AC / DC hybrid power distribution network voltage prediction method considering VSC control strategy

Abstract

The invention relates to an AC / DC hybrid power distribution network voltage prediction method considering a VSC control strategy, and belongs to the technical field of power distribution networks. The method comprises the following steps: S1, acquiring operation data of the AC / DC hybrid power distribution network, including node voltage, node active power, node reactive power, time characteristics, weather characteristics, VSC control strategies and the like, and processing VSC nodes; s2, performing correlation analysis on the operation data of the power distribution network and the to-be-predicted node voltage, selecting data having strong correlation with the to-be-predicted node voltage as prediction model input sample data, and dividing the sample data into a training set and a test set according to a proportion; and S3, establishing a voltage prediction model considering the VSC control strategy, training the AC side and the DC side of the hybrid power distribution network by using the training set data, and verifying the prediction effect by using the test set data.

Description

Technical Field

[0001] The present invention belongs to the technical field of distribution networks and relates to a voltage prediction method for an AC / DC hybrid distribution network considering a VSC control strategy. Background Art

[0002] In recent years, the proportion of DC power sources and loads such as photovoltaics and electric vehicle charging piles in the distribution network has gradually increased. The DC distribution network is connected to the AC distribution network through a voltage source converter (VSC) to form an AC / DC hybrid distribution network, which has become a trend of future development. However, the access to the DC distribution network is likely to cause changes in the distribution of the distribution network flow, thereby causing problems such as high voltage over-limit and low voltage over-limit, affecting voltage stability. Therefore, by predicting the voltage of the distribution network node, the impending voltage over-limit situation can be identified in advance, so that the distribution network voltage can be managed in time. At present, the distribution network voltage prediction methods include BP neural network and LSTM methods. However, when processing time series data, BP neural network lacks the ability to model the internal dependencies of the data, and although LSTM can handle long-term dependencies in the data, it is relatively weak in feature extraction.

[0003] To this end, the present invention proposes a voltage prediction model based on the combination of CNN and LSTM, which can simultaneously capture the spatial and temporal characteristics of the data, thereby improving the accuracy of the voltage prediction model. VSC has a strong voltage regulation capability and can stabilize or change the voltage level in the power grid by adjusting the output voltage, reactive power and active power. Since the control strategy of VSC directly affects its output behavior, different control strategies will lead to different voltage regulation effects. Therefore, when performing voltage prediction, if the control strategy of VSC is not considered, the prediction result may not be consistent with the actual situation.

[0004] To solve this problem, the present invention proposes a voltage prediction method for an AC / DC hybrid distribution network considering a VSC control strategy. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a voltage prediction method for an AC / DC hybrid distribution network considering a VSC control strategy. First, the power flow operation data of the AC / DC hybrid distribution network is obtained, and then a neural network model is established on the AC side and the DC side according to the distribution network operation data, and the node voltage is predicted.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] The voltage prediction method of AC / DC hybrid distribution network considering VSC control strategy includes the following steps:

[0008] S1: Acquire the operation data of the AC / DC hybrid distribution network including node voltage, node active power, node reactive power, time characteristics, weather characteristics and voltage source converter (VSC) control strategy data, and process the VSC nodes;

[0009] S2: Perform correlation analysis on the distribution network operation data and the node voltage to be predicted, select data with strong correlation with the node voltage to be predicted as the prediction model input sample data, and divide the sample data into training set and test set according to proportion;

[0010] S3: A voltage prediction model considering the VSC control strategy is established, and the training set data is used for training on the AC side and DC side of the hybrid distribution network respectively, and the prediction effect is verified using the test set data.

[0011] Furthermore, in S1, weather characteristics include temperature, humidity, human comfort and weather phenomena.

[0012] Furthermore, in S1, the control strategy of the VSC is represented by numbers:

[0013] ① Indicates constant DC voltage and constant AC reactive power;

[0014] ②Indicates constant DC voltage and constant AC voltage;

[0015] ③Indicates constant AC active power and constant AC reactive power;

[0016] ④Indicates constant AC active power and constant AC voltage;

[0017] ⑤ Indicates VP droop control and constant AC reactive power;

[0018] ⑥ indicates VP droop control and constant AC voltage;

[0019] ⑦ Indicates VI droop control and constant AC reactive power;

[0020] ⑧ represents VI droop control and constant AC voltage.

[0021] Furthermore, in S1, the VSC node is processed, including:

[0022] Predict the AC side node voltage:

[0023] When the VSC control strategy is ①, ③, ⑤ or ⑦, the VSC node voltage is used as the model input feature;

[0024] When the VSC control strategy is ②, ④, ⑥ or ⑧, the VSC node reactive power is used as the model input feature;

[0025] Predict the DC side node voltage:

[0026] When the control strategy is ①, ②, ⑤, ⑦, ⑥ or ⑧, the VSC node active power is used as the model input feature;

[0027] When the control strategy is ③ or ④, the VSC node voltage is used as the model input feature.

[0028] Furthermore, in S2, a correlation analysis is performed on the distribution network operation data and the node voltage, specifically including:

[0029] (1) Determine the reference sequence

[0030] The reference sequence is fixed sequence data, that is, the voltage data of the node to be measured, which is used to calculate the correlation with other data. The reference sequence X0 is expressed as:

[0031] X0=(x0(1),x0(2),x0(3),…,x0(n))

[0032] In the formula, n represents the number of samples in the sequence, and 0 represents a fixed sequence;

[0033] (2) Determine the comparison sequence

[0034] When there are m types of comparison sequences, each of which has n samples, then the comparison sequence X i If expressed as:

[0035]

[0036] (3) Data normalization

[0037] The original data is normalized using the mean method, and the formula is:

[0038]

[0039] In the formula, k is the kth sample data in type i;

[0040] (4) Calculation of grey correlation coefficient

[0041] Calculate the grey correlation coefficient of the normalized data:

[0042]

[0043] In the formula, k is the kth sample data in type i, δ represents the resolution coefficient, and its value range is (0, 1). The smaller its value is, the higher the recognition is, and it is 0.5;

[0044] (5) Calculation of grey relational degree

[0045] Grey relational degree r iIndicates the overall relevance of the reference sequence to the comparison sequence:

[0046]

[0047] (6) Grey relational degree absolute value sorting:

[0048] Sort the absolute values ​​of grey relational degree from large to small:

[0049] r rank =rank(|r1|,|r2|,…,|r m |)

[0050] In the formula, |r m | represents the absolute value of the gray correlation between the voltage of the tested area and other data, rank() represents the ordering of the absolute values ​​of the gray correlation from large to small, r rank Indicates the sorting result.

[0051] Furthermore, in S3, a voltage prediction model considering the VSC control strategy is established, which specifically includes:

[0052] S31: Acquire AC / DC hybrid distribution network operation data, including node voltage data, node active power data, node reactive power data, VSC control strategy, and weather characteristics data;

[0053] S32: preprocessing the acquired data, including outlier removal, missing value filling and data normalization;

[0054] S33: Calculate the grey correlation between the preprocessed node voltage data to be measured and other node data within a certain distance from the node, and sort the absolute values ​​of the grey correlation from large to small; wherein the other node data include node voltage, node active power and node reactive power; and sort the absolute values ​​of the grey correlation from large to small;

[0055] S34: According to the grey correlation absolute value sorting result, the variables with the largest absolute values ​​are selected as the input features of the prediction model, the value of k is defined by the user, and the voltage of the node to be measured is used as the output of the model;

[0056] S35: Divide the preprocessed data into training sets and test sets in proportion, then build a voltage prediction model based on the combination of CNN and LSTM, and train it on the AC and DC sides of the hybrid distribution network based on the training set, and use the test set to verify the model effect.

[0057] Further, in S35, a voltage prediction model based on the combination of CNN and LSTM is constructed, wherein the model structure includes 2 convolutional layers, 2 pooling layers, 1 LSTM layer and an activation layer;

[0058] The activation layer uses the ReLu function, expressed as:

[0059] f(a)=max(a,0)

[0060] In the formula, a represents the input of the activation function, f(a) represents the output of the activation function, and max(a,0) means that the activation function takes the maximum value between the input a and 0 as the output.

[0061] Furthermore, in S35, the model effect is verified, including:

[0062] (1) Calculate the mean absolute error (MAE) of the voltage prediction model

[0063]

[0064] In the formula, n is the total number of samples, y is i is the true value, is the model prediction value;

[0065] (2) Calculate the root mean square error (RMSE) of the prediction model

[0066]

[0067] In the formula, n is the total number of samples, y is i is the true value, is the model's predicted value.

[0068] The beneficial effects of the present invention are:

[0069] (1) The present invention proposes a voltage prediction model based on CNN+LSTM for predicting the voltage of the distribution network. Compared with the traditional BP and LSTM neural networks, the voltage prediction model can simultaneously extract the spatial and temporal characteristics of the data, thereby improving the prediction accuracy of the voltage prediction model.

[0070] (2) The present invention processes the VSC nodes, selects the node data to be tested (including active power and reactive power), other nodes close to the node to be predicted and the VSC node data (including voltage, active power and reactive power), weather characteristic data and time characteristic data as input variables of the voltage prediction model, and predicts the voltage, thereby enriching the model input characteristics and improving the generalization of the voltage prediction model.

[0071] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0073] Figure 1 is a flow chart of the present invention;

[0074] Figure 2 It is a schematic diagram of the topological structure of AC / DC hybrid distribution network;

[0075] Figure 3 It is the power flow operation data of nodes in AC / DC hybrid distribution network;

[0076] Figure 4 It is the voltage prediction model process;

[0077] Figure 5 This is the AC node voltage prediction result diagram;

[0078] Figure 6 This is the DC node voltage prediction result diagram. DETAILED DESCRIPTION

[0079] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0080] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0081] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0082] like Figure 1 As shown, a voltage prediction method for an AC / DC hybrid distribution network considering a VSC control strategy comprises the following steps:

[0083] S1: Acquire the operation data of the AC / DC hybrid distribution network including node voltage, node active power, node reactive power, time characteristics, weather characteristics, VSC control strategy and other data, and process the VSC nodes.

[0084] It should be noted that, in S1, weather characteristics include temperature, humidity, human comfort, weather phenomena, etc.

[0085] It should be noted that in S1, the control strategy of the VSC is represented by numbers: ① constant DC voltage and constant AC reactive power, ② constant DC voltage and constant AC voltage, ③ constant AC active power and constant AC reactive power, ④ constant AC active power and constant AC voltage, ⑤ V-P droop control and constant AC reactive power, ⑥ V-P droop control and constant AC voltage, ⑦ V-I droop control and constant AC reactive power, ⑧ V-I droop control and constant AC voltage.

[0086] It should be noted that, in S1, the processing of the VSC node includes:

[0087] The AC side node voltage is predicted. When the VSC control strategy is ①, ③, ⑤, and ⑦, the VSC node voltage is used as the model input feature. When the VSC control strategy is ②, ④, ⑥, and ⑧, the VSC node reactive power is used as the model input feature. The DC side node voltage is predicted. When the control strategy is ①, ②, ⑤, ⑦, ⑥, and ⑧, the VSC node active power is used as the model input feature. When the control strategy is ③ and ④, the VSC node voltage is used as the model input feature.

[0088] This embodiment uses the measured operation data of a distribution network for analysis. The data sampling time is from June 1, 2021 to June 30, 2022, the data sampling interval is 1 hour, and there are 9480 data in total. The schematic diagram of the AC / DC hybrid distribution network topology is as follows: Figure 2 As shown in the figure, the AC distribution network is connected to the DC distribution network through the VSC. When the VSC control strategy is changed, the flow operation data of the nodes in the AC / DC hybrid distribution network are as follows: Figure 3 shown.

[0089] S2: Perform correlation analysis on the distribution network operation data and the node voltage to be predicted, select data with strong correlation with the node voltage to be predicted as the prediction model input sample data, and divide the sample data into training set and test set in proportion.

[0090] It should be noted that the specific steps for performing correlation analysis on distribution network operation data and node voltage include:

[0091] (1) Determine the reference sequence

[0092] The reference sequence is fixed sequence data, that is, the voltage data of the node to be measured, which is used to calculate the correlation with other data. The reference sequence X0 is expressed as:

[0093] X0=(x0(1),x0(2),x0(3),…,x0(n))

[0094] In the formula, n represents the number of samples in the sequence, and 0 represents a fixed sequence.

[0095] (2) Determine the comparison sequence

[0096] When there are m types of comparison sequences, each of which has n samples, then the comparison sequence X i If expressed as:

[0097]

[0098] (3) Data normalization

[0099] The original data is normalized using the mean method, and the formula is:

[0100]

[0101] Where k is the kth sample data in type i.

[0102] (4) Calculation of grey correlation coefficient

[0103] Calculate the grey correlation coefficient of the normalized data:

[0104]

[0105] Where k is the kth sample data in type i, δ represents the resolution coefficient, and its value range is (0, 1). The smaller its value is, the higher the recognition is, and it is 0.5.

[0106] (5) Calculation of grey relational degree

[0107] Grey relational degree r i Indicates the overall relevance of the reference sequence to the comparison sequence:

[0108]

[0109] (6) Grey relational degree absolute value sorting:

[0110] Sort the absolute values ​​of grey relational degree from large to small:

[0111] r rank =rank(|r1|,|r2|,…,|r m |)

[0112] In the formula, |r m | represents the absolute value of the gray correlation between the voltage of the tested area and other data, rank() represents the ordering of the absolute values ​​of the gray correlation from large to small, r rank Indicates the sorting result.

[0113] This example takes a node to be predicted on the AC side and DC side of the hybrid distribution network as an example, and performs grey correlation calculation on the voltage data of other nodes and the node to be predicted. The results of the absolute value of the grey correlation are shown in Table 1.

[0114] Table 1

[0115] Communication node variables Grey relational degree DC node variables Grey relational degree Adjacent node 1 voltage 0.940271 Adjacent node 2 voltage 0.996213 Adjacent node 3 voltage 0.938829 Adjacent node 1 voltage 0.996154 Adjacent node 2 voltage 0.936875 Adjacent node 3 voltage 0.995913 Temperature and humidity index 0.93274 Active power of neighboring node 1 0.991387 Adjacent node 4 voltage 0.899329 Adjacent node 4 voltage 0.990397 Active power of the node to be tested 0.894652 Adjacent node 5 voltage 0.980522 Active power of neighboring node 3 0.864952 Active power of the node to be tested 0.979963 … … … …

[0116] S3: A voltage prediction model considering the VSC control strategy is established, and the training set data is used for training on the AC side and DC side of the hybrid distribution network respectively, and the prediction effect is verified using the test set data.

[0117] It should be noted that in S3, a voltage prediction model considering the VSC control strategy is established, and the steps include:

[0118] S31: Acquire AC / DC hybrid distribution network operation data, including node voltage data, node active power data, node reactive power data, VSC control strategy, weather characteristics and other data;

[0119] S32: preprocessing the acquired data, including outlier removal, missing value filling and data normalization;

[0120] S33: Calculate the grey correlation between the pre-processed node voltage data to be measured and other node data (node ​​voltage, node active power and node reactive power) close to the node, and sort the absolute values ​​of the grey correlation from large to small;

[0121] S34: According to the grey correlation absolute value sorting result, the variables with the largest absolute values ​​are selected as the input features of the prediction model, the value of k is defined by the user, and the voltage of the node to be measured is used as the output of the model;

[0122] S35: Divide the preprocessed data into training sets and test sets in proportion, then build a voltage prediction model based on the combination of CNN and LSTM, and train it on the AC and DC sides of the hybrid distribution network based on the training set, and use the test set to verify the model effect.

[0123] It should be noted that, in S35, a voltage prediction model based on the combination of CNN and LSTM is constructed, wherein the model structure includes 2 convolutional layers, 2 pooling layers, 1 LSTM layer and an activation layer.

[0124] The activation layer uses the ReLu function, expressed as:

[0125] f(a)=max(a,0)

[0126] In the formula, a represents the input of the activation function, f(a) represents the output of the activation function, and max(a,0) means that the activation function takes the maximum value between the input a and 0 as the output.

[0127] It should be noted that, in S35, the verification of the model effect includes:

[0128] (1) Calculate the mean absolute error (MAE) of the voltage prediction model

[0129]

[0130] In the formula, n is the total number of samples, y is i is the true value, is the model's predicted value.

[0131] (2) Calculate the root mean square error (RMSE) of the prediction model

[0132]

[0133] In the formula, n is the total number of samples, y is i is the true value, is the model's predicted value.

[0134] This embodiment takes a node to be predicted on the AC side and DC side of a hybrid distribution network as an example to predict voltage. First, a neural network prediction model based on CNN+LSTM is constructed, and then the voltage of the node to be predicted is predicted using the AC side data and the DC side data respectively. The network structure diagram is shown in the figure below. Figure 4 As shown in the figure, the voltage prediction results of the nodes to be predicted on the AC side and the DC side are respectively as follows: Figure 5 , Figure 6 As shown in Table 2, the prediction model evaluation indicators are shown in Table 2.

[0135] Table 2

[0136] Dataset MAE RMSE Communication side training set 0.89 1.03 AC side test set 0.91 1.25 DC side training set 0.87 1.12 DC side test set 0.89 1.23

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A voltage prediction method for an AC / DC hybrid distribution network considering a VSC control strategy, characterized by: The method comprises the following steps: S1: Acquire the operation data of the AC / DC hybrid distribution network including node voltage, node active power, node reactive power, time characteristics, weather characteristics and voltage source converter (VSC) control strategy data, and process the VSC nodes; S2: Perform correlation analysis on the distribution network operation data and the node voltage to be predicted, select data with strong correlation with the node voltage to be predicted as the prediction model input sample data, and divide the sample data into training set and test set according to proportion; S3: A voltage prediction model considering the VSC control strategy is established, and the training set data is used for training on the AC side and DC side of the hybrid distribution network respectively, and the prediction effect is verified using the test set data.

2. The method for predicting voltage in an AC / DC hybrid distribution network considering a VSC control strategy according to claim 1 is characterized in that: In S1, weather characteristics include temperature, humidity, human comfort and weather phenomena.

3. The method for predicting voltage in an AC / DC hybrid distribution network considering a VSC control strategy according to claim 1 is characterized in that: In S1, the control strategy of VSC is represented by numbers: ① Indicates constant DC voltage and constant AC reactive power; ②Indicates constant DC voltage and constant AC voltage; ③Indicates constant AC active power and constant AC reactive power; ④Indicates constant AC active power and constant AC voltage; ⑤ Indicates VP droop control and constant AC reactive power; ⑥ indicates VP droop control and constant AC voltage; ⑦ Indicates VI droop control and constant AC reactive power; ⑧ represents VI droop control and constant AC voltage.

4. The method for predicting voltage in an AC / DC hybrid distribution network considering a VSC control strategy according to claim 3 is characterized in that: In S1, the VSC node is processed, including: Predict the AC side node voltage: When the VSC control strategy is ①, ③, ⑤ or ⑦, the VSC node voltage is used as the model input feature; When the VSC control strategy is ②, ④, ⑥ or ⑧, the VSC node reactive power is used as the model input feature; Predict the DC side node voltage: When the control strategy is ①, ②, ⑤, ⑦, ⑥ or ⑧, the VSC node active power is used as the model input feature; When the control strategy is ③ or ④, the VSC node voltage is used as the model input feature.

5. The method for predicting voltage in an AC / DC hybrid distribution network considering a VSC control strategy according to claim 4 is characterized in that: In S2, correlation analysis is performed on the distribution network operation data and the node voltage, specifically including: (1) Determine the reference sequence The reference sequence is fixed sequence data, that is, the voltage data of the node to be measured, which is used to calculate the correlation with other data. The reference sequence X0 is expressed as: X0=(x0(1),x0(2),x0(3),…,x0(n)) In the formula, n represents the number of samples in the sequence, and 0 represents a fixed sequence; (2) Determine the comparison sequence When there are m types of comparison sequences, each of which has n samples, then the comparison sequence X i If expressed as: (3) Data normalization The original data is normalized using the mean method, and the formula is: In the formula, k is the kth sample data in type i; (4) Calculation of grey correlation coefficient Calculate the grey correlation coefficient of the normalized data: In the formula, k is the kth sample data in type i, δ represents the resolution coefficient, and its value range is (0, 1). The smaller its value is, the higher the recognition is, and it is 0.5; (5) Calculation of grey relational degree Grey relational degree r i Indicates the overall relevance of the reference sequence to the comparison sequence: (6) Grey relational degree absolute value sorting: Sort the absolute values ​​of grey relational degree from large to small: r rank =rank(|r1|,|r2|,…,|r m |) In the formula, |r m | represents the absolute value of the gray correlation between the voltage of the tested area and other data, rank() represents the ordering of the absolute values ​​of the gray correlation from large to small, r rank Indicates the sorting result.

6. The method for predicting voltage in an AC / DC hybrid distribution network considering a VSC control strategy according to claim 5 is characterized in that: In S3, a voltage prediction model considering the VSC control strategy is established, which specifically includes: S31: Acquire AC / DC hybrid distribution network operation data, including node voltage data, node active power data, node reactive power data, VSC control strategy, and weather characteristics data; S32: preprocessing the acquired data, including outlier removal, missing value filling and data normalization; S33: Calculate the grey correlation between the preprocessed node voltage data to be measured and other node data within a certain distance from the node, and sort the absolute values ​​of the grey correlation from large to small; wherein the other node data include node voltage, node active power and node reactive power; and sort the absolute values ​​of the grey correlation from large to small; S34: According to the grey correlation absolute value sorting result, the variables with the largest absolute values ​​are selected as the input features of the prediction model, the value of k is defined by the user, and the voltage of the node to be measured is used as the output of the model; S35: Divide the preprocessed data into training sets and test sets in proportion, then build a voltage prediction model based on the combination of CNN and LSTM, and train it on the AC and DC sides of the hybrid distribution network based on the training set, and use the test set to verify the model effect.

7. The method for predicting voltage in an AC / DC hybrid distribution network considering a VSC control strategy according to claim 6 is characterized in that: In the S35, a voltage prediction model based on the combination of CNN and LSTM is constructed, wherein the model structure includes 2 convolutional layers, 2 pooling layers, 1 LSTM layer and an activation layer; The activation layer uses the ReLu function, expressed as: f(a)=max(a,0) In the formula, a represents the input of the activation function, f(a) represents the output of the activation function, and max(a,0) means that the activation function takes the maximum value between the input a and 0 as the output.

8. The method for predicting voltage in an AC / DC hybrid distribution network considering a VSC control strategy according to claim 6 is characterized in that: In S35, the model effect is verified, including: (1) Calculate the mean absolute error (MAE) of the voltage prediction model In the formula, n is the total number of samples, y is i is the true value, is the model prediction value; (2) Calculate the root mean square error (RMSE) of the prediction model In the formula, n is the total number of samples, y is i is the true value, is the model's predicted value.

Images