Virtual power plant scheduling method and device, equipment, storage medium and program product

Abstract

The invention relates to a virtual power plant scheduling method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring illumination intensity historical data of a photovoltaic module in a virtual power plant and wind speed historical data of a wind turbine module in the virtual power plant; predicting the illumination intensity at the next moment based on the illumination intensity historical data; predicting the wind speed at the next moment based on the wind speed historical data; and scheduling the virtual power plant based on the predicted illumination intensity at the next moment and the predicted wind speed at the next moment. According to the invention, the variable load can be predicted to improve the effect of virtual power plant scheduling.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a scheduling method, device, equipment, storage medium and program product for a virtual power plant. Background Art

[0002] A virtual power plant is a special power plant that does not have a physical power plant. It uses information and software technology to achieve the aggregation and coordinated optimization of multiple distributed resources such as distributed power sources, energy storage, and adjustable loads in different spaces. Virtual power plants can provide grid operation services such as peak load regulation and frequency regulation, and can also participate in electricity market transactions. The current virtual power plant can be regarded as an advanced regional centralized power management model.

[0003] The existing virtual power plants have the following characteristics: First, the capacity of a single virtual power plant is small, while the number of virtual power plants is large; second, the virtual power plant and the grid have different access points, different network losses, different impacts on the flow, and large differences in electricity costs; third, the resource types of virtual power plants vary greatly. The above characteristics lead to the fact that if the traditional centralized dispatching method is used to dispatch virtual power plants, it is not only time-consuming and labor-intensive, but more importantly, it is impossible to dispatch them in a targeted manner according to the different characteristics of virtual power plants. The cloud-edge collaborative virtual power plant dispatching method can meet the current virtual power plant dispatching needs, and can perform global, non-real-time, and long-cycle big data processing and analysis through the cloud, which can play its advantages in long-term maintenance, business decision support and other fields. The processing and analysis of local, real-time, and short-cycle data at the edge can better support real-time intelligent decision-making of local businesses. In the cloud-edge collaborative environment, for virtual power plants, the information of distributed power sources, energy storage, and adjustable loads collected by sensors can be integrated and sent to the edge with simple data processing capabilities for automatic data entry, data preprocessing and other operations. The processed data is sent to the cloud for more complete data analysis and decision making based on the analysis results, and finally the decision results are sent back to the edge for scheduling of the virtual power plant. In this way, targeted scheduling can be achieved.

[0004] However, the traditional virtual power plant dispatching method using cloud-edge collaboration faces the problem of unpredictable variable loads. How to predict variable loads to improve the effect of virtual power plant dispatching is still an urgent problem to be solved. Summary of the invention

[0005] Based on this, it is necessary to provide a virtual power plant scheduling method, device, equipment, storage medium and program product that can predict variable load to improve the scheduling effect of virtual power plants in response to the above technical problems.

[0006] In a first aspect, the present application provides a scheduling method for a virtual power plant, the method comprising:

[0007] Obtain historical data on the light intensity of photovoltaic components in the virtual power plant and historical data on the wind speed of wind turbine components in the virtual power plant;

[0008] Based on the historical data of light intensity, predict the light intensity at the next moment;

[0009] Based on the historical wind speed data, predict the wind speed at the next moment;

[0010] The virtual power plant is dispatched based on the predicted light intensity at the next moment and the predicted wind speed at the next moment.

[0011] In one embodiment, the illumination intensity historical data includes N first historical data, where N is a natural number greater than 1; and predicting the illumination intensity at a next moment based on the illumination intensity historical data includes:

[0012] A first matrix is ​​constructed based on N first historical data;

[0013] The last w rows of data groups sorted from the first row to the last row in the first matrix are moved to the first w rows sorted from the first row to the last row without changing the sorting in the last w rows of data groups, until each row of data groups in the first matrix has been moved to obtain a second matrix, or, until the M rows of data groups that have not been moved in the first matrix cannot be moved according to the w rows, the M rows of data groups are moved to obtain the second matrix; wherein M is not less than zero and less than w; wherein the moving of the M rows of data groups includes: moving the remaining M rows of data groups to the position of the last M rows of data groups in the direction from the first row to the last row in the first matrix;

[0014] Constructing a first intermediate matrix according to the value of each element in the second matrix and the average value of the element; sorting the distance variance corresponding to each element in the first intermediate matrix in ascending order, and generating a third matrix according to the sorting result;

[0015] For two different intermediate variables of the third matrix, constrained linear least squares coefficients are used to constrain the variance values ​​of the two intermediate variables to be minimum;

[0016] Based on the constrained third matrix and the constrained linear least squares coefficients, the light intensity at the next moment is predicted.

[0017] In one embodiment, the first matrix is ​​constructed based on N first historical data, including:

[0018] Constructing an initial matrix based on N first historical data;

[0019] Obtaining the first-order derivative of the initial matrix, and calculating the standard deviation of the first-order derivative to obtain a standardized error;

[0020] The initial matrix is ​​corrected according to the standardized error to obtain a first matrix.

[0021] In one embodiment, the wind speed historical data includes N second historical data, where N is a natural number greater than 1; and predicting the wind speed at the next moment based on the wind speed historical data includes:

[0022] A fourth matrix is ​​constructed based on the N second historical data;

[0023] The last w rows of data groups sorted in the direction from the first row to the last row in the fourth matrix are moved to the first w rows sorted in the direction from the first row to the last row without changing the sorting in the last w rows of data groups, until each row of data groups in the fourth matrix has been moved to obtain a fifth matrix, or, until the M rows of data groups that have not been moved in the fourth matrix cannot be moved according to the w rows, the M rows of data groups are moved to obtain the fifth matrix; wherein M is not less than zero and less than w; wherein the moving of the M rows of data groups includes: moving the remaining M rows of data groups to the position of the last M rows of data groups in the direction from the first row to the last row in the fourth matrix;

[0024] Constructing a second intermediate matrix according to the value of each element in the fifth matrix and the average value of the element; sorting the distance variance corresponding to each element in the second intermediate matrix in ascending order, and generating a sixth matrix according to the sorting result;

[0025] For two different intermediate variables of the sixth matrix, constrained linear least squares coefficients are used to constrain the variance values ​​of the two intermediate variables to be minimum;

[0026] Based on the constrained sixth matrix and the constrained linear least squares coefficients, the wind speed at the next moment is predicted.

[0027] In one embodiment, the fourth matrix is ​​constructed based on the N second historical data, including:

[0028] Constructing an initial matrix based on N second historical data;

[0029] Obtaining the first-order derivative of the initial matrix, and calculating the standard deviation of the first-order derivative to obtain a standardized error;

[0030] The initial matrix is ​​corrected according to the standardized error to obtain a fourth matrix.

[0031] In one embodiment, the scheduling of the virtual power plant based on the predicted light intensity at the next moment and the predicted wind speed at the next moment includes:

[0032] When the predicted light intensity at the next moment is greater than or equal to the light intensity threshold, and the predicted wind speed at the next moment is greater than or equal to the wind speed threshold, the photovoltaic components, wind turbine components and energy storage components of the virtual power plant are used to power the load, and the photovoltaic components and wind turbine components are used to charge the energy storage components;

[0033] When the predicted light intensity at the next moment is greater than or equal to the light intensity threshold, and the predicted wind speed at the next moment is less than the wind speed threshold, the photovoltaic components and energy storage components of the virtual power plant are used to power the load;

[0034] When the predicted light intensity at the next moment is less than the light intensity threshold, and the predicted wind speed at the next moment is greater than or equal to the wind speed threshold, the wind turbine component and energy storage component of the virtual power plant are used to power the load;

[0035] When the predicted light intensity at the next moment is less than the light intensity threshold, and the predicted wind speed at the next moment is less than the wind speed threshold, the energy storage component is used to power the load.

[0036] In a second aspect, the present application provides a scheduling device for a virtual power plant, the device comprising:

[0037] An acquisition module, used to acquire historical data of light intensity of photovoltaic components in the virtual power plant and historical data of wind speed of wind turbine components in the virtual power plant;

[0038] A processing module, used for predicting the light intensity at a next moment based on the light intensity historical data;

[0039] The processing module is used to predict the wind speed at the next moment based on the historical wind speed data;

[0040] The scheduling module is used to schedule the virtual power plant based on the predicted light intensity at the next moment and the predicted wind speed at the next moment.

[0041] In a third aspect, the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the first aspect are implemented.

[0042] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect.

[0043] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0044] In the above-mentioned virtual power plant scheduling method, device, equipment, storage medium and program product, light intensity is an important factor affecting the efficiency of photovoltaic power generation. The higher the light intensity, the more light energy the solar electronic materials in the photovoltaic panel can absorb, thereby generating more electron flow, thereby improving the efficiency of power conversion. For wind power, wind power generation is closely related to wind speed. It is generally believed that the greater the wind speed (of course, it needs to be less than the overload wind speed, otherwise the wind turbine components are easily damaged), the faster the wind turbine rotor speed, and the greater the amount of electricity output by the generator. That is, light intensity and wind speed are both key factors affecting the load. Therefore, this embodiment judges the output of photovoltaic and wind turbines by judging the light intensity and wind speed, realizes the prediction of variable load, and then formulates the scheduling strategy of the virtual power plant to improve the effect of virtual power plant scheduling. In addition, it has been verified by experiments that the method provided in this embodiment can also improve the level of new energy consumption and reduce carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions 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 related drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 An application environment diagram of a scheduling method for a virtual power plant in one embodiment;

[0047] Figure 2 A schematic diagram of a flow chart of a scheduling method for a virtual power plant in one embodiment;

[0048] Figure 3 A partial flow chart of a scheduling method for a virtual power plant in one embodiment;

[0049] Figure 4 A partial flow chart of a scheduling method for a virtual power plant in another embodiment;

[0050] Figure 5 is a structural block diagram of a virtual power plant dispatching system in one embodiment;

[0051] FIG6 (a) is a data verification simulation diagram of light intensity using a scheduling method for a virtual power plant in one embodiment;

[0052] FIG6( b ) is a data verification simulation diagram of wind speed of a scheduling method using a virtual power plant in one embodiment;

[0053] Figure 7 It is a structural schematic diagram of a scheduling device of a virtual power plant in one embodiment;

[0054] Figure 8 FIG. 4 is a diagram showing the internal structure of an electronic device in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] The virtual power plant scheduling method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, sensors, smart meters and other devices. The terminal 102 is used to upload real-time data to the edge layer or server 104, and receive scheduling instructions from the server 104 at the same time. Among them, the edge layer is located between the cloud layer and the terminal layer, and is responsible for the preliminary processing of data, real-time response and communication with the server 104. The edge layer realizes localized processing of data by deploying edge computing nodes, reduces data transmission delays, and improves response speed. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. Preferably, the server 104 is a cloud server.

[0057] In an exemplary embodiment, Figure 2 As shown, a virtual power plant scheduling method is provided, and the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps 202 to 206. Among them:

[0058] Step 202, obtaining historical data of light intensity of photovoltaic components in the virtual power plant and historical data of wind speed of wind turbine components in the virtual power plant.

[0059] The control unit in the edge layer is used to obtain the historical data of light intensity of the photovoltaic components of the virtual power plant and the historical data of wind speed of the wind turbine components. The control unit then sends the obtained historical data of light intensity and wind speed to the server 104.

[0060] Exemplarily, the average daily light intensity in the past two years is obtained as the light intensity historical data.

[0061] Exemplarily, the average daily wind speed in the past two years is obtained as the wind speed historical data.

[0062] Step 204: predict the light intensity at the next moment based on the light intensity historical data.

[0063] The control unit of the server 104 predicts the light intensity at the next moment based on the light intensity history data.

[0064] For example, the moving average method can be used to predict the light intensity at the next moment. That is, by calculating the average value of all data in the light intensity history data, the average value of all calculated data is used as the predicted light intensity at the next moment. The moving average method has a certain robustness to abnormal data.

[0065] For example, the exponential smoothing method can be used to predict the light intensity at the next moment. That is, based on the idea of ​​weighted average, different weights are assigned to data at different time points to predict future values. The more recent the observation value, the greater the weight, while the older the weight, the smaller the weight. The final weighted average value is used as the predicted light intensity at the next moment.

[0066] Step 206: predict the wind speed at the next moment based on the historical wind speed data.

[0067] The control unit of the server 104 predicts the wind speed at the next moment based on the historical wind speed data.

[0068] For example, the moving average method can be used to predict the wind speed at the next moment. That is, by calculating the average value of all data in the wind speed history data, the average value of all calculated data is used as the predicted wind speed at the next moment. The moving average method has a certain robustness to abnormal data.

[0069] For example, the exponential smoothing method can be used to predict the wind speed at the next moment. That is, based on the idea of ​​weighted average, different weights are assigned to data at different time points to predict future values. The more recent the observation value, the greater the weight, while the older the weight, the smaller the weight. The final weighted average value is used as the predicted wind speed at the next moment.

[0070] Step 208, scheduling the virtual power plant based on the predicted light intensity at the next moment and the predicted wind speed at the next moment.

[0071] After combining different light intensities and different wind speeds, the corresponding virtual power plant has different scheduling strategies. The scheduling strategy of the virtual power plant can be that when the predicted light intensity at the next moment is greater than the first light intensity and less than the second light intensity, the photovoltaic components of the virtual power plant are used to supply power to the loads respectively. The scheduling strategy of the power plant can be that when the predicted wind speed at the next moment is greater than the first wind speed, and the predicted light intensity at the next moment is less than or equal to the first light intensity, the wind turbine components of the virtual power plant are used to supply power to the loads. Among them, the first light intensity, the second light intensity and the first wind speed can all be set according to actual needs.

[0072] For example, the predicted light intensity L at the next moment predict (L' N+1 ) is greater than or equal to the light intensity threshold, and the predicted wind speed W at the next moment predict (W' N+1 ) is greater than or equal to the wind speed threshold, the photovoltaic components, wind turbine components and energy storage components of the virtual power plant are used to power the load, and the photovoltaic components and wind turbine components can also be used to charge the energy storage components.

[0073] For example, the predicted light intensity L at the next moment predict (L' N+1 ) is greater than or equal to the light intensity threshold, and the predicted wind speed W at the next moment predict (W' N+1 ) is less than the wind speed threshold, the photovoltaic components and energy storage components of the virtual power plant are used to power the load.

[0074] For example, the predicted light intensity L at the next moment predict (L' N+1 ) is less than the light intensity threshold, and the predicted wind speed W at the next moment predict (W' N+1 ) is greater than or equal to the wind speed threshold, the wind turbine components and energy storage components of the virtual power plant are used to power the load.

[0075] For example, the predicted light intensity L at the next moment predict (L' N+1 ) is less than the light intensity threshold, and the predicted wind speed W at the next moment predict (W' N+1 ) is less than the wind speed threshold, the energy storage component is used to power the load.

[0076] It can be understood that the setting of the above-mentioned light intensity threshold and wind speed threshold needs to be determined according to the geographical location, load fluctuations, and grid topology nodes of the virtual power plant. It is preferred to set relatively high light intensity threshold and wind speed threshold to ensure the power supply stability of the virtual power plant.

[0077] In the above-mentioned virtual power plant scheduling method, light intensity is an important factor affecting the efficiency of photovoltaic power generation. The higher the light intensity, the more light energy the solar electronic materials in the photovoltaic panels can absorb, thereby generating more electron flow, thereby improving the efficiency of power conversion. For wind power, wind power generation is closely related to wind speed. It is generally believed that the greater the wind speed (of course, it needs to be less than the overload wind speed, otherwise the wind turbine components are easily damaged), the faster the wind turbine rotor speed, and the greater the amount of electricity output by the generator. That is, light intensity and wind speed are both key factors affecting the load. Therefore, this embodiment judges the output of photovoltaics and wind turbines by judging the light intensity and wind speed, realizes the prediction of variable loads, and then formulates the scheduling strategy of the virtual power plant to improve the scheduling effect of the virtual power plant. In addition, it has been verified by experiments that the method provided in this embodiment can also improve the level of new energy consumption and reduce carbon emissions.

[0078] In an exemplary embodiment, the illumination intensity historical data includes N first historical data, where N is a natural number greater than 1. Figure 3 As shown, step 204 includes steps 302 to 310. Among them:

[0079] Step 302: construct a first matrix based on N first historical data.

[0080] The number of rows and columns of the first matrix is ​​not limited in this embodiment.

[0081] Exemplarily, the first matrix can be constructed directly based on the N first historical data, and the obtained first matrix can be expressed as L his (L 1 …L N ), where L 1 Indicates the first historical data, L N It represents the Nth first historical data, where N represents the number of first historical data.

[0082] Exemplarily, an initial matrix may be constructed based on N first historical data, and the initial matrix may be expressed as: his (L 1 …L N ). Then obtain the first-order derivative of the initial matrix, which can be expressed as diff(L his (L 1 …L N )). The standard deviation of the first-order derivative is calculated to obtain the standardized error, which can be expressed as A= , Indicates the standard deviation, and A represents the standardized error. According to the standardized error A, the initial matrix diff (L his (L1 …L N )) is corrected, and the first matrix can be obtained ,in represents the first historical data after the first standardization, represents the first historical data after the N-1th normalization. Specifically, .

[0083] Step 304, the last w rows of data groups sorted from the first row to the last row in the first matrix are moved to the first w rows sorted from the first row to the last row without changing the order within the last w rows of data groups, until each row of data groups in the first matrix has been moved to obtain the second matrix, or, until the M rows of data groups that have not been moved in the first matrix cannot be moved according to the w rows, the M rows of data groups are moved to obtain the second matrix.

[0084] Wherein, M is not less than zero and less than w.

[0085] The step of moving the M rows of data groups includes: moving the remaining M rows of data groups to the position of the last M rows of data groups in the first matrix along the direction from the first row to the last row.

[0086] Assume that the first matrix is ​​represented as , the second matrix is ​​expressed as ,but .in, Represents the first historical data after matrix transformation, and w represents the number of conversion rows. Mt[]w means that the matrix to be transformed (i.e., the first matrix) is read upward starting from the wth-to-last row, with every w rows as the minimum unit. For example, matrix J'=Mt[J]2 means moving the second-to-last row and the first-to-last row of matrix J to the first and second rows of matrix J', moving the fourth-to-last row and the third-to-last row of matrix J to the third and fourth rows of matrix J', and so on. If the data group cannot be moved with w as the minimum unit at the end, move the data group with the remaining rows (i.e., the M-row data group) to the end of J'.

[0087] Step 306: construct a first intermediate matrix according to the value of each element in the second matrix and the average value of the elements.

[0088] Assume that the second matrix is ​​represented as , first construct the first intermediate matrix based on the second matrix, the first intermediate matrix is ​​expressed as . ,in, Represents the mean value function. Represents the second matrix Elements in , Represents the second matrix Elements in , Represents the second matrix Elements in .

[0089] Step 308 , sort the distance variance corresponding to each element in order from small to large, and generate a third matrix according to the sorting result.

[0090] The third matrix is ​​constructed based on the first intermediate matrix. Specifically, , () represents the mean function, () means sorting the results in ascending order. represents the first distance variance matrix and also represents the third matrix.

[0091] Step 310: for two different intermediate variables of the third matrix, constrain the variance values ​​of the two intermediate variables to be minimum by using constrained linear least square coefficients.

[0092] is a matrix (e.g. a 346 by 3 matrix), () function means to find the mean of a matrix, mean( ) returns a row vector, that is, an array, and then sorts the array to get ind as the distance variance matrix (that is, the third matrix).

[0093] The intermediate variable index of the third matrix is ​​obtained, and then two different intermediate variables are determined based on the intermediate variable index. Specifically, the intermediate variable index is represented by index, index=ind(1:w+1).

[0094] One of the two intermediate variables is denoted as AA1. AA1 can be The matrix takes four rows of index, for example, index=(1 2 3 4), then AA1 is taken The first to fourth rows of the matrix are assigned to AA1. The matrix is ​​a 346 by 3 matrix, so AA1 is a 4-row 3-column matrix. Similarly, AA2 is based on the index index. A matrix with four rows and one column to which the matrix is ​​assigned after taking its value.

[0095] The constrained linear least squares coefficients are used to constrain the variance of the two intermediate variables to the minimum, and the constrained third matrix is ​​obtained. The constrained third matrix can be expressed as Specifically, , st-1<g<1, where g represents the constrained linear least squares coefficient, represents one of the two intermediate variables, represents the other intermediate variable among the two intermediate variables. st represents the constraint condition of the formula. represents the prediction order, and in this embodiment, k=1:100. Then . It represents the predicted data obtained by using the constrained linear least squares coefficients, and in this step it represents the predicted light intensity at the next moment.

[0096] It can be understood that optimizing the prediction result using the constrained linear least squares coefficient g ensures that the sum of square errors between the prediction result and the actual data is minimized, that is, it ensures that the light intensity at the next moment conforms to the data regularity of the N first historical data in the historical light intensity.

[0097] In this embodiment, the constrained linear least squares coefficient g is used to optimize the prediction result, which ensures that the sum of square errors between the prediction result and the actual data is minimized, thereby improving the accuracy and credibility of the prediction result.

[0098] In an exemplary embodiment, the wind speed historical data includes N second historical data, where N is a natural number greater than 1. Figure 4 As shown, step 206 includes steps 402 to 410. Among them:

[0099] Step 402: construct a fourth matrix based on N second historical data.

[0100] The number of rows and columns of the fourth matrix is ​​not limited in this embodiment.

[0101] Exemplarily, a fourth matrix can be constructed directly based on the N second historical data, and the fourth matrix can be expressed as L his (L 1 …L N ), where L 1 Indicates the first and second historical data, L N It represents the Nth second historical data, where N represents the number of the second historical data.

[0102] Exemplarily, an initial matrix may be constructed based on N second historical data, and the initial matrix may be expressed as: his (L 1 …L N ). Then obtain the first-order derivative of the initial matrix, which can be expressed as diff(L his (L 1 …L N )). The standard deviation of the first-order derivative is calculated to obtain the standardized error, which can be expressed as A= , Indicates the standard deviation, and A represents the standardized error. According to the standardized error A, the initial matrix diff (L his (L 1 …L N )) is corrected, and the fourth matrix can be obtained ,in represents the second historical data after the first normalization, represents the second historical data after the N-1th normalization. Specifically, .

[0103] Step 404, the last w rows of data groups sorted from the first row to the last row in the fourth matrix are moved to the first w rows sorted from the first row to the last row without changing the sorting within the last w rows of data groups, until each row of data groups in the fourth matrix has been moved to obtain a fifth matrix, or, until the M rows of data groups that have not been moved in the fourth matrix cannot be moved according to the w rows, the M rows of data groups are moved to obtain the fifth matrix.

[0104] Wherein, M is not less than zero and less than w.

[0105] The step of moving the M rows of data groups includes: moving the remaining M rows of data groups to the position of the last M rows of data groups in the fourth matrix along the direction from the first row to the last row.

[0106] Assume that the fourth matrix is ​​represented as , the fifth matrix is ​​expressed as ,but .in, Represents the second historical data after matrix transformation, and w represents the number of conversion rows. Mt[]w means that the matrix to be transformed (i.e., the fourth matrix) is read upward starting from the wth-to-last row, with every w rows as the minimum unit. For example, matrix J'=Mt[J]2 means moving the second-to-last row and the first-to-last row of matrix J to the first and second rows of matrix J', moving the fourth-to-last row and the third-to-last row of matrix J to the third and fourth rows of matrix J', and so on. If the data group cannot be moved with w as the minimum unit at the end, move the data group of the remaining rows (i.e., the M-row data group) to the end of J'.

[0107] Step 406: construct a second intermediate matrix according to the value of each element in the fifth matrix and the average value of the elements.

[0108] Assume that the fifth matrix is ​​represented as , first construct the first intermediate matrix based on the fifth matrix, the first intermediate matrix is ​​expressed as . ,in, Represents the mean value function. Represents the fifth matrix Elements in , Represents the fifth matrix Elements in , Represents the fifth matrix Elements in .

[0109] Step 408 , sort the distance variance corresponding to each element in the second intermediate matrix in ascending order, and generate a sixth matrix according to the sorting result.

[0110] The sixth matrix is ​​constructed based on the second intermediate matrix. Specifically, , () represents the mean function, () means sorting the results in ascending order. represents the second distance variance matrix and also represents the sixth matrix.

[0111] Step 410: for two different intermediate variables of the sixth matrix, constrain the variance values ​​of the two intermediate variables to be minimum by using constrained linear least square coefficients.

[0112] is a matrix (e.g. a 346 by 3 matrix), () function means to find the mean of a matrix, mean( ) returns a row vector, that is, an array, and then sorts the array to get ind as the distance variance matrix (that is, the sixth matrix).

[0113] The intermediate variable index of the sixth matrix is ​​obtained, and then two different intermediate variables are determined based on the intermediate variable index. Specifically, the intermediate variable index is represented by index, index=ind(1:w+1).

[0114] One of the two intermediate variables is denoted as AA1. AA1 can be The matrix takes four rows of index, for example, index=(1 2 3 4), then AA1 is taken The first to fourth rows of the matrix are assigned to AA1. The matrix is ​​a 346 by 3 matrix, so AA1 is a 4-row 3-column matrix. Similarly, AA2 is based on the index index. A matrix with four rows and one column to which the matrix is ​​assigned after taking its value.

[0115] The constrained linear least squares coefficient is used to constrain the variance of the two intermediate variables to the minimum, and the constrained sixth matrix is ​​obtained. The constrained sixth matrix can be expressed as Specifically, , st-1<g<1, where g represents the constrained linear least squares coefficient, represents one of the two intermediate variables, represents the other intermediate variable among the two intermediate variables. st represents the constraint condition of the formula. represents the prediction order, and in this embodiment, k=1:100. Then . It represents the predicted data obtained by using the constrained linear least squares coefficients, and in this step it represents the predicted wind speed at the next moment.

[0116] It can be understood that the use of the constrained linear least squares coefficient g to optimize the prediction results ensures that the sum of square errors between the prediction results and the actual data is minimized, that is, it ensures that the wind speed at the next moment is consistent with the data rules of the N second historical data in the historical wind speed.

[0117] In this embodiment, the constrained linear least squares coefficient g is used to optimize the prediction result, which ensures that the sum of square errors between the prediction result and the actual data is minimized, thereby improving the accuracy and credibility of the prediction result.

[0118] In an exemplary embodiment, see Figure 5 The present application also provides a virtual power plant dispatching system. The virtual power plant dispatching system includes a cloud control unit and an edge control unit, and the cloud control unit is connected to the edge control unit. The edge control unit includes a historical data acquisition module and a data sending module, and the historical data acquisition module is connected to the data sending module.

[0119] The historical data acquisition module is used to retrieve the historical data of light intensity and wind speed, and send them to the cloud control unit (which can be understood as the server 104) through the data sending module. The cloud control unit includes a data receiving module, a data analysis module, and a scheduling instruction generation and sending module. The data receiving module is connected to the data analysis module, and the data analysis module is connected to the scheduling instruction generation and sending module.

[0120] The communication architecture of the virtual power plant adopts the basic architecture of physical layer, link layer, network layer and application layer. The data sending module and data receiving module belong to the physical layer, and data is sent and received through the data link layer and the Internet based on the Transmission Control Protocol (TCP), the Internet Protocol (IP) or the Controller Area Network (CAN) network.

[0121] The data analysis module is used to analyze the historical data of light intensity and wind speed received by the data receiving module of the cloud control unit, and send the analysis results to the scheduling instruction generation and sending module. The scheduling instruction generation and sending module generates a scheduling instruction based on the analysis results and sends it to the edge control unit, which specifically executes the scheduling instruction, that is, controls the output of the photovoltaic component, the wind turbine component and the energy storage component.

[0122] In an exemplary embodiment, FIG6 shows a data verification simulation diagram of the method provided by any of the above embodiments, wherein FIG6 (a) is a data verification simulation diagram of light intensity, and FIG6 (b) is a data verification simulation diagram of wind speed. In FIG6 (a) and FIG6 (b), the data point number represents the serial number of consecutive sampling points or sampling moments, 1000 represents the 1000th sampling point or sampling moment, and 1200 represents the 1200th sampling point or sampling moment.

[0123] The data verification simulation diagram of light intensity is drawn based on the real historical data of light intensity and the predicted light intensity. The data verification simulation diagram of wind speed is drawn based on the real historical data of wind speed and the predicted wind speed. It can be seen from Figure 6 (a) and Figure 6 (b) that the error between the predicted data and the actual data is relatively small, whether it is light intensity or wind speed, which can meet the prediction requirements of light intensity and wind speed.

[0124] In addition, by setting reasonable light intensity thresholds and wind speed thresholds, it is possible to objectively reflect the sufficiency of light resources and wind energy resources, and then dispatch the output of photovoltaic components, wind turbine components and energy storage components, thereby meeting the energy demand of the virtual power plant load while improving the level of new energy consumption and reducing carbon emissions.

[0125] It should be noted that the method provided in any of the above embodiments can support ultra-short-term predictions, such as predictions in units of 24 hours. The prediction accuracy of the light intensity and wind speed for the next day is higher than the medium- and long-term prediction accuracy for the next week, month, etc.

[0126] FIG6 (a) and FIG6 (b) show the application of the historical data of daily average light intensity and wind speed in the past two years to predict the average daily light intensity and wind speed of the next day. As shown in FIG6 (a) and FIG6 (b), using the method provided by any of the above embodiments, the predicted light intensity and wind speed of the next day are lower than that of the current day. The predicted light intensity and wind speed of the next day are compared with the first light intensity threshold and the first wind speed threshold, respectively, to generate a dispatching instruction, that is, to use wind, solar and energy storage to power the load at the same time, to use wind storage to power the load at the same time, to use solar storage to power the load at the same time, or to use only energy storage components to power the load.

[0127] It should be understood that, although the steps in the flowcharts of the embodiments described above are shown in sequence according to the instructions of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the steps or stages in other steps.

[0128] Based on the same inventive concept, the embodiment of the present application also provides a virtual power plant dispatching device for implementing the virtual power plant dispatching method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more virtual power plant dispatching device embodiments provided below can refer to the above limitations on the virtual power plant dispatching method, which will not be repeated here.

[0129] In an exemplary embodiment, Figure 7 As shown, a scheduling device for a virtual power plant is provided, including: an acquisition module 701, a processing module 702 and a scheduling module 703, wherein:

[0130] The acquisition module 701 is used to acquire the historical data of light intensity of photovoltaic components in the virtual power plant and the historical data of wind speed of wind turbine components in the virtual power plant.

[0131] The processing module 702 is used to predict the light intensity at the next moment based on the light intensity historical data.

[0132] The processing module 702 is used to predict the wind speed at the next moment based on the historical wind speed data.

[0133] The scheduling module 703 is used to schedule the virtual power plant based on the predicted light intensity at the next moment and the predicted wind speed at the next moment.

[0134] In one embodiment, the illumination intensity history data includes N first history data, where N is a natural number greater than 1. The processing module 702 is used to construct a first matrix based on the N first history data; move the last w rows of data groups sorted from the first row to the last row in the first matrix to the first w rows sorted from the first row to the last row without changing the sorting in the last w rows of data groups, until each row of data groups in the first matrix has been moved to obtain a second matrix, or, until the M rows of data groups that have not been moved in the first matrix cannot be moved according to the w rows, the M rows of data groups are moved to obtain the second matrix; wherein M is not less than zero and less than w; wherein, the M rows of data groups are moved, The method comprises: moving the remaining M rows of data groups to the position of the last M rows of data groups in the direction from the first row to the last row in the first matrix; constructing a first intermediate matrix according to the value of each element in the second matrix and the average value of the element; sorting the distance variance corresponding to each element in the first intermediate matrix in order from small to large, and generating a third matrix according to the sorting result; for two different intermediate variables of the third matrix, using constrained linear least squares coefficients to constrain the variance values ​​of the two intermediate variables to be minimum; and predicting the light intensity at the next moment based on the constrained third matrix and the constrained linear least squares coefficients.

[0135] In one embodiment, the processing module 702 is used to construct an initial matrix based on N first historical data; obtain the first-order derivative of the initial matrix, and calculate the standard deviation of the first-order derivative to obtain a standardized error; and correct the initial matrix according to the standardized error to obtain a first matrix.

[0136] In one embodiment, the wind speed historical data includes N second historical data, where N is a natural number greater than 1. The processing module 702 is specifically used to construct a fourth matrix based on the N second historical data; move the last w rows of data groups sorted from the first row to the last row in the fourth matrix to the first w rows sorted from the first row to the last row without changing the sorting in the last w rows of data groups, until each row of data groups in the fourth matrix has been moved to obtain a fifth matrix, or, until the M rows of data groups that have not been moved in the fourth matrix cannot be moved according to the w rows, the M rows of data groups are moved to obtain the fifth matrix; wherein M is not less than zero and less than w; wherein, the M rows of data groups are moved The method comprises: moving the remaining M rows of data groups to the position of the last M rows of data groups in the direction from the first row to the last row in the fourth matrix; constructing a second intermediate matrix according to the value of each element in the fifth matrix and the average value of the element; sorting the distance variance corresponding to each element in the second intermediate matrix in order from small to large, and generating a sixth matrix according to the sorting result; for two different intermediate variables of the sixth matrix, using constrained linear least squares coefficients to constrain the variance values ​​of the two intermediate variables to be minimum; and predicting the wind speed at the next moment based on the constrained sixth matrix and the constrained linear least squares coefficients.

[0137] In one embodiment, the processing module 702 is used to construct an initial matrix based on N second historical data; obtain the first-order derivative of the initial matrix, and calculate the standard deviation of the first-order derivative to obtain a standardized error; based on the standardized error, correct the initial matrix to obtain a fourth matrix.

[0138] In one embodiment, the scheduling module 703 is used to use the photovoltaic components, wind turbine components and energy storage components of the virtual power plant to power the load when the light intensity predicted at the next moment is greater than or equal to the light intensity threshold, and the wind speed predicted at the next moment is greater than or equal to the wind speed threshold, and also use the photovoltaic components and wind turbine components to charge the energy storage components; when the light intensity predicted at the next moment is greater than or equal to the light intensity threshold, and the wind speed predicted at the next moment is less than the wind speed threshold, use the photovoltaic components and energy storage components of the virtual power plant to power the load; when the light intensity predicted at the next moment is less than the light intensity threshold, and the wind speed predicted at the next moment is greater than or equal to the wind speed threshold, use the wind turbine components and energy storage components of the virtual power plant to power the load; when the light intensity predicted at the next moment is less than the light intensity threshold, and the wind speed predicted at the next moment is greater than or equal to the wind speed threshold, use the energy storage components to power the load.

[0139] Each module in the above-mentioned virtual power plant dispatching device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0140] In an exemplary embodiment, an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The electronic device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store historical data of light intensity, historical data of wind speed, predicted light intensity at the next moment and predicted wind speed, etc. The input / output interface of the electronic device is used to exchange information between the processor and an external device. The communication interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a scheduling method for a virtual power plant is implemented.

[0141] Those skilled in the art will understand that Figure 8 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0142] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the scheduling method of a virtual power plant provided in any of the above embodiments is implemented.

[0143] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the scheduling method of a virtual power plant provided in any of the above embodiments.

[0144] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0145] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this application.

[0146] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A scheduling method for a virtual power plant, characterized in that: The method comprises: Obtain historical data on the light intensity of photovoltaic components in the virtual power plant and historical data on the wind speed of wind turbine components in the virtual power plant; Based on the historical data of light intensity, predict the light intensity at the next moment; Based on the historical wind speed data, predict the wind speed at the next moment; The virtual power plant is dispatched based on the predicted light intensity at the next moment and the predicted wind speed at the next moment.

2. The method according to claim 1, characterized in that The illumination intensity historical data includes N first historical data, where N is a natural number greater than 1; The step of predicting the light intensity at the next moment based on the light intensity historical data includes: A first matrix is ​​constructed based on N first historical data; The last w rows of data groups sorted from the first row to the last row in the first matrix are moved to the first w rows sorted from the first row to the last row without changing the sorting in the last w rows of data groups, until each row of data groups in the first matrix has been moved to obtain a second matrix, or, until the M rows of data groups that have not been moved in the first matrix cannot be moved according to the w rows, the M rows of data groups are moved to obtain the second matrix; wherein M is not less than zero and less than w; wherein the moving of the M rows of data groups includes: moving the remaining M rows of data groups to the position of the last M rows of data groups in the direction from the first row to the last row in the first matrix; Constructing a first intermediate matrix according to the value of each element in the second matrix and the average value of the element; sorting the distance variance corresponding to each element in the first intermediate matrix in ascending order, and generating a third matrix according to the sorting result; For two different intermediate variables of the third matrix, constrained linear least squares coefficients are used to constrain the variance values ​​of the two intermediate variables to be minimum; Based on the constrained third matrix and the constrained linear least squares coefficients, the light intensity at the next moment is predicted.

3. The method according to claim 2, characterized in that The first matrix is ​​constructed based on N first historical data, including: Constructing an initial matrix based on N first historical data; Obtaining the first-order derivative of the initial matrix, and calculating the standard deviation of the first-order derivative to obtain a standardized error; The initial matrix is ​​corrected according to the standardized error to obtain a first matrix.

4. The method according to any one of claims 1 to 3, characterized in that: The wind speed historical data includes N second historical data, where N is a natural number greater than 1; The predicting of the wind speed at the next moment based on the wind speed historical data includes: A fourth matrix is ​​constructed based on the N second historical data; The last w rows of data groups sorted in the direction from the first row to the last row in the fourth matrix are moved to the first w rows sorted in the direction from the first row to the last row without changing the sorting in the last w rows of data groups, until each row of data groups in the fourth matrix has been moved to obtain a fifth matrix, or, until the M rows of data groups that have not been moved in the fourth matrix cannot be moved according to the w rows, the M rows of data groups are moved to obtain the fifth matrix; wherein M is not less than zero and less than w; wherein the moving of the M rows of data groups includes: moving the remaining M rows of data groups to the position of the last M rows of data groups in the direction from the first row to the last row in the fourth matrix; Constructing a second intermediate matrix according to the value of each element in the fifth matrix and the average value of the element; sorting the distance variance corresponding to each element in the second intermediate matrix in ascending order, and generating a sixth matrix according to the sorting result; For two different intermediate variables of the sixth matrix, constrained linear least squares coefficients are used to constrain the variance values ​​of the two intermediate variables to be minimum; Based on the constrained sixth matrix and the constrained linear least squares coefficients, the wind speed at the next moment is predicted.

5. The method according to claim 4, characterized in that The fourth matrix is ​​constructed based on the N second historical data, including: Constructing an initial matrix based on N second historical data; Obtaining the first-order derivative of the initial matrix, and calculating the standard deviation of the first-order derivative to obtain a standardized error; The initial matrix is ​​corrected according to the standardized error to obtain a fourth matrix.

6. The method according to any one of claims 1 to 3, characterized in that: The scheduling of the virtual power plant based on the predicted light intensity at the next moment and the predicted wind speed at the next moment includes: When the predicted light intensity at the next moment is greater than or equal to the light intensity threshold, and the predicted wind speed at the next moment is greater than or equal to the wind speed threshold, the photovoltaic components, wind turbine components and energy storage components of the virtual power plant are used to power the load, and the photovoltaic components and wind turbine components are used to charge the energy storage components; When the predicted light intensity at the next moment is greater than or equal to the light intensity threshold, and the predicted wind speed at the next moment is less than the wind speed threshold, the photovoltaic components and energy storage components of the virtual power plant are used to power the load; When the predicted light intensity at the next moment is less than the light intensity threshold, and the predicted wind speed at the next moment is greater than or equal to the wind speed threshold, the wind turbine component and energy storage component of the virtual power plant are used to power the load; When the predicted light intensity at the next moment is less than the light intensity threshold, and the predicted wind speed at the next moment is less than the wind speed threshold, the energy storage component is used to power the load.

7. A virtual power plant dispatching device, characterized in that: The device comprises: An acquisition module, used to acquire historical data of light intensity of photovoltaic components in the virtual power plant and historical data of wind speed of wind turbine components in the virtual power plant; A processing module, used for predicting the light intensity at a next moment based on the light intensity historical data; The processing module is used to predict the wind speed at the next moment based on the historical wind speed data; The scheduling module is used to schedule the virtual power plant based on the predicted light intensity at the next moment and the predicted wind speed at the next moment.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images