Split type electric vehicle direct current charging pile energy consumption analysis method based on data driving

Abstract

The invention provides a split type electric vehicle direct current charging pile energy consumption analysis method based on data driving. The method comprises the steps that electricity consumption data of a box type transformer and historical order data of all charging guns are acquired; based on the electricity consumption data and the historical order data, obtaining total time corresponding to different total output powers of the charging gun in a fixed time period and electricity loss of the charging pile in the fixed time period; adopting a multiple linear regression model to construct an electric quantity loss prediction model for fitting the electric quantity loss of the box-type transformer under different total output powers of the charging gun, and constructing a constraint condition and a target function of the electric quantity loss prediction model; solving model parameters of the electric quantity loss prediction model to obtain a final electric quantity loss prediction model; through the final electric quantity loss prediction model, the energy consumption analysis of the split type electric vehicle DC charging pile is carried out, and the technical problems of multi-point layout and complex test of the energy efficiency measurement method of the split type electric vehicle charging pile in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the technical field of power loss analysis of split-type electric vehicle DC charging piles, and in particular to a data-driven energy consumption analysis method for split-type electric vehicle DC charging piles. Background Art

[0002] With the increase of environmental awareness, the support of government policies and the development of electric vehicle technology, the sales of electric vehicles continue to rise. As the most basic and important supporting facilities for electric vehicles, electric vehicle charging piles have been built in large quantities. Among them, split electric vehicle DC charging piles have been widely built and applied because of their more flexible configuration and ability to adapt to different charging needs. The energy efficiency level of electric vehicle charging equipment can reflect the ability of the electric vehicle industry to save energy and reduce emissions to a certain extent. Therefore, evaluating its energy consumption is of great significance to achieving energy saving and loss reduction and improving energy utilization.

[0003] At present, the energy efficiency test of electric vehicle charging piles can be carried out by input and output power measurement method, standard test load method, simulated charging test method and other methods. Split electric vehicle charging piles are composed of box transformers, charging control boxes and charging guns, which are connected by cables. The configuration is more flexible and can adapt to different charging needs. However, the use of input and output power test methods for split electric vehicle charging piles requires multi-point layout, and there is a problem of too many test points and complex testing; the use of standard test load method and simulated charging test method cannot cope with the flexible configuration characteristics of split electric vehicle loads. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first purpose of this application is to propose a data-driven split electric vehicle DC charging pile energy consumption analysis method to realize the energy consumption analysis of the split electric vehicle DC charging pile, and solve the problems of multi-point layout and complex testing in the traditional electric vehicle charging pile energy efficiency measurement method for the split electric vehicle charging pile.

[0006] The second purpose of the present application is to propose a data-driven split-type electric vehicle DC charging pile energy consumption analysis device.

[0007] The third objective of the present application is to provide an electronic device.

[0008] A fourth objective of the present application is to provide a computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a data-driven split electric vehicle DC charging pile energy consumption analysis method, wherein the split electric vehicle DC charging pile includes a box-type transformer, a charging control box and a plurality of charging guns, and the method includes the following steps:

[0011] Obtaining power consumption data of the box-type transformer and historical order data of each of the multiple charging guns;

[0012] Based on the historical order data, the total time corresponding to the total output power of different charging guns within a fixed time period is obtained;

[0013] Based on the power consumption data of the box-type transformer and the historical order data, the power consumption of the split electric vehicle DC charging pile in a fixed time period is obtained;

[0014] A multivariate linear regression model is used to construct an electric power loss prediction model for fitting the electric power loss of a box-type transformer under different total output powers of charging guns, and constraints and objective functions of the electric power loss prediction model are constructed;

[0015] Based on the total time corresponding to the total output power of different charging guns within the fixed time period, the power loss of the split electric vehicle DC charging pile in the fixed time period, the constraint conditions and the objective function, the model parameters of the power loss prediction model are solved to obtain the final power loss prediction model; and the energy consumption analysis of the split electric vehicle DC charging pile is performed through the final power loss prediction model.

[0016] In some implementations, obtaining the power consumption data of the box-type transformer includes:

[0017] Acquire the input power data of the box-type transformer; the input power data is time series data;

[0018] Preprocessing the input power data includes performing a first-order difference operation on the time series of the input power data to obtain a first abnormal point whose first-order difference value is negative and a second abnormal point whose first-order difference value is greater than a maximum sampling value; replacing the data of the first abnormal point by a linear interpolation method, and processing the data of the second abnormal point by a segmented labeling method; performing a first-order difference operation on the power series of the input power data to obtain a third abnormal point whose first-order difference value is negative; and replacing the data of the third abnormal point by a linear interpolation method;

[0019] The input power data after preprocessing is verified, and after the verification is passed, the power consumption data of the box-type transformer is obtained based on the input power data after preprocessing.

[0020] In some implementations, the historical order data includes the order start time, order end time, and charging power of each charging order, and obtaining the total time corresponding to the total output power of different charging guns within a fixed time period based on the historical order data includes:

[0021] Based on the order start time, order end time and charging power of each charging order, the average output power of each charging order of each charging gun is calculated by the following formula:

[0022]

[0023] Where: W in represents the charging capacity of the nth order of the i-th charging gun, t e Indicates the order end time of the nth order, t s represents the order start time of the nth order, P it Indicates the average output power of the i-th charging gun in the current order time period, which is equivalent to the average output power of the n-th order start time t s Until the order ends e Output power at each time point within

[0024] Based on the average output power of each charging order of each charging gun, the total output power of the multiple charging guns at each time point is calculated by the following formula:

[0025]

[0026] Where t represents the current time point, N represents the total number of charging guns, and P it Indicates the output power of the i-th charging gun at the current time point t, which is equivalent to the average output power of the current time period;

[0027] Based on the total output power of the multiple charging guns at each time point, the total time corresponding to the total output power of different charging guns in a fixed time period is obtained by the following formula:

[0028]

[0029] Among them, t m Indicates that the total output power of the charging gun within a fixed time period from t1 to t2 is P m The total time of .

[0030] In some implementations, the method of obtaining the power consumption of the split electric vehicle DC charging pile in a fixed time period based on the power consumption data of the box-type transformer and the historical order data includes:

[0031] Based on the power consumption data of the box-type transformer, the power loss W of the split electric vehicle DC charging pile in a fixed time period is obtained by the following formula: loss :

[0032]

[0033] Among them: t1 and t2 represent the starting and ending positions of fixed time. According to the order statistical characteristics, a fixed time period can be selected to calculate the total power loss of the box-type transformer, W in It represents the charging capacity of the nth order of the ith charging gun in the current time period, V represents the total number of charging guns in the current time period, and N represents the total number of orders in the current time period.

[0034] In some implementations, the power loss prediction model is expressed by the following formula:

[0035]

[0036] Among them, W loss Indicates power loss, M indicates the number of different charging guns with total output power, P m_loss It represents the power loss under different total output powers of the charging gun, which is the model parameter that needs to be fitted.

[0037] In some implementations, the constraint is expressed as follows:

[0038] h(p)=P m_loss ≥0, m∈(0,M);

[0039] The objective function is expressed as follows:

[0040]

[0041] In some implementations, the total time corresponding to the total output power of different charging guns in the fixed time period, the power loss of the split electric vehicle DC charging pile in the fixed time period, the constraint conditions and the objective function, solving the model parameters of the power loss prediction model; includes:

[0042] The Lagrangian multiplier is introduced as the penalty term λ of the inequality h(p) constraint function, and the Lagrangian function is defined. The Lagrangian function is expressed as follows:

[0043] L(p,λ)=f(p)+λ T h(p)

[0044] Based on the Lagrangian function, the iterative update rule is determined as follows:

[0045]

[0046] in, The Jacobian matrix representing the constraint function of the inequality h(p);

[0047] Based on the iterative update rule, the total time corresponding to the total output power of different charging guns in the fixed time period and the power loss of the split electric vehicle DC charging pile in the fixed time period, the objective function, the gradient, the constraint conditions and the Jacobian matrix thereof are iteratively calculated; until the iteration termination condition is met.

[0048] In some implementations, during the iterative calculation process, the correction direction Δp is calculated by Newton's method, and the iterative update is calculated by the following formula:

[0049] α=min(1,r)

[0050] r=max(β s ,r t )

[0051]

[0052] p k+1 =p k +αΔp

[0053] Among them, α represents the update step size, and s and t represent positive scaling factors.

[0054] In some implementations, after obtaining the final power loss prediction model, the method further includes:

[0055] The evaluation performance of the final power loss prediction model is judged by the determination coefficient, root mean square error and mean absolute error value.

[0056] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a data-driven split electric vehicle DC charging pile energy consumption analysis device, wherein the split electric vehicle DC charging pile includes a box-type transformer, a charging control box and a plurality of charging guns, and the device includes:

[0057] A data acquisition module, used to acquire the power consumption data of the box-type transformer and the historical order data of each of the multiple charging guns;

[0058] A parameter calculation module, used to obtain the total time corresponding to the total output power of different charging guns within a fixed time period based on the historical order data;

[0059] The parameter calculation module is further used to obtain the power consumption of the split electric vehicle DC charging pile in a fixed time period based on the power consumption data of the box-type transformer and the historical order data;

[0060] A model building module, for building a power loss prediction model for fitting the power loss of a box-type transformer under different total output powers of charging guns using a multivariate linear regression model, and building constraints and objective functions of the power loss prediction model;

[0061] The model solving module is used to solve the model parameters of the power loss prediction model based on the total time corresponding to the total output power of different charging guns within the fixed time period, the power loss of the split electric vehicle DC charging pile in the fixed time period, the constraint conditions and the objective function, so as to obtain the final power loss prediction model; and to perform energy consumption analysis of the split electric vehicle DC charging pile through the final power loss prediction model.

[0062] In some implementations, obtaining the power consumption data of the box-type transformer includes:

[0063] Acquire the input power data of the box-type transformer; the input power data is time series data;

[0064] Preprocessing the input power data includes performing a first-order difference operation on the time series of the input power data to obtain a first abnormal point whose first-order difference value is negative and a second abnormal point whose first-order difference value is greater than a maximum sampling value; replacing the data of the first abnormal point by a linear interpolation method, and processing the data of the second abnormal point by a segmented labeling method; performing a first-order difference operation on the power series of the input power data to obtain a third abnormal point whose first-order difference value is negative; and replacing the data of the third abnormal point by a linear interpolation method;

[0065] The input power data after preprocessing is verified, and after the verification is passed, the power consumption data of the box-type transformer is obtained based on the input power data after preprocessing.

[0066] In some implementations, the historical order data includes the order start time, order end time, and charging power of each charging order. When the parameter calculation module obtains the total time corresponding to the total output power of different charging guns within a fixed time period based on the historical order data, it is used to:

[0067] Based on the order start time, order end time and charging power of each charging order, the average output power of each charging order of each charging gun is calculated by the following formula:

[0068]

[0069] Where: W in represents the charging capacity of the nth order of the i-th charging gun, t e Indicates the order end time of the nth order, t srepresents the order start time of the nth order, P it Indicates the average output power of the i-th charging gun in the current order time period, which is equivalent to the average output power of the n-th order start time t s Until the order ends e Output power at each time point within

[0070] Based on the average output power of each charging order of each charging gun, the total output power of the multiple charging guns at each time point is calculated by the following formula:

[0071]

[0072] Where t represents the current time point, N represents the total number of charging guns, and P it Indicates the output power of the i-th charging gun at the current time point t, which is equivalent to the average output power of the current time period;

[0073] Based on the total output power of the multiple charging guns at each time point, the total time corresponding to the total output power of different charging guns in a fixed time period is obtained by the following formula:

[0074]

[0075] Among them, t m Indicates that the total output power of the charging gun within a fixed time period from t1 to t2 is P m The total time of .

[0076] In some implementations, the parameter calculation module is used to obtain the power consumption of the split electric vehicle DC charging pile in a fixed time period based on the power consumption data of the box-type transformer and the historical order data;

[0077] Based on the power consumption data of the box-type transformer, the power loss W of the split electric vehicle DC charging pile in a fixed time period is obtained by the following formula: loss :

[0078]

[0079] Among them: t1 and t2 represent the starting and ending positions of fixed time. According to the order statistical characteristics, a fixed time period can be selected to calculate the total power loss of the box-type transformer, W in It represents the charging capacity of the nth order of the ith charging gun in the current time period, V represents the total number of charging guns in the current time period, and N represents the total number of orders in the current time period.

[0080] In some implementations, the power loss prediction model is expressed by the following formula:

[0081]

[0082] Among them, W loss Indicates power loss, M indicates the number of different charging guns with total output power, P m_loss It represents the power loss under different total output powers of the charging gun, which is the model parameter that needs to be fitted.

[0083] In some implementations, the constraint is expressed as follows:

[0084] h(p)=P m_loss ≥0, m∈(0,M);

[0085] The objective function is expressed as follows:

[0086]

[0087] In some implementations, the model solving module is specifically used to:

[0088] The Lagrangian multiplier is introduced as the penalty term λ of the inequality h(p) constraint function, and the Lagrangian function is defined. The Lagrangian function is expressed as follows:

[0089] L(p,λ)=f(p)+λ T h(p)

[0090] Based on the Lagrangian function, the iterative update rule is determined as follows:

[0091]

[0092] in, The Jacobian matrix representing the constraint function of the inequality h(p);

[0093] Based on the iterative update rule, the total time corresponding to the total output power of different charging guns in the fixed time period and the power loss of the split electric vehicle DC charging pile in the fixed time period, the objective function, the gradient, the constraint conditions and the Jacobian matrix thereof are iteratively calculated; until the iteration termination condition is met.

[0094] In some implementations, the model solving module calculates the correction direction Δp by Newton's method during the iterative calculation process, and calculates the iterative update by the following formula:

[0095] α=min(1,r)

[0096] r=max(β s ,r t )

[0097]

[0098] p k+1 =p k +αΔp

[0099] Among them, α represents the update step size, and s and t represent positive scaling factors.

[0100] In some implementations, after obtaining the final power loss prediction model, the model solving module is used to:

[0101] The evaluation performance of the final power loss prediction model is judged by the determination coefficient, root mean square error and mean absolute error value.

[0102] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect.

[0103] To achieve the above-mentioned purpose, the fourth aspect of the present application proposes a computer-readable storage medium, in which computer-readable storage medium is stored computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0104] To achieve the above-mentioned purpose, the fifth aspect of the present application proposes a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0105] The present application provides a data-driven energy consumption analysis method for a split electric vehicle DC charging pile. Based on the power consumption data of a box transformer generated during the use of the split electric vehicle DC charging pile and the historical order data of each charging gun, the total time corresponding to different charging gun total output powers in a fixed time period and the power loss of the split electric vehicle DC charging pile in a fixed time period are obtained, and then a multivariate linear regression model is constructed to fit the power loss of the split electric vehicle DC charging pile under different charging gun total output powers. Based on the total time corresponding to different charging gun total output powers in a fixed time period and the power loss in a fixed time period, the model parameters are determined by solving the model through an optimization algorithm to obtain a fitting model, that is, a final power loss prediction model; thereby, the energy consumption analysis of the split electric vehicle DC charging pile can be realized through the final power loss prediction model; based on the fitting model and a large amount of real data, end-to-end energy consumption analysis can be realized, which can more accurately reflect the performance of the split electric vehicle DC charging pile in actual use, and long-term data accumulation and analysis can provide monitoring of the long-term operating efficiency of the charging pile system. The data can be automatically collected, processed and analyzed through automated tools, reducing manual intervention; the model parameters can be flexibly adjusted according to the actual operation situation, and the energy efficiency analysis can be quickly responded to. Compared with the traditional measurement method, the charging pile operation status can be monitored in real time, which is fast, simple, efficient, easy to maintain and upgrade. It solves the problems of multi-point layout, complex load and complex model in the traditional energy efficiency measurement method of split electric vehicle charging piles.

[0106] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0107] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0108] Figure 1 A schematic diagram of a flow chart of a data-driven split-type electric vehicle DC charging pile energy consumption analysis method provided in an embodiment of the present application;

[0109] Figure 2 This is a graph showing the accumulated electricity consumption of the box-type transformer of the 4# split-type electric vehicle DC charging pile provided as an example in this application;

[0110] Figure 3 A line chart of daily power consumption of a box-type transformer of a 4# split-type electric vehicle DC charging pile provided as an example of this application;

[0111] Figure 4A Gantt chart of historical order data of charging guns provided for an example of this application;

[0112] Figure 5 A schematic diagram of power loss fitting coefficients under different total output powers of charging guns provided for an example of the present application;

[0113] Figure 6 A comparison chart of the actual power loss and the power loss predicted by the model calculation provided in an example of this application;

[0114] Figure 7 A block diagram of a data-driven split-type electric vehicle DC charging pile energy consumption analysis device provided in an embodiment of the present application;

[0115] Figure 8 A block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0116] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0117] The following describes the data-driven split electric vehicle DC charging pile energy consumption analysis method, device and equipment according to an embodiment of the present application with reference to the accompanying drawings.

[0118] Figure 1 A schematic flow chart of a data-driven split-type electric vehicle DC charging pile energy consumption analysis method provided in an embodiment of the present application, wherein the split-type electric vehicle DC charging pile includes a box-type transformer, a charging control box and multiple charging guns.

[0119] It should be noted that the executor of the data-driven split-type electric vehicle DC charging pile energy consumption analysis method in the embodiment of the present application is the data-driven split-type electric vehicle DC charging pile energy consumption analysis device in the embodiment of the present application. The data-driven split-type electric vehicle DC charging pile energy consumption analysis device can be configured in an electronic device so that the electronic device can execute the function of the data-driven split-type electric vehicle DC charging pile energy consumption analysis method.

[0120] like Figure 1 As shown, the data-driven split electric vehicle DC charging pile energy consumption analysis method includes the following steps:

[0121] Step 101, obtaining the power consumption data of the box-type transformer and the historical order data of each of the multiple charging guns.

[0122] As an implementation method, obtaining the power consumption data of the box-type transformer includes:

[0123] Acquire the input power data of the box-type transformer; the input power data is time series data;

[0124] Preprocessing the input power data includes performing a first-order difference operation on the time series of the input power data to obtain a first abnormal point whose first-order difference value is negative and a second abnormal point whose first-order difference value is greater than a maximum sampling value; replacing the data of the first abnormal point by a linear interpolation method, and processing the data of the second abnormal point by a segmented labeling method; performing a first-order difference operation on the power series of the input power data to obtain a third abnormal point whose first-order difference value is negative; and replacing the data of the third abnormal point by a linear interpolation method;

[0125] The input power data after preprocessing is verified, and after the verification is passed, the power consumption data of the box-type transformer is obtained based on the input power data after preprocessing.

[0126] As an implementation method, a method for obtaining input power data of the box-type transformer includes: collecting power status data of an input power meter of the box-type transformer, and obtaining input power data based on the power status data; the input power data is time series data.

[0127] For example, taking the box-type transformer of the 4# split electric vehicle DC charging pile as an example, its power situation data is the original cumulative power consumption data. The cumulative power consumption line chart is as follows: Figure 2 As shown, the daily power consumption can be obtained based on the accumulated power consumption data, that is, the power consumption at each time point can be obtained based on the accumulated power consumption.

[0128] When preprocessing the input power data, perform first-order difference operations on the time series and power series of the power consumption data, mark and process the abnormal points of the time series: points with negative first-order difference values ​​are abnormal points, and the abnormal data are replaced by linear interpolation; points with first-order difference values ​​greater than the maximum sampling value are abnormal points, and the segmented marking method is used as new data. Mark and process the abnormal points of the power consumption series: points with negative first-order difference values ​​are abnormal points, and the abnormal data are replaced by linear interpolation. Verify the input power data after preprocessing. If the verification fails, re-perform the preprocessing operation.

[0129] For example, taking the box-type transformer of the 4# split electric vehicle DC charging pile as an example, the line graph of the daily power consumption data calculated based on the pre-processed input power data of the box-type transformer is as follows: Figure 3 shown.

[0130] As an implementation method, a method for obtaining historical order data of each charging gun includes: collecting historical order data of each charging gun, the historical order data including order start time, order end time and charging power. The charging power refers to the total power charged to the electric vehicle by the charging gun during the charging process.

[0131] For example, taking January 1, 2024 as an example, the Gantt chart of the historical order data of 8 charging guns of the 4# split electric vehicle DC charging pile is as follows: Figure 4 shown.

[0132] In this embodiment, the power consumption is expressed as W t , where t represents the current time point.

[0133] Step 102: Based on the historical order data, the total time corresponding to the total output power of different charging guns within a fixed time period is obtained.

[0134] As an implementation method, based on the order start time, order end time and charging power of each charging order, the average output power of each charging order of each charging gun is calculated; based on the average output power of each charging order of each charging gun, the total output power of the multiple charging guns at each time point is calculated; based on the total output power of the multiple charging guns at each time point, the total time corresponding to the total output powers of different charging guns within a fixed time period is obtained.

[0135] As an implementation method, based on the order start time, order end time and charging power of each charging order, the average output power of each charging order of each charging gun is calculated by the following formula:

[0136]

[0137] Where: W in represents the charging capacity of the nth order of the i-th charging gun, t e Indicates the order end time of the nth order, t s represents the order start time of the nth order, P it Indicates the average output power of the i-th charging gun in the current order time period, which is equivalent to the average output power of the n-th order start time t s Until the order ends e The output power at each time point.

[0138] As an implementation method, based on the average output power of each charging order of each charging gun, the total output power of the multiple charging guns at each time point is calculated by the following formula (that is, the total output power of all charging guns at each time point is calculated):

[0139]

[0140] Where t represents the current time point, N represents the total number of charging guns, and P it Indicates the output power of the i-th charging gun at the current time point t, which is equivalent to the average output power in the current time period.

[0141] It can be understood that when calculating the total output power of all charging guns at each time point, all historical orders at each time point are searched, and the average output power of all charging guns is accumulated.

[0142] As an implementation method, based on the total output power of the multiple charging guns at each time point, the total time corresponding to the total output power of different charging guns in a fixed time period is obtained by the following formula:

[0143]

[0144] Among them, t m Indicates that the total output power of the charging gun within a fixed time period from t1 to t2 is P m The total time of .

[0145] The total time corresponding to the total output power of different charging guns within a fixed time period is obtained, that is, the time occupied by the total output power of different charging guns within a fixed time period is obtained.

[0146] Step 103: Based on the power consumption data of the box-type transformer and the historical order data, the power consumption of the split electric vehicle DC charging pile in a fixed time period is obtained.

[0147] It should be noted that the power loss of a split-type electric vehicle DC charging pile in a fixed time period is the difference between the input power of the box-type transformer in a fixed time period and the output power of all charging guns. The fixed time period can be determined according to the fixed time period selected according to the order statistical characteristics, that is, according to the order statistical characteristics, a fixed time period can be selected to calculate the total power loss of the box-type transformer.

[0148] As an implementation method, based on the power consumption data of the box-type transformer and the historical order data, a method for obtaining the power consumption of the split electric vehicle DC charging pile in a fixed time period includes:

[0149] The power loss is calculated by the following formula (4), as shown in (4):

[0150]

[0151] Among them: t1 and t2 represent the starting and ending positions of fixed time. According to the order statistical characteristics, a fixed time period can be selected to calculate the total power loss of the box-type transformer, W inrepresents the charging capacity of the nth order of the i-th charging gun in the current time period, V represents the total number of charging guns in the current time period, N represents the total number of orders in the current time period, and W t1 Indicates the cumulative power consumption at time t1, W t2 Indicates the cumulative power consumption at time point t2.

[0152] Step 104, using a multivariate linear regression model to construct a power loss prediction model for fitting the power loss of a box-type transformer under different total output powers of charging guns, and constructing constraints and an objective function of the power loss prediction model.

[0153] It can be understood that the multivariate linear regression model is used to fit the power loss of the box-type transformer under different total output powers of the charging gun, and the model parameters are obtained according to the data to obtain the fitting model, that is, the final power loss prediction model.

[0154] The regression formula constructed using the multivariate linear regression model, that is, the power loss prediction model is expressed as follows:

[0155]

[0156] Among them, W loss Indicates power loss, M indicates the number of different charging guns with total output power, P m_loss It represents the power loss under different total output powers of the charging gun, which is the model parameter that needs to be fitted.

[0157] Constraints:

[0158] According to objective reality, the constraints of power loss under different total output powers of charging guns are shown in formula (6):

[0159] h(p)=P m_loss ≥0,m∈(0,M) (6)

[0160] Objective function:

[0161] For the regression formula (5), we hope to obtain a set of model parameters P m_loss , m∈(0,M), so that the predicted power consumption Close to the actual power loss Wl oss , thus, the objective function is defined as the minimum mean square error, as shown in formula (7):

[0162]

[0163] The closer f(p) is to 0, the better the prediction effect of the model.

[0164] Step 105, based on the total time corresponding to the total output power of different charging guns within the fixed time period, the power loss of the split electric vehicle DC charging pile in the fixed time period, the constraint conditions and the objective function, solve the model parameters of the power loss prediction model to obtain the final power loss prediction model; and perform energy consumption analysis of the split electric vehicle DC charging pile through the final power loss prediction model.

[0165] It should be noted that using a multivariate linear regression model to fit the power loss of a box-type transformer under different total output powers of a charging gun to obtain a fitting model is to solve a numerical optimal problem under constraints, and there are many algorithms for solving it. This embodiment uses a continuous least squares algorithm for solving it, and the solution process is as follows:

[0166] The Lagrangian multiplier is introduced as the penalty term λ of the inequality h(p) constraint function, and the Lagrangian function is defined to transform the solution problem into an unconstrained least squares problem. The Lagrangian function is expressed as follows:

[0167] L(p,λ)=f(p)+λ T h(p) (8)

[0168] Based on the Lagrangian function, an iterative update rule is determined, and the iterative update rule is obtained by calculating the first-order necessary conditions as shown in formula (9):

[0169]

[0170] in, The Jacobian matrix representing the constraint function of the inequality h(p);

[0171] Based on the iterative update rule, the total time corresponding to the total output power of different charging guns in the fixed time period and the power loss of the split electric vehicle DC charging pile in the fixed time period, the objective function, the gradient, the constraint conditions and the Jacobian matrix thereof are iteratively calculated; until the iteration termination condition is met.

[0172] In the iterative process, according to the above iterative update rules, in each iteration, the objective function, gradient, constraint conditions and Jacobian matrix are calculated. The rule of iterative termination conditions is shown in formula 10:

[0173]

[0174] Among them, k represents the current number of iterations, ε represents the preset data accuracy, and K represents the preset number of iterations.

[0175] In some embodiments, during the iterative calculation process, the iterative rule is updated: Newton's method is used to calculate the correction direction Δp, and the calculation update is shown in formula (11):

[0176]

[0177] Among them, α represents the update step size, and s and t represent positive scaling factors.

[0178] In some embodiments, after obtaining the model parameters and determining the final fitting model, a cross-validation method is used:

[0179] The present invention improves the generalization ability of the fitting model by using a method. Specifically, 80% of the data set obtained in step 101 is used as model fitting data, and 20% is used as test data. A 5-fold cross validation method is used. Finally, the performance of the fitting model is evaluated by the average results of 5 tests.

[0180] In some embodiments, the evaluation index of the quality of the fitting model includes the coefficient of determination (R 2 ), root mean square error (RMSE) and mean absolute error (MAE) values, that is, using the coefficient of determination (R 2 ), root mean square error (RMSE) and mean absolute error (MAE) values ​​to judge the evaluation performance of the fitting model. 2 The calculation formulas of , RMSE, and MAE are shown in formula (12), formula (13), and formula (14), respectively.

[0181]

[0182] Among them, y i represents the true value, represents the predicted value, It represents the average value of the true value, SSR is the regression sum of squares, SSE is the residual sum of squares, and SST is the total deviation sum of squares.

[0183]

[0184] Where n represents the number of samples, y i represents the true value, Represents the predicted value.

[0185]

[0186] Where n represents the number of samples, y i represents the true value, Represents the predicted value.

[0187] The closer the root mean square error RMSE and mean absolute error MAE are to 0, the better the model fit is and the higher the prediction accuracy of the data is. 2 The closer it is to 1, the better the model fits the observed data.

[0188] For example, taking the box-type transformer of the 4# split electric vehicle DC charging pile as an example, the output power segment interval is 0.5kwh / min, 80% of the data is used as training data, and the regression model (i.e., the power loss prediction model) is fitted. The power loss fitting coefficients under different total output powers of the charging gun are as follows: Figure 5 As shown in Figure 2, the comparison between the actual power loss and the predicted power loss is Figure 6 The remaining 20% ​​of the data is imported as test data into the fitting model with determined model parameters to verify the stability and fitting performance of the fitting model. Table 1 shows the determination coefficient R of the predicted power loss and the actual power loss of the fitting model 2 , root mean square error RMSE and mean absolute error MAE.

[0189] Table 1: Determination coefficient R of predicted power loss and actual power loss of the fitting model 2 , root mean square error RMSE and mean absolute error MAE values

[0190]

[0191] The data-driven split electric vehicle DC charging pile energy consumption analysis method of the embodiment of the present application is based on the power consumption data of the box transformer generated by the split electric vehicle DC charging pile during use and the historical order data of each charging gun, the total time corresponding to the total output power of different charging guns in a fixed time period and the power loss of the split electric vehicle DC charging pile in a fixed time period are obtained, and then a multivariate linear regression model is constructed to fit the power loss of the split electric vehicle DC charging pile under different total output powers of the charging guns. Based on the total time corresponding to the total output power of different charging guns in the fixed time period and the power loss in the fixed time period, the model parameters are determined by solving the model through an optimization algorithm to obtain a fitting model, that is, a final power loss prediction model; thereby, the energy consumption analysis of the split electric vehicle DC charging pile can be realized through the final power loss prediction model; based on the fitting model and a large amount of real data, end-to-end energy consumption analysis can be realized, which can more accurately reflect the performance of the split electric vehicle DC charging pile in actual use, and can provide monitoring of the long-term operating efficiency of the charging pile system through long-term data accumulation and analysis. The automatic data collection, processing and analysis can be realized through automated tools, reducing manual intervention; the model parameters can be flexibly adjusted according to the actual operation situation, and the energy efficiency analysis can be quickly responded. Compared with the traditional measurement method, the operation status of the charging pile can be monitored in real time, and it has the characteristics of being fast, simple, efficient, and easy to maintain and upgrade. Aiming at the problem that the energy loss process of the split-type electric vehicle DC charging pile is extremely complex during the charging process, the present invention uses the input power data of the box-type transformer and the historical order data of each charging gun to realize end-to-end energy consumption analysis, and provides a new data-driven method for clarifying the energy consumption analysis of the process.

[0192] In order to implement the above embodiment, the present application also proposes a data-driven split electric vehicle DC charging pile energy consumption analysis device, wherein the split electric vehicle DC charging pile includes a box-type transformer, a charging control box and multiple charging guns. Figure 7 The schematic diagram of the structure of a data-driven split-type electric vehicle DC charging pile energy consumption analysis device provided in the embodiment of the present application. Figure 7 As shown, the data-driven split electric vehicle DC charging pile energy consumption analysis device may include: a data acquisition module 701, a parameter calculation module 702, a model construction module 703 and a model solution module 704.

[0193] The data acquisition module 701 is used to acquire the power consumption data of the box-type transformer and the historical order data of each of the multiple charging guns;

[0194] A parameter calculation module 702 is used to obtain the total time corresponding to the total output power of different charging guns within a fixed time period based on the historical order data;

[0195] The parameter calculation module 702 is further used to obtain the power consumption of the split electric vehicle DC charging pile in a fixed time period based on the power consumption data of the box-type transformer and the historical order data;

[0196] A model building module 703 is used to use a multivariate linear regression model to build an electric power loss prediction model for fitting the electric power loss of a box-type transformer under different total output powers of charging guns, and to build constraints and objective functions of the electric power loss prediction model;

[0197] The model solving module 704 is used to solve the model parameters of the power loss prediction model based on the total time corresponding to the total output power of different charging guns within the fixed time period, the power loss of the split electric vehicle DC charging pile in the fixed time period, the constraint conditions and the objective function, so as to obtain the final power loss prediction model; and to perform energy consumption analysis of the split electric vehicle DC charging pile through the final power loss prediction model.

[0198] In some implementations, when acquiring the power consumption data of the box-type transformer, the data acquisition module 701 is used to:

[0199] Acquire the input power data of the box-type transformer; the input power data is time series data;

[0200] Preprocessing the input power data includes performing a first-order difference operation on the time series of the input power data to obtain a first abnormal point whose first-order difference value is negative and a second abnormal point whose first-order difference value is greater than a maximum sampling value; replacing the data of the first abnormal point by a linear interpolation method, and processing the data of the second abnormal point by a segmented labeling method; performing a first-order difference operation on the power series of the input power data to obtain a third abnormal point whose first-order difference value is negative; and replacing the data of the third abnormal point by a linear interpolation method;

[0201] The input power data after preprocessing is verified, and after the verification is passed, the power consumption data of the box-type transformer is obtained based on the input power data after preprocessing.

[0202] In some implementations, the historical order data includes the order start time, order end time, and charging power of each charging order. When the parameter calculation module 702 obtains the total time corresponding to the total output power of different charging guns within a fixed time period based on the historical order data, it is used to:

[0203] Based on the order start time, order end time and charging power of each charging order, the average output power of each charging order of each charging gun is calculated by the following formula:

[0204]

[0205] Where: W in represents the charging capacity of the nth order of the i-th charging gun, t e Indicates the order end time of the nth order, t s represents the order start time of the nth order, P it Indicates the average output power of the i-th charging gun in the current order time period, which is equivalent to the average output power of the n-th order start time t s Until the order ends e Output power at each time point within

[0206] Based on the average output power of each charging order of each charging gun, the total output power of the multiple charging guns at each time point is calculated by the following formula:

[0207]

[0208] Where t represents the current time point, N represents the total number of charging guns, and P it Indicates the output power of the i-th charging gun at the current time point t, which is equivalent to the average output power of the current time period;

[0209] Based on the total output power of the multiple charging guns at each time point, the total time corresponding to the total output power of different charging guns in a fixed time period is obtained by the following formula:

[0210]

[0211] Among them, t m Indicates that the total output power of the charging gun within a fixed time period from t1 to t2 is P m The total time of .

[0212] In some implementations, the parameter calculation module 702 is used to obtain the power consumption of the split electric vehicle DC charging pile in a fixed time period based on the power consumption data of the box-type transformer and the historical order data;

[0213] Based on the power consumption data of the box-type transformer, the power loss W of the split electric vehicle DC charging pile in a fixed time period is obtained by the following formula: loss :

[0214]

[0215] Among them: t1 and t2 represent the starting and ending positions of fixed time. According to the order statistical characteristics, a fixed time period can be selected to calculate the total power loss of the box-type transformer, W inIt represents the charging capacity of the nth order of the ith charging gun in the current time period, V represents the total number of charging guns in the current time period, and N represents the total number of orders in the current time period.

[0216] In some implementations, the power loss prediction model is expressed by the following formula:

[0217]

[0218] Among them, W loss Indicates power loss, M indicates the number of different charging guns with total output power, P m_loss It represents the power loss under different total output powers of the charging gun, which is the model parameter that needs to be fitted.

[0219] In some implementations, the constraint is expressed as follows:

[0220] h(p)=P m_loss ≥0, m∈(0,M);

[0221] The objective function is expressed as follows:

[0222]

[0223] In some implementations, the model solving module is specifically used to:

[0224] The Lagrangian multiplier is introduced as the penalty term λ of the inequality h(p) constraint function, and the Lagrangian function is defined. The Lagrangian function is expressed as follows:

[0225] L(p,λ)=f(p)+λ T h(p)

[0226] Based on the Lagrangian function, the iterative update rule is determined as follows:

[0227]

[0228] in, The Jacobian matrix representing the constraint function of the inequality h(p);

[0229] Based on the iterative update rule, the total time corresponding to the total output power of different charging guns in the fixed time period and the power loss of the split electric vehicle DC charging pile in the fixed time period, the objective function, the gradient, the constraint conditions and the Jacobian matrix thereof are iteratively calculated; until the iteration termination condition is met.

[0230] In some implementations, the model solving module 704 calculates the correction direction Δp by Newton's method during the iterative calculation process, and calculates the iterative update by the following formula:

[0231] α=min(1,r)

[0232] r=max(β s ,r t )

[0233]

[0234] p k+1 =p k +αΔp

[0235] Among them, α represents the update step size, and s and t represent positive scaling factors.

[0236] In some implementations, after obtaining the final power loss prediction model, the model solving module 704 is used to:

[0237] The evaluation performance of the final power loss prediction model is judged by the determination coefficient, root mean square error and mean absolute error value.

[0238] It should be noted that the above explanation of the data-driven split-type electric vehicle DC charging pile energy consumption analysis method embodiment is also applicable to the data-driven split-type electric vehicle DC charging pile energy consumption analysis device of this embodiment, which will not be repeated here.

[0239] In order to implement the above embodiment, the present application also proposes an electronic device. Figure 8 , Figure 8 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 8 As shown, the electronic device 800 includes: a processor 801, and a memory 802 communicatively connected to the processor 801; the memory 802 stores computer-executable instructions; the processor 801 executes the computer-executable instructions stored in the memory to implement the method provided in the aforementioned embodiment.

[0240] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0241] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0242] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0243] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0244] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0245] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0246] In addition, 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 the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0247] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0248] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0249] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0250] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0251] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0252] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A data-driven split-type electric vehicle DC charging pile energy consumption analysis method, wherein the split-type electric vehicle DC charging pile includes a box-type transformer, a charging control box and a plurality of charging guns, characterized in that: The method comprises the following steps: Obtaining power consumption data of the box-type transformer and historical order data of each of the multiple charging guns; Based on the historical order data, the total time corresponding to the total output power of different charging guns within a fixed time period is obtained; Based on the power consumption data of the box-type transformer and the historical order data, the power consumption of the split electric vehicle DC charging pile in a fixed time period is obtained; A multivariate linear regression model is used to construct an electric power loss prediction model for fitting the electric power loss of a box-type transformer under different total output powers of charging guns, and constraints and objective functions of the electric power loss prediction model are constructed; Based on the total time corresponding to the total output power of different charging guns within the fixed time period, the power loss of the split electric vehicle DC charging pile in the fixed time period, the constraint conditions and the objective function, the model parameters of the power loss prediction model are solved to obtain the final power loss prediction model; and the energy consumption analysis of the split electric vehicle DC charging pile is performed through the final power loss prediction model.

2. The method according to claim 1, characterized in that The obtaining of the power consumption data of the box-type transformer comprises: Acquire the input power data of the box-type transformer; the input power data is time series data; Preprocessing the input power data includes performing a first-order difference operation on the time series of the input power data to obtain a first abnormal point whose first-order difference value is negative and a second abnormal point whose first-order difference value is greater than a maximum sampling value; replacing the data of the first abnormal point by a linear interpolation method, and processing the data of the second abnormal point by a segmented labeling method; performing a first-order difference operation on the power series of the input power data to obtain a third abnormal point whose first-order difference value is negative; and replacing the data of the third abnormal point by a linear interpolation method; The input power data after preprocessing is verified, and after the verification is passed, the power consumption data of the box-type transformer is obtained based on the input power data after preprocessing.

3. The method according to claim 1, characterized in that The historical order data includes the order start time, order end time and charging power of each charging order, and the total time corresponding to the total output power of different charging guns within a fixed time period is obtained based on the historical order data; including: Based on the order start time, order end time and charging power of each charging order, the average output power of each charging order of each charging gun is calculated by the following formula: Where: W in represents the charging capacity of the nth order of the i-th charging gun, t e Indicates the order end time of the nth order, t s represents the order start time of the nth order, P it Indicates the average output power of the i-th charging gun in the current order time period, which is equivalent to the average output power of the n-th order start time t s Until the order ends e Output power at each time point within Based on the average output power of each charging order of each charging gun, the total output power of the multiple charging guns at each time point is calculated by the following formula: Where t represents the current time point, N represents the total number of charging guns, and P it Indicates the output power of the i-th charging gun at the current time point t, which is equivalent to the average output power of the current time period; Based on the total output power of the multiple charging guns at each time point, the total time corresponding to the total output power of different charging guns in a fixed time period is obtained by the following formula: Among them, t m Indicates that the total output power of the charging gun within a fixed time period from t1 to t2 is P m The total time of .

4. The method according to claim 1, characterized in that: The method of obtaining the power consumption of the split electric vehicle DC charging pile in a fixed time period based on the power consumption data of the box-type transformer and the historical order data comprises: Based on the power consumption data of the box-type transformer, the power loss W of the split electric vehicle DC charging pile in a fixed time period is obtained by the following formula: loss : Among them: t1 and t2 represent the starting and ending positions of fixed time. According to the order statistical characteristics, a fixed time period can be selected to calculate the total power loss of the box-type transformer, W in It represents the charging capacity of the nth order of the i-th charging gun in the current time period, V represents the total number of charging guns in the current time period, and N represents the total number of orders in the current time period.

5. The method according to claim 1, characterized in that The power loss prediction model is expressed by the following formula: Among them, W loss Indicates power loss, M indicates the number of different charging guns with total output power, P m_loss It represents the power loss under different total output powers of the charging gun, which is the model parameter that needs to be fitted.

6. The method according to claim 5, characterized in that The constraints are expressed as follows: h(p)=P m_loss ≥0,m∈(0,M); The objective function is expressed as follows:

7. The method according to claim 6, characterized in that The method of solving the model parameters of the power loss prediction model based on the total time corresponding to the total output power of different charging guns in the fixed time period, the power loss of the split electric vehicle DC charging pile in the fixed time period, the constraint conditions and the objective function includes: The Lagrangian multiplier is introduced as the penalty term λ of the inequality h(p) constraint function, and the Lagrangian function is defined. The Lagrangian function is expressed as follows: L(p,λ)=f(p)+λ T h(p) Based on the Lagrangian function, the iterative update rule is determined as follows: in, The Jacobian matrix representing the constraint function of the inequality h(p); Based on the iterative update rule, the total time corresponding to the total output power of different charging guns in the fixed time period and the power loss of the split electric vehicle DC charging pile in the fixed time period, the objective function, the gradient, the constraint conditions and the Jacobian matrix thereof are iteratively calculated; until the iteration termination condition is met.

8. The method according to claim 7, characterized in that In the iterative calculation process, the correction direction Δp is calculated by Newton's method, and the iterative update is calculated by the following formula: α=min(1,r) r=max(β s ,r t ) p k+1 =p k +αΔp Among them, α represents the update step size, and s and t represent positive scaling factors.

9. The method according to claim 1, characterized in that: After obtaining the final power loss prediction model, include: The evaluation performance of the final power loss prediction model is judged by the determination coefficient, root mean square error and mean absolute error value.

10. A data-driven split-type electric vehicle DC charging pile energy consumption analysis device, the split-type electric vehicle DC charging pile includes a box-type transformer, a charging control box and a plurality of charging guns, characterized in that: The device comprises: A data acquisition module, used to acquire the power consumption data of the box-type transformer and the historical order data of each of the multiple charging guns; A parameter calculation module, used to obtain the total time corresponding to the total output power of different charging guns within a fixed time period based on the historical order data; The parameter calculation module is further used to obtain the power consumption of the split electric vehicle DC charging pile in a fixed time period based on the power consumption data of the box-type transformer and the historical order data; A model building module, for building a power loss prediction model for fitting the power loss of a box-type transformer under different total output powers of charging guns using a multivariate linear regression model, and building constraints and objective functions of the power loss prediction model; The model solving module is used to solve the model parameters of the power loss prediction model based on the total time corresponding to the total output power of different charging guns within the fixed time period, the power loss of the split electric vehicle DC charging pile in the fixed time period, the constraint conditions and the objective function, so as to obtain the final power loss prediction model; and to perform energy consumption analysis of the split electric vehicle DC charging pile through the final power loss prediction model.

Images