Electric vehicle ownership prediction method

Abstract

The invention provides an electric vehicle ownership prediction method, which comprises the following steps of: according to electric vehicle ownership historical data, fitting by using an exponential function to obtain an ownership historical function; determining an inventory prediction function by using the inventory historical function and the grey prediction model; and predicting the ownership of the electric vehicle by using the ownership prediction function. The invention further provides an electric vehicle inventory prediction device, electronic equipment and a storage medium. According to the method, the historical function of the ownership is utilized to participate in solving of the gray prediction model, so that the gray prediction model has higher prediction precision for prediction of the electric vehicle ownership growing at a high speed.

Description

Technical Field

[0001] The present disclosure relates to the technical field of automobile ownership prediction, and more specifically to a method for predicting the ownership of electric vehicles. Background Art

[0002] In recent years, with the implementation of relevant policies, the continuous improvement of industry maturity, the rapid decline in car purchase costs and the gradual deepening of environmental protection concepts, the purchase and ownership of new energy electric vehicles in my country have ushered in a golden period of rapid development. Relevant literature shows that the ownership of new energy electric vehicles in my country is growing exponentially.

[0003] When using the traditional grey prediction model to predict the rapidly growing number of electric vehicles, the model has certain defects. Relevant research literature has proved that the prediction accuracy of the GM (1,1) model is similar to the background value z (1) (k) is closely related. Since the gray model has a transition between discrete equations and continuous equations in the modeling process, it will cause errors in parameter estimation. Furthermore, when the gray system is a high-growth sequence, the relative error of the traditional gray model will increase significantly, so it is difficult to effectively model the high-growth sequence. In addition, due to the influence of raw material supply, price and user psychology, the annual number of new energy electric vehicles will show a certain degree of dispersion on the basis of expectations. The greater the degree of dispersion of the data, the greater the grayness of the system, making the prediction result less accurate. Therefore, it is necessary to reduce the prediction error and improve the prediction accuracy through error correction. Summary of the invention

[0004] In view of the above problems, the present disclosure provides a method for predicting the number of electric vehicles in use, which improves the prediction accuracy in the high-speed growth stage.

[0005] The present disclosure provides a method for predicting the number of electric vehicles in stock, comprising: obtaining a stock history function by using an exponential function to fit the historical data of the number of electric vehicles in stock; determining a stock prediction function by using the stock history function and a grey prediction model; and predicting the number of electric vehicles in stock by using the stock prediction function.

[0006] According to an embodiment of the present disclosure, using historical functions and a gray prediction model to determine a stock prediction function includes: using the stock historical function and geometric summation to determine a stock accumulation function; using the stock accumulation function to determine a whitening background value of the gray prediction model; using the whitening background value to determine a development coefficient and a gray action amount of the gray prediction model; using the development coefficient and the gray action amount to determine a stock prediction function.

[0007] According to an embodiment of the present disclosure, the whitening background value of the gray prediction model is determined by using the retention accumulation function, including: using the retention accumulation function to determine a first whitening background value expression and a second whitening background expression; using the first whitening background value expression and the second whitening background expression, determining an expression of a weight coefficient for determining the whitening background value;

[0008] Among them, the first whitened background value expression is as follows:

[0009]

[0010] In the formula, z (1) (k) represents the whitened background value; x (1) (t) represents the stock accumulation function; G and D represent the coefficients of the stock accumulation function; a represents the development coefficient; e represents a constant; k represents a time point; α represents a weight coefficient;

[0011] Among them, the second whitening background value expression is as follows:

[0012] z (1) (k) = αx (1) (k-1)+(1-α)x (1) (k)=

[0013] α[Ge -a(k-2) +D]+(1-α)[Ge -a(k-1) +D]=

[0014] Ge -a(k-2) [α(1-e -a )+e -a ]+D

[0015] In the formula, z (1) (k) represents the whitened background value; x (1) (k) represents the stock accumulation sequence; G and D represent the coefficients of the stock accumulation function; a represents the development coefficient; e represents a constant; k represents a time point; α represents a weight coefficient; the stock accumulation sequence is a sequence composed of the values ​​of the stock accumulation function at each time point;

[0016] The expression of the weight coefficient is as follows:

[0017]

[0018] In the formula, a is the development coefficient; e is a constant; α represents the weight coefficient.

[0019] According to an embodiment of the present disclosure, the development coefficient and the gray action of the gray prediction model are determined by using the whitened background value, including: using the whitened background value to determine the gray differential equation; using the least squares method to determine the development coefficient and the gray action of the gray differential equation; wherein the expression of the gray differential equation is as follows:

[0020] x (0) (k)+az (1) (k) = b

[0021] In the formula, a is the development coefficient; b is the gray action; z (1) (k) represents the whitened background value; x (0) (k) represents the inventory history sequence; the inventory history sequence is a sequence composed of the values ​​of the inventory history function at each time point.

[0022] According to an embodiment of the present disclosure, the development coefficient and the grey action of the grey differential equation are determined by the least square method, including: simplifying the grey differential equation, substituting the inventory accumulation sequence and the inventory history sequence into an equation group with the development coefficient and the grey action as unknowns; solving the equation group by the least square method to obtain the development coefficient and the grey action;

[0023] Among them, the equations with development coefficient and gray action as unknowns are as follows:

[0024]

[0025] In the formula, a is the development coefficient; b is the gray action; α is the weight coefficient; a * 、b * Indicates the intermediate quantity; x (0) (k) represents the historical sequence of holdings; x (1) (k) represents the cumulative sequence of inventory; the historical sequence of inventory is a sequence composed of the values ​​of the inventory history function at each time point.

[0026] According to an embodiment of the present disclosure, a vehicle ownership prediction function is determined using the development coefficient and the gray action, including: using the development coefficient and the gray action to determine a preliminary vehicle ownership prediction function; using the preliminary vehicle ownership prediction function to determine the predicted vehicle ownership at each time point in the historical data; using the predicted vehicle ownership and the historical data of electric vehicle ownership to determine the vehicle ownership residual function; using the vehicle ownership residual function to correct the preliminary vehicle ownership prediction function to obtain the final vehicle ownership prediction function.

[0027] According to an embodiment of the present disclosure, the predicted vehicle ownership and the historical data of the electric vehicle ownership are used to determine the residual function of the vehicle ownership, including: using the predicted vehicle ownership and the historical data of the electric vehicle ownership to confirm the actual sequence of residuals; using the actual sequence of residuals to confirm the actual function of residuals; using the geometric summation of the actual function of residuals to determine the residual accumulation function; using the residual accumulation function to determine the whitened background value of the gray prediction model of the residual; using the whitened background value to determine the development coefficient and gray action of the gray prediction model of the residual; using the development coefficient and gray action to determine the residual function of the vehicle ownership.

[0028] The second aspect of the present disclosure provides an electric vehicle ownership prediction device, which can be used to implement the above method, and the device includes: a historical data module, which is used to obtain an ownership history function using an exponential function according to the electric vehicle ownership history data; a prediction function module, which is used to determine the ownership prediction function using the ownership history function and a gray prediction model; and an ownership prediction module, which is used to predict the electric vehicle ownership using the ownership prediction function.

[0029] The third aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned electric vehicle ownership prediction method.

[0030] The fourth aspect of the present disclosure further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above-mentioned electric vehicle ownership prediction method.

[0031] According to the electric vehicle ownership prediction method provided by the present disclosure, the ownership prediction function is corrected by the ownership history function and the gray prediction model. Since the ownership history function reflects the characteristics of the exponential growth of the electric vehicle ownership, it at least partially solves the technical problem of inaccurate prediction of the electric vehicle ownership in the high-speed growth stage, and achieves the technical effect of improving the prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A flowchart of a method for predicting the number of electric vehicles in use according to an embodiment of the present disclosure is schematically shown;

[0033] Figure 2 A schematic diagram schematically shows the number of new energy vehicles in different years and their development trends according to an embodiment of the present disclosure;

[0034] Figure 3 A schematic diagram schematically shows a comparison of prediction results of various models according to an embodiment of the present disclosure;

[0035] Figure 4 The structure block diagram of the electric vehicle ownership prediction device according to the embodiment of the present disclosure is schematically shown;

[0036] Figure 5 A block diagram of an electronic device suitable for implementing a method for predicting the number of electric vehicles in use according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0037] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0038] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0039] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0040] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0041] First, the technical terms involved in this disclosure are explained as follows:

[0042] Traditional grey prediction model: The traditional grey prediction model is based on the following theories and steps. Assume that x(0) is a sequence of n elements, that is, x (0) =[x (0) (1),x (0) (2),...,x (0)(n)], and the accumulated generating sequence x(1) of the sequence is obtained through the accumulated generating operation (AGO), which can be expressed as: (1) =[x (1) (1),x (1) (2),...,x (1) (n)]. Each element in this sequence can be represented by the following formula:

[0043]

[0044] Then the grey derivative of x(1) is defined as d(k)=x (0) (k) = x (1) (k)-x (1) (k-1) In addition, the mean sequence of x(1) is defined as z(1), which can be expressed as: (1) =[z (1) (2),z (1) (3),...,z (1) (n)]. Each element in the mean series is defined by:

[0045] z (1) (k) = 0.5x (1) (k)+0.5x (1) (k-1)(k=2,3,...,n)

[0046] In summary, the grey differential equation model of the grey prediction model can be defined as:

[0047] d(k)+az (1) (k) = b

[0048] The above formula can be expressed according to the grey derivative as:

[0049] x (0) (k)+az (1) (k) = b

[0050] In the above formula, x (0) (k) is also called grey derivative, a is the development coefficient, z (1) (k) is called the whitening background value, and b is called the gray action. When k = 2, 3, ..., n, the gray differential equation model can be expressed in the form of the following system of equations:

[0051]

[0052] Then, using the least squares method, find Reaching the minimum

[0053]

[0054] in, It can be expressed as:

[0055]

[0056] Where B and Y1 are:

[0057]

[0058] Y1=[x (0) (2),x (0) (3),...,x (0) (n)] T

[0059] Corresponding to the grey differential equation, k = 2, 3, ..., n is regarded as a continuous variable t, and the white differential equation of the grey prediction model is obtained as follows:

[0060]

[0061] Solving the above equation, we get the predicted value of the k+1th variable:

[0062]

[0063] The above formula can be used to predict subsequent values ​​in the system.

[0064] In the traditional method, as shown in the whitening background value formula, when constructing the background value z (1) (k) When the adjacent elements in the sequence are assumed to be of equal weight, the traditional background value calculation formula means that x (1) (t) is the size of the equivalent trapezoidal area enclosed by the horizontal axis on [k-1, k]. For high-growth sequences, the area between the horizontal axis and the trapezoidal area is obviously not equal to the equivalent trapezoidal area. This is the main reason why the traditional grey model has a large prediction error for high-growth sequences.

[0065] According to relevant statistics, the number of new energy electric vehicles has increased exponentially in recent years. Figure 2 As shown in the figure, the cumulative generated series is obtained by using the electric vehicle ownership data from 2016 to 2023. After observation and parameter fitting, it is found that it increases exponentially. Therefore, the z shown in the traditional method is used. (1) (k) The calculation method will produce errors in the prediction results and the growth pattern of the actual number of electric vehicles.

[0066] Figure 1 The flowchart of the method for predicting the number of electric vehicles in use according to an embodiment of the present disclosure is schematically shown. Figure 1As shown, an embodiment of the present disclosure provides a method for predicting the number of electric vehicles in stock, comprising: obtaining a stock history function by fitting an exponential function based on historical data of the number of electric vehicles in stock; determining a stock prediction function by using the stock history function and a grey prediction model; and predicting the number of electric vehicles in stock by using the stock prediction function.

[0067] Through the embodiments of the present disclosure, when the growth rate of the ownership sequence is high, such as exponential growth, the prediction result deviates greatly from the actual result; by fitting historical data, a function that can reflect the historical change trend of electric vehicle ownership is obtained, which can better simulate data with exponential growth or attenuation characteristics, and the prediction function obtained by combining this function is more accurate.

[0068] On the basis of the above embodiments, the historical function and the gray prediction model are used to determine the inventory prediction function, including: using the inventory historical function and geometric summation to determine the inventory accumulation function; using the inventory accumulation function to determine the whitening background value of the gray prediction model; using the whitening background value to determine the development coefficient and gray action of the gray prediction model; using the development coefficient and gray action to determine the inventory prediction function.

[0069] Through the embodiments of the present disclosure, the ownership prediction function and the ownership history function are used to better fit the rapidly growing changes in the number of electric vehicles, thereby obtaining a whitening background value that is more in line with the rapid growth, and further confirming the ownership prediction function.

[0070] On the basis of the above embodiment, the whitening background value of the grey prediction model is determined by using the accumulation function of the holding amount, including: using the accumulation function of the holding amount to determine the first whitening background value expression and the second whitening background expression; using the first whitening background value expression and the second whitening background expression, determining the expression of the weight coefficient for determining the whitening background value;

[0071] Among them, the first whitened background value expression is as follows:

[0072]

[0073] In the formula, z (1) (k) represents the whitened background value; x (1) (t) represents the stock accumulation function; G and D represent the coefficients of the stock accumulation function; a represents the development coefficient; e represents a constant; k represents a time point; α represents a weight coefficient;

[0074] Among them, the second whitening background value expression is as follows:

[0075] z (1) (k) = αx (1) (k-1)+(1-α)x (1) (k)=

[0076] α[Ge -a(k-2) +D]+(1-α)[Ge -a(k-1) +D]=

[0077] Ge -a(k-2) [α(1-e -a )+e -a ]+D

[0078] In the formula, z (1) (k) represents the whitened background value; x (1) (k) represents the stock accumulation sequence; G and D represent the coefficients of the stock accumulation function; a represents the development coefficient; e represents a constant; k represents a time point; α represents a weight coefficient; the stock accumulation sequence is a sequence composed of the values ​​of the stock accumulation function at each time point;

[0079] The expression of the weight coefficient is as follows:

[0080]

[0081] In the formula, a is the development coefficient; e is a constant; α represents the weight coefficient.

[0082] Through the embodiments of the present disclosure, the whitening background value is an important parameter in the gray prediction model, which is used to describe the background information of the system; by combining the inventory accumulation function, a more accurate weight coefficient can be determined (so that higher inventory historical data occupies a higher weight) to obtain a more accurate whitening background value and improve the prediction accuracy. In addition, in the traditional prediction method, its form is an exponential distribution, and the meaning can be understood as using the exponential distribution function to fit and accumulate the generated series. However, the actual series also needs to consider the impact of the prediction error. The present disclosure analyzes the law of the annual prediction error based on the objective data law, so as to predict the value of the future prediction error.

[0083] On the basis of the above embodiment, the development coefficient and the gray action of the gray prediction model are determined by using the whitened background value, including: using the whitened background value to determine the gray differential equation; using the least square method to determine the development coefficient and the gray action of the gray differential equation; wherein the expression of the gray differential equation is as follows:

[0084] x (0) (k)+az (1) (k) = b

[0085] In the formula, a is the development coefficient; b is the gray action; z (1) (k) represents the whitened background value; x (0) (k) represents the inventory history sequence; the inventory history sequence is a sequence composed of the values ​​of the inventory history function at each time point.

[0086] Through the embodiments of the present disclosure, the development coefficient and the gray action are key parameters in the gray prediction model, which are used to describe the dynamic characteristics of the system. By calculating these two parameters with more accurate whitening background values, we can have a deeper understanding of the changing trend of the number of electric vehicles, providing strong support for the prediction.

[0087] On the basis of the above embodiment, the development coefficient and the grey action of the grey differential equation are determined by the least square method, including: simplifying the grey differential equation, substituting the inventory accumulation sequence and the inventory history sequence into an equation group with the development coefficient and the grey action as unknowns; solving the equation group by the least square method to obtain the development coefficient and the grey action;

[0088] Among them, the equations with development coefficient and gray action as unknowns are as follows:

[0089]

[0090] In the formula, a is the development coefficient; b is the gray action; α is the weight coefficient; a * 、b * Indicates the intermediate quantity; x (0) (k) represents the historical sequence of holdings; x (1) (k) represents the cumulative sequence of inventory; the historical sequence of inventory is a sequence composed of the values ​​of the inventory history function at each time point.

[0091] In this embodiment, therefore, by improving z (1) The calculation method of (k) can be derived to form the calculation method of the present disclosure, which is specifically:

[0092] Pair The two ends are integrated over the interval [k-1,k]:

[0093]

[0094] Simplifying, we get:

[0095]

[0096] Compared with traditional (0) (k)+az (1) (k) = b and the above formula shows:

[0097]

[0098] Then, from the integral mean value theorem, we know that there exists a constant α such that:

[0099] z (1) (k) = αx (1) (k-1)+(1-α)x (1)(k)(α∈[0,1])

[0100] If the original sequence of the original grey system conforms to the homogeneous exponential form x (0) (k) = g -a(k-1) , then its cumulative generation sequence x (1) It can be expressed as a non-homogeneous exponential form x (1) (k) = Ge -a(k-1) +D, then:

[0101]

[0102] In addition, by z (1) Another expression of is:

[0103] z (1) (k) = αx (1) (k-1)+(1-α)x (1) (k)=

[0104] α[Ge -a(k-2) +D]+(1-α)[Ge -a(k-1) +D]=

[0105] Ge -a(k-2) [α(1-e -a )+e -a ]+D

[0106] Lianliz (1) Simplifying the two expressions of , we can see:

[0107]

[0108] Then x can be (0) (k)+az (1) The grey differential equation shown in (k)=b becomes the following form:

[0109] x (0) (k)+az (1) (k) = x (0) (k)+a[αx (1) (k-1)+(1-α)x (1) (k)]=b

[0110] The above formula can be further simplified to:

[0111]

[0112] Expand the above formula into a system of equations:

[0113]

[0114] Then the least squares solution that satisfies the minimum model error can be obtained:

[0115]

[0116] But it is different from the traditional gray model:

[0117]

[0118] Y1=[x (0) (1),x (0) (2),...,x (0) (n)] T

[0119] Finally, we obtain:

[0120]

[0121] Bring it back The improved prediction results can be obtained.

[0122] According to the embodiments of the present disclosure, the least square method is an optimization method for solving unknowns in a system of equations. By using the least square method, the optimal solution of the development coefficient and the gray action can be obtained, thereby improving the accuracy and stability of the prediction.

[0123] On the basis of the above embodiment, the development coefficient and the gray action are used to determine the vehicle ownership prediction function, including: using the development coefficient and the gray action to determine the preliminary vehicle ownership prediction function; using the preliminary vehicle ownership prediction function to determine the predicted vehicle ownership at each time point in the historical data; using the predicted vehicle ownership and the historical data of electric vehicle ownership to determine the vehicle ownership residual function; using the vehicle ownership residual function to correct the preliminary vehicle ownership prediction function to obtain the final vehicle ownership prediction function.

[0124] Through the embodiments of the present disclosure, due to the influence of accidental factors such as policies, raw material supply, prices and user psychology, the actual number of electric vehicles will be somewhat discrete from the predicted value on the basis of expectations. The conventional gray prediction model cannot handle this accidental error, resulting in inaccurate prediction results. By comparing the predicted number of vehicles with historical data, the residual is obtained, and a residual function is generated to correct the prediction function. The introduction of the residual function can further improve the accuracy of the prediction and make the prediction results more in line with the actual situation.

[0125] On the basis of the above embodiments, the predicted ownership and the historical data of the electric vehicle ownership are used to determine the residual function of the ownership, including: using the predicted ownership and the historical data of the electric vehicle ownership to confirm the actual sequence of residuals; using the actual sequence of residuals to confirm the actual function of residuals; using the geometric summation of the actual function of residuals to determine the residual accumulation function; using the residual accumulation function to determine the whitening background value of the gray prediction model of the residual; using the whitening background value to determine the development coefficient and gray action of the gray prediction model of the residual; using the development coefficient and gray action to determine the residual function of the ownership.

[0126] Through the embodiments of the present disclosure, the inventory residual function can be predicted by the same method as the inventory prediction function, thereby making the prediction of the inventory residual more accurate.

[0127] Based on the above embodiment, the process of obtaining the electric vehicle ownership prediction function is as follows:

[0128] (1) Input the historical data of electric vehicle ownership. The ownership data is a sequence of the actual number of electric vehicles corresponding to each time point in the same interval of n groups (n ≥ 4), recorded as:

[0129] x (0) =[x (0) (1),x (0) (2),...,x (0) (n)]

[0130] In the formula, x (0) (n) represents the number of electric vehicles at the nth time point.

[0131] (2) Use the following formula to estimate the inventory at the kth time point:

[0132]

[0133] In the formula, represents the estimated value of electric vehicle ownership at the kth time point, Represents the estimated value of the cumulative generated sequence at the kth time point, where:

[0134]

[0135] Where a is the corrected development coefficient, and b is the corrected gray action.

[0136] (3) The calculation method of the corrected development coefficient a and the corrected gray action b is:

[0137]

[0138] In the formula They are the estimated coefficients obtained by the least squares method to satisfy the following equation with the minimum error.

[0139]

[0140] The least squares solution to this equation is calculated as:

[0141]

[0142] in:

[0143]

[0144] Y1 * =[x (0) (1),x (0) (2),...,x (0) (n)] T

[0145] (4) Using the method of steps (1)-(3), the estimated number of electric vehicles corresponding to the first n time points is obtained:

[0146]

[0147] The actual number of electric vehicles in use is subtracted from the predicted number of electric vehicles in use to obtain the residual e corresponding to the kth time point. (0) (k):

[0148]

[0149] And form the residual sequence e (0) =[e (0) (1),e (0) (2),...,e (0) (n)]

[0150] The residual sequence e (0) Considered as x in step (1) (0) , and use steps (1)-(3) to obtain the estimated value of the residual sequence:

[0151]

[0152] In the formula Generate a sequence of estimates for the accumulation of residual sequences:

[0153]

[0154] (5) Finally, the predicted value of electric vehicle ownership at the kth time point is obtained The expression is:

[0155]

[0156] On the basis of the above embodiments, the electric vehicle ownership prediction method disclosed in the present invention is used as the basis for the annual ownership data of new energy electric vehicles in my country to predict and analyze the ownership in 2024 and 2025.

[0157] Table 1 and Figure 2 Actual statistical data on the number of new energy electric vehicles in my country from 2016 to 2023

[0158] Table 1 Changes in the number of new energy vehicles in my country

[0159]

[0160] From Table 1 and Figure 2 It can be seen that the number of new energy vehicles in my country is increasing exponentially, and the method disclosed in this disclosure can be used to obtain a * and b * for:

[0161]

[0162] Then the corrected development coefficient a and ash action amount b are obtained as estimated values:

[0163]

[0164] Further, we can get:

[0165]

[0166] After cumulative reduction, the predicted series is:

[0167]

[0168] Then the residual of electric vehicle ownership in each year is shown in Table 2:

[0169] Table 2 Estimation and residual of electric vehicle ownership in my country

[0170]

[0171] After obtaining the grey system residual, the residual sequence is regarded as x (0) Sequence, using the steps of solving the inventory prediction function to solve the residual prediction function to estimate the residual value of each year, the results are shown in Table 3:

[0172] Table 3 Prediction values ​​of residual sequence based on background error minimization

[0173]

[0174] Finally, the corrected annual new energy electric vehicle ownership is shown in Table 4. In order to reflect the accuracy of the method proposed in this paper, the traditional grey prediction model GM (1, 1) is represented as model 1, and the grey prediction model after the traditional residual correction is represented as model 2. The above model and the model proposed in this paper obtain the prediction calculation results of the annual new energy electric vehicle ownership as shown in Table 4, and the corresponding Figure 3 The comparison chart of prediction results of each model is shown.

[0175] Table 4 Comparison of prediction results of different models for annual car ownership

[0176]

[0177] In order to quantitatively judge the accuracy of model prediction, this paper selects the root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) as the evaluation criteria for the fitting effect. The smaller the three indicators are, the better. When the indicator is 0, it means that the predicted value is completely consistent with the true value.

[0178] After calculation, the RMSE, MAE and MAPE corresponding to the three models are shown in Table 5.

[0179] Table 5 Comparison of prediction accuracy results of each model

[0180]

[0181] The model proposed in the present invention is much smaller than the traditional GM (1, 1) model represented by model 1 and the traditional residual corrected GM (1, 1) model represented by model 2 in terms of indicators such as root mean square error RMSE, mean absolute error MAE, mean absolute percentage error MAPE and posterior error. The posterior error obtained by the improved model in the present invention is 0.0595, which is 60.46% and 49.48% less than that of model 1 and model 2, respectively. The accuracy is significantly improved, so better fitting and prediction results can be obtained.

[0182] Based on the above electric vehicle ownership prediction method, the present disclosure also provides an electric vehicle ownership prediction device. Figure 4 The device is described in detail.

[0183] like Figure 4 As shown, the electric vehicle ownership prediction device of this embodiment includes a historical data module, a prediction function module and an ownership prediction module.

[0184] The historical data module is used to obtain the historical function of the number of electric vehicles by fitting the historical data of the number of electric vehicles using an exponential function. In one embodiment, the historical data module can be used to perform the operation S1 described above, which will not be described in detail here.

[0185] The prediction function module is used to determine the vehicle inventory prediction function by using the vehicle inventory history function and the grey prediction model. In one embodiment, the prediction function module can be used to perform the operation S2 described above, which will not be described in detail here.

[0186] The vehicle inventory prediction module is used to predict the vehicle inventory of electric vehicles using the vehicle inventory prediction function. In one embodiment, the vehicle inventory prediction module can be used to perform the operation S3 described above, which will not be described in detail here.

[0187] Figure 5 A block diagram of an electronic device suitable for implementing a method for predicting the number of electric vehicles in use according to an embodiment of the present disclosure is schematically shown.

[0188] like Figure 5 As shown, the electronic device 500 according to an embodiment of the present disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include an onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0189] In RAM 503, various programs and data required for the operation of electronic device 500 are stored. Processor 501, ROM 502 and RAM 503 are connected to each other via bus 504. Processor 501 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 502 and / or RAM 503. It should be noted that the program can also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0190] According to an embodiment of the present disclosure, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to the bus 504. The electronic device 500 may further include one or more of the following components connected to the I / O interface 505: an input portion 506 including a keyboard, a mouse, etc.; an output portion 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 508 including a hard disk, etc.; and a communication portion 509 including a network interface card such as a LAN card, a modem, etc. The communication portion 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage portion 508 as needed.

[0191] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0192] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiment of the present disclosure.

[0193] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0194] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0195] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0196] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for predicting the number of electric vehicles, characterized in that: include: According to the historical data of electric vehicle ownership, the historical function of ownership is obtained by using exponential function fitting; Determine a vehicle inventory prediction function by using the vehicle inventory history function and the grey prediction model; The electric vehicle ownership prediction function is used to predict the electric vehicle ownership.

2. The method according to claim 1, wherein: Determining the inventory prediction function by using the historical function and the grey prediction model includes: Determine the inventory accumulation function by using the inventory history function and geometric sum; Determine the whitening background value of the grey prediction model by using the stock accumulation function; Determine the development coefficient and grey action amount of the grey prediction model by using the whitened background value; The stock prediction function is determined by using the development coefficient and the grey action amount.

3. The method according to claim 2, wherein: Using the inventory accumulation function, determining the whitening background value of the grey prediction model includes: Determine a first whitened background value expression and a second whitened background expression by using the inventory accumulation function; Using the first whitened background value expression and the second whitened background expression, determine an expression of a weight coefficient for determining the whitened background value; Wherein, the first whitened background value expression is as follows: In the formula, z (1) (k) represents the whitened background value; x (1) (t) represents the stock accumulation function; G and D represent the coefficients of the stock accumulation function; a represents the development coefficient; e represents a constant; k represents a time point; α represents a weight coefficient; Wherein, the second whitened background value expression is as follows: z (1) (k)=αx (1) (k-1)+(1-α)x (1) (k)= α[Ge -a(k-2) +D]+(1-α)[Ge -a(k-1) +D]= If -a(k-2) [α(1-e -a )+e -a ]+D In the formula, z (1) (k) represents the whitened background value; x (1) (k) represents the inventory accumulation sequence; G and D represent the coefficients of the inventory accumulation function; α is the development coefficient; e is a constant; k represents a time point; α represents a weight coefficient; the inventory accumulation sequence is a sequence composed of the values ​​of the inventory accumulation function at each time point; The expression of the weight coefficient is as follows: In the formula, α is the development coefficient; e is a constant; α represents the weight coefficient.

4. The method according to claim 2, wherein: The step of using the whitened background value to determine the development coefficient and the gray action amount of the gray prediction model includes: Determining a grey differential equation using the whitened background value; Determining the development coefficient and grey action of the grey differential equation by using the least square method; The grey differential equation is expressed as follows: x (0) (k)+az (1) (k)=b In the formula, a is the development coefficient; b is the gray action; z (1) (k) represents the whitened background value; x (0) (k) represents the inventory history sequence; the inventory history sequence is a sequence composed of the values ​​of the inventory history function at each time point.

5. The method according to claim 4, wherein: The method of using the least square method to determine the development coefficient and the grey action of the grey differential equation includes: Simplify the grey differential equation, substitute it into the stock accumulation sequence and the stock history sequence to obtain the equation system with the development coefficient and the grey action as unknown variables; Solving the equations by the least square method to obtain the development coefficient and the grey action; The equation group with the development coefficient and the gray action as unknowns is as follows: In the formula, a is the development coefficient; b is the gray action; α is the weight coefficient; a * 、b * Indicates the intermediate quantity; x (0) (k) represents the historical sequence of holdings; x (1) (k) represents the cumulative sequence of inventory; the inventory history sequence is a sequence composed of the values ​​of the inventory history function at each time point.

6. The method according to claim 2, wherein: The method of using the development coefficient and the gray action amount to determine the inventory prediction function includes: Determine a preliminary stock prediction function by using the development coefficient and the gray action amount; Determine the predicted inventory at each time point in the historical data by using the preliminary inventory prediction function; Determine a residual function of electric vehicle ownership by using the predicted ownership and the historical data of electric vehicle ownership; The preliminary vehicle inventory prediction function is corrected using the vehicle inventory residual function to obtain a final vehicle inventory prediction function.

7. The method according to claim 6, wherein: The method of using the predicted number of vehicles in stock and the historical data of the number of electric vehicles in stock to determine the number of vehicles in stock residual function comprises: Using the predicted number of vehicles in stock and the historical data of the number of electric vehicles in stock, confirming the actual sequence of residuals; Using the actual sequence of residuals, confirm the actual function of residuals; Determine the residual accumulation function by geometrically summing the residual actual function; Determine the whitening background value of the residual grey prediction model by using the residual accumulation function; Determine the development coefficient and grey action amount of the grey prediction model of the residual using the whitened background value; The residual function of the stock is determined by using the development coefficient and the grey action.

8. An electric vehicle ownership prediction device, characterized in that: The device can be used to implement the method according to any one of claims 1 to 7, and the device comprises: A historical data module is used to obtain a historical function of electric vehicle ownership by fitting an exponential function based on the historical data of electric vehicle ownership; A prediction function module, used to determine a vehicle inventory prediction function using the vehicle inventory history function and a grey prediction model; The vehicle ownership prediction module is used to predict the vehicle ownership using the vehicle ownership prediction function.

9. An electronic device, comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 7.

Images