A method for classifying electric vehicle vehicle scale prediction

Abstract

The application relates to the technical field of vehicle scale prediction, and discloses a type-divided electric vehicle scale prediction method. The method comprises the following steps: obtaining the quantity of vehicles of multiple use types in a target area in a future period; obtaining the increment proportion of first-type and second-type power type vehicles in each type of vehicle; predicting the newly added quantity of each type of vehicle based on the quantity and a corresponding scrapping curve; combining the newly added quantity and the increment proportion to determine the newly added quantity of the two types of power type vehicles; rolling calculating the dynamic quantity of the two types of vehicles based on the newly added quantity and respective scrapping curves; and predicting the scale of electric vehicles participating in vehicle-grid interaction based on the quantity of the two types of vehicles and in combination with vehicle-grid interaction adaptation rules. The application realizes full-link dynamic prediction from macro traffic data to vehicle-grid interaction available resources, significantly improves prediction accuracy and engineering practicability, and supports precise layout of power grid dispatching and charging infrastructure.

Description

Technical Field

[0001] This invention relates to the field of vehicle size prediction, and more specifically, to a method for predicting the size of electric vehicles by type. Background Technology

[0002] With the widespread adoption of electric vehicles, effectively integrating them as distributed energy storage resources to participate in vehicle-to-grid (V2G) interaction has become a crucial issue for energy systems. Scientifically predicting the scale of electric vehicles that can participate in V2G interaction is a prerequisite for formulating grid dispatch strategies and constructing supporting infrastructure.

[0003] Current methods are often oversimplified, lacking integration of multi-dimensional factors and dynamic lifecycle considerations, resulting in insufficient prediction accuracy and limited practicality. They cannot effectively support the strategic needs of vehicle-to-grid (V2G) interaction, and specifically have the following shortcomings:

[0004] First, the model is oversimplified and ignores the differences in market segments: Current technology often uses a uniform model to predict the scale of electric vehicles, without fully considering the characteristics of different market segments such as private cars, ride-hailing vehicles, public transportation, and logistics vehicles (such as usage frequency and charging behavior), which leads to the prediction results being out of sync with the actual resource distribution.

[0005] Second, the factors are not fully considered and the superposition of multiple effects is ignored: Traditional methods for predicting the penetration rate of electric vehicles often rely on a single factor (such as policy subsidies) while ignoring the interactive effects of multiple driving factors such as user acceptance, charging convenience, and safety perception, making the prediction lack a realistic basis.

[0006] Third, the framework lacks integration and dynamic linkage is insufficient: current technology fails to systematically link vehicle ownership, sales, scrapping rate with technology penetration rate and vehicle-to-grid interaction capability in modeling, resulting in static and isolated prediction results that cannot reflect the dynamic evolution of resources over time, affecting the operability of power grid planning.

[0007] There is currently no effective solution to the above problems. Summary of the Invention

[0008] This invention provides a method for predicting the scale of electric vehicles by type, which at least solves the technical problems of current electric vehicle scale prediction methods that ignore vehicle model differences, single-factor penetration rate modeling, and static prediction.

[0009] According to one aspect of the present invention, a method for predicting the scale of electric vehicles is provided, comprising: obtaining the number of vehicles of various usage types in a target area within a preset future period, wherein the number of vehicles in the target area represents the actual number of vehicles in use; obtaining the incremental proportion of a first power type vehicle and the incremental proportion of a second power type vehicle for each type of vehicle in the target area within the preset future period; predicting the new number of vehicles of various usage types based on the number of vehicles in use and the vehicle scrapping curves for each type of vehicle; and determining the number of vehicles of various usage types based on the new number of vehicles of various usage types, the incremental proportion of the first power type vehicle for each type of vehicle, and the incremental proportion of the second power type vehicle for each type of vehicle. The system calculates the new incremental number of vehicles of the first power type corresponding to each vehicle type and the new incremental number of vehicles of the second power type corresponding to each vehicle type. Based on the new incremental number of vehicles of the first power type and the new incremental number of vehicles of the second power type corresponding to each vehicle type, and combined with the vehicle scrapping curves of the first and second power types, the system determines the number of vehicles of the first power type and the number of vehicles of the second power type corresponding to each vehicle type. Based on the number of vehicles of the first power type and the number of vehicles of the second power type corresponding to each vehicle type, and combined with the vehicle-to-grid interaction adaptation rules, the system predicts the scale of electric vehicles participating in vehicle-to-grid interaction.

[0010] Optionally, the following steps are taken to obtain the number of vehicles of various usage types in the target area within a preset future period: obtaining historical population data, historical GDP data, and the number of vehicles per unit for various usage types in the target area within a preset historical period; performing trend extrapolation on the historical population data to predict the population size of the target area within the preset future period; performing regression fitting on the historical GDP data to predict the GDP of the target area within the preset future period; and calculating the number of vehicles of various usage types based on the number of vehicles per unit, the population size, and the GDP of the target area within the preset future period.

[0011] Optionally, the incremental proportions of vehicles of the first power type and the second power type for various usage types in the target area within a preset future period are obtained. This includes: obtaining policy subsidy intensity data, charging facility coverage data, user charging satisfaction survey data, electric vehicle safety perception index, supply-side conversion rate data, and user scenario preference weight data for the target area; for each usage type of vehicle, the policy subsidy intensity data and charging facility coverage data are normalized to construct an initial value for policy-based penetration rate; for each usage type of vehicle, the user charging satisfaction survey data, electric vehicle safety perception index, supply-side conversion rate data, and user scenario preference weight data are weighted and fused to construct an initial value for market-based penetration rate; for each usage type of vehicle, the initial value for policy-based penetration rate and the initial value for market-based penetration rate are non-linearly coupled and calculated to generate the incremental proportions of vehicles of the first power type and the second power type.

[0012] Optionally, based on the respective stock of vehicles of various usage types and their respective scrapping curves, the new stock of vehicles of various usage types is predicted, including: performing differential processing on the stock of vehicles of various usage types to calculate the change in stock of vehicles of various usage types; determining the scrapping and replacement volume of vehicles of various usage types based on the vehicle scrapping curves; and adding the change in stock of vehicles of various usage types to the scrapping and replacement volume of vehicles of various usage types to obtain the new stock of vehicles of various usage types.

[0013] Optionally, based on the new additions of vehicles of the first power type corresponding to each of the various usage types and the new additions of vehicles of the second power type corresponding to each of the various usage types, and combined with the vehicle scrapping curves of the first and second power types, the total number of vehicles of the first power type corresponding to each of the various usage types and the total number of vehicles of the second power type corresponding to each of the various usage types are determined. This includes: establishing a time series of new additions for each usage type and each power type of vehicle; determining the number of vehicles still within their effective lifespan within a preset historical period for each usage type and each power type of vehicle based on the vehicle scrapping curve; and obtaining the total number of vehicles of the first power type corresponding to each of the various usage types and the total number of vehicles of the second power type corresponding to each of the various usage types of vehicles by rolling and accumulating the number of vehicles still within their effective lifespan within a preset historical period, combined with the time series of new additions for each usage type and each power type of vehicle.

[0014] Optionally, based on the number of vehicles of the first power type corresponding to each of the various usage types and the number of vehicles of the second power type corresponding to each of the various usage types, and in conjunction with the vehicle-to-grid (V2G) interaction adaptation rules, the scale of electric vehicles participating in V2G interaction is predicted. This includes: constructing a V2G interaction compatibility coefficient matrix, wherein the characteristics of the V2G interaction compatibility coefficient matrix include vehicle model compatibility, charging interface type, communication protocol support, battery health threshold, and user authorization willingness weight; for each usage type and each power type of vehicle, based on the V2G interaction compatibility coefficient matrix, determining target vehicles that meet the following requirements: communication protocol support, bidirectional charging capability, battery health higher than the battery health threshold, and user authorization willingness weight higher than a preset weight threshold; for each usage type and each power type of vehicle, determining the effective scale of participating in V2G interaction based on the number of target vehicles; and summing the effective scales of participating in V2G interaction for each usage type and each power type of vehicle to obtain the scale of electric vehicles participating in V2G interaction.

[0015] According to another aspect of the embodiments of this application, an electric vehicle scale prediction device is also provided, comprising: an acquisition module, configured to acquire the number of vehicles of various usage types in use within a preset period and the incremental ratio of vehicles of various usage types in use within a preset period, wherein the number of vehicles in use represents the actual number of vehicles in use; a first prediction module, configured to predict the new number of vehicles of various usage types in use based on the number of vehicles in use for each type and in combination with the vehicle scrapping curves of vehicles of various usage types in use; and a first determination module, configured to determine the new increment of vehicles of the first power type in use for each type of vehicle and the incremental ratio of vehicles of various usage types in use based on the new increment of vehicles of various usage types and the incremental ratio of vehicles of various usage types in use. The second determination module is used to determine the number of vehicles of the first power type and the number of vehicles of the second power type corresponding to each of the various usage types, based on the new incremental number of vehicles of the first power type and the new incremental number of vehicles of the second power type corresponding to each of the various usage types, combined with the vehicle scrapping curves of the first power type and the second power type, respectively; the second prediction module is used to predict the scale of electric vehicles participating in vehicle-to-grid interaction based on the number of vehicles of the first power type and the number of vehicles of the second power type corresponding to each of the various usage types, combined with the adaptation rules of vehicle-to-grid interaction.

[0016] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is running, the device where the non-volatile storage medium is located is controlled to execute any of the above-described vehicle size prediction methods.

[0017] According to another aspect of the embodiments of this application, a computer device is also provided, the computer device including a processor, the processor being configured to run a program, wherein the program executes any of the vehicle size prediction methods described above when it runs.

[0018] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements any of the vehicle size prediction methods described above.

[0019] The vehicle scale prediction method and apparatus provided in this application obtain the number of vehicles of various usage types in a target area in the future period; obtain the incremental ratio of the first and second power types of vehicles in each type; predict the new addition of each type of vehicle based on the number of vehicles and the corresponding scrapping curve; determine the new addition of the two power types of vehicles by combining the new addition and the incremental ratio; calculate the dynamic number of the two types of vehicles based on the new addition and their respective scrapping curves; and predict the scale of electric vehicles participating in vehicle-grid interaction based on the number of the two types of vehicles and the vehicle-grid interaction adaptation rules. This achieves the accuracy of vehicle scale prediction, provides high-precision and multi-dimensional data support for power grid dispatch and infrastructure layout, and solves the technical problems of current electric vehicle scale prediction methods that ignore vehicle model differences, single-factor penetration rate modeling, and static prediction. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0021] Figure 1 A hardware block diagram of a computer terminal for implementing a vehicle size prediction method is shown.

[0022] Figure 2 This is a flowchart illustrating the vehicle size prediction method provided according to an embodiment of the present invention;

[0023] Figure 3 This is a block diagram of a vehicle scale prediction function for predicting the total amount and structure of electric vehicle resources participating in vehicle-network interaction, provided by an optional embodiment of the present invention.

[0024] Figure 4 This is a schematic diagram of a vehicle size prediction module for electric vehicle ownership prediction in various market segments according to an optional embodiment of the present invention;

[0025] Figure 5 This is a schematic diagram of an electric vehicle penetration rate prediction module for various market segments based on a vehicle size prediction according to an optional embodiment of the present invention;

[0026] Figure 6 This is a schematic diagram of a vehicle scale prediction module for electric vehicle sales and ownership prediction in various market segments according to an optional embodiment of the present invention.

[0027] Figure 7 This is a schematic diagram of a module for predicting the total number of electric vehicles participating in vehicle-to-grid interaction in various market segments, according to an optional embodiment of the present invention.

[0028] Figure 8 This is a structural block diagram of a vehicle size prediction device provided according to an embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] According to an embodiment of the present invention, a method for predicting the size of electric vehicles by type is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a vehicle size prediction method is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0033] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0034] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the vehicle size prediction method in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the vehicle size prediction method of the aforementioned application. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0035] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0036] Figure 2 This is a flowchart illustrating the vehicle size prediction method provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the method includes the following steps:

[0037] Step S201: Obtain the number of vehicles of various usage types in the target area within a preset future period, where the number of vehicles represents the actual number of vehicles in use.

[0038] In this step, the number of vehicles of various usage types in the target area within a preset future period is obtained. These various usage types include private passenger cars, taxis and ride-hailing vehicles, buses, light logistics vehicles, medium and heavy trucks, etc. The number of vehicles refers to the total number of vehicles registered with the public security traffic management system and in actual use, which serves as the initial stock benchmark for subsequent predictions.

[0039] Step S202: Obtain the incremental proportion of the first power type vehicles and the incremental proportion of the second power type vehicles for each of the various usage types of vehicles in the target area within a preset future period.

[0040] Based on the vehicle ownership figures obtained in step S201 Figure 5 This is a schematic diagram of an electric vehicle penetration rate prediction module for various market segments based on an optional embodiment of the present invention, such as... Figure 5 As shown, in this step, the incremental ratio of the first type of power type vehicles (pure electric vehicles, BEV) to the second type of power type vehicles (plug-in hybrid electric vehicles, PHEV) within this period is obtained. This incremental ratio, i.e., the sales penetration rate, is calculated by policy factors, such as the intensity of subsidy policies and the coverage of charging piles; and market factors, such as user charging satisfaction, safety perception, usage scenario preferences, and conversion rate, through a nonlinear coupling model of the two, reflecting the real market's acceptance structure of new energy vehicle models.

[0041] Step S203: Based on the number of vehicles of various usage types and their respective scrapping curves, predict the new number of vehicles of various usage types.

[0042] Based on the vehicle inventory obtained in step S201, and combined with the vehicle scrapping curves corresponding to various usage types of vehicles, Figure 6 This is a schematic diagram of a module for predicting electric vehicle sales and ownership in various market segments according to an optional embodiment of the present invention, such as... Figure 6As shown, in this step, the annual increase in the number of vehicles of various types is predicted. This increase is equal to the total annual sales volume caused by the natural scrapping and replacement demand of vehicles. The calculation process combines the vehicle scrapping curves corresponding to various types of vehicles. These curves are mathematical distribution models (such as the Weibull function) that describe the probability of being phased out year by year during their life cycle, ensuring that the increase prediction conforms to the actual vehicle replacement pattern.

[0043] Step S204: Based on the new additions corresponding to each of the various usage types of vehicles, the incremental ratio of the first power type vehicles corresponding to each of the various usage types of vehicles, and the incremental ratio of the second power type vehicles corresponding to each of the various usage types of vehicles, determine the new increments of the first power type vehicles corresponding to each of the various usage types of vehicles and the new increments of the second power type vehicles corresponding to each of the various usage types of vehicles.

[0044] Based on the new increments of various types of vehicles obtained in step S203, and the increment ratio of the first power type vehicles to the second power type vehicles obtained in step S202, this step determines the new increments of the two power type vehicles in each type of vehicle. The new increments are the sales volume of the vehicles. Through structural ratio splitting, the total new increments are allocated to the two power type vehicles according to the penetration rate, realizing a refined decomposition from the macro total quantity to the power structure.

[0045] Step S205: Based on the new increase of the first type of power type vehicles corresponding to each of the various usage types of vehicles and the new increase of the second type of power type vehicles corresponding to each of the various usage types of vehicles, and combined with the vehicle scrapping curves of the first type of power type vehicles and the second type of power type vehicles respectively, determine the number of first type of power type vehicles corresponding to each of the various usage types of vehicles and the number of second type of power type vehicles corresponding to each of the various usage types of vehicles.

[0046] Based on the new additions of the first and second power types of vehicles obtained in step S204, this step calculates their dynamic inventory. That is, by introducing the independent vehicle scrapping curves of the first and second power types of vehicles, and considering the significant differences in battery life, technology iteration speed and fuel vehicle speed between them, a rolling accumulation method is adopted to cumulatively add up the vehicles that are still in the effective life cycle among the newly added vehicles in each year, forming an annually updated inventory sequence of the first and second power types of vehicles, realizing a dynamic closed loop of the entire life cycle from sales to inventory.

[0047] Step S206: Based on the number of vehicles of the first power type corresponding to each of the various usage types and the number of vehicles of the second power type corresponding to each of the various usage types, and in combination with the vehicle-to-grid interaction adaptation rules, predict the scale of electric vehicles participating in vehicle-to-grid interaction.

[0048] Based on the number of vehicles of the first power type and the dynamic number of vehicles of the second power type obtained in step S205, Figure 7 This is a schematic diagram of a module for predicting the total number of electric vehicles participating in vehicle-to-grid interaction in various market segments, as provided in an optional embodiment of the present invention. Figure 7 As shown, in this step, the scale of electric vehicles participating in vehicle-to-grid (V2G) interaction is predicted. This prediction is based on the V2G interaction adaptation rules, which include four hard judgment conditions: whether the vehicle supports bidirectional charging hardware, communication protocol compatibility, battery health (SOH) status, and whether the user actively authorizes participation in grid interaction. Only when all conditions are met is the vehicle recognized as a schedulable V2G resource. Finally, the total scale of electric vehicles that can participate in grid interaction is accumulated.

[0049] This application provides a vehicle scale prediction method and apparatus, which obtains the number of vehicles of various usage types in a target area in the future period; obtains the incremental ratio of the first and second power types of vehicles in each type; predicts the new addition of each type of vehicle based on the number of vehicles in stock and the corresponding scrapping curve; determines the new addition of the two power types of vehicles by combining the new addition and the incremental ratio; calculates the dynamic number of the two types of vehicles based on the new addition and their respective scrapping curves; and predicts the scale of electric vehicles participating in vehicle-grid interaction based on the number of the two types of vehicles in stock and combined with vehicle-grid interaction adaptation rules. This method breaks through the simplification limitations of traditional prediction methods and provides high-precision, multi-dimensional data support for power grid dispatching and infrastructure layout.

[0050] As an optional embodiment, step S201 can be implemented according to the following steps: obtaining the number of vehicles of various usage types in the target area within a preset future period, including:

[0051] S2011, obtain historical population data, historical GDP data, and unit ownership of vehicles of various usage types for the target area within a preset historical period;

[0052] S2012 extrapolates historical population data to predict the population size of a target area within a preset future period.

[0053] S2013, performs regression fitting on historical GDP data to predict the GDP of the target region in a preset future period;

[0054] S2014. Based on the unit ownership of vehicles of various usage types, the population size of the target area in the preset future period, and the GDP of the target area in the preset future period, calculate the ownership of vehicles of various usage types respectively.

[0055] In this step, for example, Figure 4 This is a schematic diagram of a vehicle size prediction module for electric vehicle ownership prediction in various market segments according to an optional embodiment of the present invention, such as... Figure 4 As shown, this submodule mainly reads basic parameters such as relevant population data and GDP data, and uses a logistic prediction model to calculate the vehicle size prediction data for each segment of the commercial vehicle and passenger vehicle markets, and provides data for subsequent sales segmentation calculations.

[0056] First, three basic data points were collected for the target area over a pre-defined historical period: historical population data, sourced from the public security household registration system or local statistical yearbooks, reflecting the total resident population of the region; historical gross domestic product (GDP) data, taken from the annual economic report of the local statistical bureau, characterizing the level of regional economic development; and the unit ownership of various types of vehicles, i.e., statistical correlation coefficients, including: the "ownership per thousand people" (vehicles / thousand people) of private passenger cars, i.e., the number of private cars owned per thousand people; the "ownership per unit GDP" (vehicles / 100 million yuan of GDP) of commercial vehicles (taxi and ride-hailing vehicles, company vehicles, light logistics vehicles, and medium and heavy trucks), reflecting the driving effect of economic scale on commercial vehicles; buses were calculated using the "bus route density × average number of vehicles per route" model, combined with urban public transport planning data; other passenger vehicles (such as tourist buses) were estimated based on "tourist trips × vehicle occupancy rate per trip". All of the above unit ownership figures were obtained through historical data regression analysis, possessing regional specificity and stability.

[0057] Secondly, based on the aforementioned historical data, trend predictions are made. Historical population data are extrapolated using a Logistic growth model, taking into account constraints such as urbanization saturation, population aging, and migration policies to avoid overestimation risks from linear extrapolation, and outputting annual population prediction curves for the next 5–15 years. For historical gross domestic product (GDP) data, a grey prediction model GM(1,1) or multiple linear regression method is used, incorporating regulatory variables such as new energy industry policies and transportation structure transformation to construct regional economic evolution trend equations, ensuring that the prediction results are consistent with the direction of national energy strategy.

[0058] Finally, this method substitutes the predicted population and GDP data into the unit ownership model corresponding to each vehicle type to calculate the static ownership benchmark value of each type of vehicle in future years, such as... Figure 5 As shown in the diagram, the annual sales volume of different car types and the ownership of various types of electric vehicles directly correspond to the following nodes:

[0059] Private passenger vehicle ownership = Projected population × Ownership per thousand people;

[0060] Taxi / Ride-hailing vehicles / Company vehicles = Forecasted GDP × Unit GDP ownership × Urban travel intensity correction factor (reflecting ride-hailing penetration rate).

[0061] Light logistics vehicle = Forecasted GDP × Number of logistics vehicles per unit of GDP × E-commerce penetration rate adjustment factor;

[0062] Medium and heavy-duty trucks = Forecasted GDP × Number of freight vehicles per unit of GDP × Industrial freight intensity coefficient;

[0063] Buses = Total number of bus routes × Average number of buses per route;

[0064] Other passenger vehicles = predicted number of tourists × vehicle occupancy rate per trip.

[0065] The output results are time-series data of the static ownership of seven types of vehicles in each future year, laying the foundation for subsequent dynamic ownership calculations.

[0066] As an optional embodiment, step S202 can be implemented according to the following steps: obtaining the incremental proportion of the first power type vehicles and the incremental proportion of the second power type vehicles corresponding to various usage types of vehicles in the target area within a preset future period, including:

[0067] S2021, obtain data on policy subsidy intensity, charging facility coverage, user charging satisfaction survey, electric vehicle safety perception index, supply-side conversion rate, and user scenario preference weighting in the target area;

[0068] S2022, for each type of vehicle, the data on policy subsidy intensity and charging facility coverage are normalized to construct an initial value for policy-based penetration rate;

[0069] S2023: For each type of vehicle, the user charging satisfaction survey data, electric vehicle safety perception index, supply-side conversion rate data, and user scenario preference weight data are weighted and integrated to construct an initial value for market penetration rate.

[0070] S2024, for each type of vehicle, the initial value of policy-based penetration rate and the initial value of market-based penetration rate are non-linearly coupled to calculate the incremental ratio of the first type of power type vehicles and the incremental ratio of the second type of power type vehicles.

[0071] In steps S2021 to S2024, such as Figure 5 As shown, this submodule mainly reads the basic parameters required by the penetration rate prediction module, and calculates the sales penetration rate prediction data for each power type in each market segment based on the constructed multi-factor funnel model that considers policy factors, market factors, etc., and provides data for subsequent sales segmentation calculations.

[0072] First, multi-dimensional driving data is collected through the electric vehicle penetration rate prediction module in each market segment, including: policy subsidy intensity data, such as the amount of purchase subsidies provided by local governments for pure electric vehicles / plug-in hybrid electric vehicles and the coverage of purchase tax exemption policies; charging facility coverage data, including the density of public fast charging piles, the coverage of fixed charging piles in residential areas, and the coverage of charging stations in highway service areas; user charging satisfaction survey data, derived from questionnaires or platform feedback, covering indicators such as charging waiting time, charging pile availability, and payment convenience; electric vehicle safety perception index, based on public opinion analysis and accident statistics, quantifying the public's level of concern about battery spontaneous combustion, high-voltage safety, and recycling risks; supply-side conversion rate data, referring to the sales conversion rate of car dealers recommending pure electric vehicles / plug-in hybrid electric vehicles, reflecting the market's willingness to promote supply; and user scenario preference weight data, a preference scoring system constructed for different models, quantified through factor analysis.

[0073] Secondly, for each type of vehicle, an initial value for policy-based penetration rate is constructed: the policy subsidy intensity and charging facility coverage rate are normalized using Min-Max to make them fall within the [0,1] range, eliminating the difference in dimensions; the initial value of policy-based penetration rate is calculated by weighted sum: initial value of policy-based penetration rate = α × normalized subsidy intensity + β × normalized charging coverage rate, where α + β = 1, and the weights are set according to the regional policy priority, such as α = 0.7 for cities with purchase restrictions and β = 0.6 for cities without purchase restrictions.

[0074] Next, an initial value for market penetration rate is constructed: four indicators—user charging satisfaction, perceived safety index, supply-side conversion rate, and user scenario preference—are standardized using Z-scores, and weighted by expert scoring or the Analytic Hierarchy Process (AHP). The initial market penetration rate is calculated using a weighted fusion model: Initial value for market penetration rate = γ1 × Satisfaction + γ2 × Perceived Safety + γ3 × Conversion Rate + γ4 × Scenario Preference, where γ1~γ4>0, and ∑γ i =1, and for high-frequency usage scenarios such as ride-hailing.

[0075] Finally, the initial values ​​of policy-driven penetration rate and market-driven penetration rate are nonlinearly coupled to generate the final incremental ratio of the first type of vehicle (BEV) and the second type of vehicle (PHEV). A sigmoid function or a double-threshold logic gate model is used to achieve nonlinear superposition, simulating the real evolutionary pattern of initial policy-driven explosive growth followed by market-driven stabilization. Separate models are provided for BEV and PHEV:

[0076] BEV incremental ratio = f(policy-driven, market-driven) × (1 - PHEV preference correction factor);

[0077] PHEV incremental ratio = f(policy-driven, market-driven) × PHEV preference adjustment factor;

[0078] Among them, the PHEV preference correction factor is dynamically adjusted according to the weakness of regional charging infrastructure, and the output result is the incremental ratio of BEV and PHEV for each type of vehicle in each future year.

[0079] As an optional embodiment, step S203 can be implemented according to the following steps: based on the respective stock of vehicles of various usage types, and combined with the respective vehicle scrapping curves of vehicles of various usage types, predict the respective new stock of vehicles of various usage types, including:

[0080] S2031, perform differential processing on the number of vehicles corresponding to various usage types, and calculate the change in the number of vehicles corresponding to various usage types.

[0081] S2032, combined with the vehicle scrapping curve, determines the corresponding scrapping and replacement quantity for vehicles of various usage types;

[0082] S2033, add the change in the number of vehicles of each usage type to the scrapping and replacement of vehicles of each usage type to obtain the new number of vehicles of each usage type.

[0083] In steps S2031 to S2033, such as Figure 6 As shown, this submodule mainly reads the sales penetration rate forecast data and the ownership forecast data of each power type of vehicle in each market segment obtained by the above submodules, and combines the scrapping data to calculate the sales forecast data of each market segment and power type of commercial vehicles and passenger vehicles respectively, and provides a calculation basis for the subsequent vehicle-to-everything (V2X) interaction scale.

[0084] First, the annual vehicle ownership sequence output in step S201 is processed by first-order difference to calculate the change in ownership for each year: Change in ownership = current ownership - previous ownership. This value reflects the net increase in the number of vehicles without considering scrapping, but it does not yet distinguish between new purchases and replacements.

[0085] Secondly, specific scrapping curves for various vehicle types are used to determine the annual replacement volume due to natural attrition, technological obsolescence, or mandatory scrapping. The scrapping curve is a Weibull distribution function, used to characterize the proportion of vehicles still capable of normal operation as their service life increases after they are put into operation. This curve is set according to vehicle usage characteristics, such as average daily mileage, operating frequency, and usage environment, reflecting the natural law of different models gradually withdrawing from operation after long-term use due to mechanical wear, battery degradation, or technological obsolescence. The formula for calculating the scrapping volume is: Replacement volume (t) = Σ[Inventory (tk) × Scrapping probability (k)], k = 1~15, where k is the vehicle's service life, the scrapping probability (k) is calculated from the Weibull distribution function f(k;λ,k), λ is the scale parameter, and k is the shape parameter, all obtained based on regression fitting of historical scrapping data.

[0086] Finally, the change in vehicle ownership and the number of vehicles scrapped and replaced are added together in a non-negative manner to obtain the annual increase (i.e., annual sales) of various types of vehicles: Increase = Change in vehicle ownership + Number of vehicles scrapped and replaced. This value represents the actual market demand, which includes both new car purchases due to population growth and economic development, as well as replacements due to vehicle aging and policy obsolescence.

[0087] The annual increase in the number of vehicles of various types is used as input data for the annual sales module of different vehicle types. This step is the first to achieve dynamic decoupling between "stock update" and "incremental expansion" in electric vehicle scale forecasting, ensuring that the forecast results conform to the actual evolution of the vehicle life cycle.

[0088] As an optional embodiment, step S205 can be implemented according to the following steps: based on the new increase of the first type of power type vehicles corresponding to each of the various usage types of vehicles, and the new increase of the second type of power type vehicles corresponding to each of the various usage types of vehicles, combined with the vehicle scrapping curves of the first type of power type vehicles and the second type of power type vehicles respectively, determine the number of first type of power type vehicles corresponding to each of the various usage types of vehicles and the number of second type of power type vehicles corresponding to each of the various usage types of vehicles, including:

[0089] S2051, for each type of vehicle and each type of vehicle power, establish a time series of new additions;

[0090] S2052, for each type of vehicle and each type of vehicle power, based on the vehicle scrapping curve, determine the number of vehicles that are still within their effective lifespan within a preset historical period.

[0091] S2053, for each type of vehicle and each type of vehicle power, by combining the time series of new additions, the number of vehicles still in the effective life cycle within the preset historical period is accumulated to obtain the number of vehicles of the first type of power corresponding to each type of vehicle and the number of vehicles of the second type of power corresponding to each type of vehicle.

[0092] Steps S2051 to S2053 first establish a time series of annual new vehicle sales for each type of vehicle, based on the results output in step S204, for both the first and second powertrain types. This time series, on an annual basis, records the annual sales of pure electric vehicles and plug-in hybrid electric vehicles within the forecast period, serving as the input for subsequent calculations of their dynamic vehicle ownership.

[0093] Then, for each of the above-mentioned vehicle usage types and combinations of the two power types, a corresponding vehicle scrapping curve is defined. The preset historical period must cover the effective lifespan of the vehicle from its introduction into service to its complete scrapping. Using the vehicle scrapping curve, the proportion of vehicles newly added in a specific year under any forecast can be calculated, after several years of service, to still be within their effective lifespan, thus providing a quantitative basis for the dynamic accumulation of vehicle ownership.

[0094] Finally, the annual new vehicle volume time series established in step S2051 is combined with the vehicle scrapping curve defined in step S2052, and a rolling accumulation method is used to calculate the dynamic inventory of each type of vehicle at the end of the forecast period year by year. Specifically, taking the target year as the benchmark, a 15-year backward period is used as the preset historical period. For each new addition in a historical year, the service life of the vehicle from its addition to the target year is calculated, and the survival ratio corresponding to the service life is obtained according to the vehicle scrapping curve corresponding to the combination. The new addition in that year is multiplied by its corresponding survival ratio to obtain the number of new vehicles in that year that are still within their effective life cycle in the target year. Subsequently, the product results of the combination in all years within the 15-year historical period are accumulated one by one, and the sum is the inventory of the first power type vehicle or the second power type vehicle of that usage type in the target year.

[0095] As an optional embodiment, step S206 can be implemented according to the following steps: based on the number of vehicles of the first power type corresponding to each of the various usage types and the number of vehicles of the second power type corresponding to each of the various usage types, combined with the vehicle-to-grid interaction adaptation rules, predict the scale of electric vehicles participating in vehicle-to-grid interaction, including:

[0096] S2061, construct the vehicle-to-grid (V2G) interaction adaptability coefficient matrix. The features of the V2G interaction adaptability coefficient matrix include vehicle model adaptability, charging interface type, communication protocol support, battery health threshold, and user authorization willingness weight.

[0097] S2062, for each type of vehicle and each type of vehicle power, based on the vehicle-to-network interaction adaptability coefficient matrix, determine the target vehicles that meet the requirements of communication protocol support, bidirectional charging capability, battery health above the battery health threshold, and user authorization willingness weight above the preset weight threshold.

[0098] S2063, for each type of vehicle and each type of vehicle power, determine the effective scale of participation in vehicle-to-everything (V2X) interaction based on the number of target vehicles;

[0099] S2064 sums up the effective scale of vehicles participating in vehicle-to-grid interaction for each type of vehicle and each type of vehicle with each power type to obtain the scale of electric vehicles participating in vehicle-to-grid interaction.

[0100] During steps S2061 to S2064, such as Figure 7 As shown, this submodule mainly reads the sales penetration rate forecast data and the ownership forecast data of each power type of vehicle in each market segment obtained by the above submodule, and combines the scrapping data to calculate the sales forecast data of each market segment and power type of commercial vehicles and passenger vehicles respectively, so as to provide a calculation basis for the subsequent calculation of the scale of charging facilities participating in vehicle-to-grid interaction.

[0101] First, using the vehicle ownership of the first and second power types output in step S2053 as input, a vehicle-to-grid (V2G) interaction coefficient matrix is ​​constructed to dynamically calculate the V2G interaction rate for each market segment and power type. This matrix consists of five characteristic parameters: vehicle type compatibility (reflecting the degree of matching between vehicle usage and grid dispatch, e.g., private cars have higher daily idle time than public transport, indicating higher compatibility); charging interface type (only vehicles supporting the GB / T 20234.3-2015 DC bidirectional interface have V2G capability); communication protocol support (only vehicles with ISO 15118 or V2G-TP protocols can respond to grid dispatch commands); battery health threshold (only vehicles with a remaining capacity ≥80% can participate in charging and discharging to ensure grid safety); and user authorization willingness weight (based on survey data on vehicle owners' willingness to enable V2G function in the charging app, assigned a dynamic weight from 0 to 1).

[0102] Then, for each combination of vehicle type and power type, based on the vehicle-to-network interaction adaptability coefficient matrix, target vehicles are selected that simultaneously meet the following criteria: communication protocol support is higher than a preset threshold, charging interface is bidirectional, battery health is not lower than 80%, and user authorization willingness weight is higher than a preset weight threshold. The proportion of the number of target vehicles to the total number of vehicles of this type is defined as the vehicle-to-network interaction rate of this combination.

[0103] Finally, the vehicle-to-network interaction rate is multiplied by the corresponding number of pure electric vehicles and plug-in hybrid electric vehicles to obtain their respective scale of participation in vehicle-to-network interaction. Then, the vehicle-to-network interaction scales of all pure electric vehicles and plug-in hybrid electric vehicles in the seven usage types are summed to output the vehicle-to-network interaction scales of pure electric vehicles and plug-in hybrid electric vehicles, respectively. Finally, the summation is used to obtain the total scale of vehicle-to-network interaction for electric vehicles.

[0104] In conjunction with the above optional embodiments, another functional module framework for predicting total electric vehicle resources and structure is also provided. Figure 3 It is a functional module architecture for predicting the total amount and structure of electric vehicle resources, such as Figure 3 As shown, it consists of four sub-computation modules: electric vehicle penetration rate prediction module for each market segment, electric vehicle ownership prediction module for each market segment, electric vehicle sales and ownership prediction module for each market segment, and total scale prediction module for electric vehicles participating in vehicle-to-grid interaction in each market segment.

[0105] In summary, the vehicle scale prediction method and device provided in this application, through a categorized prediction method of "four-module linkage, multi-factor funnel, and full life cycle coupling," achieves differentiated modeling for seven types of vehicles, including private cars, ride-hailing vehicles, buses, and logistics vehicles, for the first time; constructs a multi-dimensional funnel model that integrates policy and market factors (such as charging satisfaction, user preferences, and conversion rates) to accurately predict the electrification penetration rate; and introduces a scrapping curve, linking vehicle ownership, sales volume, and V2G resources to achieve dynamic time-series extrapolation across the entire chain, significantly improving prediction accuracy and grid dispatch support capabilities.

[0106] Specifically, compared with the prior art, this application has the following beneficial effects:

[0107] First, the differentiated modeling of market segments is highly accurate. It incorporates seven market segments, including private cars, ride-hailing vehicles, buses, and logistics vehicles, into a unified prediction framework. Independent prediction logic is designed for the usage frequency and charging behavior characteristics of different vehicle types, which significantly improves the accuracy of resource distribution prediction.

[0108] Second, the multi-factor funnel model drives the scientific prediction of penetration rate. It constructs an interactive model of multiple influencing factors such as charging satisfaction, safety perception, supply-side conversion rate, and user scenario preferences, avoiding the bias of traditional single-factor reliance. The penetration rate prediction is more in line with the actual market evolution.

[0109] Third, dynamic lifecycle linkage avoids static errors. By introducing the vehicle scrapping rate curve, the entire link from traditional car sales to the scale of available V2G resources is dynamically coupled and calculated, ensuring the rationality of the prediction results as they evolve over time.

[0110] Fifth, modular decoupling enhances system scalability. Standardized interface design supports independent upgrades or embedding into the energy management system, significantly reducing the difficulty of engineering integration.

[0111] According to an embodiment of this application, an electric vehicle scale prediction apparatus for implementing the above-described electric vehicle scale prediction method is also provided. Figure 8 This is a structural block diagram of an electric vehicle scale prediction device provided according to an embodiment of this application, such as... Figure 8 As shown, the electric vehicle scale prediction device includes:

[0112] The acquisition module 81 is used to acquire the number of vehicles of various usage types within a preset period and the incremental ratio of vehicles of various usage types within a preset period, wherein the number of vehicles represents the actual number of vehicles.

[0113] The first prediction module 82 is used to predict the new addition of vehicles for various usage types based on the number of vehicles in use for various usage types and the vehicle scrapping curves for various usage types.

[0114] The first determining module 83 is used to determine the new increment of the first power type vehicles and the new increment of the second power type vehicles corresponding to the various types of vehicles based on the new increment corresponding to each of the various types of vehicles and the increment ratio corresponding to each of the various types of vehicles.

[0115] The second determining module 84 is used to determine the number of vehicles of the first power type and the number of vehicles of the second power type corresponding to each of the various types of vehicles based on the new increment of vehicles of the first power type and the new increment of vehicles of the second power type corresponding to each of the various types of vehicles, combined with the vehicle scrapping curves of vehicles of the first power type and vehicles of the second power type.

[0116] The second prediction module 85 is used to predict the scale of electric vehicles participating in vehicle-to-grid interaction based on the number of vehicles of the first power type corresponding to each of the various usage types and the number of vehicles of the second power type corresponding to each of the various usage types, combined with the adaptation rules of vehicle-to-grid interaction.

[0117] Optionally, module 81 can also be configured as follows:

[0118] Acquire historical population data, historical GDP data, and the unit ownership of vehicles of various usage types for the target area within a preset historical period;

[0119] By extrapolating historical population data, the population size of a target area can be predicted within a preset future period.

[0120] Regression fitting is performed on historical GDP data to predict the GDP of the target region in a preset future period;

[0121] Based on the unit ownership of vehicles of various usage types, the population size of the target area in the preset future period, and the GDP of the target area in the preset future period, the ownership of vehicles of various usage types is calculated respectively.

[0122] Acquire data on policy subsidy intensity, charging infrastructure coverage, user charging satisfaction survey data, electric vehicle safety perception index, supply-side conversion rate, and user scenario preference weighting in the target area;

[0123] For each type of vehicle, the data on policy subsidy intensity and charging facility coverage are normalized to construct an initial value for policy-based penetration rate.

[0124] For each type of vehicle, user charging satisfaction survey data, electric vehicle safety perception index, supply-side conversion rate data, and user scenario preference weight data are weighted and integrated to construct an initial value for market penetration rate.

[0125] For each type of vehicle, the initial value of policy-driven penetration rate and the initial value of market-driven penetration rate are non-linearly coupled to calculate the incremental ratio of the first type of power type vehicles and the incremental ratio of the second type of power type vehicles.

[0126] Optionally, the first prediction module 82 is also configured as follows:

[0127] Differential processing is performed on the ownership of vehicles of various usage types to calculate the change in ownership of vehicles of various usage types.

[0128] Based on vehicle scrapping curves, determine the corresponding scrapping and replacement quantities for vehicles of various usage types;

[0129] The change in the number of vehicles of each usage type is added to the change in the number of vehicles scrapped and replaced for each usage type to obtain the increase in the number of vehicles of each usage type.

[0130] Optionally, the second determining module 84 is also configured as follows:

[0131] For each type of vehicle and each type of vehicle with different power sources, establish a time series of new additions;

[0132] For each type of vehicle and each type of vehicle with different power sources, the number of vehicles still within their effective lifespan within a preset historical period is determined based on the vehicle scrapping curve.

[0133] For each type of vehicle and each type of vehicle powertrain, by combining the time series of new additions, the number of vehicles still within their effective lifecycle within a preset historical period is accumulated on a rolling basis to obtain the number of vehicles of the first type of powertrain corresponding to each type of vehicle and the number of vehicles of the second type of powertrain corresponding to each type of vehicle.

[0134] Optionally, the second prediction module 85 is also configured as follows:

[0135] A vehicle-to-grid (V2G) interaction adaptability coefficient matrix is ​​constructed. The features of the V2G interaction adaptability coefficient matrix include vehicle model adaptability, charging interface type, communication protocol support, battery health threshold, and user authorization willingness weight.

[0136] For each type of vehicle and each type of vehicle power, target vehicles are determined based on the vehicle-to-network interaction adaptability coefficient matrix, which meet the requirements of communication protocol support, bidirectional charging capability, battery health above the battery health threshold, and user authorization willingness weight above the preset weight threshold.

[0137] For each type of vehicle and each type of vehicle powertrain, the effective scale for participating in vehicle-to-everything (V2X) interaction is determined based on the number of target vehicles.

[0138] The effective scale of vehicles participating in vehicle-to-grid interaction is obtained by summing up the effective scale of each type of vehicle and each type of vehicle power.

[0139] It should be noted that the aforementioned acquisition module 81, first prediction module 82, first determination module 83, second determination module 84, and second prediction module 85 correspond to steps S201 to S206 in the embodiments. Multiple modules implement the same instances and application scenarios as their corresponding steps, but are not limited to the content disclosed in the above embodiments. It should also be noted that the aforementioned modules, as part of the device, can run on the computer terminal 10 provided in the embodiments.

[0140] Embodiments of this application may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0141] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the vehicle size prediction method and device in this application embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned vehicle size prediction method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0142] The processor can access information and applications stored in memory via a transmission device to perform the following steps: obtaining the number of vehicles of various usage types in the target area over a future period; obtaining the incremental ratio of Class I and Class II power type vehicles in each type of vehicle; predicting the new addition of each type of vehicle based on the number of vehicles in stock and the corresponding scrapping curves; determining the new addition of the two power type vehicles by combining the new addition and the incremental ratio; calculating the dynamic number of the two types of vehicles in stock on a rolling basis based on the new addition and their respective scrapping curves; and predicting the scale of electric vehicles participating in vehicle-to-grid interaction based on the number of the two types of vehicles in stock and the vehicle-to-grid interaction adaptation rules.

[0143] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a non-volatile storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0144] Embodiments of this application also provide a non-volatile storage medium. Optionally, in this embodiment, the aforementioned non-volatile storage medium can be used to store the program code executed by the vehicle size prediction method provided in the above embodiments.

[0145] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0146] Embodiments of this application also provide a computer program product, including a computer program. Optionally, in this embodiment, the computer program, when executed by a processor, can implement:

[0147] The system obtains the number of vehicles of various usage types in the target area over the future period; obtains the incremental ratio of Class I and Class II power types among each vehicle type; predicts the new addition of each type of vehicle based on the number of vehicles in stock and the corresponding scrapping curves; determines the new addition of vehicles of the two power types by combining the new addition and the incremental ratio; calculates the dynamic number of vehicles of the two types on a rolling basis based on the new addition and their respective scrapping curves; and predicts the scale of electric vehicles participating in vehicle-to-grid interaction based on the number of vehicles of the two types and the vehicle-to-grid interaction adaptation rules.

[0148] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0149] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0150] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0151] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0152] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0153] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0154] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for predicting the scale of electric vehicles, characterized in that, include: The number of vehicles of various usage types in a target area within a preset future period is obtained, wherein the number of vehicles represents the actual number in existence. Obtain the incremental proportion of the first power type vehicles and the incremental proportion of the second power type vehicles corresponding to the various usage types of vehicles in the target area within the preset future period; Based on the number of vehicles of each of the various usage types, and combined with the vehicle scrapping curves of each of the various usage types, the new number of vehicles of each of the various usage types is predicted. Based on the new additions of vehicles for each of the various usage types, the incremental proportion of vehicles of the first power type for each of the various usage types, and the incremental proportion of vehicles of the second power type for each of the various usage types, the new additions of vehicles of the first power type for each of the various usage types and the new additions of vehicles of the second power type for each of the various usage types are determined. Based on the new increase of the first type of power type vehicles corresponding to each of the various usage types of vehicles, the new increase of the second type of power type vehicles corresponding to each of the various usage types of vehicles, and combined with the vehicle scrapping curves of the first type of power type vehicles and the second type of power type vehicles, the number of vehicles in operation corresponding to the first type of power type vehicles and the number of vehicles in operation corresponding to the second type of power type vehicles corresponding to each of the various usage types of vehicles are determined. Based on the number of vehicles of the first power type corresponding to each of the various usage types and the number of vehicles of the second power type corresponding to each of the various usage types, and in combination with the vehicle-to-grid interaction adaptation rules, the scale of electric vehicles participating in vehicle-to-grid interaction is predicted.

2. The method according to claim 1, characterized in that, The acquisition of the number of vehicles of various usage types in the target area within a preset future period includes: Acquire historical population data, historical GDP data, and the unit ownership of vehicles of each of the various usage types for the target area within a preset historical period; By extrapolating the historical population data, the population size of the target area within the preset future period is predicted. Regression fitting is performed on the historical GDP data to predict the GDP of the target region in the preset future period; Based on the unit ownership of vehicles of each of the various usage types, the population size of the target area in the preset future period, and the GDP of the target area in the preset future period, the ownership of vehicles of each of the various usage types is calculated respectively.

3. The method according to claim 1, characterized in that, The step of obtaining the incremental proportions of the first power type vehicles and the second power type vehicles corresponding to the various usage types of vehicles in the target area within the preset future period includes: Obtain data on policy subsidy intensity, charging facility coverage, user charging satisfaction survey, electric vehicle safety perception index, supply-side conversion rate, and user scenario preference weighting for the target area. For each type of vehicle, the policy subsidy intensity data and the charging facility coverage data are normalized to construct an initial value for the policy-based penetration rate. For each type of vehicle, the user charging satisfaction survey data, the electric vehicle safety perception index, the supply-side conversion rate data, and the user scenario preference weight data are weighted and fused to construct an initial value for market penetration rate; For each type of vehicle, the initial value of the policy-driven penetration rate and the initial value of the market-driven penetration rate are non-linearly coupled to generate the incremental proportion of the first type of power type vehicles and the incremental proportion of the second type of power type vehicles.

4. The method according to claim 1, characterized in that, The method of predicting the new additions of vehicles for each of the various usage types based on their respective inventory levels and vehicle scrapping curves includes: Differential processing is performed on the number of vehicles corresponding to each of the various usage types to calculate the change in the number of vehicles corresponding to each of the various usage types. Based on the vehicle scrapping curve, determine the corresponding scrapping and replacement quantity for each of the various usage types of vehicles; The change in the number of vehicles of each of the various usage types is added to the scrapping and replacement of vehicles of each of the various usage types to obtain the new addition of vehicles of each of the various usage types.

5. The method according to claim 1, characterized in that, The determination of the number of vehicles in operation for each of the various usage types based on the new additions of vehicles of the first power type corresponding to each of the various usage types, the new additions of vehicles of the second power type corresponding to each of the various usage types, and the vehicle scrapping curves of the first power type vehicles and the second power type vehicles respectively, includes: For each type of vehicle and each type of vehicle power, establish a time series of the aforementioned increase; For each type of vehicle and each type of vehicle with different power sources, the number of vehicles still within their effective lifespan within the preset historical period is determined based on the vehicle scrapping curve. For each type of vehicle and each type of vehicle powertrain, by combining the time series of the new additions and by rolling the sum of the number of vehicles still within their effective lifecycle within the preset historical period, the number of vehicles of the first type of powertrain corresponding to each of the various types of vehicles and the number of vehicles of the second type of powertrain corresponding to each of the various types of vehicles are obtained.

6. The method according to claim 1, characterized in that, The prediction of the scale of electric vehicles participating in vehicle-to-grid interaction, based on the number of vehicles of the first power type corresponding to each of the various usage types, the number of vehicles of the second power type corresponding to each of the various usage types, and the adaptation rules of vehicle-to-grid interaction, includes: Construct a vehicle-to-grid (V2G) interaction adaptability coefficient matrix, wherein the features of the V2G interaction adaptability coefficient matrix include vehicle model adaptability, charging interface type, communication protocol support, battery health threshold, and user authorization willingness weight. For each type of vehicle and each type of vehicle power, based on the vehicle-to-network interaction adaptability coefficient matrix, target vehicles are determined that meet the following criteria: communication protocol support, bidirectional charging capability, battery health level higher than the battery health level threshold, and user authorization willingness weight higher than the preset weight threshold. For each type of vehicle and each type of vehicle powertrain, the effective scale for participating in vehicle-to-everything (V2X) interaction is determined based on the number of the target vehicles. The effective scale of vehicles participating in vehicle-to-grid interaction is obtained by summing up the effective scale of each type of vehicle and each type of vehicle power.

7. An electric vehicle scale prediction device, characterized in that, include: The acquisition module is used to acquire the number of vehicles of various usage types within a preset period and the incremental ratio of vehicles of various usage types within the preset period, wherein the number of vehicles represents the actual number in existence. The first prediction module is used to predict the new number of vehicles for each of the various usage types based on the number of vehicles in operation for each of the various usage types and the vehicle scrapping curves for each of the various usage types. The first determining module is used to determine the new increment of the first power type vehicles corresponding to each of the multiple usage types and the new increment of the second power type vehicles corresponding to each of the multiple usage types based on the new quantity corresponding to each of the multiple usage types and the increment ratio corresponding to each of the multiple usage types. The second determining module is used to determine the number of vehicles of the first power type corresponding to each of the multiple types of vehicles and the number of vehicles of the second power type corresponding to each of the multiple types of vehicles based on the new increase of vehicles of the first power type corresponding to each of the multiple types of vehicles and the new increase of vehicles of the second power type corresponding to each of the multiple types of vehicles, combined with the vehicle scrapping curves of vehicles of the first power type and vehicles of the second power type respectively. The second prediction module is used to predict the scale of electric vehicles participating in vehicle-to-grid interaction based on the number of vehicles of the first power type corresponding to each of the various usage types, the number of vehicles of the second power type corresponding to each of the various usage types, and the adaptation rules of vehicle-to-grid interaction.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the non-volatile storage medium to perform the electric vehicle scale prediction method according to any one of claims 1 to 6.

9. A computer device, characterized in that, include: Memory and processor The memory stores computer programs; The processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, the processor performs the electric vehicle scale prediction method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the electric vehicle scale prediction method according to any one of claims 1 to 6.

Images