Power grid multi-energy complementary dispatching method and device based on wind and light output uncertainty

Abstract

The application discloses a kind of based on wind and light output uncertainty power grid multi-energy complementary scheduling method and device, comprising: obtaining the actual wind and light output data and predicted wind and light output data of target power grid corresponding to multiple historical time points in historical time period, covariance matrix is constructed based on the difference between actual wind and light output data and predicted wind and light output data;Determine wind and light prediction output error based on covariance matrix, obtain multiple initial wind and light prediction output scene set, correct each initial wind and light prediction output scene set using wind and light prediction output error, obtain multiple wind and light prediction output scene set, wherein each wind and light prediction output scene set includes wind and light prediction output data of each time point in future time period;Each wind and light prediction output scene set is input into preset wind and light complementary scheduling model to select output scene set, obtain target wind and light prediction output scene set, and carry out electric energy scheduling according to target wind and light prediction output scene set.

Description

Technical Field

[0001] This invention relates to the field of power system dispatching technology, and in particular to a method and apparatus for multi-energy complementary dispatching of power grids based on the uncertainty of wind and solar power output. Background Technology

[0002] The rapid growth of new energy installed capacity, coupled with low power prediction accuracy, has led to insufficient power system flexibility and regulation resources, which is particularly serious in power systems dominated by thermal power. This poses a threat to the safe and stable operation of the power grid. Based on this, it is necessary to carry out complementary power dispatch for power grids with uncertain wind and solar power output.

[0003] Currently, power dispatch is usually based directly on the predicted wind and solar power output capacity. However, this approach only focuses on the static capacity of wind and solar power output. Since wind and solar power output has time-varying characteristics, the static capacity cannot represent the actual output capacity of wind and solar power, resulting in poor dispatch performance and affecting the stable operation of the power grid. Summary of the Invention

[0004] This invention provides a method and apparatus for multi-energy complementary scheduling of power grids based on the uncertainty of wind and solar power output. The main purpose is to improve the accuracy of multi-energy complementary scheduling of power grids based on the uncertainty of wind and solar power output and ensure the stable operation of the power grid.

[0005] According to a first aspect of the present invention, a multi-energy complementary dispatching method for power grids based on the uncertainty of wind and solar power output is provided, comprising:

[0006] Obtain actual and predicted wind and solar power output data for the target power grid at multiple historical time points within a historical period. Construct a covariance matrix based on the difference between the actual and predicted wind and solar power output data at the same historical time point.

[0007] Based on the covariance matrix, the wind and solar power prediction error is determined, and multiple initial wind and solar power prediction scenario sets are obtained. The wind and solar power prediction error is used to correct each initial wind and solar power prediction scenario set to obtain multiple wind and solar power prediction scenario sets. Each wind and solar power prediction scenario set includes wind and solar power prediction data for each time point in a future time period.

[0008] Each of the predicted wind and solar power output scenarios is input into a preset wind-solar complementary scheduling model to select the power output scenario set, thereby obtaining the target predicted wind and solar power output scenario set, and power scheduling is performed according to the target predicted wind and solar power output scenario set.

[0009] According to a second aspect of the present invention, a grid multi-energy complementary dispatching device based on the uncertainty of wind and solar power output is provided, comprising:

[0010] The acquisition unit is used to acquire the actual wind and solar power output data and the predicted wind and solar power output data corresponding to the target power grid at multiple historical time points within a historical time period, and to construct a covariance matrix based on the difference between the actual wind and solar power output data and the predicted wind and solar power output data at the same historical time point.

[0011] The correction unit is used to determine the wind and solar power prediction error based on the covariance matrix, and to obtain multiple initial wind and solar power prediction scene sets. The wind and solar power prediction error is used to correct each initial wind and solar power prediction scene set to obtain multiple wind and solar power prediction scene sets. Each wind and solar power prediction scene set includes wind and solar power prediction data for each time point in a future time period.

[0012] The selection unit is used to input each of the wind and solar predicted power output scenario sets into a preset wind and solar complementary scheduling model to select the power output scenario set, obtain the target wind and solar predicted power output scenario set, and perform power scheduling according to the target wind and solar predicted power output scenario set.

[0013] According to a third aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described grid multi-energy complementary scheduling method based on the uncertainty of wind and solar power output.

[0014] According to a fourth aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described multi-energy complementary power grid scheduling method based on the uncertainty of wind and solar power output.

[0015] According to the present invention, a method and apparatus for multi-energy complementary power grid scheduling based on the uncertainty of wind and solar power output is provided. Compared with the current method of directly scheduling power based on the predicted wind and solar power output capacity, the present invention obtains the actual and predicted wind and solar power output data corresponding to the target power grid at multiple historical time points within a historical period. Based on the difference between the actual and predicted wind and solar power output data at the same historical time point, a covariance matrix is ​​constructed. Based on the covariance matrix, the wind and solar power output prediction error is determined, and multiple initial wind and solar power output prediction scenario sets are obtained. Each initial wind and solar power output prediction scenario set is corrected using the wind and solar power output prediction error to obtain multiple wind and solar power output prediction scenario sets. Each wind and solar power output prediction scenario set includes wind and solar power output prediction data for each time point within a future period. Finally, each wind and solar power output prediction scenario set is input into a preset wind and solar complementary scheduling model to select the output scenario set, obtain the target wind and solar power output prediction scenario set, and perform power scheduling according to the target wind and solar power output prediction scenario set. Therefore, a covariance matrix is ​​constructed using actual and predicted wind and solar power output data with time series. Based on the covariance matrix, the time-varying wind and solar power output prediction error is determined. This error is then used to correct the wind and solar power output prediction data in the initial wind and solar power output prediction scenario set. Finally, the error-corrected wind and solar power output prediction data is used to achieve complementary grid scheduling, thereby improving the accuracy of power dispatch in the grid and ensuring the stable operation of the grid. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This invention provides a flowchart of a power grid multi-energy complementary scheduling method based on the uncertainty of wind and solar power output, according to an embodiment of the present invention.

[0018] Figure 2 This invention provides a flowchart of another grid multi-energy complementary scheduling method based on the uncertainty of wind and solar power output, according to an embodiment of the present invention.

[0019] Figure 3 This illustration shows a schematic diagram of actual wind power output, predicted output, and generated scenario provided by an embodiment of the present invention;

[0020] Figure 4 This illustration shows a schematic diagram of actual photovoltaic power output, predicted power output, and generation scenario provided by an embodiment of the present invention;

[0021] Figure 5A schematic diagram illustrating the adjustment range for thermal power generation under a certain existing power grid dispatching method is shown.

[0022] Figure 6 This diagram illustrates the power curtailment and power shortage scenarios under a certain existing power grid dispatching method.

[0023] Figure 7 This diagram illustrates the thermal power output adjustment range in a multi-energy complementary dispatching process for power grids based on the uncertainty of wind and solar power output, according to an embodiment of the present invention.

[0024] Figure 8 This diagram illustrates the power curtailment and power shortage scenarios in a multi-energy complementary power grid dispatching process based on the uncertainty of wind and solar power output, according to an embodiment of the present invention.

[0025] Figure 9 This figure shows a schematic diagram of a power grid multi-energy complementary dispatching device based on the uncertainty of wind and solar power output provided by an embodiment of the present invention;

[0026] Figure 10 This invention provides a schematic diagram of another grid multi-energy complementary dispatching device based on the uncertainty of wind and solar power output, according to an embodiment of the present invention.

[0027] Figure 11 A schematic diagram of the physical structure of a computer device provided in an embodiment of the present invention is shown. Detailed Implementation

[0028] The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the present application can be combined with each other.

[0029] Currently, the method of dispatching power directly based on the predicted wind and solar power output capacity is ineffective because the wind and solar power output has time-varying characteristics. Therefore, the static wind and solar power output capacity cannot represent the actual output capacity, resulting in poor dispatching effect and affecting the stable operation of the power grid.

[0030] To address the aforementioned problems, embodiments of the present invention provide a grid multi-energy complementary dispatch method based on the uncertainty of wind and solar power output, such as... Figure 1 As shown, the method includes:

[0031] 101. Obtain the actual and predicted wind and solar power output data for the target power grid at multiple historical time points within a historical period. Construct a covariance matrix based on the difference between the actual and predicted wind and solar power output data at the same historical time point.

[0032] The historical time period can be selected according to actual needs, such as the past several months or the past year; the historical time point can be each day within the past month; the actual wind and solar power output data includes the sum of the actual processing data of wind power generation equipment and the actual processing data of photovoltaic power generation equipment.

[0033] In this embodiment of the invention, the uncertainties of wind and solar power (wind power generation equipment and photovoltaic power generation equipment) are considered. Actual wind and solar power output data of the target power grid at multiple time points within a historical period are obtained through the power grid monitoring system, and predicted wind and solar power output data for the corresponding time points are obtained through the wind and solar power output prediction system. The acquired actual and predicted data are cleaned to remove outliers, missing values, or duplicate data. For example, interpolation or filtering methods can be used to handle missing data or outliers. Data alignment: Ensure that the actual and predicted data at the same time point correspond. Since the actual and predicted data may have inconsistent timestamps, time alignment processing is required, for example, using nearest neighbor interpolation or linear interpolation methods. Data standardization: Standardize the data to eliminate the influence of dimensions and orders of magnitude. For example, the Z-score standardization method can be used to convert the data into a distribution with a mean of 0 and a standard deviation of 1. For each historical time point, the difference between the actual and predicted wind and solar power output data is calculated. Assuming the actual wind and solar power output data is a random variable, a covariance matrix is ​​constructed. Each element of the covariance matrix represents the covariance between the differences at two different time points. For example, if the difference vector is X = (X1, X2, ..., X...), then... t ) T , where x i Let Σ be the difference between the actual and predicted wind and solar power output at the i-th historical time point, and t be the number of historical time points. Then the covariance matrix Σ is:

[0034]

[0035] 102. Based on the covariance matrix, determine the wind and solar power prediction error and obtain multiple initial wind and solar power prediction scenario sets. Use the wind and solar power prediction error to correct each initial wind and solar power prediction scenario set to obtain multiple wind and solar power prediction scenario sets. Each of the wind and solar power prediction scenario sets includes wind and solar power prediction data for each time point in the future time period.

[0036] In this embodiment of the invention, after determining the covariance matrix, it is also necessary to determine the wind and solar power generation prediction error. Therefore, step 102 specifically includes: determining the installed capacity of the wind and solar power generation equipment corresponding to the target power grid, and based on the installed capacity, standardizing the covariance matrix to obtain a standardized covariance matrix; decomposing the standardized covariance matrix into a lower triangular matrix to obtain a lower triangular matrix; generating multiple uniformly distributed random numbers using a pseudo-random number generator, converting each random number into a standard normal distribution to obtain multiple standard normal random vectors, wherein the dimension of each standard normal random vector is the same as the vector dimension in the standardized covariance matrix; performing a linear transformation on each standard normal random vector using the lower triangular matrix, and based on the transformation result, determining the sample wind and solar power generation prediction error; and based on the sample wind and solar power generation prediction error, determining the wind and solar power generation prediction error. The method for determining the wind and solar power prediction output error based on the sample wind and solar power prediction output error includes: constructing an error feature matrix based on the sample wind and solar power prediction output error; determining the mean of each element in the error feature matrix, and subtracting the mean from each element in the error feature matrix to obtain a centered error matrix; determining the error covariance matrix corresponding to the centered error matrix; performing eigenvalue decomposition on the error covariance matrix to obtain error matrix eigenvalues ​​and error matrix eigenvectors; selecting a preset number of error matrix eigenvectors from the error matrix eigenvectors based on the magnitude of the error matrix eigenvalues, and determining the preset number of error matrix eigenvectors as principal component error eigenvectors; and determining the wind and solar power prediction output error based on the principal component error eigenvectors.

[0037] Specifically, the covariance matrix is ​​standardized according to the following formula:

[0038]

[0039] in, Let Cov[X] be the standardized covariance matrix, where Cov[X] is the matrix element and V[X] is the installed capacity. Then, the covariance matrix... Perform the decomposition of the lower triangular matrix:

[0040]

[0041] Where L is a lower triangular matrix, and simultaneously, n independent standard normal random vectors Z, which are identically distributed with the covariance matrix, are generated. (1) Z (2) ,...,Z (n) Furthermore, the standard normal samples are mapped to the sample wind and solar power prediction output error X through radiometric transformation. (i) :

[0042] X (i) =μ+LZ (i)

[0043] Where μ is the radiometric transformation coefficient set according to actual needs, and Z (i) Let be the i-th standard normal random vector. Further, based on the sample wind and solar power prediction output error, an error feature matrix is ​​constructed by stacking columns, and the centered error matrix of the error feature matrix is ​​determined. The covariance matrix (error covariance matrix) of the centered error matrix is ​​calculated, and the eigenvalue decomposition of the error covariance matrix is ​​performed as follows:

[0044] C e v i =λ i v i

[0045] Among them, C e Let v be the error covariance matrix. i For eigenvalues, v i Let be the eigenvectors. Arrange the eigenvalues ​​in descending order and calculate the cumulative variance contribution rate z of the eigenvalues ​​as shown below:

[0046]

[0047] Where i is the i-th eigenvalue, k is the preset quantity, and m is the total number of eigenvalues. The k value with the largest cumulative variance contribution rate is selected as the preset quantity. For example, if the cumulative contribution rate of the first 3 eigenvalues ​​is 90% and that of the first 4 is 96%, then k = 4. The eigenvectors corresponding to the first 4 eigenvalues ​​are determined as the principal component error eigenvectors. The error corresponding to the principal component error eigenvectors is determined in the error feature matrix, and the mean of this error is used as the wind and solar power prediction output error. This embodiment fully considers the time correlation characteristics of the prediction error, thereby improving the accuracy of error determination.

[0048] Furthermore, neural network models are used to predict the predicted wind and solar power output data for each wind and solar power generator at each future time point. These predicted output data at each time point constitute multiple initial wind and solar power output prediction scenario sets. Each initial wind and solar power output prediction scenario set contains predicted wind and solar power output data for different locations at each time point within a future time period. The prediction error and the predicted output are then superimposed to obtain the wind and solar power output prediction scenario set. This embodiment of the invention uses the wind and solar power output prediction error to correct the wind and solar power output data in the initial wind and solar power output prediction scenario set. Finally, the error-corrected wind and solar power output data is used to achieve complementary grid scheduling, thereby improving the accuracy of power dispatching in the grid and ensuring the stable operation of the grid.

[0049] 103. Input each wind and solar predicted power output scenario set into the preset wind and solar complementary scheduling model to select the power output scenario set, obtain the target wind and solar predicted power output scenario set, and perform power scheduling according to the target wind and solar predicted power output scenario set.

[0050] In this embodiment of the invention, to improve the scheduling accuracy of the preset wind-solar complementary scheduling model, it is first necessary to train and construct the preset wind-solar complementary scheduling model. Based on this, the method includes: constructing a preset initial wind-solar complementary scheduling model; obtaining a sample dataset, wherein the sample dataset includes multiple sample wind-solar predicted output scene sets labeled with wind-solar output scene sets whose scheduling effects meet the requirements; dividing the sample dataset into a training set and a test set, using the training set to train the preset initial wind-solar complementary scheduling model, and using the test set to test the trained preset initial wind-solar complementary scheduling model, and finally using the trained preset initial wind-solar complementary scheduling model that meets the test conditions as the preset wind-solar complementary scheduling model.

[0051] Specifically, during model training, a pre-defined initial wind-solar hybrid scheduling model is first constructed, followed by the acquisition of a sample dataset. The dataset is ensured to contain all necessary files, and the data is converted to a format understandable by the pre-defined initial wind-solar hybrid scheduling model. Finally, the model is trained and tested. Specifically, the dataset can be divided first: using randomness or a specific strategy (such as stratified sampling), the sample dataset is divided into a training set and a test set. The model is then trained using the training set, and tested using the test set to evaluate its performance on unseen data. Metrics such as mCP, precision, and recall on the test set are calculated and recorded. If the model performance does not meet the requirements, the training phase can be returned for further iterations or adjustments. This process yields a pre-defined wind-solar hybrid scheduling model that meets the requirements.

[0052] Furthermore, the preset wind-solar hybrid dispatch model includes a grid power shortage objective function, a grid curtailment objective function, and a thermal power operating cost objective function. After constructing the preset wind-solar hybrid dispatch model, it is necessary to use this model to select the target wind and solar predicted output scenario set. Based on this, step 103 specifically includes: using a hierarchical weight optimization method to convert the grid power shortage objective function, the grid curtailment objective function, and the thermal power operating cost objective function into a single objective scenario set selection function; obtaining the scenario set selection constraints, and determining the scenario set attribute data for each wind and solar predicted output scenario set, the power generation attribute data of other power generation equipment, the unit attribute data of thermal power generation equipment, and the regional power attribute information of the target grid area. The scenario set attribute data includes the number of wind and solar power generation equipment in each wind and solar predicted output scenario set, and the number of wind and solar power generation equipment in each future time period. The wind and solar power output forecast data at each time point includes the power generation attribute data (including the output data of other power generation equipment), the regional power attribute data (including mutual assistance power and load), and the unit attribute data (including the number of thermal power units, thermal power combustion cost coefficient, unit output data, and unit start-up and shutdown costs). Based on the scenario set selection constraints, the scenario set attribute data, the power generation attribute data, the unit attribute data, and the regional power attribute information of each wind and solar power output forecast scenario set are substituted into the single-objective scenario set selection function to obtain the evaluation value corresponding to each wind and solar power output forecast scenario set. Based on the evaluation value, the target wind and solar power output forecast scenario set is determined for each wind and solar power output forecast scenario set. The method of converting the grid power shortage objective function, the grid power curtailment objective function, and the thermal power operation cost objective function into a single-objective scenario set selection function using a hierarchical weight optimization approach includes: the grid power shortage objective function is set as... in, The objective function for power grid curtailment is set as follows: in, The objective function for thermal power plant operating costs is set as follows: Wherein, MinF1 represents power shortage data, MinF2 represents power curtailment data, MinF3 represents thermal power operating costs, n represents the identifier of wind and solar power generation equipment in the wind and solar power prediction output scenario set, N represents the total number of wind and solar power generation equipment, t represents the identifier of the future time period, T represents the total length of the future time period, p represents the regional identifier of the target power grid, M represents the total number of regions in the target power grid, and loe n,t,p foe n,t,p These represent the power shortage and power abandonment in region p at time point t in the nth scenario set. Contribute to the scenery of region p at time point t under scene set n. These represent the hydropower output, thermal power output, nuclear power output, pumped storage power output, and DC power output in region p at time point t. The total output of other power sources in region p at time point t. The mutual assistance power input to region p at time point t in the nth scenario set, L t,p Let P be the load in region p at time point t, k and K be the thermal power unit serial number and number of units respectively, a, b, and c be the thermal power combustion cost coefficients respectively, and P be the load in region p. k For the output of unit k of the thermal power generation equipment, S k Let k be the start-up and shutdown cost of unit k. The range algorithm is used to perform dimensionless processing on the grid power shortage objective function, the grid power curtailment objective function, and the thermal power operation cost objective function, respectively, resulting in the processed grid power shortage objective function, the processed grid power curtailment objective function, and the processed thermal power operation cost objective function. These processed functions are then divided into different levels, and the same-level weight coefficients for each objective function within the same level and the inter-level weight coefficients for objective functions between different levels are determined. Based on the same-level weight coefficients and the inter-level weight coefficients, the processed grid power shortage objective function, the processed grid power curtailment objective function, and the processed thermal power operation cost objective function are weighted and aggregated to obtain the single-objective scenario set selection function.

[0053] Specifically, with the objectives of minimizing the sum of power shortages and curtailment across the entire power grid and minimizing the operating costs of thermal power, the pre-defined wind-solar hybrid dispatch model is constructed as follows:

[0054] Objective function 1 (preset wind-solar hybrid scheduling model) is as follows:

[0055]

[0056] Objective function 2 (objective function for power grid curtailment) is shown below:

[0057]

[0058] in,

[0059]

[0060] Objective function 3 (Objective function for thermal power plant operating cost):

[0061]

[0062] The scene set selection constraints are set as follows:

[0063] Water level and reservoir capacity constraints:

[0064]

[0065] Among them, Z i,tLet V be the water level of reservoir i on day t. i,t The reservoir's capacity on day t is These represent the lower and upper limits of the water level of reservoir i on day t, respectively. These are the lower and upper limits of the reservoir capacity on day t, respectively.

[0066] Water balance equation:

[0067] V i,t+1 =V i,t +(q i,t +R i-1 -R i,t )Δ t

[0068] Among them, R i,t =Q i,t +S i,t . q i,t R i,t Q i,t S i,t V represents the interval flow, outflow, power generation flow, and wastewater discharge of reservoir i on day t. i,t+1 Let V be the water volume of reservoir i on day t+1. i,t Let denot be the water volume of reservoir i on day t, and Δt be the change over time.

[0069] Power generation flow constraints:

[0070]

[0071] in, Q represents the lower and upper limits of the power generation flow of reservoir i on day t, respectively. i,t Let t be the power generation of reservoir i on day t.

[0072] Outbound flow constraints:

[0073]

[0074] in, R represents the lower and upper limits of the outflow from reservoir i on day t, respectively. i,t Let be the outflow from reservoir i on day t.

[0075] Hydropower output constraints:

[0076]

[0077] in, and These are the lower and upper limits of the output of reservoir i, respectively. This refers to the power output data of reservoir i.

[0078] Thermal power unit output constraints:

[0079]

[0080] in, and These are the minimum and maximum output of thermal power unit i, respectively. This refers to the output data of thermal power unit i.

[0081] Total output constraints of thermal power plants:

[0082] In the future, the total amount of electricity generated by thermal power should be limited by fuel, and consumption should not exceed the supply plan.

[0083]

[0084] in, For the output of thermal power unit i on day t, I th This refers to the number of thermal power units. This represents the upper limit of total thermal power output during time period T.

[0085] Minimum start-up and shutdown time for thermal power units:

[0086] The start-up and shutdown operations of large thermal power units involve the complex dynamic characteristics of the boiler thermal system. The transition from cold standby to grid-connected operation typically takes 24 to 48 hours, and this process may be further extended. Furthermore, each start-up and shutdown operation of a thermal power unit incurs significant economic costs. From the perspective of economic operation of the power system, frequent start-up and shutdown are not feasible. Based on the physical characteristics and actual operational requirements of thermal power units, the dispatch model must consider the minimum continuous operating time constraint of the units on a daily basis.

[0087]

[0088] Among them, U i,k Let U be the state variable of unit i on day k. If unit i is powered on, then U i,k =1, otherwise U i,k =0; Y i,t Let Y be the startup variable of unit i on day t. If unit i goes from shutdown to startup, then... i,t =1 otherwise =Y i,t =0; Z i,t Let Z be the shutdown variable of unit i on day t. If unit i runs from startup to shutdown, then Z... i,t It is 1 if it is 1, otherwise it is Z. i,t The value is 0, and T is the total duration of the future time period.

[0089] Minimum number of thermal power units to be in operation:

[0090] To ensure the safe operation of the power grid, the minimum number of generating units required to be in operation must be met:

[0091]

[0092] Where, N th,min U is the minimum number of thermal power units required to be in operation. i,t Let I be the number of the i-th thermal power unit in operation at time t. th This represents the total number of thermal power units.

[0093] Nuclear power output constraints:

[0094]

[0095] in, For the power output of nuclear power plants sent to the region on day t, The actual power output process of the nuclear power plant under grid dispatch.

[0096] Pumped storage output constraints:

[0097]

[0098] in, To pump the power supplied to region p on day t, This refers to the actual power output process of the grid-controlled pumped storage system.

[0099] Inter-regional mutual assistance constraints:

[0100] The gradual increase in the proportion of wind and solar power generation necessitates full coordination and mutual assistance between power grids to address the challenges of future renewable energy consumption and supply.

[0101]

[0102] in, The mutual assistance power volume in region p on day t. This represents the mutual power transfer from region p to region s on day t, where S represents other regions besides the sending region. Let p be the amount of electricity generated in region p on day t. Let p be the power generation of region p on day t in the nth scene set. To pump the power supplied to region p on day t, The output of pumped storage power sent to other power generation systems in region p on day t. L contributed to the scenery of area p on day t. t,p Output force to account for error.

[0103] Power plant distribution constraints:

[0104] All grid-dispatch power sources should meet the regional power grid distribution requirements.

[0105]

[0106] Among them, P i,t For grid-controlled power output, P i,t,p Let i be the power output of power plant i to region p on day t, k be the power distribution ratio of the grid-dispatched power source designated by the power grid, and M be the total number of regions.

[0107] The multi-objective problem is transformed into a single-objective problem using a hierarchical weighted optimization method. The specific steps are as follows:

[0108] Model a multi-objective optimization problem using min F(x) = [f1(x), f2(x), ..., f m (x)] T Where, minF(x) is the single-objective scenario set selection function, f1(x) is the grid power shortage objective function, f2(x) is the grid power curtailment objective function, and f m (x) is the objective function for the operating cost of thermal power plants.

[0109] The range method is used to perform dimensionless processing on each objective function. Among them, f ic (x) represents the processed functions, f i max (x) is f i The maximum value of the function f(x) i min (x) is f i Find the minimum value of function (x). Determine the priority of the objective function based on expert experience or production requirements. Let the objective priority be P = {p1, p2, ..., p...} m}, where P i The priority of objective function i is given by p1, which has the highest priority. m The lowest priority. Based on the priority P, the m objective functions are divided into L levels (L≤m), resulting in a hierarchy F={F 1 ,F 2 ,...,F L}, F represents different levels, F i Let F be the i-th objective function in hierarchy F. Higher-level objectives have a strictly higher priority than lower-level objectives, while the priority difference between objectives within the same hierarchy is relatively small. For each objective function in different hierarchies F, an exponential weighting distribution is used, with priority reflected through differences in order of magnitude. The specific rules are as follows: High-priority objective (F1): weight coefficient ω1 = M, where M is a very large positive number, ensuring that its optimization contributes far more to the aggregation function value than other objectives; Second-priority objective (F2): ... 2 ~F L ): Weighting coefficient ω j =ε·M, where ε is the exponential decay coefficient (a very small positive number), ensuring that its contribution is only ε times that of the higher priority. For each objective function within the same level F, the relative weights are determined using the tomographic analysis method. That is, the weighting coefficients at the same level, where, These represent the weight coefficients of different objective functions at the same level, where n is the total number of objective functions. Additionally, weight coefficients between objective functions at different levels can be determined based on actual needs; these are the inter-level weight coefficients. Then, an aggregation function is constructed to ensure the priority of key objective functions while considering the coordination of multiple objectives, resulting in the single-objective scene set selection function Φ(x):

[0110]

[0111] Where ω1, ω2, ..., ω L The functions are f1(x), f2(x), ..., f, respectively. m The inter-level weighting coefficient of (x), These are the weight coefficients at the same level corresponding to the function. Further, based on the scenario set selection constraints, the scenario set attribute data, power generation attribute data, generator attribute data, and regional power attribute information of each wind and solar predicted output scenario set are substituted into the single-objective scenario set selection function to obtain the evaluation value corresponding to each wind and solar predicted output scenario set. Finally, the wind and solar predicted output scenario set corresponding to the maximum evaluation value is determined as the target wind and solar predicted output scenario set. Then, power dispatch in the power grid is performed according to the wind and solar output data at each time point in the target wind and solar predicted output scenario set. This invention, in the process of power grid dispatch, fully considers factors such as power curtailment, power shortage, and cost, which can further improve the dispatch accuracy of the power grid and ensure the coordinated and stable operation of the power grid.

[0112] According to the present invention, a multi-energy complementary power grid dispatching method based on the uncertainty of wind and solar power output provides a method for power dispatching that, compared with the current method of directly dispatching power based on the predicted wind and solar power output capacity, obtains the actual and predicted wind and solar power output data of the target power grid at multiple historical time points within a historical period. Based on the difference between the actual and predicted wind and solar power output data at the same historical time point, a covariance matrix is ​​constructed. Based on the covariance matrix, the wind and solar power output prediction error is determined, and multiple initial wind and solar power output prediction scenario sets are obtained. Each initial wind and solar power output prediction scenario set is corrected using the wind and solar power output prediction error to obtain multiple wind and solar power output prediction scenario sets. Each wind and solar power output prediction scenario set includes wind and solar power output prediction data for each time point within a future time period. Finally, each wind and solar power output prediction scenario set is input into a preset wind and solar complementary dispatching model to select the output scenario set, obtaining the target wind and solar power output prediction scenario set, and power dispatching is performed according to the target wind and solar power output prediction scenario set. Therefore, a covariance matrix is ​​constructed using actual and predicted wind and solar power output data with time series. Based on the covariance matrix, the time-varying wind and solar power output prediction error is determined. This error is then used to correct the wind and solar power output prediction data in the initial wind and solar power output prediction scenario set. Finally, the error-corrected wind and solar power output prediction data is used to achieve complementary grid scheduling, thereby improving the accuracy of power dispatch in the grid and ensuring the stable operation of the grid.

[0113] Furthermore, to better illustrate the above process of multi-energy complementary scheduling of the power grid based on the uncertainty of wind and solar power output, as a refinement and extension of the above embodiments, this invention provides another method for multi-energy complementary scheduling of the power grid based on the uncertainty of wind and solar power output, such as... Figure 2 As shown, the method includes:

[0114] 201. Obtain the actual and predicted wind and solar power output data of the target power grid at multiple historical time points within the historical time period. Based on the difference between the actual and predicted wind and solar power output data at the same historical time point, construct a covariance matrix.

[0115] 202. Based on the covariance matrix, determine the wind and solar power prediction error and obtain multiple initial wind and solar power prediction scenario sets. Use the wind and solar power prediction error to correct each initial wind and solar power prediction scenario set to obtain multiple wind and solar power prediction scenario sets. Each wind and solar power prediction scenario set includes wind and solar power prediction data for each time point in the future time period.

[0116] Specifically, the generation of typical wind and solar power output scenarios that take into account the time-varying characteristics of wind and solar power involves the following steps: Based on the actual wind and solar power output data of the regional power grid under different forecast periods (future time periods). and predicted output data Calculate the prediction error X for wind and solar power processing in each region's power grid. i,m Input the wind and solar forecast error vector X = (X1, X2, ..., X...) under different forecast periods. t ) T X t Let be the random variable of the prediction error on day t within the prediction period, where t is the length of the prediction period; calculate the covariance matrix Σ of the wind and solar power prediction error; since the prediction error of new energy is still affected by the installed capacity, the covariance matrix is ​​standardized; based on the standardized covariance matrix and the multivariate normal sampling method, the wind and solar power prediction error is sampled; superimpose the wind and solar power prediction error and the wind and solar power prediction output to generate the power output scenario set.

[0117] 203. Determine the wind power generation limit for wind power generation equipment, the photovoltaic power generation limit for photovoltaic power generation equipment, and the thermal power generation limit for thermal power generation equipment respectively.

[0118] 204. Based on the limits for wind power generation, photovoltaic power generation, and thermal power generation, a scenario set is selected for each wind and solar power predicted output scenario set to obtain a wind and solar power predicted output scenario set that meets the output requirements.

[0119] Specifically, based on the limits for wind power generation, photovoltaic power generation, and thermal power generation, scenario set screening is performed for each wind and solar power predicted output scenario set, that is, scenario sets that exceed the limits are removed.

[0120] 205. Input the wind and solar power output scenario set that meets the power output demand into the preset wind and solar complementary scheduling model to select the power output scenario set, obtain the target wind and solar power output scenario set, and perform power dispatch according to the target wind and solar power output scenario set.

[0121] Specifically, the predicted wind and solar power output scenarios that meet the power output requirements are input into a pre-set wind-solar hybrid dispatch model. The model can directly output a target set of predicted wind and solar power output scenarios that meet the dispatch requirements. Finally, based on the wind power output data and photovoltaic power output data in the target set of predicted wind and solar power output scenarios, the power grid is dispatched. This can be used for dispatching power sources such as thermal power, hydropower, nuclear power, and pumped storage.

[0122] For example, in recent years, with the rapid growth of new energy installed capacity in the power grid area, the impact of daily power output fluctuations of new energy on the safe and stable operation of the power grid has become increasingly prominent, placing higher demands on the regulation capabilities of grid-dispatched power sources. This embodiment of the invention implements multi-energy complementary dispatching for grid-dispatched power sources (thermal power, hydropower, nuclear power, pumped storage) in a certain region and wind and solar power stations in other regions. Grid-dispatched power sources in other regions are not included in the optimization calculation. A typical operating mode is given based on actual operating data from 2024, and the basic parameters are shown in Table 1. Other parameters mainly include combustion cost, start-up and shutdown cost, and minimum start-up and shutdown time. The combustion cost coefficients are a = 0.02, b = 15, and c = 350, respectively. Different start-up and shutdown costs are set for units with different installed capacities: 3 million yuan for a 1000MW unit, 1.5 million yuan for a 700MW unit, and 1.2 million yuan for other units; the minimum start-up and shutdown time is 10 days for all units.

[0123] Table 1 Basic parameters of the power plant

[0124]

[0125] Figure 3 , Figure 4 Five sets of new energy (wind and solar power) scenarios were generated, and their actual and predicted power outputs were compared. Within a short forecast period, the prediction accuracy for wind and solar power output was high, and the scenario fluctuation range was small. However, as the forecast period lengthened, the fluctuation range of the scenarios gradually increased, leading to greater balancing pressure on the power grid. Current prediction results generally show an overestimation trend, reflecting insufficient prediction accuracy. If power grid dispatching plans are formulated solely based on predicted power output, the risk of system power shortages will significantly increase. Scenario 1: The period from January 1, 2024 to December 25, 2024 (360 days) is divided into 36 time periods, numbered 1 to 36, and a rolling calculation is performed. The results are shown in Tables 2 and 3.

[0126] Table 2. Quota abandonment situation in various regions under the two scheduling modes (January 1st to January 10th)

[0127]

[0128] Table 3 shows the number of regions with better performance in skipping tasks under the two scheduling modes.

[0129]

[0130] Figure 5 , Figure 6 This demonstrates the adjustment range and rejection scenarios under traditional methods. Figure 7 , Figure 8This paper demonstrates the adjustment range and power curtailment situation under the method of this invention. From January 1st to January 10th, after further adjustments based on the plan, the traditional method resulted in a maximum power shortage of 120 million kWh and a total power shortage of 670 million kWh, while the method of this invention resulted in a maximum power shortage of 48 million kWh and a total power shortage of 180 million kWh. During the forecast period, the traditional model accounted for 20% of the days with complete balance, while the method of this invention accounted for 50%. Neither method resulted in power curtailment after adjustments, and renewable energy was further integrated. Analysis shows that the method of this invention still significantly outperforms the traditional method overall, providing guidance for the safe operation of the power grid.

[0131] According to another method for multi-energy complementary power grid scheduling based on the uncertainty of wind and solar power output provided by the present invention, compared with the current method of directly scheduling power based on the predicted wind and solar power output capacity, the present invention obtains the actual and predicted wind and solar power output data corresponding to the target power grid at multiple historical time points within a historical period. Based on the difference between the actual and predicted wind and solar power output data at the same historical time point, a covariance matrix is ​​constructed. Based on the covariance matrix, the wind and solar power output prediction error is determined, and multiple initial wind and solar power output prediction scenario sets are obtained. Each initial wind and solar power output prediction scenario set is corrected using the wind and solar power output prediction error to obtain multiple wind and solar power output prediction scenario sets. Each wind and solar power output prediction scenario set includes the wind and solar power output prediction data at each time point within a future time period. Finally, each wind and solar power output prediction scenario set is input into a preset wind and solar complementary scheduling model to select the output scenario set, obtain the target wind and solar power output prediction scenario set, and perform power scheduling according to the target wind and solar power output prediction scenario set. Therefore, a covariance matrix is ​​constructed using actual and predicted wind and solar power output data with time series. Based on the covariance matrix, the time-varying wind and solar power output prediction error is determined. This error is then used to correct the wind and solar power output prediction data in the initial wind and solar power output prediction scenario set. Finally, the error-corrected wind and solar power output prediction data is used to achieve complementary grid scheduling, thereby improving the accuracy of power dispatch in the grid and ensuring the stable operation of the grid.

[0132] Furthermore, as Figure 1 In specific implementation, embodiments of the present invention provide a grid multi-energy complementary dispatching device based on the uncertainty of wind and solar power output, such as... Figure 9 As shown, the device includes: an acquisition unit 31, a correction unit 32, and a selection unit 33.

[0133] The acquisition unit 31 can be used to acquire the actual wind and solar power output data and the predicted wind and solar power output data corresponding to the target power grid at multiple historical time points within a historical time period, and construct a covariance matrix based on the difference between the actual wind and solar power output data and the predicted wind and solar power output data at the same historical time point.

[0134] The correction unit 32 can be used to determine the wind and solar power prediction error based on the covariance matrix, and obtain multiple initial wind and solar power prediction scene sets. The wind and solar power prediction error is used to correct each initial wind and solar power prediction scene set to obtain multiple wind and solar power prediction scene sets. Each wind and solar power prediction scene set includes wind and solar power prediction data for each time point in the future time period.

[0135] The selection unit 33 can be used to input each of the wind and solar predicted power output scenario sets into a preset wind and solar complementary scheduling model to select the power output scenario set, obtain the target wind and solar predicted power output scenario set, and perform power scheduling according to the target wind and solar predicted power output scenario set.

[0136] In specific application scenarios, in order to determine the power output error of wind and solar forecasts, such as Figure 10 As shown, the correction unit 32 includes a standardization module 321, a decomposition module 322, a generation module 323, and a first determination module 324.

[0137] The standardization module 321 can be used to determine the installed capacity of wind and solar power generation equipment corresponding to the target power grid, and based on the installed capacity, to standardize the covariance matrix to obtain a standardized covariance matrix.

[0138] The decomposition module 322 can be used to decompose the standardized covariance matrix into a lower triangular matrix to obtain a lower triangular matrix.

[0139] The generation module 323 can be used to generate multiple uniformly distributed random numbers using a pseudo-random number generator, convert each random number into a standard normal distribution, and obtain multiple standard normal random vectors, wherein the dimension of each standard normal random vector is the same as the vector dimension in the standardized covariance matrix.

[0140] The first determining module 324 can be used to perform linear transformation on each of the standard normal random vectors using the lower triangular matrix, and determine the sample wind and solar power prediction output error based on the transformation result.

[0141] In a specific application scenario, to determine the wind and solar power prediction output error, the first determining module 324 can be used to construct an error feature matrix based on the sample wind and solar power prediction output error; determine the mean of each element in the error feature matrix, and subtract the mean from each element in the error feature matrix to obtain a centered error matrix; determine the error covariance matrix corresponding to the centered error matrix; perform eigenvalue decomposition on the error covariance matrix to obtain error matrix eigenvalues ​​and error matrix eigenvectors; select a preset number of error matrix eigenvectors from the error matrix eigenvectors based on the magnitude of the error matrix eigenvalues, and determine the preset number of error matrix eigenvectors as principal component error eigenvectors; and determine the wind and solar power prediction output error based on the principal component error eigenvectors.

[0142] In specific application scenarios, in order to construct a preset wind-solar hybrid scheduling model, the device also includes a construction unit 34.

[0143] The construction unit 34 can be used to construct a preset initial wind-solar complementary scheduling model; obtain a sample dataset, wherein the sample dataset includes multiple sample wind-solar output scene sets labeled with wind-solar output scene sets whose scheduling effect meets the requirements; divide the sample dataset into a training set and a test set, use the training set to train the preset initial wind-solar complementary scheduling model, and use the test set to test the trained preset initial wind-solar complementary scheduling model, and finally use the trained preset initial wind-solar complementary scheduling model that meets the test conditions as the preset wind-solar complementary scheduling model.

[0144] In specific application scenarios, the preset wind-solar complementary scheduling model includes a power grid shortage objective function, a power grid curtailment objective function, and a thermal power operation cost objective function; in order to obtain the target wind and solar predicted output scenario set, the selection unit 33 includes a conversion module 331, a second determination module 332, and a prediction module 333.

[0145] The conversion module 331 can be used to convert the power grid shortage objective function, the power grid curtailment objective function, and the thermal power operation cost objective function into a single objective scenario set selection function using a hierarchical weight optimization method.

[0146] The second determining module 332 can be used to obtain the scene set selection constraints and determine the scene set attribute data of each wind and solar power predicted output scene set, the power generation attribute data of the remaining power generation equipment, the unit attribute data of the thermal power generation equipment, and the regional power attribute information of the target power grid area. The scene set attribute data includes the number of wind and solar power generation equipment in each wind and solar power predicted output scene set and the wind and solar power predicted output data at each time point in the future time period. The power generation attribute data includes the output data of the remaining power generation equipment. The regional power attribute data includes mutual assistance power and load. The unit attribute data includes the number of thermal power generation units, thermal power combustion cost coefficient, unit output data, and unit start-up and shutdown costs.

[0147] The prediction module 333 can be used to, based on the scenario set selection constraints, substitute the scenario set attribute data, the power generation attribute data, the generator attribute data, and the regional power attribute information of each wind and solar power predicted output scenario set into the single-objective scenario set selection function to obtain the evaluation value corresponding to each wind and solar power predicted output scenario set. Based on the evaluation value, the target wind and solar power predicted output scenario set is determined in each wind and solar power predicted output scenario set. In a specific application scenario, in order to determine the single-objective scenario set selection function, the conversion module 331 can be specifically used to set the grid power shortage objective function as follows: in,

[0148] The objective function for power grid curtailment is set as follows: in, The objective function for thermal power plant operating costs is set as follows: Wherein, MinF1 represents power shortage data, MinF2 represents power curtailment data, MinF3 represents thermal power operating costs, n represents the identifier of wind and solar power generation equipment in the wind and solar power prediction output scenario set, N represents the total number of wind and solar power generation equipment, t represents the identifier of the future time period, T represents the total length of the future time period, p represents the regional identifier of the target power grid, M represents the total number of regions in the target power grid, and loe n,t,p foe n,t,p These represent the power shortage and power abandonment in region p at time point t in the nth scenario set. Contribute to the scenery of region p at time point t under scene set n. These represent the hydropower output, thermal power output, nuclear power output, pumped storage power output, and DC power output in region p at time point t. The total output of other power sources in region p at time point t. The mutual assistance power input to region p at time point t in the nth scenario set, L t,p Let P be the load in region p at time point t, k and K be the thermal power unit serial number and number of units respectively, a, b, and c be the thermal power combustion cost coefficients respectively, and P be the load in region p.k For the output of unit k of the thermal power generation equipment, S k Let k be the start-up and shutdown cost of unit k. The range algorithm is used to perform dimensionless processing on the grid power shortage objective function, the grid power curtailment objective function, and the thermal power operation cost objective function, respectively, resulting in the processed grid power shortage objective function, the processed grid power curtailment objective function, and the processed thermal power operation cost objective function. These processed functions are then divided into different levels, and the same-level weight coefficients for each objective function within the same level and the inter-level weight coefficients for objective functions between different levels are determined. Based on the same-level weight coefficients and the inter-level weight coefficients, the processed grid power shortage objective function, the processed grid power curtailment objective function, and the processed thermal power operation cost objective function are weighted and aggregated to obtain the single-objective scenario set selection function.

[0149] In specific application scenarios, in order to filter the set of wind and solar power prediction scenarios, the device also includes a filtering unit 35.

[0150] The filtering unit 35 can be used to determine the wind power generation limit of wind power generation equipment, the photovoltaic power generation limit of photovoltaic power generation equipment, and the thermal power generation limit of thermal power generation equipment respectively; based on the wind power generation limit, the photovoltaic power generation limit, and the thermal power generation limit, the scene set filtering is performed on each of the wind and solar predicted output scene sets to obtain the wind and solar predicted output scene sets that meet the output requirements.

[0151] The selection unit 33 can also be used to input the wind and solar predicted power output scenario set that meets the power output requirements into the preset wind and solar complementary scheduling model to select the power output scenario set and obtain the target wind and solar predicted power output scenario set.

[0152] It should be noted that other corresponding descriptions of the functional modules involved in the multi-energy complementary dispatching device for power grids based on the uncertainty of wind and solar power output provided in this embodiment of the invention can be found in the following references. Figure 1 The corresponding description of the method shown will not be repeated here.

[0153] Based on the above, Figure 1Accordingly, this embodiment of the invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the following steps: acquiring actual and predicted wind and solar power output data corresponding to the target power grid at multiple historical time points within a historical time period; constructing a covariance matrix based on the difference between the actual and predicted wind and solar power output data at the same historical time point; determining the wind and solar power prediction output error based on the covariance matrix and acquiring multiple initial wind and solar power prediction output scenario sets; correcting each initial wind and solar power prediction output scenario set using the wind and solar power prediction output error to obtain multiple wind and solar power prediction output scenario sets, wherein each wind and solar power prediction output scenario set includes wind and solar power prediction output data at each time point within a future time period; inputting each wind and solar power prediction output scenario set into a preset wind and solar complementary scheduling model for selecting the output scenario set to obtain a target wind and solar power prediction output scenario set, and performing power scheduling according to the target wind and solar power prediction scenario set.

[0154] Based on the above, Figure 1 The method shown and as Figure 9 The embodiment of the device shown in the invention also provides a physical structure diagram of a computer device, such as... Figure 11 As shown, the computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor. Both the memory 42 and the processor 41 are mounted on a bus 43. When the processor 41 executes the program, it performs the following steps: acquiring actual and predicted wind and solar power output data corresponding to the target power grid at multiple historical time points within a historical time period; constructing a covariance matrix based on the difference between the actual and predicted wind and solar power output data at the same historical time point; and determining the wind power output based on the covariance matrix. The system calculates the predicted power output error and obtains multiple initial wind and solar power output prediction scenario sets. Each initial wind and solar power output prediction scenario set is then corrected using the predicted power output error to obtain multiple wind and solar power output prediction scenario sets. Each wind and solar power output prediction scenario set includes wind and solar power output prediction data for each time point within a future time period. Each wind and solar power output prediction scenario set is then input into a preset wind and solar complementary scheduling model to select a power output scenario set, resulting in a target wind and solar power output prediction scenario set. Power scheduling is then performed according to the target wind and solar power output prediction scenario set.

[0155] Through the technical solution of this invention, the present invention acquires actual and predicted wind and solar power output data corresponding to the target power grid at multiple historical time points within a historical period. Based on the difference between the actual and predicted wind and solar power output data at the same historical time point, a covariance matrix is ​​constructed. Based on the covariance matrix, the wind and solar power output prediction error is determined, and multiple initial wind and solar power output prediction scenario sets are obtained. Each initial wind and solar power output prediction scenario set is corrected using the wind and solar power output prediction error to obtain multiple wind and solar power output prediction scenario sets. Each wind and solar power output prediction scenario set includes wind and solar power output prediction data for each time point within a future period. Finally, each wind and solar power output prediction scenario set is input into a preset wind and solar complementary scheduling model to select the output scenario set, obtaining the target wind and solar power output prediction scenario set, and power scheduling is performed according to the target wind and solar power output prediction scenario set. Therefore, a covariance matrix is ​​constructed using actual and predicted wind and solar power output data with time series. Based on the covariance matrix, the time-varying wind and solar power output prediction error is determined. This error is then used to correct the wind and solar power output prediction data in the initial wind and solar power output prediction scenario set. Finally, the error-corrected wind and solar power output prediction data is used to achieve complementary grid scheduling, thereby improving the accuracy of power dispatch in the grid and ensuring the stable operation of the grid.

[0156] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0157] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A grid multi-energy complementary dispatch method based on the uncertainty of wind and solar power output, characterized in that, include: Obtain actual and predicted wind and solar power output data for the target power grid at multiple historical time points within a historical period. Construct a covariance matrix based on the difference between the actual and predicted wind and solar power output data at the same historical time point. Based on the covariance matrix, the wind and solar power prediction error is determined, and multiple initial wind and solar power prediction scenario sets are obtained. The wind and solar power prediction error is used to correct each initial wind and solar power prediction scenario set to obtain multiple wind and solar power prediction scenario sets. Each wind and solar power prediction scenario set includes wind and solar power prediction data for each time point in a future time period. Each of the predicted wind and solar power output scenarios is input into a preset wind and solar complementary scheduling model to select the power output scenario set, thereby obtaining the target predicted wind and solar power output scenario set, and power scheduling is performed according to the target predicted wind and solar power output scenario set. The preset wind-solar hybrid scheduling model includes a power grid shortage objective function, a power grid curtailment objective function, and a thermal power operation cost objective function. Each predicted wind-solar output scenario set is input into the preset wind-solar hybrid scheduling model to select the output scenario set, resulting in a target predicted wind-solar output scenario set, including: The objective functions for power grid shortage, power grid curtailment, and thermal power operating cost are transformed into a single-objective scenario set selection function using a hierarchical weighted optimization approach. Scenario set selection constraints are obtained, and scenario set attribute data, power generation attribute data of other power generation equipment, unit attribute data of thermal power generation equipment, and regional power attribute information of the target power grid region are determined for each wind and solar power predicted output scenario set. The scenario set attribute data includes the number of wind and solar power generation equipment in each wind and solar power predicted output scenario set, and the wind and solar power predicted output data at each time point within the future time period. The power generation attribute data includes the remaining power generation... The equipment output data, the regional power attribute data including mutual assistance power and load, and the unit attribute data including the number of thermal power generation units, thermal power combustion cost coefficient, unit output data, and unit start-up and shutdown costs; based on the scenario set selection constraints, the scenario set attribute data, the power generation attribute data, the unit attribute data, and the regional power attribute information of each wind and solar predicted output scenario set are substituted into the single-objective scenario set selection function to obtain the evaluation value corresponding to each wind and solar predicted output scenario set. Based on the evaluation value, the target wind and solar predicted output scenario set is determined in each wind and solar predicted output scenario set.

2. The method according to claim 1, characterized in that, Based on the covariance matrix, the wind and solar power prediction output error is determined, including: Determine the installed capacity of wind and solar power generation equipment corresponding to the target power grid, and based on the installed capacity, standardize the covariance matrix to obtain a standardized covariance matrix; The standardized covariance matrix is ​​decomposed into a lower triangular matrix to obtain the lower triangular matrix; Multiple uniformly distributed random numbers are generated using a pseudo-random number generator. Each of the random numbers is then converted into a standard normal distribution, resulting in multiple standard normal random vectors. The dimension of each standard normal random vector is the same as the vector dimension in the standardized covariance matrix. The lower triangular matrix is ​​used to perform a linear transformation on each of the standard normal random vectors, and the sample wind and solar power prediction output error is determined based on the transformation results. Based on the sample wind and solar power prediction output error, the wind and solar power prediction output error is determined.

3. The method according to claim 2, characterized in that, Based on the sample wind and solar power prediction output error, the wind and solar power prediction output error is determined, including: Based on the wind and solar power prediction error of the sample, an error feature matrix is ​​constructed; Determine the mean of each element in the error feature matrix, and subtract the mean from each element in the error feature matrix to obtain the centered error matrix; Determine the error covariance matrix corresponding to the centered error matrix; The error covariance matrix is ​​decomposed into eigenvalues ​​to obtain the eigenvalues ​​and eigenvectors of the error matrix. Based on the magnitude of the eigenvalues ​​of the error matrix, a preset number of error matrix eigenvectors are selected from the error matrix eigenvectors, and the preset number of error matrix eigenvectors are determined as principal component error eigenvectors. The wind and solar power prediction output error is determined based on the principal component error eigenvectors.

4. The method according to claim 1, characterized in that, Before inputting each of the predicted wind and solar power output scenarios into a preset wind-solar complementary scheduling model to select the power output scenario set and obtaining the target predicted wind and solar power output scenario set, the method further includes: Construct a pre-defined initial wind-solar hybrid scheduling model; Obtain a sample dataset, wherein the sample dataset includes multiple sample wind and solar power output scene sets labeled with wind and solar power output scene sets whose scheduling effect meets the requirements; The sample dataset is divided into a training set and a test set. The preset initial wind-solar complementary scheduling model is trained using the training set, and the trained preset initial wind-solar complementary scheduling model is tested using the test set. Finally, the trained preset initial wind-solar complementary scheduling model that meets the test conditions is taken as the preset wind-solar complementary scheduling model.

5. The method according to claim 1, characterized in that, The objective functions for power grid shortage, power grid curtailment, and thermal power operation cost are transformed into a single-objective scenario set selection function using a hierarchical weighted optimization approach, including: The objective function for power grid shortage is set as follows: ,in, ; The objective function for power grid curtailment is set as follows: ,in, ; The objective function for thermal power plant operating costs is set as follows: ,in, For power shortage data, For abandoned electricity data, Let n be the operating cost of thermal power, n be the identifier of wind and solar power generation equipment in the predicted output scenario, N be the total number of wind and solar power generation equipment, t be the identifier of the future time period, T be the total length of the future time period, p be the regional identifier of the target power grid, and M be the total number of regions in the target power grid. , These represent the power shortage and power abandonment in region p at time point t in the nth scenario set. Contribute to the scenery of region p at time point t under scene set n. , , , , These represent the hydropower output, thermal power output, nuclear power output, pumped storage power output, and DC power output in region p at time point t. The total output of other power sources in region p at time point t. The mutual assistance power fed into region p at time point t in the nth scenario set. The load of region p at time point t, , These represent the thermal power unit serial number and the number of units, respectively; a, b, and c represent the thermal power combustion cost coefficients, respectively. For thermal power generation equipment Unit output, for Start-up and shutdown costs of the generating unit; The range algorithm is used to perform dimensionless processing on the target functions of power grid shortage, power grid curtailment, and thermal power operation cost, respectively, to obtain the processed target functions of power grid shortage, power grid curtailment, and thermal power operation cost. The processed target functions for power grid shortage, power grid curtailment, and thermal power operation cost are divided into different levels, and the weight coefficients of each target function in the same level and the weight coefficients of the target functions in different levels are determined. Based on the same-level weight coefficient and the inter-level weight coefficient, the processed power grid shortage objective function, the processed power grid curtailment objective function, and the processed thermal power operation cost objective function are weighted and aggregated to obtain the single-objective scenario set selection function.

6. The method according to claim 1, characterized in that, Before inputting each of the predicted wind and solar power output scenarios into a preset wind-solar complementary scheduling model to select the power output scenario set and obtaining the target predicted wind and solar power output scenario set, the method further includes: Determine the limits for wind power generation of wind power generation equipment, the limits for photovoltaic power generation of photovoltaic power generation equipment, and the limits for thermal power generation of thermal power generation equipment respectively; Based on the wind power generation limit, the photovoltaic power generation limit, and the thermal power generation limit, a scenario set is selected for each wind and solar power generation prediction scenario set to obtain a wind and solar power generation prediction scenario set that meets the power output requirements. Each of the predicted wind and solar power output scenarios is input into a preset wind-solar complementary scheduling model to select the power output scenario set, thereby obtaining the target predicted wind and solar power output scenario set, including: The wind and solar power output scenario set that meets the power output requirements is input into the preset wind and solar complementary scheduling model to select the power output scenario set and obtain the target wind and solar power output scenario set.

7. A power grid multi-energy complementary dispatching device based on the uncertainty of wind and solar power output, characterized in that, include: The acquisition unit is used to acquire the actual wind and solar power output data and the predicted wind and solar power output data corresponding to the target power grid at multiple historical time points within a historical time period, and to construct a covariance matrix based on the difference between the actual wind and solar power output data and the predicted wind and solar power output data at the same historical time point. The correction unit is used to determine the wind and solar power prediction error based on the covariance matrix, and to obtain multiple initial wind and solar power prediction scene sets. The wind and solar power prediction error is used to correct each initial wind and solar power prediction scene set to obtain multiple wind and solar power prediction scene sets. Each wind and solar power prediction scene set includes wind and solar power prediction data for each time point in a future time period. The selection unit is used to input each of the predicted wind and solar power output scenarios into a preset wind-solar complementary scheduling model to select the output scenario set, thereby obtaining a target predicted wind and solar power output scenario set, and to perform power dispatch according to the target predicted wind and solar power output scenario set. The preset wind-solar complementary scheduling model includes a grid power shortage objective function, a grid curtailment objective function, and a thermal power operating cost objective function. Inputting each of the predicted wind and solar power output scenarios into the preset wind-solar complementary scheduling model to select the output scenario set and obtain the target predicted wind and solar power output scenario set includes: using a hierarchical weight optimization method to convert the grid power shortage objective function, the grid curtailment objective function, and the thermal power operating cost objective function into a single-objective scenario set selection function; obtaining scenario set selection constraints; and determining the scenario set attribute data for each predicted wind and solar power output scenario set, as well as the power generation attribute data of other power generation equipment and the unit attribute data of thermal power generation equipment. The system comprises: 1) 2) 3) 4) 5) 6) 6) 7) 6) 7) 7) 6) 7) 6) 7) 6) 6) 6)" 7)" 6)" 7)" 8)" 8)"" 8)" 8)"" 8)"""" 8)—" """" 8""" "" ....""""""""""""""""""""""""."""""""""""""""""."""""""""""""""".""""""""""""".""""""""" 8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images