And the position and the capacity of the charging station are determined by comparing parameters such as network loss and voltage change, so that the suppression of the charging station on the uncertainty of the distributed energy is realized.

Description

Technical Field

[0001] The present application is applicable to the technical field of power systems, and in particular, relates to a method, device and computer equipment for site selection and capacity determination of a distribution network. Background Art

[0002] With the increasing proportion of distributed generation (DG) in the distribution network, the power consumption of active distribution network (ADN) has gradually increased, resulting in a continuous increase in the peak-to-valley difference of the load at each node. In order to improve the energy efficiency and stability of the distribution network system containing distributed energy, the optimal configuration of the distribution network considering a high proportion of wind and solar devices and electric vehicles (EV) is studied. Considering the use of the dispatchable potential model of electric vehicle clusters instead of the energy storage model as a control measure to reduce its own energy consumption risk, it is worth further studying the solution of using the improved multi-objective particle swarm optimizer (MOPSO) to deal with the distribution network loss and voltage fluctuation. MOPSO is an efficient algorithm for dealing with optimization problems, with the advantages of fast convergence speed, few controlled parameters, and strong robustness.

[0003] Since the current active distribution network contains a large amount of distributed energy and the model is complex and difficult to solve, although the use of the MOPSO algorithm for model solving can solve the problem to a certain extent, the optimization performance of the MOPSO algorithm may be highly affected by the selection of control parameters and mutation strategies, because constant parameter settings or a single mutation strategy cannot handle all types of problems well or adapt to different stages of search. Therefore, the MOPSO algorithm is prone to slow convergence and fall into local optimality in the later stages of iteration.

[0004] Therefore, how to utilize distributed energy sources such as wind power and photovoltaic power and model construction constraint solving to improve the efficiency and accuracy of distribution network site selection and sizing has become an urgent problem to be solved. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a distribution network site selection and sizing method, device and computer equipment to solve the problem of how to use distributed energy such as wind power and photovoltaic power and model construction constraint solving to improve the efficiency and accuracy of distribution network site selection and sizing.

[0006] In a first aspect, an embodiment of the present application provides a method for site selection and capacity determination of a distribution network, the method comprising: Acquire first historical data of a wind turbine group and second historical data of a photovoltaic group in the distribution network to be evaluated, construct a first output probability function of the wind turbine group according to the first historical data, and construct a second output probability function of the photovoltaic group according to the second historical data; Using a preset joint function, the first output probability function and the second output probability function are combined to obtain a combined output probability function, sampling the combined function in each time period to obtain a sampling result in each time period, and calculating the output of the corresponding time period according to the sampling result in each time period and the combined output probability function; Obtaining a network loss function, a node voltage fluctuation function, and an optimal capacity objective function of the distribution network to be evaluated, and constructing an overall objective function of the distribution network to be evaluated according to the network loss function, the node voltage fluctuation function, and the optimal capacity objective function; An energy storage model with an electric vehicle charging station as an energy storage device and charging history data of known charging stations with different locations and capacities are obtained, and the optimal capacity and optimal location of the electric vehicle charging station are determined based on the energy storage model, the charging history data and the output, in combination with a preset neural network model, with the overall objective function as the target.

[0007] In a second aspect, an embodiment of the present application provides a distribution network site selection and capacity determination device, the distribution network site selection and capacity determination device comprising: A wind and solar data analysis module, used to obtain first historical data of a wind turbine group and second historical data of a photovoltaic group in the distribution network to be evaluated, and to construct a first output probability function of the wind turbine group according to the first historical data, and to construct a second output probability function of the photovoltaic group according to the second historical data; A wind-solar data combination module, configured to combine the first output probability function and the second output probability function using a preset combination function to obtain a combined output probability function, sample the combined function in each time period to obtain a sampling result in each time period, and calculate the output of the corresponding time period according to the sampling result in each time period and the combined output probability function; An objective function construction module is used to obtain a network loss function, a node voltage fluctuation function and an optimal capacity objective function of the distribution network to be evaluated, and construct an overall objective function of the distribution network to be evaluated according to the network loss function, the node voltage fluctuation function and the optimal capacity objective function; The optimal location and capacity determination module is used to obtain an energy storage model with an electric vehicle charging station as an energy storage device, and charging history data of known charging stations of different locations and capacities, and determine the optimal capacity and optimal location of the electric vehicle charging station based on the energy storage model, the charging history data and the output, combined with a preset neural network model, with the overall objective function as the target.

[0008] In a third aspect, an embodiment of the present application provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the distribution network site selection and sizing method as described in the first aspect when executing the computer program.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the distribution network site selection and sizing method as described in the first aspect is implemented.

[0010] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the present application obtains first historical data of wind turbines and second historical data of photovoltaic groups in the distribution network to be evaluated, constructs a first output probability function of the wind turbines according to the first historical data, constructs a second output probability function of the photovoltaic group according to the second historical data, uses a preset joint function to combine the first output probability function and the second output probability function to obtain a joint output probability function, samples the joint function in each time period to obtain a sampling result for each time period, calculates the output of the corresponding time period according to the sampling result for each time period and the joint output probability function, obtains a network loss function, a node voltage fluctuation function and an optimal capacity target function of the distribution network to be evaluated, constructs a total target function of the distribution network to be evaluated according to the network loss function, the node voltage fluctuation function and the optimal capacity target function, obtains an energy storage model with an electric vehicle charging station as an energy storage device, and charging history data of known charging stations of different locations and capacities, and determines the optimal capacity and optimal location of the electric vehicle charging station according to the energy storage model, the charging history data and the output, combined with a preset neural network model, with the total target function as the target. By comparing relevant parameters such as network loss and voltage change, the location and capacity of the charging station can be determined, thereby achieving the smoothing of the uncertainty of distributed energy by the shared energy storage characteristics of electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0012] Figure 1 It is a flow chart of a method for selecting a site and determining the capacity of a distribution network provided in Example 1 of the present application; Figure 2 This is a schematic diagram of a process for generating a wind-solar day curve provided in Example 1 of the present application; Figure 3 is a SOC variation curve diagram of an energy storage device 1 provided in Example 1 of the present application; Figure 4 It is a SOC variation curve diagram of an energy storage device 2 provided in Example 1 of the present application; Figure 5 It is a visual schematic diagram of the site selection of an energy storage device provided in Example 1 of the present application; Figure 6 This is a schematic diagram of wind power output uncertainty provided in the first embodiment of the present application; Figure 7 This is a schematic diagram of an output of a photoelectric uncertainty output provided in Example 1 of the present application; Figure 8 This is a schematic diagram of a test sample composition of an EV entry time provided in Example 1 of the present application; Fig. 9 This is a schematic diagram of a test sample composition of an EV's exit time provided in the first embodiment of the present application; Fig.10 It is a schematic diagram of a test sample composition of an initial SOC of an EV provided in Example 1 of the present application; Fig.11 It is a structural schematic diagram of a distribution network site selection and capacity determination device provided in Example 2 of the present application; Fig.12 It is a structural diagram of a computer device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0013] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0014] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0015] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0016] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0017] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0018] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0019] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0020] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0021] It should be understood that the size of the serial numbers of the steps in the following embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0022] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.

[0023] See also Figure 1 , is a flow chart of a method for site selection and capacity determination of a distribution network provided in Embodiment 1 of the present application. The method for site selection and capacity determination of a distribution network can be applied to a computer device, and the computer device executes a corresponding program to implement the method. The method for site selection and capacity determination of a distribution network includes the following steps: Step S101, obtaining first historical data of wind turbines and second historical data of photovoltaic groups in the distribution network to be evaluated, constructing a first output probability function of the wind turbines according to the first historical data, and constructing a second output probability function of the photovoltaic groups according to the second historical data.

[0024] Among them, the distribution network to be evaluated is ADN, and the distributed energy set in AND can include at least one photovoltaic group and at least one wind turbine group. Of course, in some other scenarios, the distributed energy can also include tidal turbine groups, thermal turbine groups, etc.

[0025] By acquiring the historical operation data of the photovoltaic group and the wind turbine group, the corresponding output probability distribution can be obtained, wherein the output probability distribution represents the possibility of supplying power to the distribution network in a time period. Optionally, constructing a first output probability function of the wind turbine group according to the first historical data, and constructing a second output probability function of the photovoltaic group according to the second historical data, includes: Using a nonparametric kernel density estimation method, the first historical data is fitted to obtain a kernel density estimation expression of the wind turbine group as a first output probability function; The second historical data is fitted using a nonparametric kernel density estimation method to obtain a kernel density estimate of the photovoltaic group expressed as a second output probability function.

[0026] Among them, the non-parametric kernel density estimation method fits the historical data of DG (including wind turbines and photovoltaic groups) to obtain the kernel density estimation expressions of wind turbines and photovoltaic groups, which can be specifically expressed as: In the formula, n is the number of samples, h is the window width, and K(·) is the kernel function. This nonparametric kernel density estimation method does not need to assume the distribution of historical data. Its advantage is that it can directly process the output data of the DG unit and generate the output probability function of the corresponding unit in each period within a single day.

[0027] Step S102: Use a preset joint function to combine the first output probability function and the second output probability function to obtain a joint output probability function, sample the joint function in each time period to obtain a sampling result for each time period, and calculate the output of the corresponding time period based on the sampling result of each time period and the joint output probability function.

[0028] The joint function is used to describe the relationship between distributed energy sources such as wind power and photovoltaic power to achieve the combination of distributed energy sources. The joint function can include all variations of the Copula function, for example, the Frank Copula function. The joint function combines the first processing probability function and the second output probability function to obtain a joint output probability function, which is used to express the output situation in the wind and solar scene.

[0029] like Figure 2 As shown, it is a schematic diagram of the process of generating a wind-solar day curve provided in the first embodiment of the present application. In order to describe the output of wind and solar, the joint function is sampled to obtain the sampling result, wherein the sampling result is the corresponding time point. Substituting the sampling result into the joint output probability function can obtain the corresponding output result, which can be described as the output for the whole year or the output for a single day, etc.

[0030] Combined with the time period, the output can generate an output curve, such as Figure 3 As shown, it is a schematic diagram of wind power output uncertainty provided in the first embodiment of the present application, such as Figure 4 As shown, it is a schematic diagram of the output of a photoelectric uncertainty output provided in the first embodiment of the present application. Optionally, a preset joint function is used to combine the first output probability function and the second output probability function to obtain a joint output probability function, including: The optimal Copula joint probability function is used to describe the correlation between the first output probability function and the second output probability function, and the joint output probability function is obtained as follows: In the formula, F n (x i ,y i ) is the probability function of the combined output of wind and solar, C(,) is the optimal Copula joint probability function, is the first output probability function, is the second output probability function.

[0031] Among them, the Frank Copula function is used as the optimal Copula joint probability function to perform the joint, and the Frank Copula function is subsequently sampled to obtain the sampling results. The output of each period is calculated based on the sampling results and the joint output probability function, and a typical daily curve considering the DG correlation and randomness is generated.

[0032] Step S103, obtaining the network loss function, node voltage fluctuation function and optimal capacity objective function of the distribution network to be evaluated, and constructing the total objective function of the distribution network to be evaluated according to the network loss function, node voltage fluctuation function and optimal capacity objective function.

[0033] Among them, the network loss function represents the transmission loss of distributed energy. Each distributed energy corresponds to a loss, and the sum of the losses can be used as the network loss of the entire ADN, thus forming a network loss function.

[0034] The node voltage fluctuation function represents the voltage difference between the nodes of each distribution network (for example, distribution stations, etc.). The voltage difference between two nodes should meet the standard voltage. The node voltage fluctuation function is constructed by summing the relationship between the voltage difference between all nodes and the standard voltage as the node voltage fluctuation of the entire AND.

[0035] The optimal capacity objective function represents the charge and discharge capacity of the energy storage device (this application uses an electric vehicle charging station as the energy storage device) per unit time. The sum of the capacities of all energy storage devices in AND can be used as the optimal capacity of the entire AND, thereby forming an optimal capacity function.

[0036] Optionally, a network loss function, a node voltage fluctuation function, and an optimal capacity objective function of the distribution network to be evaluated are obtained, and a total objective function of the distribution network to be evaluated is constructed based on the network loss function, the node voltage fluctuation function, and the optimal capacity objective function, including: The voltage and standard voltage between each node are obtained. According to the voltage and standard voltage between each node, the sum of the node voltage fluctuations is calculated as the node voltage fluctuation function, as follows: Where V ij is the voltage between the i-th node and the j-th node, is the standard voltage; Obtain the unit network loss cost, each branch current and branch resistance of the distribution network to be evaluated, and calculate the sum of network losses as the network loss function based on the unit network loss cost, each branch current and branch resistance, as follows: In the formula, c loss is the unit network loss cost, Eline is the set of branches in the distribution network to be evaluated, I ij，t is the branch current of the ijth branch, r ij is the branch resistance of the ijth branch; Obtain the charging power and discharging power of each energy storage device at any charging and discharging time. According to the charging power and discharging power, calculate the optimal capacity objective function as follows: Where t0 is the time when charging starts, P cha (j) is the charging power of the jth energy storage device, P dis (j) the discharge power of the jth energy storage device, Δt is any charge and discharge time; The network loss function, the node voltage fluctuation function and the optimal capacity objective function are added together, and the sum is determined as the total objective function of the distribution network to be evaluated.

[0037] The sum of the network loss function, the node voltage fluctuation function and the optimal capacity objective function is taken as the total objective function, and the total objective function is used for optimization, so as to obtain a comprehensive optimization result that takes into account the node voltage, network loss and optimal capacity.

[0038] Step S104, obtaining an energy storage model with an electric vehicle charging station as an energy storage device, and charging history data of known charging stations of different locations and capacities, and determining the optimal capacity and optimal location of the electric vehicle charging station based on the energy storage model, charging history data and output, combined with a preset neural network model, with the overall objective function as the goal.

[0039] The energy storage model is an expression of constraints on the power, charging and discharging of energy storage equipment, which can prevent data from deviating from the reasonable working scenario of electric vehicle charging stations in subsequent calculations. The charging history data of known charging stations with different locations and capacities are used to form the two variables of location and capacity, so that the optimal capacity and location can be predicted when the neural network model is used for training.

[0040] Optionally, an energy storage model using an electric vehicle charging station as an energy storage device is obtained, including: Get the state of charge expression and constraint expression of the electric vehicle charging station as follows: In the formula, is the state of charge of the electric vehicle charging station, η EV is the charging and discharging efficiency of electric vehicles, is the charging and discharging status of electric vehicles derived from historical data, are the upper and lower limits of the state of charge, respectively. are the state of charge and expected value of the electric vehicle when it leaves the charging station, They are the upper limits of the charging power and discharging power of electric vehicles respectively; According to the expression of state of charge and constraint conditions, an energy storage model with electric vehicle charging station as energy storage equipment is obtained.

[0041] Optionally, after calculating the output of the corresponding time period according to the sampling result of each time period and the joint output probability function, the method further includes: Generate a wind and solar daily output curve based on the output in each period; According to the energy storage model, charging history data and output, combined with the preset neural network model, the optimal capacity and optimal location of the electric vehicle charging station are determined with the overall objective function as the goal, including: According to the energy storage model, charging history data and wind and solar power daily output curve, combined with the preset neural network model, the optimal capacity and optimal location of the electric vehicle charging station are determined with the overall objective function as the goal.

[0042] Optionally, the preset neural network models include convolutional neural network and bidirectional long short-term memory network: According to the energy storage model, charging history data and wind and solar power daily output curve, combined with the preset neural network model, the optimal capacity and optimal location of the electric vehicle charging station are determined with the overall objective function as the goal, including: The charging history data and wind and solar daily power curves are input into the convolutional neural network, and the charging station characteristics and peak and trough characteristics are output; the charging station characteristics and peak and trough characteristics are input into the bidirectional long short-term memory network, and the energy storage model is used as a constraint. Combined with the overall objective function, the objective function values ​​of known charging stations at different locations and capacities are output, and the location and capacity corresponding to the optimal objective function value are determined as the optimal capacity and optimal location.

[0043] Among them, Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) form the CNN-Bi-LSTM algorithm, which processes the charging history data of electric vehicle charging stations as follows: CNN processes the initial data into high-dimensional mapping through local connections and weight sharing, effectively reflecting the data features. First, in the convolution layer operation, CNN greatly reduces the number of parameters in the training process by connecting local neurons and sharing convolution kernel weights, reducing the model training time while facilitating the extraction of data feature information. Secondly, in the pooling layer, by reducing the feature dimension of the data, the degree of model fitting is reduced, and the efficiency of obtaining data features is improved.

[0044] After the historical data of the arrival and departure time of the EV in the charging station and the initial SOC are known, they are divided into training group and test group. First, the data of the training group is used to explore the internal connection, and then the data of the test group is used to verify the accuracy. Compared with the traditional LSTM, Bi-LSTM adds a reverse LSTM process, which can better connect historical data with future data.

[0045] For example, three scenarios are established: Scenario 1: not connected to distributed power sources; Scenario 2: connected to distributed power sources, without adding energy storage; Scenario 3: connected to distributed power sources, with EVS energy storage.

[0046] Comparative analysis of the node voltage curves of the three scenarios shows that compared with scenario 1 without considering DG, the voltage fluctuation of scenario 2 is significantly improved after considering DG, indicating that the access of DG has a great impact on the voltage of the ADN system. In scenario 3, the voltage stability of the ADN system has been significantly improved after adding the energy storage model with the dispatchable potential of the EV cluster. Taking the voltage of node 16 as an example, the voltage deviation of node 16 in scenario 3 compared with node 16 in scenario 1 is 9.4%, while the voltage deviation of node 16 in scenario 2 compared with node 16 in scenario 1 is 40%, which fully verifies the effectiveness of the proposed scheme.

[0047] The comparison of the target values ​​of the multi-objective function results of the three scenarios is shown in Table 1: Table 1 Scenario 1 Scenario 2 Scene 3 Goal 1 0.319736 0.369132 0.36345 Goal 2 1.657225 0.947059 1.170143 Goal 3 2.565299 As can be seen from Table 1, the ADN network vulnerability of scenario 2 after adding DG is improved compared with scenario 1. Considering the addition of EV cluster energy storage, scenario 3 reduces the system network vulnerability compared with scenario 2, and further reduces the system network loss compared with scenario 1.

[0048] Figure 3 and Figure 4 The SOC variation curve of the cluster energy storage of the two energy storage devices in scenario 3. It can be seen that the two energy storage devices maintain the SOC range in the 10:00-15:00 time period when the DG output is higher to cope with the impact of the uncertainty of the DG output. When the DG output is higher, the energy storage device performs a charging process to absorb the additional output of the DG; when the DG output is lower, the discharge operation is performed to compensate for the insufficient DG output, thereby verifying the effectiveness of the proposed scheme in smoothing DG fluctuations.

[0049] Figure 5 As the final site selection location for the electric vehicle charging station as the energy storage device, after considering the site selection and sizing model of the energy storage device, the 24-hour average voltage of node 16 and node 31 in scenario 1 and scenario 3 decreased by 29.5% and 21.5%, respectively, which fully verified the advantage of energy storage equipment in smoothing ADN voltage fluctuations.

[0050] The DG output probability density curve obtained by the Frank Copula function is as follows: Figure 6 and 7 As shown, the output power in the figure is expressed in per unit. According to the scenario generation method, 500 wind-solar complementary scenarios are generated and the generated wind power and photovoltaic output scenarios are reduced, and the probability of each scenario is calculated. The results of DG scenario generation can more accurately generate the randomness and correlation of the DG unit output in the selected area. The DG data after the above data processing is conducive to the overall planning of the ADN system in the early stage of construction, further improving the operational reliability of the AND system.

[0051] Depend on Figure 8 , Fig. 9 and Fig.10 It can be seen that after using the CNN-Bi-LSTM model to mine and predict the rules of EV cluster historical data, the accuracy is improved compared to the unpredicted scenario and other initial algorithms, which shows that it meets the actual needs of ADN planning. Therefore, the distribution network site selection and sizing method proposed in this application that considers the uncertainty of wind and solar power and shared energy storage of electric vehicles has better economic efficiency, fully considers the ability of active distribution networks to absorb the output of distributed power sources, and improves the overall economy of active distribution networks through multi-objective particle swarm algorithms while reducing the energy cost of the system.

[0052] The embodiment of the present application obtains first historical data of wind turbines and second historical data of photovoltaic groups in the distribution network to be evaluated, constructs a first output probability function of the wind turbines according to the first historical data, constructs a second output probability function of the photovoltaic group according to the second historical data, uses a preset joint function to combine the first output probability function and the second output probability function to obtain a joint output probability function, samples the joint function in each time period to obtain a sampling result for each time period, calculates the output of the corresponding time period according to the sampling result of each time period and the joint output probability function, obtains the network loss function, the node voltage fluctuation function and the optimal capacity objective function of the distribution network to be evaluated, constructs the total objective function of the distribution network to be evaluated according to the network loss function, the node voltage fluctuation function and the optimal capacity objective function, obtains an energy storage model with an electric vehicle charging station as an energy storage device, and charging history data of known charging stations of different locations and capacities, and determines the optimal capacity and optimal location of the electric vehicle charging station according to the energy storage model, the charging history data and the output, in combination with a preset neural network model, with the total objective function as the goal. By comparing relevant parameters such as network loss and voltage change, the location and capacity of the charging station can be determined, thereby achieving the smoothing of the uncertainty of distributed energy by the shared energy storage characteristics of electric vehicles.

[0053] Corresponding to the distribution network site selection and capacity determination method in the above embodiment, Fig.11 The structural block diagram of the distribution network site selection and capacity determination device provided in the second embodiment of the present application is shown. For the convenience of explanation, only the part related to the embodiment of the present application is shown.

[0054] See also Fig.11 , the distribution network site selection and capacity determination device includes: The wind and solar data analysis module 111 is used to obtain the first historical data of the wind turbine group and the second historical data of the photovoltaic group in the distribution network to be evaluated, and to construct a first output probability function of the wind turbine group according to the first historical data, and to construct a second output probability function of the photovoltaic group according to the second historical data; The wind-solar data combining module 112 is used to combine the first output probability function and the second output probability function using a preset combining function to obtain a combined output probability function, sample the combined function in each time period to obtain a sampling result in each time period, and calculate the output of the corresponding time period according to the sampling result in each time period and the combined output probability function; The objective function construction module 113 is used to obtain the network loss function, the node voltage fluctuation function and the optimal capacity objective function of the distribution network to be evaluated, and construct the total objective function of the distribution network to be evaluated according to the network loss function, the node voltage fluctuation function and the optimal capacity objective function; The optimal location and capacity determination module 114 is used to obtain the energy storage model with the electric vehicle charging station as the energy storage device, and the charging history data of known charging stations with different locations and capacities, and determine the optimal capacity and optimal location of the electric vehicle charging station based on the energy storage model, charging history data and output, combined with a preset neural network model, with the overall objective function as the goal.

[0055] Optionally, the wind and solar data analysis module 111 includes: A first analysis unit is used to fit the first historical data using a non-parametric kernel density estimation method to obtain a kernel density estimation expression of the wind turbine group as a first output probability function; The second analysis unit is used to use a non-parametric kernel density estimation method to fit the second historical data to obtain a kernel density estimate of the photovoltaic group expressed as a second output probability function.

[0056] Optionally, the wind and solar data combining module 112 includes: The joint calculation unit is used to use the optimal Copula joint probability function to describe the correlation between the first output probability function and the second output probability function to obtain a joint output probability function as follows: In the formula, F n (x i ,y i) is the probability function of the combined output of wind and solar, C(,) is the optimal Copula joint probability function, is the first output probability function, is the second output probability function.

[0057] Optionally, the objective function construction module 113 includes: The node voltage unit is used to obtain the voltage between each node and the standard voltage. According to the voltage between each node and the standard voltage, the sum of the node voltage fluctuations is calculated as the node voltage fluctuation function, as follows: Where V ij is the voltage between the i-th node and the j-th node, is the standard voltage; The network loss unit is used to obtain the unit network loss cost, each branch current and branch resistance of the distribution network to be evaluated. According to the unit network loss cost, each branch current and branch resistance, the sum of the network loss is calculated as the network loss function, as follows: In the formula, c loss is the unit network loss cost, E line is the set of branches in the distribution network to be evaluated, I ij，t is the branch current of the ijth branch, r ij is the branch resistance of the ijth branch; The energy storage device capacity unit is used to obtain the charging power and discharging power of each energy storage device at any charging and discharging time. According to the charging power and discharging power, the optimal capacity objective function is calculated as follows: Where t0 is the time when charging starts, P cha (j) is the charging power of the jth energy storage device, P dis (j) the discharge power of the jth energy storage device, Δt is any charge and discharge time; The objective function construction unit is used to add the network loss function, the node voltage fluctuation function and the optimal capacity objective function, and determine the addition result as the total objective function of the distribution network to be evaluated.

[0058] Optionally, the optimal addressing and volume determination module 114 includes: The constraint acquisition unit is used to obtain the state of charge expression and constraint condition expression of the electric vehicle charging station, as follows: In the formula, is the state of charge of the electric vehicle charging station, η EV is the charging and discharging efficiency of electric vehicles, is the charging and discharging status of electric vehicles derived from historical data, are the upper and lower limits of the state of charge, respectively. are the state of charge and expected value of the electric vehicle when it leaves the charging station, They are the upper limits of the charging power and discharging power of electric vehicles respectively; The energy storage model building unit is used to obtain an energy storage model with an electric vehicle charging station as an energy storage device according to the charge state expression and constraint condition expression.

[0059] Optionally, the distribution network site selection and capacity determination device further includes: The curve generation module is used to generate a wind and solar power daily output curve according to the output of each period after calculating the output of the corresponding period according to the sampling results of each period and the joint output probability function; The optimal addressing and volume determination module 114 includes: The optimal location and capacity determination unit is used to determine the optimal capacity and optimal location of the electric vehicle charging station based on the energy storage model, charging history data and wind and solar power daily output curve, combined with a preset neural network model, with the overall objective function as the goal.

[0060] Optionally, the preset neural network models include convolutional neural network and bidirectional long short-term memory network: The most preferred location for the fixed volume unit includes: The feature analysis subunit is used to input charging history data and wind and solar power daily output curves into the convolutional neural network, and output charging station characteristics and peak and trough characteristics; The site selection and capacity determination calculation subunit is used to input the charging station characteristics and peak and trough characteristics into the bidirectional long short-term memory network, use the energy storage model as a constraint, combine with the overall objective function, output the objective function values ​​of known charging stations of different locations and capacities, and determine the location and capacity corresponding to the optimal objective function value as the optimal capacity and optimal location.

[0061] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0062] Fig.12 This is a schematic diagram of the structure of a computer device provided in Example 3 of this application. Fig.12 As shown, the computer device of this embodiment includes: at least one processor ( Fig.12 Only one is shown), a memory, and a computer program stored in the memory and executable on at least one processor, wherein when the processor executes the computer program, the steps in any of the above-mentioned distribution network site selection and capacity determination method embodiments are implemented.

[0063] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that Fig.12 This is merely an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, it may also include a network interface, a display screen, and an input device.

[0064] The processor may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0065] The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory may be the memory of a computer device, and the internal memory provides an environment for the operation of an operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be a hard disk of a computer device, and in other embodiments may also be an external storage device of a computer device, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on a computer device. Further, the memory may also include both an internal storage unit of a computer device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as program codes of computer programs, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0066] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiment when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0067] The present application implements all or part of the processes in the above-mentioned embodiment method, and may also be completed through a computer program product. When the computer program product runs on a computer device, the computer device can implement the steps in the above-mentioned method embodiment when executing the computer program product.

[0068] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0069] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0070] In the embodiments provided in the present application, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0071] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for selecting a site and determining the capacity of a distribution network, characterized in that: The methods for site selection and capacity determination of distribution networks include: Acquire first historical data of a wind turbine group and second historical data of a photovoltaic group in the distribution network to be evaluated, construct a first output probability function of the wind turbine group according to the first historical data, and construct a second output probability function of the photovoltaic group according to the second historical data; Using a preset joint function, the first output probability function and the second output probability function are combined to obtain a combined output probability function, sampling the combined function in each time period to obtain a sampling result in each time period, and calculating the output of the corresponding time period according to the sampling result in each time period and the combined output probability function; Obtaining a network loss function, a node voltage fluctuation function, and an optimal capacity objective function of the distribution network to be evaluated, and constructing an overall objective function of the distribution network to be evaluated according to the network loss function, the node voltage fluctuation function, and the optimal capacity objective function; An energy storage model with an electric vehicle charging station as an energy storage device and charging history data of known charging stations with different locations and capacities are obtained, and the optimal capacity and optimal location of the electric vehicle charging station are determined based on the energy storage model, the charging history data and the output, in combination with a preset neural network model, with the overall objective function as the target.

2. The method for site selection and capacity determination of a distribution network according to claim 1, characterized in that: The step of constructing a first output probability function of the wind turbine group according to the first historical data, and constructing a second output probability function of the photovoltaic group according to the second historical data, includes: Using a non-parametric kernel density estimation method, fitting the first historical data to obtain a kernel density estimation expression of the wind turbine group as a first output probability function; The second historical data is fitted using the nonparametric kernel density estimation method to obtain a kernel density estimate of the photovoltaic group expressed as a second output probability function.

3. The method for site selection and capacity determination of a distribution network according to claim 1, characterized in that: The using of a preset joint function to combine the first output probability function and the second output probability function to obtain a joint output probability function includes: using an optimal Copula joint probability function to describe the correlation between the first output probability function and the second output probability function to obtain a joint output probability function, as follows: In the formula, F n (x i ,y i ) is the probability function of the combined output of wind and solar, C(,) is the optimal Copula joint probability function, is the first output probability function, is the second output probability function.

4. The method for selecting a site and determining the capacity of a distribution network according to claim 1, characterized in that: The obtaining of the network loss function, the node voltage fluctuation function and the optimal capacity objective function of the distribution network to be evaluated, and constructing the total objective function of the distribution network to be evaluated according to the network loss function, the node voltage fluctuation function and the optimal capacity objective function, comprises: obtaining the voltage between each node and the standard voltage, and calculating the sum of the node voltage fluctuations as the node voltage fluctuation function according to the voltage between each node and the standard voltage, as follows: Where V ij is the voltage between the i-th node and the j-th node, is the standard voltage; The unit network loss cost, each branch current and branch resistance of the distribution network to be evaluated are obtained, and the sum of the network loss is calculated as a network loss function according to the unit network loss cost, each branch current and branch resistance, as follows: In the formula, c loss is the unit network loss cost, E line is the branch set in the distribution network to be evaluated, I ij，t is the branch current of the ijth branch, r ij is the branch resistance of the ijth branch; The charging power and discharging power of each energy storage device at any charging and discharging time are obtained, and the optimal capacity objective function is calculated based on the charging power and discharging power, as follows: Where t0 is the time when charging starts, P cha (j) is the charging power of the jth energy storage device, P dis (j) the discharge power of the jth energy storage device, Δt is any charge and discharge time; The network loss function, the node voltage fluctuation function and the optimal capacity objective function are added together, and the addition result is determined as the total objective function of the distribution network to be evaluated.

5. The method for selecting a site and determining the capacity of a distribution network according to claim 3, characterized in that: The step of obtaining an energy storage model using an electric vehicle charging station as an energy storage device includes: Get the state of charge expression and constraint expression of the electric vehicle charging station as follows: In the formula, is the state of charge of the electric vehicle charging station, η EV is the charging and discharging efficiency of electric vehicles, is the charging and discharging status of electric vehicles derived from historical data, are the upper and lower limits of the state of charge, respectively. are the state of charge and expected value of the electric vehicle when it leaves the charging station, They are the upper limits of the charging power and discharging power of electric vehicles respectively; According to the state of charge expression and the constraint condition expression, an energy storage model with the electric vehicle charging station as the energy storage device is obtained.

6. The method for site selection and capacity determination of a distribution network according to any one of claims 1 to 5, characterized in that: After calculating the output of the corresponding time period according to the sampling result of each time period and the joint output probability function, the method further includes: Generate a wind and solar daily output curve according to the output of each period; The method of determining the optimal capacity and optimal location of the electric vehicle charging station based on the energy storage model, the charging history data and the output in combination with a preset neural network model and taking the overall objective function as a target includes: According to the energy storage model, the charging history data and the wind and solar day output curve, combined with a preset neural network model, the optimal capacity and optimal location of the electric vehicle charging station are determined with the overall objective function as the goal.

7. The method for selecting a site and determining the capacity of a distribution network according to claim 6, characterized in that: The preset neural network model includes a convolutional neural network and a bidirectional long short-term memory network: The method of determining the optimal capacity and optimal location of the electric vehicle charging station based on the energy storage model, the charging history data and the wind and solar day power curve in combination with a preset neural network model and taking the total objective function as a target includes: Input the charging history data and the wind and solar daily power curve into the convolutional neural network, and output charging station characteristics and peak and trough characteristics; The charging station characteristics and the peak and trough characteristics are input into the bidirectional long short-term memory network. Taking the energy storage model as a constraint and combining it with the overall objective function, the objective function values ​​of known charging stations of different locations and capacities are output, and the location and capacity corresponding to the optimal objective function value are determined as the optimal capacity and optimal location.

8. A distribution network site selection and capacity determination device, characterized in that: The distribution network site selection and capacity determination device comprises: A wind and solar data analysis module, used to obtain first historical data of a wind turbine group and second historical data of a photovoltaic group in the distribution network to be evaluated, and to construct a first output probability function of the wind turbine group according to the first historical data, and to construct a second output probability function of the photovoltaic group according to the second historical data; A wind-solar data combination module, configured to combine the first output probability function and the second output probability function using a preset combination function to obtain a combined output probability function, sample the combined function in each time period to obtain a sampling result in each time period, and calculate the output of the corresponding time period according to the sampling result in each time period and the combined output probability function; An objective function construction module is used to obtain a network loss function, a node voltage fluctuation function and an optimal capacity objective function of the distribution network to be evaluated, and construct an overall objective function of the distribution network to be evaluated according to the network loss function, the node voltage fluctuation function and the optimal capacity objective function; The optimal location and capacity determination module is used to obtain an energy storage model with an electric vehicle charging station as an energy storage device, and charging history data of known charging stations of different locations and capacities, and determine the optimal capacity and optimal location of the electric vehicle charging station based on the energy storage model, the charging history data and the output, combined with a preset neural network model, with the overall objective function as the target.

9. The device for selecting a site and determining the capacity of a distribution network according to claim 8, characterized in that: The wind and solar data analysis module comprises: A first analysis unit is used to fit the first historical data using a non-parametric kernel density estimation method to obtain a kernel density estimation expression of the wind turbine group as a first output probability function; The second analysis unit is used to use the non-parametric kernel density estimation method to fit the second historical data to obtain a kernel density estimation expression of the photovoltaic group as a second output probability function.

10. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for site selection and sizing of a distribution network as described in any one of claims 1 to 7 is implemented.

Images