Electric vehicle ownership and penetration prediction method based on logistic growth model

Abstract

The application relates to a kind of electric vehicle stock and possession rate prediction method based on Logistic growth model, which comprises the following steps: based on the historical data of the obtained automobile and electric vehicle stock, Logistic growth model of automobile stock and electric vehicle stock is respectively constructed; the parameters of the aforementioned model are respectively fitted, to obtain the initial model of automobile stock and the initial model of electric vehicle stock; the parameters of the initial model of automobile stock and the initial model of electric vehicle stock are optimized, to obtain the optimized prediction model of automobile stock and the optimized prediction model of electric vehicle stock; input the year to be predicted, to obtain the prediction value of automobile stock and electric vehicle stock, and to obtain the possession rate of electric vehicle. The application effectively reduces the complexity of the electric vehicle stock and possession rate prediction method, and provides a data basis for the planning and construction of charging infrastructure, power grid and transportation network, which has practical significance.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle ownership prediction technology, and in particular to a method for predicting electric vehicle ownership and market share based on a Logistic growth model. Background Technology

[0002] In recent years, China's electric vehicle industry has developed rapidly, with its ownership continuously increasing. As a replacement for traditional fuel vehicles, electric vehicles are characterized by low carbon emissions, environmental friendliness, energy conservation, and economy, making them an effective way to address energy supply and demand imbalances and environmental pollution. Data from the Traffic Management Bureau of the Ministry of Public Security shows that as of June 2023, my country's electric vehicle ownership reached 16.2 million vehicles. In the first half of 2023, 3.128 million new electric vehicles were registered, a year-on-year increase of 41.6%, setting a new record. New electric vehicle registrations accounted for 26.6% of all new vehicle registrations, achieving the goal set in the "New Energy Vehicle Industry Development Plan (2021-2035)" that "by 2025, new energy vehicle sales will reach approximately 20% of total new vehicle sales."

[0003] Electric vehicles (EVs), as a crucial link between the energy and transportation systems, will have a significant impact on my country's charging infrastructure and power distribution network. First, the continuous and rapid growth in EV ownership places stringent demands on charging infrastructure construction. The number of charging stations built in various scenarios, including urban areas, intercity areas, rural areas, and highways, is highly correlated with the total number of EVs and their proportion of the total vehicle fleet. Second, as a new type of electricity load, EV charging load is influenced by user charging habits, exhibiting both clustered and random spatial and temporal distribution patterns, significantly impacting the safe and stable operation of the power system and the expansion of power distribution network investment. Simultaneously, EVs, as a means of transportation, also affect urban traffic conditions. When the proportion of EVs on the road increases to a certain level, road congestion will become related to EV travel behavior. Therefore, forecasting the number of vehicles and EVs is of great significance for the planning and construction of charging infrastructure, power grids, and transportation networks.

[0004] Current electric vehicle (EV) ownership prediction technologies suffer from complex model building processes and challenging parameter fitting, making it difficult to obtain prediction results quickly and conveniently. Most existing technologies predict EV ownership by collecting historical data, building a prediction model, and outputting the prediction results, with the main difference lying in the model building process. Some technologies use iterative methods to output EV ownership predictions annually, but iterative methods may lead to non-convergence of error propagation, limiting their applicability to short-term predictions. Other technologies employ composite prediction models, integrating multiple prediction methods to correct the results. However, these methods involve complex model building processes, requiring users to be proficient in the principles of various methods, and parameter fitting is challenging, making it difficult to obtain reliable prediction results quickly. Summary of the Invention

[0005] Therefore, the technical problem to be solved by the present invention is to overcome the problems of complex model construction process, difficult parameter fitting, and difficulty in obtaining prediction results quickly and conveniently in the prior art. By constructing a prediction model based on the Logistic growth model, the parameters to be fitted are controllable, and open source and convenient functions are used to fit the parameters. Under the premise of ensuring prediction accuracy, the fitting process is faster and more efficient, which can provide convenient electric vehicle prediction results for engineering technicians.

[0006] To address the aforementioned technical problems, this invention provides a method for predicting the number and market share of electric vehicles based on a Logistic growth model, comprising the following steps:

[0007] S1: Obtain historical data on the number of cars and electric vehicles in use;

[0008] S2: Based on the historical data, construct a Logistic growth model for car ownership and a Logistic growth model for electric vehicle ownership, respectively.

[0009] S3: Fit the parameters of the Logistic growth model of the car ownership and the Logistic growth model of the electric vehicle ownership respectively to obtain the initial model of the car ownership and the initial model of the electric vehicle ownership;

[0010] S4: Optimize the parameters of the initial model of the vehicle ownership and the initial model of the electric vehicle ownership to obtain the optimized prediction model of the vehicle ownership and the prediction model of the electric vehicle ownership.

[0011] S5: Based on the optimized prediction model for vehicle ownership and electric vehicle ownership, input the year to be predicted for the future time period to obtain the predicted values ​​for vehicle ownership and electric vehicle ownership. Based on the predicted values ​​for vehicle ownership and electric vehicle ownership, obtain the occupancy rate of electric vehicles.

[0012] In one embodiment of the present invention, the specific method for constructing the Logistic growth model of car ownership and the Logistic growth model of electric vehicle ownership is as follows:

[0013] Based on the collected data on car ownership V over the past n years t =[v t-n+1 …,v t-1 ,v t [and past m years' electric vehicle ownership data EV] t =[ev t-m+1 …,ev t-1 ,ev t ] as input, where v t and ev t Let be the number of cars and electric vehicles in year t, respectively. The expressions for the Logistic growth models for the car ownership and electric vehicle ownership are both:

[0014]

[0015] Where t represents time, N t Let N be the number of cars or electric vehicles in year t; K is the number of cars or electric vehicles when t approaches infinity. t The limit value; N0 is the value of N when t = 0. t The initial value is r; the growth rate is r.

[0016] In one embodiment of the present invention, in S3, the method for obtaining the initial model of car ownership and the initial model of electric vehicle ownership is as follows: taking the Logistic growth model of car ownership and the Logistic growth model of electric vehicle ownership, the historical data sampling time of cars and electric vehicles and the ownership at the corresponding time as inputs, respectively, the fitting function is used to obtain the fitting parameters, and then the initial model of car ownership and the initial model of electric vehicle ownership are obtained.

[0017] In one embodiment of the present invention, S4, the method for obtaining the optimized prediction model for vehicle ownership and the prediction model for electric vehicle ownership specifically includes:

[0018] Based on the predicted population p and the predicted car ownership saturation value v of the region ∞ The predicted saturation value of car ownership per thousand people was calculated.

[0019] The predicted saturation value of car ownership per thousand people is compared with the expert analysis results of car ownership per thousand people in the predicted region: if the predicted saturation value of car ownership per thousand people is greater than the expert analysis results of car ownership per thousand people in the predicted region, the parameters N0 or r are lowered, and all parameters of the initial model of car ownership and the initial model of electric vehicle ownership are fitted; otherwise, the parameters N0 or r are increased, and all parameters of the initial model of car ownership and the initial model of electric vehicle ownership are fitted until v perk With v perk_exp The error is within the specified range.

[0020] In one embodiment of the present invention, the predicted result v of the saturation value of car ownership per thousand people perk The calculation method is as follows:

[0021]

[0022] Among them, v t This represents the number of cars in year t, and the saturation value of the predicted number of cars.

[0023] In one embodiment of the present invention, a fitting function is used to fit all parameters of the initial model of the vehicle ownership and the initial model of the electric vehicle ownership.

[0024] In one embodiment of the present invention, the occupancy rate p of the electric vehicle evt The calculation method is as follows:

[0025]

[0026] Among them, ev t v is the predicted value for the number of electric vehicles. t This is a predicted value for the number of cars in use.

[0027] Based on the same inventive concept, this invention also provides a system for predicting the number and market share of electric vehicles based on a Logistic growth model, comprising:

[0028] The data acquisition module is used to acquire historical data on the number of cars and electric vehicles in use.

[0029] The vehicle ownership prediction model construction module is used to construct a Logistic growth model for vehicle ownership and a Logistic growth model for electric vehicle ownership based on the historical data.

[0030] The model parameter fitting module is used to fit the parameters of the Logistic growth model of the car ownership and the Logistic growth model of the electric vehicle ownership, respectively, to obtain the initial model of the car ownership and the initial model of the electric vehicle ownership.

[0031] The prediction model optimization module is used to optimize the parameters of the initial model of the vehicle ownership and the initial model of the electric vehicle ownership, so as to obtain the optimized prediction model of the vehicle ownership and the prediction model of the electric vehicle ownership.

[0032] The prediction result output module is used to input the year to be predicted in the future time period according to the optimized prediction model of car ownership and the prediction model of electric vehicle ownership, obtain the predicted value of car ownership and the predicted value of electric vehicle ownership, and obtain the occupancy rate of electric vehicles based on the predicted value of car ownership and the predicted value of electric vehicle ownership.

[0033] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement instructions for the electric vehicle ownership and occupancy prediction method based on the Logistic growth model as described in any one of the claims.

[0034] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any of the methods for predicting the number and market share of electric vehicles based on the Logistic growth model.

[0035] The technical solution of the present invention has the following advantages compared with the prior art:

[0036] This invention predicts the number and market share of electric vehicles based on a Logistic growth model. The number of fitting parameters is controllable, and open-source functions are used to fit the parameters, which simplifies the construction process of the prediction model. At the same time, the fitting process is faster and more efficient while ensuring prediction accuracy. The parameter optimization process is flexible and convenient, effectively reducing the complexity of the method for predicting the number and market share of electric vehicles. In addition, this invention provides a data foundation for the planning and construction of charging infrastructure, power grid, and transportation network by predicting the number of electric vehicles, which has practical significance. Attached Figure Description

[0037] To make the content of this invention easier to understand, the invention will be further described in detail below with reference to specific embodiments and accompanying drawings, wherein...

[0038] Figure 1This is a flowchart illustrating the implementation of the method for predicting the number and market share of electric vehicles based on the Logistic growth model described in this invention.

[0039] Figure 2 In this embodiment of the invention, the predicted years are 2023 to 2060. By adjusting the parameters, the predicted car ownership results with different growth rates and saturation values ​​can be obtained.

[0040] Figure 3 In this embodiment of the invention, the predicted years are 2023 to 2060. By adjusting the parameters, the predicted electric vehicle ownership results with different growth rates and saturation values ​​can be obtained.

[0041] Figure 4 This is a comparison of the predicted car ownership and electric vehicle ownership results in this embodiment of the invention;

[0042] Figure 5 This is the result of electric vehicle occupancy rate in an embodiment of the present invention. Detailed Implementation

[0043] The present invention will be further described below with reference to the accompanying drawings and specific embodiments, so that those skilled in the art can better understand and implement the present invention. However, the embodiments described are not intended to limit the present invention.

[0044] Example 1

[0045] Reference Figure 1 As shown, this invention provides a method for predicting the number and market share of electric vehicles based on a Logistic growth model, comprising the following steps:

[0046] S1: Obtain historical data on the number of cars and electric vehicles in use;

[0047] S2: Based on the historical data, construct a Logistic growth model for car ownership and a Logistic growth model for electric vehicle ownership, respectively.

[0048] S3: Fit the parameters of the Logistic growth model of the car ownership and the Logistic growth model of the electric vehicle ownership respectively to obtain the initial model of the car ownership and the initial model of the electric vehicle ownership;

[0049] S4: Optimize the parameters of the initial model of the vehicle ownership and the initial model of the electric vehicle ownership using the vehicle ownership per thousand people method to obtain the optimized prediction model of the vehicle ownership and the prediction model of the electric vehicle ownership.

[0050] S5: Based on the optimized prediction model for vehicle ownership and electric vehicle ownership, input the year to be predicted for the future time period to obtain the predicted values ​​for vehicle ownership and electric vehicle ownership. Based on the predicted values ​​for vehicle ownership and electric vehicle ownership, obtain the occupancy rate of electric vehicles.

[0051] From the above technical solutions, it can be seen that the present invention makes full use of the inherent laws of the acquired historical data, constructs a prediction model based on the Logistic growth model, the parameters to be fitted are controllable, and multiple methods are used to fit the parameters. The number of parameters to be fitted is small. Compared with the existing vehicle ownership prediction model, the parameter fitting is less difficult, and the parameters to be fitted are controllable, so the prediction results can be obtained quickly.

[0052] In step S2, the specific methods for constructing the Logistic growth model for car ownership and the Logistic growth model for electric vehicle ownership are as follows:

[0053] Based on the collected data on car ownership V over the past n years t =[v t-n+1 …,v t-1 ,v t [and past m years' electric vehicle ownership data EV] t =[ev t-m+1 …,ev t-1 ,ev t ] as input, where v t and ev t Let be the number of cars and electric vehicles in year t, respectively. The expressions for the Logistic growth models for the car ownership and electric vehicle ownership are both:

[0054]

[0055] Where t represents time, N t Let N be the number of cars or electric vehicles in year t; K is the number of cars or electric vehicles when t approaches infinity. t The limit value; N0 is the value of N when t = 0. t The initial value is r; the growth rate is r.

[0056] In this embodiment, the method for obtaining the initial model of car ownership and the initial model of electric vehicle ownership in step S3 is as follows:

[0057] Using the Logistic growth models for both vehicle and electric vehicle ownership, historical data sampling times for both vehicles and electric vehicles, and the ownership figures at corresponding times as inputs, fitting functions are employed to obtain fitting parameters, thereby generating initial models for both vehicle and electric vehicle ownership. Specifically, the fitting function includes, but is not limited to, the nonlinear least squares method.

[0058] In this embodiment, step S4, the method for obtaining the optimized prediction model for vehicle ownership and the prediction model for electric vehicle ownership specifically includes:

[0059] Based on the predicted population p and the predicted car ownership saturation value v of the region ∞ The predicted saturation value of car ownership per thousand people was calculated.

[0060] The predicted saturation value of car ownership per thousand people is compared with the expert analysis results of car ownership per thousand people in the predicted region: if the predicted saturation value of car ownership per thousand people is greater than the expert analysis results of car ownership per thousand people in the predicted region, the parameter N0 or r is lowered, and all parameters of the initial model of car ownership and the initial model of electric vehicle ownership are fitted using a fitting function; otherwise, the parameter N0 or r is increased, and all parameters of the initial model of car ownership and the initial model of electric vehicle ownership are fitted using a fitting function until v perk With v perk_exp The error is within the specified range.

[0061] Among them, the predicted result of the saturation value of car ownership per thousand people v perk The calculation method is as follows:

[0062]

[0063] Among them, v t This represents the number of cars in year t, and the saturation value of the predicted car ownership.

[0064] In this embodiment, the occupancy rate p of the electric vehicles evt The calculation method is as follows:

[0065]

[0066] Among them, ev t v is the predicted value for the number of electric vehicles. t This is a predicted value for the number of cars in use.

[0067] The beneficial effects of the present invention will be further illustrated below with specific examples. Taking Jiangsu Province as the region to be predicted, the number of cars in Jiangsu Province (V) over the past 20 years, from 2003 to 2022, was collected through statistical yearbooks or industry reports. t = [131.77,161.19,231.11,277.60,330.09,373.09,458.06,567.71,688.38,813.12,954.38,1103.98,1247.86,1434.52,1619.46,1783.23,1919.22,2044.40,2179.40,2309.69] 10,000 vehicles and the data on the number of electric vehicles in Jiangsu Province over the past four years, from 2019 to 2022. t = [20.10, 22.73, 50.51, 99.10] ten thousand vehicles.

[0068] Based on historical data, two Logistic growth models were constructed: one for vehicle ownership and one for electric vehicle ownership. The expression for the Logistic growth model is as follows:

[0069]

[0070] Where t represents time, N t Let N be the number of cars or electric vehicles in year t; K is the number of cars or electric vehicles when t approaches infinity. t The limit value; N0 is the value of N when t = 0. t The initial value is denoted by , and r is the growth rate. In this step, the parameters K, N0, and r of both models are variables to be determined.

[0071] The `curve_fit` function in Python is used to fit the parameters of the Logistic growth model for automobiles and the Logistic growth model for electric vehicles, respectively, and outputs two sets of K, N0, and r. The `curve_fit` function is an open-source function in Python that can be directly called. Its inputs are the Logistic growth model expression, the historical data sampling time, and the corresponding vehicle ownership data at that time; the outputs are the fitted values ​​of the three parameters K, N0, and r.

[0072] Using the fitted parameters as deterministic parameters in the Logistic growth model, and inputting the years to be predicted as 2023–2060, we obtain the predicted value v of car ownership. 2023 ,v 2024 ,…v 2060 Electric vehicle ownership forecast (ev) 2023 ,ev 2024 …,ev 2060 .

[0073] The prediction model was validated and its fitting parameters were optimized using the per capita car ownership method. First, the predicted regional population p (in thousands) and the saturation value v of the predicted car ownership were compared. ∞ Calculate the predicted saturation value of car ownership per thousand people v perk Then, the results were analyzed by experts on the number of cars per thousand people in the region. perk_exp Compare. If v perk >v perk_exp You can appropriately lower the parameters N0 or r, and then call the curve_fit function again to fit all parameters; if v perk <v perk_exp You can appropriately increase the parameters N0 or r, and then call the curve_fit function again to fit all parameters until v perk With v perk_exp The deviation is small. The data selected in this step is as follows: Jiangsu Province currently has a resident population of 85.15 million, with approximately 271 cars per 1,000 people. The future saturation point for car ownership per 1,000 people is expected to be 400-450 cars per 1,000 people; therefore, v is selected. perk_exp ∈[400,450].

[0074] Using the optimized parameters as deterministic parameters for the Logistic growth model, and inputting the years to be predicted as 2023–2060, the predicted value of car ownership, v, is obtained. 2023 ,v 2024 ,…v 2060 Electric vehicle ownership forecast (ev) 2023 ,ev 2024 …,ev 2060 The prediction results are as follows Figures 2-5 As shown. By Figures 4-5 It is evident that the rapid growth of electric vehicles is quickly approaching the total number of automobiles, and the market share of electric vehicles has stabilized after a rapid increase. This indicates that the present invention is applicable to the long-term prediction of electric vehicle ownership, laying the foundation for subsequent load forecasting and grid connection research.

[0075] Example 2

[0076] Based on the same inventive concept as the prediction method described in Embodiment 1, the present invention also provides a prediction system for electric vehicle ownership and market share based on the Logistic growth model, comprising the following modules:

[0077] The data acquisition module is used to acquire historical data on the number of cars and electric vehicles in use.

[0078] The vehicle ownership prediction model construction module is used to construct a Logistic growth model for vehicle ownership and a Logistic growth model for electric vehicle ownership based on the historical data.

[0079] The model parameter fitting module is used to fit the parameters of the Logistic growth model of the car ownership and the Logistic growth model of the electric vehicle ownership, respectively, to obtain the initial model of the car ownership and the initial model of the electric vehicle ownership.

[0080] The prediction model optimization module is used to optimize the parameters of the initial model of the vehicle ownership and the initial model of the electric vehicle ownership, so as to obtain the optimized prediction model of the vehicle ownership and the prediction model of the electric vehicle ownership.

[0081] The prediction result output module is used to input the year to be predicted in the future time period according to the optimized prediction model of car ownership and the prediction model of electric vehicle ownership, obtain the predicted value of car ownership and the predicted value of electric vehicle ownership, and obtain the occupancy rate of electric vehicles based on the predicted value of car ownership and the predicted value of electric vehicle ownership.

[0082] Example 3

[0083] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements instructions for the electric vehicle ownership and occupancy prediction method based on the Logistic growth model as described in any of the embodiments.

[0084] Example 4

[0085] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for predicting the number and occupancy of electric vehicles based on the Logistic growth model as described in any one of Embodiments 1.

[0086] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0088] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0089] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0090] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A method for predicting the number and market share of electric vehicles based on a Logistic growth model, characterized in that, Includes the following steps: S1: Obtain historical data on the number of cars and electric vehicles in use; S2: Based on the historical data, construct a Logistic growth model for car ownership and a Logistic growth model for electric vehicle ownership, respectively. The specific methods for constructing the Logistic growth model for car ownership and the Logistic growth model for electric vehicle ownership are as follows: Based on the collected past n Annual car ownership V t =[ v t-n+1 …, v t-1 , v t and the past m Annual electric vehicle ownership data EV t =[ ev t-m+1 …,ev t-1 ,ev t ] as input, where v t and ev t The first t The expressions for constructing the Logistic growth models for both annual car ownership and electric vehicle ownership are: ； in, t Indicates time, For the first t The number of cars or electric vehicles per year; K For when t When approaching infinity The limit value; for t =0 The initial value; r For growth rate; S3: Fit the parameters of the Logistic growth model of the car ownership and the Logistic growth model of the electric vehicle ownership respectively to obtain the initial model of the car ownership and the initial model of the electric vehicle ownership; In S3, the method for obtaining the initial model of car ownership and the initial model of electric vehicle ownership is as follows: taking the Logistic growth model of car ownership and the Logistic growth model of electric vehicle ownership, the historical data sampling time of cars and electric vehicles and the ownership at the corresponding time as inputs, respectively, the fitting function is used to obtain the fitting parameters, and then the initial model of car ownership and the initial model of electric vehicle ownership are obtained. S4: Optimize the parameters of the initial model of the vehicle ownership and the initial model of the electric vehicle ownership to obtain the optimized prediction model of the vehicle ownership and the prediction model of the electric vehicle ownership. In S4, the methods for obtaining the optimized prediction models for vehicle ownership and electric vehicle ownership specifically include: Based on the predicted population of the region p Saturation value of car ownership prediction results The predicted saturation value of car ownership per thousand people was calculated. Compare the predicted saturation value of car ownership per thousand people with the expert analysis results of car ownership per thousand people in the predicted area: if the predicted saturation value of car ownership per thousand people is greater than the expert analysis results of car ownership per thousand people in the predicted area, lower the parameter. N 0 or r Then, fit all parameters of the initial model for the number of cars and the initial model for the number of electric vehicles; otherwise, increase the parameters. N 0 or r Fit all parameters of the initial model for the number of cars and the initial model for the number of electric vehicles until... v perk and v perk_exp The error is within the specified range; S5: Based on the optimized prediction model for vehicle ownership and electric vehicle ownership, input the year to be predicted for the future time period to obtain the predicted values ​​for vehicle ownership and electric vehicle ownership. Based on the predicted values ​​for vehicle ownership and electric vehicle ownership, obtain the occupancy rate of electric vehicles.

2. The method for predicting the number and market share of electric vehicles based on the Logistic growth model according to claim 1, characterized in that: The predicted saturation value of car ownership per thousand people The calculation method is as follows: ； in, Indicates the first t Annual vehicle ownership, and the saturation value of vehicle ownership prediction results. .

3. The method for predicting the number and market share of electric vehicles based on the Logistic growth model according to claim 1, characterized in that: All parameters of the initial model of the vehicle ownership and the initial model of the electric vehicle ownership are fitted using a fitting function.

4. The method for predicting the number and market share of electric vehicles based on the Logistic growth model according to claim 1, characterized in that: The market share of electric vehicles The calculation method is as follows: ； in, This is a predicted value for the number of electric vehicles. This is a predicted value for the number of cars in use.

5. A system for predicting the number and market share of electric vehicles based on a Logistic growth model, used to implement the method for predicting the number and market share of electric vehicles based on a Logistic growth model as described in any one of claims 1 to 4, characterized in that, include: The data acquisition module is used to acquire historical data on the number of cars and electric vehicles in use. The vehicle ownership prediction model construction module is used to construct a Logistic growth model for vehicle ownership and a Logistic growth model for electric vehicle ownership based on the historical data. The model parameter fitting module is used to fit the parameters of the Logistic growth model of the car ownership and the Logistic growth model of the electric vehicle ownership, respectively, to obtain the initial model of the car ownership and the initial model of the electric vehicle ownership. The prediction model optimization module is used to optimize the parameters of the initial model of the vehicle ownership and the initial model of the electric vehicle ownership, so as to obtain the optimized prediction model of the vehicle ownership and the prediction model of the electric vehicle ownership. The prediction result output module is used to input the year to be predicted in the future time period according to the optimized prediction model of car ownership and the prediction model of electric vehicle ownership, obtain the predicted value of car ownership and the predicted value of electric vehicle ownership, and obtain the occupancy rate of electric vehicles based on the predicted value of car ownership and the predicted value of electric vehicle ownership.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the instructions for the method of predicting the number and market share of electric vehicles based on the Logistic growth model as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for predicting the number and market share of electric vehicles based on the Logistic growth model as described in any one of claims 1 to 4.

Images