A multi-energy park load scenario generation method, device and storage medium

Abstract

The present invention discloses a method, device and storage medium for generating load scenarios in a multi-energy park, wherein the method comprises: obtaining a data set of electric, heating and cooling loads in a multi-energy park; calculating a correlation matrix of the data set of electric, heating and cooling loads; calculating the mean square error between the actual cumulative distribution function and the empirical cumulative distribution function of the marginal distribution corresponding to the electric, heating and cooling random variables in the multi-energy park according to the data set of electric, heating and cooling loads, and judging whether the mean square error meets a preset condition; if the preset condition is not met, correcting the marginal distribution of the random variables in the electric, heating and cooling load scenario set in the multi-energy park, updating the marginal distribution one by one according to the result of the marginal distribution correction, and repeating the calculation of the cumulative distribution error until the mean square error meets the preset condition; and outputting a typical scenario of electric, heating and cooling loads in a multi-energy park that meets the preset condition. The present invention adopts a cumulative distribution function to generate load scenarios, which can better control the marginal distribution, thereby effectively improving the accuracy of the scenario generation result.

Description

Technical Field

[0001] The present invention relates to the field of energy optimization technology, and in particular to a method, device and storage medium for generating a multi-energy park load scenario. Background Art

[0002] At present, energy is the foundation for human survival and development, and is a fundamental strategic resource related to national security and stability, as well as national economic development. With the increasing depletion of petrochemical energy and the proposal of the dual carbon goals, changing the traditional energy supply mode and improving the comprehensive utilization efficiency of energy have become a new focus of international academic attention. In recent years, my country has developed rapidly in the field of energy, but it still faces severe challenges. On the source side, the problem of wind and solar power abandonment is serious. On the energy consumption side, my country's energy consumption per unit GDP remains high. In the face of many problems in today's energy development, the integrated energy system with multi-energy coupling of electricity, heat and cold has received widespread attention and can be regarded as a feasible development state for the transformation of my country's energy field. Among them, the regional energy system represented by the park has the characteristics of high energy density, high load utilization hours, high penetration rate of renewable energy and diversified energy forms. It is an effective way to promote large-scale local consumption of renewable energy, improve the comprehensive utilization efficiency of energy and achieve the dual carbon goals.

[0003] Load scenario sets are the basis for planning, modeling, operation and scheduling of all links in regional energy systems. Existing scenario generation methods usually generate representative scenario sets through massive historical load data of multi-energy parks. However, existing scenario generation methods are difficult to accurately generate multi-energy park load scenarios. Summary of the invention

[0004] The present invention provides a multi-energy park load scenario generation method, device and storage medium to solve the technical problem that the existing scenario generation method is difficult to accurately generate multi-energy park load scenarios.

[0005] An embodiment of the present invention provides a method for generating a multi-energy park load scenario, comprising:

[0006] Data acquisition steps: obtain the electric heating and cooling load data set of the multi-energy park;

[0007] Correlation matrix calculation step: calculating the correlation matrix of the electric, heating and cooling load data set;

[0008] Cumulative distribution error calculation step: according to the electric heating and cooling load data set, calculate the mean square error between the actual cumulative distribution function and the empirical cumulative distribution function of the marginal distribution corresponding to the electric heating and cooling random variable of the multi-energy park, and determine whether the mean square error meets the preset conditions;

[0009] Marginal distribution correction step: if the preset conditions are not met, the marginal distribution of the random variables of the multi-energy park electric heating and cooling load scenario set is corrected, and the marginal distribution is updated one by one according to the marginal distribution correction result, and the cumulative distribution error calculation is repeated until the mean square error meets the preset conditions;

[0010] Load scenario generation steps: Output typical scenarios of electric heating and cooling loads in a multi-energy park that meet preset conditions.

[0011] Furthermore, the data acquisition step includes:

[0012]

[0013]

[0014]

[0015] in, This is a data set of electric, heating and cooling loads in a multi-energy park. It is required to sample every hour. The electric, heating and cooling loads constitute n (=24×3) columns of data. is the electricity / heating / cooling load data of the i-th hour, d is the sampling day, and l is the identifier of the electricity / heating / cooling load; is the n-dimensional random variable of the electric heating and cooling load data set of the multi-energy park, represents the random variable of the electric load in the i-th hour, represents the random variable of the heat load at the i-th hour, is a random variable representing the cooling load at the i-th hour.

[0016] Furthermore, the correlation matrix calculation step includes:

[0017]

[0018]

[0019]

[0020] Among them, R is the correlation matrix, ρ ij represents the correlation coefficient of the i-th row and j-th column in the correlation matrix R, Represents a dataset of electric heating and cooling loads in a multi-energy park After transposition, the i-th row vector and the j-th row vector The covariance of express After the correlation matrix R is obtained, the lower triangular matrix L can be obtained by cholesky decomposition using formula (6). This decomposition transformation can ensure that the correlation matrix R is symmetric and positive definite. In order to make the generated multi-energy park electric heating and cooling load scenario set meet the load The relevance of Perform matrix transformation update:

[0021]

[0022] Based on the above calculations and matrix transformation, the correlation matrix R and the matrix satisfying the multi-energy park electric heating and cooling load data set are obtained. Correlation of random variables

[0023] Furthermore, the cumulative distribution error calculation step includes:

[0024] According to the multi-energy park electric heating and cooling load data set Use express The corresponding electrical load edge distribution, express The corresponding edge distribution of heat load, express The corresponding marginal distribution of cooling load is calculated by The mean square error between the actual cumulative distribution function and the empirical cumulative distribution function of the corresponding marginal distribution:

[0025]

[0026] Where F(·) is the n-dimensional random variable of the electric heating and cooling load of the multi-energy park The actual cumulative distribution function corresponding to the marginal distribution, is the n-dimensional random variable of the heating and cooling load of the multi-energy park The empirical cumulative distribution function of the corresponding marginal distribution, m is the number of samples taken from the corresponding marginal distribution, and ε is the preset mean square error threshold.

[0027] Furthermore, if the preset condition is not met, the marginal distribution of the random variable of the multi-energy park electric heating and cooling load scenario set is corrected, and the marginal distribution is updated one by one according to the marginal distribution correction result, including:

[0028] Ignore the superscript l indicating the electric heating and cooling load type and use F -1 Represents the inverse function of the cumulative distribution function;

[0029] The marginal distribution of electric heating and cooling loads in the multi-energy park is converted into a uniform distribution U(0,1). The expression that satisfies the distribution can be written as:

[0030]

[0031] Among them, x represents the corresponding edge distribution of electric heating and cooling load, rank(x p ,x) means for the elements x1,...,x in x m After sorting from small to large, x p The specific ranking, u p is a distribution vector u=(u1,...,u m ), substitute the elements in the cumulative distribution function and invert them one by one, and update x p For x p ′:

[0032] x p ′=F -1 (u p ),p=1...m (21)

[0033] The above process is repeatedly applied to different types of load scenario data at different times to correct the marginal distribution of random variables of electric, heating and cooling loads in the multi-energy park in turn, and the updated and Repeat the cumulative distribution error calculation until the mean square error meets the preset conditions, thereby Updated to

[0034] Furthermore, the load scenario generation step includes:

[0035] Perform an inverse transformation on the L matrix in the correlation matrix to obtain n-dimensional random variables of electric heating and cooling loads in multi-energy parks with correlation

[0036]

[0037] According to the required typical days, through n-dimensional random variables The sampling output meets the typical scenarios of electric heating and cooling loads in multi-energy parks.

[0038] An embodiment of the present invention provides a multi-energy park load scenario generating device, comprising:

[0039] A data acquisition module is used to obtain the electric, heating and cooling load data set of the multi-energy park;

[0040] A correlation matrix calculation module, used to calculate the correlation matrix of the electric heating and cooling load data set;

[0041] A cumulative distribution error calculation module is used to calculate the mean square error between the actual cumulative distribution function and the empirical cumulative distribution function of the marginal distribution corresponding to the electric heating and cooling random variable of the multi-energy park according to the electric heating and cooling load data set, and determine whether the mean square error meets the preset conditions;

[0042] The edge distribution correction module is used to correct the edge distribution of the random variables of the electric, heating and cooling load scene set of the multi-energy park if the preset conditions are not met, update the edge distribution one by one according to the edge distribution correction results, and repeat the cumulative distribution error calculation until the mean square error meets the preset conditions;

[0043] The load scenario generation step module is used to output typical scenarios of electric heating and cooling loads in a multi-energy park that meet preset conditions.

[0044] An embodiment of the present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the multi-energy park load scenario generation method as described above. .

[0045] The embodiment of the present invention calculates the correlation matrix of electric, heating and cooling load data, and performs edge distribution correction on the electric, heating and cooling load data based on the correlation matrix through a cumulative distribution function, and generates a load scenario of a multi-energy park according to the edge distribution correction result. The method of using the cumulative distribution function to realize scenario generation is not limited to the original data cluster classification. A new scenario set can be generated according to the correlation matrix and the edge distribution, so that a new data scenario different from the original data set can be generated and the scenario conforms to the characteristics of the original data set, so as to reflect the coupling and uncertainty between various loads in the integrated energy system, thereby improving the management efficiency of the integrated energy system.

[0046] Furthermore, the embodiment of the present invention adopts a cumulative distribution function to generate load scenarios, which can better control the edge distribution and take into account the correlation between supply and demand of different time sections and different energy systems, thereby effectively improving the accuracy of the scenario generation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of a method for generating a multi-energy park load scenario provided by an embodiment of the present invention;

[0048] Figure 2 It is a schematic diagram of an annual electric load curve of the original electric heating and cooling load provided by an embodiment of the present invention;

[0049] Figure 3 It is a schematic diagram of an annual heat load curve of the original electric heating and cooling load provided by an embodiment of the present invention;

[0050] Figure 4 It is a schematic diagram of an annual cooling load curve of the original electric heating cooling load provided by an embodiment of the present invention;

[0051] Figure 5 is a schematic diagram of a typical daily load curve of a typical scenario set provided by an embodiment of the present invention;

[0052] Figure 6 is a schematic diagram of a typical daily heat load curve of a typical scenario set provided by an embodiment of the present invention;

[0053] Figure 7 is a schematic diagram of a typical daily cooling load curve of a typical scenario set provided by an embodiment of the present invention;

[0054] Figure 8 It is a structural schematic diagram of a multi-energy park load scenario generating device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0056] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0057] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0058] See also Figure 1-7 An embodiment of the present invention provides a method for generating a multi-energy park load scenario, comprising:

[0059] S1. Obtain the electric heating and cooling load data set of the multi-energy park;

[0060] S2, calculate the correlation matrix of the electric heating and cooling load data set;

[0061] S3. Calculate the mean square error between the actual cumulative distribution function and the empirical cumulative distribution function of the marginal distribution corresponding to the electric heating and cooling random variables of the multi-energy park based on the electric heating and cooling load data set, and determine whether the mean square error meets the preset conditions;

[0062] S4. If the preset conditions are not met, the edge distribution of the random variables of the electric heating and cooling load scenario set of the multi-energy park is corrected, and the edge distribution is updated one by one according to the edge distribution correction result, and the cumulative distribution error calculation is repeated until the mean square error meets the preset conditions;

[0063] S5. Output typical scenarios of electric heating and cooling loads in a multi-energy park that meet preset conditions.

[0064] The embodiment of the present invention calculates the correlation matrix of electric, heating and cooling load data, and performs edge distribution correction on the electric, heating and cooling load data based on the correlation matrix through a cumulative distribution function, and generates a load scenario of a multi-energy park according to the edge distribution correction result. The method of using a cumulative distribution function to realize scenario generation is not limited to the original data cluster classification. A new set of scenarios can be generated according to the correlation matrix and the edge distribution, so that a new data scenario different from the original data set can be generated and the scenario conforms to the characteristics of the original data set, so as to reflect the coupling and uncertainty between various loads in the integrated energy system, thereby improving the management efficiency of the integrated energy system.

[0065] In one embodiment, the data acquisition step includes:

[0066]

[0067]

[0068]

[0069] in, This is a data set of electric, heating and cooling loads in a multi-energy park. It is required to sample every hour. The electric, heating and cooling loads constitute n (=24×3) columns of data. is the electricity / heating / cooling load data of the i-th hour, d is the sampling day, and l is the identifier of the electricity / heating / cooling load; is the n-dimensional random variable of the electric heating and cooling load data set of the multi-energy park, represents the random variable of the electric load in the i-th hour, represents the random variable of the heat load at the i-th hour, is a random variable representing the cooling load at the i-th hour.

[0070] In one embodiment, the correlation matrix calculation step includes:

[0071]

[0072]

[0073]

[0074] Among them, R is the correlation matrix, ρ ij represents the correlation coefficient of the i-th row and j-th column in the correlation matrix R, Represents a dataset of electric heating and cooling loads in a multi-energy park After transposition, the i-th row vector and the j-th row vector The covariance of express After the correlation matrix R is obtained, the lower triangular matrix L can be obtained by cholesky decomposition using formula (6). This decomposition transformation can ensure that the correlation matrix R is symmetric and positive definite. In order to make the generated multi-energy park electric heating and cooling load scenario set meet the load The relevance of Perform matrix transformation update:

[0075]

[0076] Based on the above calculations and matrix transformation, the correlation matrix R and the matrix satisfying the multi-energy park electric heating and cooling load data set are obtained. Correlation of random variables

[0077] In one embodiment, the cumulative distribution error calculation step includes:

[0078] Based on the multi-energy park electric heating and cooling load data set Use express The corresponding electrical load edge distribution, express The corresponding edge distribution of heat load, express The corresponding marginal distribution of cooling load is calculated by random variable The mean square error between the actual cumulative distribution function and the empirical cumulative distribution function of the corresponding marginal distribution:

[0079]

[0080] Where F(·) is the n-dimensional random variable of the electric heating and cooling load of the multi-energy park The actual cumulative distribution function corresponding to the marginal distribution, is the n-dimensional random variable of the heating and cooling load of the multi-energy park The empirical cumulative distribution function of the corresponding marginal distribution, m is the number of samples taken from the corresponding marginal distribution, and ε is the preset mean square error threshold.

[0081] In one embodiment, if the preset condition is not met, the edge distribution of the random variable of the electric, heating and cooling load scenario set of the multi-energy park is corrected, and the edge distribution is updated one by one according to the edge distribution correction result, including:

[0082] Ignore the superscript l indicating the electric heating and cooling load type and use F -1 Represents the inverse function of the cumulative distribution function;

[0083] The marginal distribution of electric heating and cooling loads in the multi-energy park is converted into a uniform distribution U(0,1). The expression that satisfies the distribution can be written as:

[0084]

[0085] Among them, x represents the corresponding edge distribution of electric heating and cooling load, rank(x p ,x) means for the elements x1,...,x in x m After sorting from small to large, x p The specific ranking, u p is a distribution vector u=(u1,...,u m ), substitute the elements in the cumulative distribution function and invert them one by one, and update x p For x p ′:

[0086] x p ′=F -1 (u p ),p=1...m (32)

[0087] The above process is repeatedly applied to different types of load scenario data at different times to correct the marginal distribution of random variables of electric, heating and cooling loads in the multi-energy park in turn, and the updated and Repeat the cumulative distribution error calculation until the mean square error meets the preset conditions, thereby Updated to

[0088] In one embodiment, the load scenario generation step includes:

[0089] Perform an inverse transformation on the L matrix in the correlation matrix to obtain n-dimensional random variables of electric heating and cooling loads in multi-energy parks with correlation

[0090]

[0091] According to the required typical days, through n-dimensional random variables The sampling output meets the typical scenarios of electric heating and cooling loads in multi-energy parks.

[0092] In a specific embodiment, taking a certain regional multi-energy park as an example, the original electric heating and cooling load data is as follows: Figure 2-4 As shown in the figure, the electric heating and cooling load data of the typical scenario set is as follows Figure 5-7 As shown. The embodiment of the present invention can generate any scenario based on the original data set through the cumulative distribution function. The cumulative distribution function scenario generation algorithm is not limited to the original data cluster classification, and a new scenario set is generated according to mathematical features such as correlation matrix and marginal distribution to generate a new data scenario that is different from the original data set and meets the characteristics of the original data set.

[0093] The implementation of the embodiments of the present invention has the following beneficial effects:

[0094] The embodiment of the present invention calculates the correlation matrix of electric, heating and cooling load data, and performs edge distribution correction on the electric, heating and cooling load data based on the correlation matrix through a cumulative distribution function, and generates a load scenario of a multi-energy park according to the edge distribution correction result. The method of using a cumulative distribution function to realize scenario generation is not limited to the original data cluster classification. A new set of scenarios can be generated according to the correlation matrix and the edge distribution, so that a new data scenario different from the original data set can be generated and the scenario conforms to the characteristics of the original data set, so as to reflect the coupling and uncertainty between various loads in the integrated energy system, thereby improving the management efficiency of the integrated energy system.

[0095] Furthermore, the embodiment of the present invention adopts a cumulative distribution function to generate load scenarios, which can better control the edge distribution and take into account the correlation between supply and demand of different time sections and different energy systems, thereby effectively improving the accuracy of the scenario generation results.

[0096] See also Figure 8 Based on the same technical concept as the above-mentioned embodiment of the invention, an embodiment of the present invention provides a multi-energy park load scenario generating device, comprising:

[0097] The data acquisition module 10 is used to acquire the electric heating and cooling load data set of the multi-energy park;

[0098] A correlation matrix calculation module 20 is used to calculate the correlation matrix of the electric, heating and cooling load data set;

[0099] The cumulative distribution error calculation module 30 is used to calculate the mean square error between the actual cumulative distribution function and the empirical cumulative distribution function of the marginal distribution corresponding to the electric heating and cooling random variables of the multi-energy park according to the electric heating and cooling load data set, and determine whether the mean square error meets the preset conditions;

[0100] The edge distribution correction module 40 is used to correct the edge distribution of the random variables of the electric, heating and cooling load scene set of the multi-energy park if the preset conditions are not met, update the edge distribution one by one according to the edge distribution correction results, and repeat the cumulative distribution error calculation until the mean square error meets the preset conditions;

[0101] The load scenario generation module 50 is used to output a typical scenario of electric, heating and cooling loads in a multi-energy park that meets preset conditions.

[0102] In one embodiment, the data acquisition module 10 is further used to:

[0103]

[0104]

[0105]

[0106] in, This is a data set of electric, heating and cooling loads in a multi-energy park. It is required to sample every hour. The electric, heating and cooling loads constitute n (=24×3) columns of data. is the electricity / heating / cooling load data of the i-th hour, d is the sampling day, and l is the identifier of the electricity / heating / cooling load; is the n-dimensional random variable of the electric heating and cooling load data set of the multi-energy park, represents the random variable of the electric load in the i-th hour, represents the random variable of the heat load at the i-th hour, is a random variable representing the cooling load at the i-th hour.

[0107] In one embodiment, the correlation matrix calculation module 20 is further used for:

[0108]

[0109]

[0110]

[0111] Among them, R is the correlation matrix, ρ ij represents the correlation coefficient of the i-th row and j-th column in the correlation matrix R, Represents a dataset of electric heating and cooling loads in a multi-energy park After transposition, the i-th row vector and the j-th row vector The covariance of express After the correlation matrix R is obtained, the lower triangular matrix L can be obtained by cholesky decomposition using formula (6). This decomposition transformation can ensure that the correlation matrix R is symmetric and positive definite. In order to make the generated multi-energy park electric heating and cooling load scenario set meet the load The relevance of Perform matrix transformation update:

[0112]

[0113] Based on the above calculations and matrix transformation, the correlation matrix R and the matrix satisfying the multi-energy park electric heating and cooling load data set are obtained. Correlation of random variables

[0114] In one embodiment, the cumulative distribution error calculation module 30 is further used to:

[0115] Based on the multi-energy park electric heating and cooling load data set Use express The corresponding electrical load edge distribution, express The corresponding edge distribution of heat load, express The corresponding marginal distribution of cooling load is calculated by random variable The mean square error between the actual cumulative distribution function and the empirical cumulative distribution function of the corresponding marginal distribution:

[0116]

[0117] Where F(·) is the n-dimensional random variable of the electric heating and cooling load of the multi-energy park The actual cumulative distribution function corresponding to the marginal distribution, is the n-dimensional random variable of the heating and cooling load of the multi-energy park The empirical cumulative distribution function of the corresponding marginal distribution, m is the number of samples taken from the corresponding marginal distribution, and ε is the preset mean square error threshold.

[0118] In one implementation, if the preset conditions are not met, the marginal distribution of the random variables of the electric, heating and cooling load scenario set of the multi-energy park is corrected, and the marginal distribution is updated one by one according to the marginal distribution correction result, including:

[0119] Ignore the superscript l indicating the electric heating and cooling load type and use F -1 Represents the inverse function of the cumulative distribution function;

[0120] The marginal distribution of electric heating and cooling loads in the multi-energy park is converted into a uniform distribution U(0,1). The expression that satisfies the distribution can be written as:

[0121]

[0122] Among them, x represents the corresponding edge distribution of electric heating and cooling load, rank(x p ,x) means for the elements x1,...,x in x m After sorting from small to large, x p The specific ranking, u p is a distribution vector u=(u1,...,u m ), substitute the elements in the cumulative distribution function and invert them one by one, and update x p For x p ′:

[0123] x p ′=F -1 (u p ),p=1...m (43)

[0124] The above process is repeatedly applied to different types of load scenario data at different times to correct the marginal distribution of random variables of electric, heating and cooling loads in the multi-energy park in turn, and the updated and Repeat the cumulative distribution error calculation until the mean square error meets the preset conditions, thereby Updated to

[0125] In one embodiment, the load scenario generating module 50 is further configured to:

[0126] Perform an inverse transformation on the L matrix in the correlation matrix to obtain n-dimensional random variables of electric heating and cooling loads in multi-energy parks with correlation

[0127]

[0128] According to the required typical days, through n-dimensional random variables The sampling output meets the typical scenarios of electric heating and cooling loads in multi-energy parks.

[0129] The above are preferred embodiments of the present invention. It should be noted that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for generating a multi-energy park load scenario, characterized in that: include: Data acquisition steps: obtain the electric heating and cooling load data set of the multi-energy park; Correlation matrix calculation step: calculating the correlation matrix of the electric, heating and cooling load data set; Cumulative distribution error calculation step: according to the electric heating and cooling load data set, calculate the mean square error between the actual cumulative distribution function and the empirical cumulative distribution function of the marginal distribution corresponding to the electric heating and cooling random variable of the multi-energy park, and determine whether the mean square error meets the preset conditions; Marginal distribution correction step: if the preset conditions are not met, the marginal distribution of the random variables of the multi-energy park electric heating and cooling load scenario set is corrected, and the marginal distribution is updated one by one according to the marginal distribution correction result, and the cumulative distribution error calculation is repeated until the mean square error meets the preset conditions; if the preset conditions are not met, the marginal distribution of the random variables of the multi-energy park electric heating and cooling load scenario set is corrected, and the marginal distribution is updated one by one according to the marginal distribution correction result, including: Ignore the superscript l indicating the electric heating and cooling load type and use F -1 Represents the inverse function of the cumulative distribution function; The marginal distribution of electric heating and cooling loads in the multi-energy park is converted into a uniform distribution U(0,1). The expression that satisfies the distribution can be written as: Among them, x represents the corresponding edge distribution of electric heating and cooling load, rank(x p ,x) means for the elements x1,...,x in x m After sorting from small to large, x p The specific ranking, u p is a distribution vector u=(u1,...,u m ), substitute the elements in the cumulative distribution function and invert them one by one, and update x p For x p ′: x p ′=F -1 (u p ),p=1...m (2) The above process is repeatedly applied to different types of load scenario data at different times to correct the marginal distribution of random variables of electric, heating and cooling loads in the multi-energy park in turn, and the updated and Repeat the cumulative distribution error calculation until the mean square error meets the preset conditions, thereby Updated to Load scenario generation step: outputting typical scenarios of electric, heating and cooling loads in a multi-energy park that meet preset conditions; the outputting typical scenarios of electric, heating and cooling loads in a multi-energy park that meet preset conditions includes: inversely transforming the L matrix in the correlation matrix to obtain the scenarios that meet n-dimensional random variables of electric heating and cooling loads in multi-energy parks with correlation According to the required typical days, through n-dimensional random variables The sampling output meets the typical scenarios of electric heating and cooling loads in multi-energy parks.

2. The multi-energy park load scenario generation method according to claim 1, characterized in that: The data acquisition step comprises: in, This is a data set of electric, heating and cooling loads in a multi-energy park. It is required to sample every hour. The electric, heating and cooling loads constitute n (=24×3) columns of data. is the electricity / heating / cooling load data of the i-th hour, d is the sampling day, and l is the identifier of the electricity / heating / cooling load; is the n-dimensional random variable of the electric heating and cooling load data set of the multi-energy park, represents the random variable of the electric load in the i-th hour, represents the random variable of the heat load at the i-th hour, is a random variable representing the cooling load at the i-th hour.

3. The multi-energy park load scenario generation method according to claim 1, characterized in that: The correlation matrix calculation step comprises: Among them, R is the correlation matrix, ρ ij represents the correlation coefficient of the i-th row and j-th column in the correlation matrix R, Represents a dataset of electric heating and cooling loads in a multi-energy park After transposition, the i-th row vector and the j-th row vector The covariance of express After the correlation matrix R is obtained, the lower triangular matrix L can be obtained by cholesky decomposition using formula (6). This decomposition transformation can ensure that the correlation matrix R is symmetric and positive definite. In order to make the generated multi-energy park electric heating and cooling load scenario set meet the load The relevance of Perform matrix transformation update: Based on the above calculations and matrix transformation, the correlation matrix R and the matrix satisfying the multi-energy park electric heating and cooling load data set are obtained. Correlation of random variables 4. The multi-energy park load scenario generation method according to claim 1, characterized in that: The steps for calculating the cumulative distribution error include: According to the multi-energy park electric heating and cooling load data set Use express The corresponding electrical load edge distribution, express The corresponding edge distribution of heat load, express The corresponding marginal distribution of cooling load is calculated by The mean square error between the actual cumulative distribution function and the empirical cumulative distribution function of the corresponding marginal distribution: Where F(·) is the n-dimensional random variable of the electric heating and cooling load of the multi-energy park The actual cumulative distribution function corresponding to the marginal distribution, is the n-dimensional random variable of the heating and cooling load of the multi-energy park The empirical cumulative distribution function of the corresponding marginal distribution, m is the number of samples taken from the corresponding marginal distribution, and ε is the preset mean square error threshold.

5. A multi-energy park load scenario generation device, characterized in that: include: A data acquisition module is used to obtain the electric, heating and cooling load data set of the multi-energy park; A correlation matrix calculation module, used to calculate the correlation matrix of the electric heating and cooling load data set; A cumulative distribution error calculation module is used to calculate the mean square error between the actual cumulative distribution function and the empirical cumulative distribution function of the marginal distribution corresponding to the electric heating and cooling random variable of the multi-energy park according to the electric heating and cooling load data set, and determine whether the mean square error meets the preset conditions; The edge distribution correction module is used to correct the edge distribution of the random variables of the electric heating and cooling load scene set of the multi-energy park if the preset conditions are not met, update the edge distribution one by one according to the edge distribution correction results, and repeat the cumulative distribution error calculation until the mean square error meets the preset conditions; specifically, it is used to ignore the superscript l indicating the electric heating and cooling load type and use F -1 Represents the inverse function of the cumulative distribution function; The marginal distribution of electric heating and cooling loads in the multi-energy park is converted into a uniform distribution U(0,1). The expression that satisfies the distribution can be written as: Among them, x represents the corresponding edge distribution of electric heating and cooling load, rank(x p ,x) means for the elements x1,...,x in x m After sorting from small to large, x p The specific ranking, u p is a distribution vector u=(u1,...,u m ), substitute the elements in the cumulative distribution function and invert them one by one, and update x p For x p ′: x p ′=F -1 (u p ),p=1...m (13) The above process is repeatedly applied to different types of load scenario data at different times to correct the marginal distribution of random variables of electric, heating and cooling loads in the multi-energy park in turn, and the updated and Repeat the cumulative distribution error calculation until the mean square error meets the preset conditions, thereby Updated to The load scenario generation step module is used to output a typical scenario of electric heating and cooling loads in a multi-energy park that meets the preset conditions; specifically, it is used to perform an inverse transformation on the L matrix in the correlation matrix to obtain a scenario that meets the preset conditions. n-dimensional random variables of electric heating and cooling loads in multi-energy parks with correlation According to the required typical days, through n-dimensional random variables The sampling output meets the typical scenarios of electric heating and cooling loads in multi-energy parks.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the multi-energy park load scenario generation method as described in any one of claims 1 to 4.

Images