A method for predicting power grid load

Abstract

The present invention relates to load forecasting, and in particular to a power grid load forecasting method, which decomposes a power grid load forecasting problem into different levels, constructs a judgment matrix, and calculates the preliminary weight of each factor based on the judgment matrix; calculates the coefficient of variation of each factor, and uses the coefficient of variation to adjust the preliminary weight of each factor to obtain the weight coefficient of each factor; constructs a grey correlation matrix of each factor according to historical power grid load data, and calculates the correlation between each factor and the power grid load based on the grey correlation matrix of each factor; constructs a fuzzy relationship matrix of each factor based on the weight coefficient and correlation of each factor, and obtains an electric quantity prediction matrix based on the fuzzy relationship matrix of each factor; inputs the electric quantity prediction matrix into a pre-trained power grid load forecasting model to obtain a first power grid load forecasting result; the technical solution provided by the present invention can effectively overcome the defect of the prior art that it is difficult to accurately predict the power grid load.

Description

Technical Field

[0001] The present invention relates to load forecasting, and in particular to a power grid load forecasting method. Background Art

[0002] The power grid, consisting of substations and transmission and distribution lines of various voltages, comprises three components: substation, transmission, and distribution. Currently, traditional grid load forecasting methods typically train and validate neural network models using historical load data, leveraging the nonlinear characteristics of the neural network model to output grid load forecast results.

[0003] However, the external factors affecting power grid load forecasting are numerous and complex, and not all factors can play a role in load forecasting. Relying solely on neural network models cannot fully consider the categories of influencing factors and their importance in affecting load forecasting, resulting in the inability to guarantee prediction accuracy. Summary of the Invention

[0004] In view of the above-mentioned shortcomings of the prior art, the present invention provides a power grid load forecasting method, which can effectively overcome the defect of the prior art that it is difficult to accurately forecast the power grid load.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0006] A method for predicting power grid load includes the following steps:

[0007] S1. Decompose the power grid load forecasting problem into different levels, construct a judgment matrix, and calculate the preliminary weight of each factor based on the judgment matrix;

[0008] S2. Calculate the coefficient of variation of each factor, and use the coefficient of variation to adjust the initial weight of each factor to obtain the weight coefficient of each factor;

[0009] S3. constructing a grey correlation matrix of each factor based on the historical data of the power grid load, and calculating the correlation between each factor and the power grid load based on the grey correlation matrix of each factor;

[0010] S4. Construct a fuzzy relationship matrix of each factor based on its weight coefficient and correlation, and obtain an electricity consumption prediction matrix based on the fuzzy relationship matrix of each factor;

[0011] S5. Inputting the power prediction matrix into a pre-trained power grid load prediction model to obtain a first power grid load prediction result;

[0012] S6. defining type 2 fuzzy sets of input variables and output variables based on historical grid load data, setting membership functions for the type 2 fuzzy sets, and formulating fuzzy rules;

[0013] S7, fuzzifying each factor based on the membership function, combining the fuzzified factors and fuzzy rules, and performing fuzzy reasoning using a type-2 fuzzy reasoning mechanism to obtain a type-2 fuzzy set corresponding to the power grid load;

[0014] S8. Defuzzify the type 2 fuzzy set corresponding to the power grid load to obtain a second power grid load forecast result;

[0015] S9. Comprehensively analyze the first power grid load forecast result and the second power grid load forecast result to obtain a final power grid load forecast result.

[0016] Preferably, in S1, the power grid load forecasting problem is decomposed into different levels, and a judgment matrix is ​​constructed. The preliminary weight of each factor is calculated based on the judgment matrix, including:

[0017] S11. Decomposing the power grid load forecasting problem into a target layer, a criterion layer, and an indicator layer, wherein the target layer is the power grid load forecasting result, the criterion layer is the main factors affecting the power grid load, and the indicator layer is the historical data of each factor;

[0018] S12, compare each factor in the criterion layer pairwise and construct a judgment matrix;

[0019] S13, calculating the eigenvectors of the judgment matrix and normalizing the eigenvectors to obtain preliminary weights of each factor;

[0020] Among them, the elements in the judgment matrix represent the relative importance of each factor.

[0021] Preferably, in S13, the eigenvector of the judgment matrix is ​​calculated and normalized to obtain the preliminary weight of each factor, including:

[0022] S131, normalizing each column of the judgment matrix, and adding the normalized judgment matrix row by row to obtain an eigenvector of the judgment matrix;

[0023] S132. Divide each element in the eigenvector by the sum of all elements to obtain a normalized eigenvector;

[0024] Among them, the elements in the normalized eigenvector represent the preliminary weights of each factor.

[0025] Preferably, in S2, the coefficient of variation of each factor is calculated, and the initial weight of each factor is adjusted using the coefficient of variation to obtain the weight coefficient of each factor, including:

[0026] S21. For each factor, obtain the corresponding historical data in the indicator layer and calculate the mean and standard deviation of the data;

[0027] S22. Divide the standard deviation by the mean to calculate the coefficient of variation, which measures the relative dispersion of the data for each factor;

[0028] S23, adding the coefficient of variation of each factor to the sum of all coefficients of variation to obtain the coefficient of variation weight of each factor based on the degree of data variation;

[0029] S24, performing weighted summation on the coefficient of variation weight and the preliminary weight of each factor to obtain the fusion weight of each factor;

[0030] S25. Normalize the fusion weights of each factor to obtain the weight coefficient of each factor.

[0031] Preferably, in S3, a grey correlation matrix of each factor is constructed according to the historical data of the power grid load, and the correlation between each factor and the power grid load is calculated based on the grey correlation matrix of each factor, including:

[0032] S31. For each factor, obtain the corresponding historical data in the indicator layer and perform feature extraction to obtain historical data features;

[0033] S32, performing intrinsic correlation processing on the historical data characteristics of each factor to obtain the grey correlation matrix of each factor;

[0034] S33, calculating the correlation between each factor and the grid load based on the grey correlation matrix of each factor;

[0035] Among them, the greater the correlation, the greater the impact of the factor on the grid load.

[0036] Preferably, in S4, a fuzzy relationship matrix of each factor is constructed by combining the weight coefficient and correlation degree of each factor, and an electricity prediction matrix is ​​obtained based on the fuzzy relationship matrix of each factor, including:

[0037] S41. Combining the weight coefficient and correlation degree of each factor, constructing a correlation matrix between each factor and the grid load;

[0038] S42, fuzzifying the correlation matrix of each factor to obtain a fuzzy correlation matrix of each factor;

[0039] S43, using a multiple linear regression algorithm to perform multiple linear regression on the fuzzy correlation matrix of each factor to obtain a prediction matrix of each factor;

[0040] S44. Use a quadratic function fitting algorithm to perform matrix fitting on the prediction matrix of each factor to obtain an electricity prediction matrix.

[0041] Preferably, in S5, the power prediction matrix is ​​input into a pre-trained power grid load prediction model to obtain a first power grid load prediction result, including:

[0042] S51. Selecting an appropriate grey prediction model as a power grid load prediction model according to the power prediction matrix;

[0043] S52, screening and constructing a historical data set from the historical power grid load data, and dividing the historical data set into a training set, a validation set, and a test set according to a preset ratio;

[0044] S53, setting a loss function and an optimizer of a power grid load forecasting model;

[0045] S54, inputting the training set into the power grid load forecasting model for model training;

[0046] S55, calculating the loss value based on the loss function, and the optimizer updating the model parameters according to the loss value and the network gradient information;

[0047] S56. If the loss value is less than the preset threshold, the model training ends and the current power grid load forecasting model is the trained power grid load forecasting model. Otherwise, the process returns to S54 and continues to use the training set for model training.

[0048] S57. Input the validation set into the trained power grid load forecasting model, evaluate the generalization ability of the model by observing its performance on the validation set, and tune the model's hyperparameters and structure;

[0049] S58, inputting the test set into the tuned power grid load forecasting model, performing model performance evaluation, and obtaining a pre-trained power grid load forecasting model;

[0050] S59: Input the power prediction matrix into a pre-trained power grid load prediction model to obtain a first power grid load prediction result.

[0051] Preferably, in S6, type 2 fuzzy sets of input variables and output variables are defined according to the historical data of the power grid load, membership functions are set for the type 2 fuzzy sets, and fuzzy rules are formulated, including:

[0052] S61. Based on the historical data of power grid load and domain knowledge, the main factors affecting the power grid load are screened as input variables, the power grid load is regarded as the output variable, and type 2 fuzzy sets of the input variables and the output variables are defined;

[0053] S62, setting an appropriate membership function for each type 2 fuzzy set to determine the degree to which the variable belongs to each type 2 fuzzy set;

[0054] S63. Based on the historical data of power grid load and domain knowledge, a series of fuzzy rules are formulated to describe the fuzzy relationship between input variables and output variables;

[0055] Among them, fuzzy rules are formulated in the form of "if-then".

[0056] Preferably, in S62, a suitable membership function is set for each type 2 fuzzy set to determine the degree to which the variable belongs to each type 2 fuzzy set, including:

[0057] S621. Determine the range of input variables and output variables based on historical grid load data and domain knowledge;

[0058] S622. According to the variable characteristics and prediction requirements, set an appropriate membership function for each type 2 fuzzy set;

[0059] S623. Determine the parameters of each membership function based on historical grid load data and domain knowledge, and adjust the shape and parameters of each membership function by taking into account the fuzziness of the variables.

[0060] Among them, the membership functions of type 2 fuzzy sets include:

[0061] 1) Linear membership function:

[0062] ;

[0063] in, f ( x ) is a variable x The membership degree of a’ 、 b’ is a constant;

[0064] 2) Triangle membership function:

[0065] ;

[0066] in, f ( x ) is a variable x The membership degree of a 、 b 、 c are the three vertices of the triangle;

[0067] 3) Gaussian membership function:

[0068] ;

[0069] in, f ( x ) is a variable x The membership degree of is the mean, is the standard deviation.

[0070] Preferably, in S7, each factor is fuzzified based on the membership function, and the fuzzified factors and fuzzy rules are combined to perform fuzzy reasoning using a type 2 fuzzy reasoning mechanism to obtain a type 2 fuzzy set corresponding to the power grid load, including:

[0071] S71. Calculate the membership degree of a factor to each type-2 fuzzy set based on the membership function, and take the type-2 fuzzy set with the largest membership degree as the type-2 fuzzy set corresponding to the factor;

[0072] S72, repeat S71 until the type 2 fuzzy sets corresponding to all factors are obtained, and the fuzzification of each factor is completed;

[0073] S73. Combining the type-2 fuzzy sets and fuzzy rules corresponding to all factors, using the type-2 fuzzy reasoning mechanism to perform fuzzy reasoning, obtain the type-2 fuzzy set corresponding to the power grid load to describe the power grid load forecast.

[0074] Compared with the prior art, the power grid load forecasting method provided by the present invention has the following beneficial effects:

[0075] 1) The power grid load forecasting problem is decomposed into different levels and a judgment matrix is ​​constructed. Based on the judgment matrix, the preliminary weights reflecting the relative importance of each factor are calculated. The coefficient of variation of each factor is then calculated and the preliminary weights of each factor are adjusted using the coefficient of variation. The coefficient of variation, which reflects the degree of dispersion of each factor data, can then be used to correct the relative importance of each factor, so that the obtained weight coefficients of each factor can better reflect the relative importance of each factor.

[0076] 2) Based on the historical data of power grid load, a grey correlation matrix of each factor is constructed. Based on the grey correlation matrix of each factor, the correlation degree reflecting the influence of each factor on the power grid load, that is, the absolute importance of each factor, is calculated. The fuzzy relationship matrix of each factor is constructed by combining the weight coefficient of each factor (reflecting the relative importance of each factor) and the correlation degree (reflecting the absolute importance of each factor). This ensures that the factors involved in the fuzzy relationship matrix are all elements that have a substantial impact on load forecasting, thereby making the power forecast matrix obtained based on the fuzzy relationship matrix of each factor more accurate. By inputting the power forecast matrix into the pre-trained power grid load forecasting model, a first power grid load forecast result with higher accuracy can be obtained.

[0077] 3) According to the historical data of power grid load, type 2 fuzzy sets of input variables and output variables are defined, membership functions are set for type 2 fuzzy sets, and fuzzy rules are formulated. Based on the membership function, each factor is fuzzified. Combining the fuzzified factors and fuzzy rules, fuzzy reasoning is performed using the type 2 fuzzy reasoning mechanism to obtain the type 2 fuzzy set corresponding to the power grid load. The type 2 fuzzy set corresponding to the power grid load is defuzzified. Through the adjustable membership function, the power grid load influencing factors with ambiguity and uncertainty can be better handled. At the same time, it is suitable for power systems with serious nonlinearity and random interference. Fuzzy rules and fuzzy reasoning can be used to capture the nonlinear characteristics of power grid load changes, thereby realizing accurate prediction of power grid load and obtaining the second power grid load prediction result. By comprehensively analyzing the first power grid load prediction result and the second power grid load prediction result, the prediction accuracy of the final power grid load prediction result is fully guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0079] Figure 1 It is a schematic diagram of the process of the present invention;

[0080] Figure 2 It is a flow chart of obtaining the second power grid load forecast result by using the type 2 fuzzy inference mechanism in the present invention. DETAILED DESCRIPTION

[0081] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0082] A power grid load forecasting method, such as Figure 1 As shown in S1, the power grid load forecasting problem is decomposed into different levels, and a judgment matrix is ​​constructed. The preliminary weights of each factor are calculated based on the judgment matrix, including:

[0083] S11. Decomposing the power grid load forecasting problem into a target layer, a criterion layer, and an indicator layer, wherein the target layer is the power grid load forecasting result, the criterion layer is the main factors affecting the power grid load, and the indicator layer is the historical data of each factor;

[0084] S12, compare each factor in the criterion layer pairwise and construct a judgment matrix;

[0085] S13, calculating the eigenvectors of the judgment matrix and normalizing the eigenvectors to obtain preliminary weights of each factor;

[0086] Among them, the elements in the judgment matrix represent the relative importance of each factor.

[0087] Specifically, in S13, the eigenvector of the judgment matrix is ​​calculated and normalized to obtain the preliminary weight of each factor, including:

[0088] S131, normalizing each column of the judgment matrix, and adding the normalized judgment matrix row by row to obtain an eigenvector of the judgment matrix;

[0089] S132. Divide each element in the eigenvector by the sum of all elements to obtain a normalized eigenvector;

[0090] Among them, the elements in the normalized eigenvector represent the preliminary weights of each factor.

[0091] S2. Calculate the coefficient of variation of each factor and use the coefficient of variation to adjust the initial weight of each factor to obtain the weight coefficient of each factor, including:

[0092] S21. For each factor, obtain the corresponding historical data in the indicator layer and calculate the mean and standard deviation of the data;

[0093] S22. Divide the standard deviation by the mean to calculate the coefficient of variation, which measures the relative dispersion of the data for each factor;

[0094] S23, adding the coefficient of variation of each factor to the sum of all coefficients of variation to obtain the coefficient of variation weight of each factor based on the degree of data variation;

[0095] S24, performing weighted summation on the coefficient of variation weight and the preliminary weight of each factor to obtain the fusion weight of each factor;

[0096] S25. Normalize the fusion weights of each factor to obtain the weight coefficient of each factor.

[0097] The above technical solution decomposes the power grid load forecasting problem into different levels and constructs a judgment matrix. Based on the judgment matrix, the preliminary weights reflecting the relative importance of each factor are calculated, and then the coefficient of variation of each factor is calculated. The preliminary weights of each factor are adjusted using the coefficient of variation, so that the relative importance of each factor can be corrected using the coefficient of variation reflecting the degree of discreteness of the data of each factor, so that the obtained weight coefficients of each factor can better reflect the relative importance of each factor.

[0098] like Figure 1 As shown, S3, constructing a grey correlation matrix of each factor based on the historical data of the power grid load, and calculating the correlation between each factor and the power grid load based on the grey correlation matrix of each factor, specifically including:

[0099] S31. For each factor, obtain the corresponding historical data in the indicator layer and perform feature extraction to obtain historical data features;

[0100] S32, performing intrinsic correlation processing on the historical data characteristics of each factor to obtain the grey correlation matrix of each factor;

[0101] S33, calculating the correlation between each factor and the grid load based on the grey correlation matrix of each factor;

[0102] Among them, the greater the correlation, the greater the impact of the factor on the grid load.

[0103] S4. Construct a fuzzy relationship matrix of each factor based on its weight coefficient and correlation. A power forecast matrix is ​​obtained based on the fuzzy relationship matrix of each factor, specifically including:

[0104] S41. Combining the weight coefficient and correlation degree of each factor, constructing a correlation matrix between each factor and the grid load;

[0105] S42, fuzzifying the correlation matrix of each factor to obtain a fuzzy correlation matrix of each factor;

[0106] S43, using a multiple linear regression algorithm to perform multiple linear regression on the fuzzy correlation matrix of each factor to obtain a prediction matrix of each factor;

[0107] S44. Use a quadratic function fitting algorithm to perform matrix fitting on the prediction matrix of each factor to obtain an electricity prediction matrix.

[0108] S5. Inputting the power prediction matrix into the pre-trained power grid load prediction model to obtain a first power grid load prediction result, specifically including:

[0109] S51. Selecting an appropriate grey prediction model as a power grid load prediction model according to the power prediction matrix;

[0110] S52, screening and constructing a historical data set from the historical power grid load data, and dividing the historical data set into a training set, a validation set, and a test set according to a preset ratio;

[0111] S53, setting a loss function and an optimizer of a power grid load forecasting model;

[0112] S54, inputting the training set into the power grid load forecasting model for model training;

[0113] S55, calculating the loss value based on the loss function, and the optimizer updating the model parameters according to the loss value and the network gradient information;

[0114] S56. If the loss value is less than the preset threshold, the model training ends and the current power grid load forecasting model is the trained power grid load forecasting model. Otherwise, the process returns to S54 and continues to use the training set for model training.

[0115] S57. Input the validation set into the trained power grid load forecasting model, evaluate the generalization ability of the model by observing its performance on the validation set, and tune the model's hyperparameters and structure;

[0116] S58, inputting the test set into the tuned power grid load forecasting model, performing model performance evaluation, and obtaining a pre-trained power grid load forecasting model;

[0117] S59: Input the power prediction matrix into a pre-trained power grid load prediction model to obtain a first power grid load prediction result.

[0118] The above technical solution constructs a grey correlation matrix of each factor based on the historical data of the power grid load, calculates the correlation degree reflecting the influence of each factor on the power grid load based on the grey correlation matrix of each factor, that is, the absolute importance of each factor, and constructs a fuzzy relationship matrix of each factor by combining the weight coefficient of each factor (reflecting the relative importance between each factor) and the correlation degree (reflecting the absolute importance of each factor), ensuring that the factors involved in the fuzzy relationship matrix are all elements that have a substantial impact on the load forecast, thereby making the power forecast matrix obtained based on the fuzzy relationship matrix of each factor more accurate. By inputting the power forecast matrix into the pre-trained power grid load forecast model, a first power grid load forecast result with higher accuracy can be obtained.

[0119] like Figure 1 and Figure 2 As shown in S6, define the type 2 fuzzy set of input variables and output variables based on the historical data of power grid load, set the membership function for the type 2 fuzzy set, and formulate fuzzy rules, including:

[0120] S61. Based on the historical data of power grid load and domain knowledge, the main factors affecting the power grid load are screened as input variables, the power grid load is regarded as the output variable, and type 2 fuzzy sets of the input variables and the output variables are defined;

[0121] S62, setting an appropriate membership function for each type 2 fuzzy set to determine the degree to which the variable belongs to each type 2 fuzzy set;

[0122] S63. Based on the historical data of power grid load and domain knowledge, a series of fuzzy rules are formulated to describe the fuzzy relationship between input variables and output variables;

[0123] Among them, fuzzy rules are formulated in the form of "if-then".

[0124] Specifically, in S62, a suitable membership function is set for each type 2 fuzzy set to determine the degree to which the variable belongs to each type 2 fuzzy set, including:

[0125] S621. Determine the range of input variables and output variables based on historical grid load data and domain knowledge;

[0126] S622. According to the variable characteristics and prediction requirements, set an appropriate membership function for each type 2 fuzzy set;

[0127] S623. Determine the parameters of each membership function based on historical grid load data and domain knowledge, and adjust the shape and parameters of each membership function by taking into account the fuzziness of the variables.

[0128] Among them, the membership functions of type 2 fuzzy sets include:

[0129] 1) Linear membership function:

[0130] ;

[0131] in, f ( x ) is a variable x The membership degree of a’ 、 b’ is a constant;

[0132] 2) Triangle membership function:

[0133] ;

[0134] in, f ( x ) is a variable x The membership degree of a 、 b 、 c are the three vertices of the triangle;

[0135] 3) Gaussian membership function:

[0136] ;

[0137] in, f ( x ) is a variable x The membership degree of is the mean, is the standard deviation.

[0138] S7. Fuzzify each factor based on the membership function, combine the fuzzified factors and fuzzy rules, and use the type 2 fuzzy reasoning mechanism to perform fuzzy reasoning to obtain the type 2 fuzzy set corresponding to the power grid load, which specifically includes:

[0139] S71. Calculate the membership degree of a factor to each type-2 fuzzy set based on the membership function, and take the type-2 fuzzy set with the largest membership degree as the type-2 fuzzy set corresponding to the factor;

[0140] S72, repeat S71 until the type 2 fuzzy sets corresponding to all factors are obtained, and the fuzzification of each factor is completed;

[0141] S73. Combining the type-2 fuzzy sets and fuzzy rules corresponding to all factors, using the type-2 fuzzy reasoning mechanism to perform fuzzy reasoning, obtain the type-2 fuzzy set corresponding to the power grid load to describe the power grid load forecast.

[0142] S8. Defuzzify the type 2 fuzzy set corresponding to the power grid load to obtain a second power grid load prediction result.

[0143] S9. Comprehensively analyze the first power grid load forecast result and the second power grid load forecast result to obtain a final power grid load forecast result.

[0144] The above technical solution defines type 2 fuzzy sets of input variables and output variables based on historical data of power grid load, sets a membership function for the type 2 fuzzy set, and formulates fuzzy rules. Based on the membership function, each factor is fuzzified. Combining the fuzzified factors and fuzzy rules, fuzzy reasoning is performed using a type 2 fuzzy reasoning mechanism to obtain a type 2 fuzzy set corresponding to the power grid load, and defuzzification is performed on the type 2 fuzzy set corresponding to the power grid load. Through the adjustable membership function, it can better handle the power grid load influencing factors with ambiguity and uncertainty. At the same time, it is suitable for power systems with serious nonlinearity and random interference. Fuzzy rules and fuzzy reasoning can be used to capture the nonlinear characteristics of power grid load changes, thereby realizing accurate prediction of the power grid load and obtaining a second power grid load prediction result. By comprehensively analyzing the first power grid load prediction result and the second power grid load prediction result, the prediction accuracy of the final power grid load prediction result is fully guaranteed.

[0145] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for predicting power grid load, characterized by: The following steps are involved: S1. Decompose the grid load forecasting problem into different levels and construct a judgment matrix. Based on the judgment matrix, calculate the preliminary weights of each factor, including: S11. Decomposing the power grid load forecasting problem into a target layer, a criterion layer, and an indicator layer, wherein the target layer is the power grid load forecasting result, the criterion layer is the main factors affecting the power grid load, and the indicator layer is the historical data of each factor; S12, compare each factor in the criterion layer pairwise and construct a judgment matrix; S13, calculating the eigenvectors of the judgment matrix and normalizing the eigenvectors to obtain preliminary weights of each factor; Among them, the elements in the judgment matrix represent the relative importance of each factor; S2. Calculate the coefficient of variation of each factor, and use the coefficient of variation to adjust the initial weight of each factor to obtain the weight coefficient of each factor; S3. Construct a grey correlation matrix of each factor based on the historical data of the power grid load, and calculate the correlation between each factor and the power grid load based on the grey correlation matrix of each factor, including: S31. For each factor, obtain the corresponding historical data in the indicator layer and perform feature extraction to obtain historical data features; S32, performing intrinsic correlation processing on the historical data characteristics of each factor to obtain the grey correlation matrix of each factor; S33, calculating the correlation between each factor and the grid load based on the grey correlation matrix of each factor; Among them, the greater the correlation, the greater the impact of the factor on the grid load; S4. Construct a fuzzy relationship matrix of each factor based on its weight coefficient and correlation. A power forecast matrix is ​​obtained based on the fuzzy relationship matrix of each factor, including: S41. Combining the weight coefficient and correlation degree of each factor, constructing a correlation matrix between each factor and the grid load; S42, fuzzifying the correlation matrix of each factor to obtain a fuzzy correlation matrix of each factor; S43, using a multiple linear regression algorithm to perform multiple linear regression on the fuzzy correlation matrix of each factor to obtain a prediction matrix of each factor; S44, using a quadratic function fitting algorithm to perform matrix fitting on the prediction matrix of each factor to obtain an electricity prediction matrix; S5. Inputting the power prediction matrix into a pre-trained power grid load prediction model to obtain a first power grid load prediction result; S6. Define type 2 fuzzy sets of input variables and output variables based on historical grid load data, set membership functions for type 2 fuzzy sets, and formulate fuzzy rules, including: S61. Based on the historical data of power grid load and domain knowledge, the main factors affecting the power grid load are screened as input variables, the power grid load is regarded as the output variable, and type 2 fuzzy sets of the input variables and the output variables are defined; S62, setting an appropriate membership function for each type 2 fuzzy set to determine the degree to which the variable belongs to each type 2 fuzzy set; S63. Based on the historical data of power grid load and domain knowledge, a series of fuzzy rules are formulated to describe the fuzzy relationship between input variables and output variables; Among them, fuzzy rules are formulated in the form of "if-then"; S7. Fuzzify each factor based on the membership function, combine the fuzzified factors and fuzzy rules, and use the type 2 fuzzy reasoning mechanism to perform fuzzy reasoning to obtain the type 2 fuzzy set corresponding to the power grid load, including: S71. Calculate the membership degree of a factor to each type-2 fuzzy set based on the membership function, and take the type-2 fuzzy set with the largest membership degree as the type-2 fuzzy set corresponding to the factor; S72, repeat S71 until the type 2 fuzzy sets corresponding to all factors are obtained, and the fuzzification of each factor is completed; S73. Combining the type-2 fuzzy sets and fuzzy rules corresponding to all factors, performing fuzzy reasoning using a type-2 fuzzy reasoning mechanism, and obtaining a type-2 fuzzy set corresponding to the power grid load to describe the power grid load forecast; S8. Defuzzify the type 2 fuzzy set corresponding to the power grid load to obtain a second power grid load forecast result; S9. Comprehensively analyze the first power grid load forecast result and the second power grid load forecast result to obtain a final power grid load forecast result.

2. The power grid load forecasting method according to claim 1, wherein: In S13, the eigenvector of the judgment matrix is ​​calculated and normalized to obtain the preliminary weight of each factor, including: S131, normalizing each column of the judgment matrix, and adding the normalized judgment matrix row by row to obtain an eigenvector of the judgment matrix; S132. Divide each element in the eigenvector by the sum of all elements to obtain a normalized eigenvector; Among them, the elements in the normalized eigenvector represent the preliminary weights of each factor.

3. The power grid load forecasting method according to claim 1, wherein: In S2, the coefficient of variation of each factor is calculated, and the initial weight of each factor is adjusted using the coefficient of variation to obtain the weight coefficient of each factor, including: S21. For each factor, obtain the corresponding historical data in the indicator layer and calculate the mean and standard deviation of the data; S22. Divide the standard deviation by the mean to calculate the coefficient of variation, which measures the relative dispersion of the data for each factor; S23. The coefficient of variation of each factor is added to the sum of all coefficients of variation to obtain the coefficient of variation weight of each factor based on the degree of data variation; S24, performing weighted summation on the coefficient of variation weight and the preliminary weight of each factor to obtain the fusion weight of each factor; S25. Normalize the fusion weights of each factor to obtain the weight coefficient of each factor.

4. The power grid load forecasting method according to claim 1, wherein: In S5, the power prediction matrix is ​​input into the pre-trained power grid load prediction model to obtain a first power grid load prediction result, including: S51. Selecting an appropriate grey prediction model as a power grid load prediction model according to the power prediction matrix; S52, screening and constructing a historical data set from the historical power grid load data, and dividing the historical data set into a training set, a validation set, and a test set according to a preset ratio; S53, setting a loss function and an optimizer of a power grid load forecasting model; S54, inputting the training set into the power grid load forecasting model for model training; S55, calculating the loss value based on the loss function, and the optimizer updating the model parameters according to the loss value and the network gradient information; S56. If the loss value is less than the preset threshold, the model training ends and the current power grid load forecasting model is the trained power grid load forecasting model. Otherwise, the process returns to S54 and continues to use the training set for model training. S57. Input the validation set into the trained power grid load forecasting model, evaluate the generalization ability of the model by observing its performance on the validation set, and tune the model's hyperparameters and structure; S58, inputting the test set into the tuned power grid load forecasting model, performing model performance evaluation, and obtaining a pre-trained power grid load forecasting model; S59: Input the power prediction matrix into a pre-trained power grid load prediction model to obtain a first power grid load prediction result.

5. The power grid load forecasting method according to claim 1, wherein: In S62, appropriate membership functions are set for each type 2 fuzzy set to determine the degree to which the variable belongs to each type 2 fuzzy set, including: S621. Determine the range of input variables and output variables based on historical grid load data and domain knowledge; S622. According to the variable characteristics and prediction requirements, set an appropriate membership function for each type 2 fuzzy set; S623. Determine the parameters of each membership function based on historical grid load data and domain knowledge, and adjust the shape and parameters of each membership function by taking into account the fuzziness of the variables. Among them, the membership functions of type 2 fuzzy sets include: 1) Linear membership function: f ( x )= a'x + b’ ； in, f ( x ) is a variable x The membership degree of a’ 、 b’ is a constant; 2) Triangle membership function: ； in, f ( x ) is a variable x The membership degree of a 、 b 、 c are the three vertices of the triangle; 3) Gaussian membership function: ； in, f ( x ) is a variable x The membership degree of is the mean, is the standard deviation.

Images