Method and device for generating configuration strategy of vehicle and processor

Abstract

The invention discloses a method and a device for generating a configuration strategy of a vehicle and a processor. The method comprises the steps that electricity price data of power equipment, battery data of a battery in a vehicle and behavior data of a target object in different time periods are acquired, and the electricity price data are used for representing charging value attributes of the power equipment for charging the vehicle and discharging value attributes of the vehicle for discharging the power equipment; the battery data is used for representing the state of the battery, and the behavior data is used for representing the charging behavior and discharging behavior of the target object to the vehicle; based on the electricity price data, the battery data and the behavior data, a membership function is determined, and the membership function is used for representing the influence degree of the electricity price data, the battery data and the behavior data on the target object; and generating a configuration strategy of the vehicle based on the membership function. The technical problem that the generation accuracy of the configuration strategy of the vehicle is low is solved.

Description

Technical Field

[0001] This invention relates to the field of data transmission technology, and more specifically, to a method, apparatus, and processor for generating vehicle configuration strategies. Background Technology

[0002] Currently, with the popularization of new energy vehicles and the development of smart grids, vehicle-to-grid (V2G) technology is becoming increasingly important as an emerging energy management method.

[0003] In related technologies, V2G parameter configuration strategies often only consider the single dimension of charging and discharging price. This simplification may reduce the universality and accuracy of models built based on charging and discharging price, failing to fully reflect the real needs and behavioral patterns of the target audience (users). Therefore, the technical problem of low accuracy in generating vehicle configuration strategies still exists.

[0004] There is currently no good solution to the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, and processor for generating vehicle configuration strategies, to at least address the technical problem of low accuracy in generating vehicle configuration strategies.

[0006] According to one aspect of the present invention, a method for generating a vehicle configuration strategy is provided, comprising: acquiring electricity price data of electrical equipment, battery data of a battery in a vehicle, and behavioral data of a target object within different time periods, wherein the electricity price data is used to represent the charging value attribute of the electrical equipment charging the vehicle and the discharging value attribute of the vehicle discharging the electrical equipment, the battery data is used to represent the state of the battery, and the behavioral data is used to represent the charging and discharging behaviors of the target object towards the vehicle; determining a membership function based on the electricity price data, battery data, and behavioral data, wherein the membership function is used to represent the degree of influence of the electricity price data, battery data, and behavioral data on the target object; and generating a vehicle configuration strategy based on the membership function, wherein the configuration strategy is used to represent the rules for adjusting the configuration information of the vehicle.

[0007] Optionally, the membership function includes a first membership function, which represents the degree of influence of electricity price data on the target object within different time periods. The membership function is determined based on electricity price data, battery data, and behavioral data, including: dividing different time periods to obtain division results; determining the target object's perception information regarding the electricity price data based on the electricity price data and the division results, wherein the perception information is used to determine whether the target object performs charging or discharging behavior on the vehicle according to the electricity price data; and analyzing the perception information to determine the first membership function.

[0008] Optionally, the membership function includes a second membership function, which represents the degree of influence of battery data on the target object within different time periods. The membership function is determined based on electricity price data, battery data, and behavioral data, including: determining battery performance change information based on battery data, where the change information represents the degree of performance degradation; determining the target object's acceptance information regarding the degradation, where the acceptance information represents the target object's acceptance of the degradation; dividing the acceptance information into intervals to obtain interval division results; and determining the second membership function based on the interval division results.

[0009] Optionally, the membership function includes a third membership function, which represents the degree of influence of behavioral data on the target object within different time periods. Based on electricity price data, battery data, and behavioral data, the membership function is determined by: standardizing the behavioral data to obtain processed behavioral data; and using a fuzzy clustering model to perform cluster analysis on the processed behavioral data to determine the third membership function. The fuzzy clustering model is obtained by training an initial fuzzy clustering model using behavioral data samples.

[0010] Optionally, the sensed information is analyzed to determine a first membership function, including: normalizing the sensed information to obtain processed sensed information; obtaining sensed deviation information of the target object, wherein the sensed deviation information is used to represent the difference of the target object to the electricity price data; adjusting the processed sensed information based on the sensed deviation information, wherein the accuracy of the adjusted sensed information is higher than the accuracy of the sensed information before adjustment; and determining a first membership function corresponding to the distribution of the adjusted sensed information.

[0011] Optionally, the method further includes: classifying the target object type according to the processed behavioral data to obtain classification results; and determining the number of classification results as the number of cluster centers of the fuzzy clustering model.

[0012] Optionally, a fuzzy clustering model is used to perform cluster analysis on the processed behavioral data to determine the third membership function. This includes: selecting initial data points from the processed behavioral data and determining these initial data points as the initial cluster centers of the fuzzy clustering model; determining the distances between the processed behavioral data points other than the initial data points and the initial cluster centers; determining the target data points whose distances are greater than a distance threshold as the next cluster centers of the initial cluster centers; repeating the following steps until the number of selected target cluster centers equals the number of cluster centers: determining the distances between the processed behavioral data points other than the initial data points and the initial cluster centers; determining the target data points whose distances are greater than a distance threshold as the next cluster centers of the initial cluster centers; and using the fuzzy clustering model to perform cluster analysis on the processed behavioral data to determine the third membership function. This includes: updating the initial cluster centers based on the distances and the distances between the initial data points and the initial cluster centers to obtain the third membership function.

[0013] Optionally, a vehicle configuration strategy is generated based on membership functions, including: determining the target object's response information in different time periods based on a first membership function, a second membership function, and a third membership function, wherein the response information is used to represent the target object's response to electricity price data, battery data, and behavioral data; and generating a vehicle configuration strategy based on the response information.

[0014] According to another aspect of the present invention, a vehicle configuration strategy generation apparatus is also provided, comprising: an acquisition unit, configured to acquire electricity price data of electrical equipment, battery data of batteries in the vehicle, and behavioral data of a target object within different time periods, wherein the electricity price data is used to represent the charging value attribute of the electrical equipment charging the vehicle and the discharging value attribute of the vehicle discharging the electrical equipment, the battery data is used to represent the state of the battery, and the behavioral data is used to represent the charging and discharging behaviors of the target object towards the vehicle; a determination unit, configured to determine a membership function based on the electricity price data, battery data, and behavioral data, wherein the membership function is used to represent the degree of influence of the electricity price data, battery data, and behavioral data on the target object; and a generation unit, configured to generate a vehicle configuration strategy based on the membership function, wherein the configuration strategy is used to represent the rules by which the target object adjusts the configuration information of the vehicle.

[0015] Optionally, the membership function includes a first membership function, which represents the degree of influence of electricity price data on the target object within different time periods. The determining unit includes: a first partitioning module, used to partition different time periods to obtain partitioning results; a first determining module, used to determine the target object's perception information of the electricity price data based on the electricity price data and the partitioning results, wherein the perception information is used to determine whether the target object performs charging or discharging behavior on the vehicle according to the electricity price data; and a second determining module, used to analyze the perception information to determine the first membership function.

[0016] Optionally, the membership function includes a second membership function, which represents the degree of influence of battery data on the target object within different time periods. The determination module includes: a third determination module, used to determine the performance change information of the battery based on the battery data, wherein the change information represents the degree of performance degradation of the battery; a fourth determination module, used to determine the target object's acceptance information of the degradation, wherein the acceptance information represents the target object's acceptance of the degradation; a second partitioning module, used to partition the acceptance information into intervals to obtain interval partitioning results; and a fifth determination module, used to determine the second membership function based on the interval partitioning results.

[0017] Optionally, the membership function includes a third membership function, which represents the degree of influence of behavioral data on the target object within different time periods. The determination module includes: a processing module, used to standardize the behavioral data to obtain processed behavioral data; and an analysis module, used to perform cluster analysis on the processed behavioral data using a fuzzy clustering model to determine the third membership function. The fuzzy clustering model is obtained by training an initial fuzzy clustering model using behavioral data samples.

[0018] Optionally, the second determining module includes: a processing module for normalizing the perceived information to obtain processed perceived information; an acquisition module for acquiring perceived deviation information of the target object, wherein the perceived deviation information represents the difference of the target object to the electricity price data; an adjustment module for adjusting the processed perceived information based on the perceived deviation information, wherein the accuracy of the adjusted perceived information is higher than the accuracy of the perceived information before adjustment; and a sixth determining module for determining a first membership function corresponding to the distribution of the adjusted perceived information.

[0019] Optionally, the generating apparatus further includes: a classification unit, used to classify the type of the target object according to the processed behavioral data to obtain a classification result; and a first determining unit, used to determine the number of classification results as the number of cluster centers of the fuzzy clustering model.

[0020] Optionally, the analysis module includes: a seventh determination module, used to select initial data points from the processed behavioral data and determine the initial data points as the initial cluster centers of the fuzzy clustering model; and to determine the target data points whose distances are greater than a distance threshold as the next cluster centers of the initial cluster centers; an eighth determination module, used to determine the distances between the processed behavioral data points other than the initial data points and the initial cluster centers; repeating the following steps until the number of selected target cluster centers equals the number of cluster centers: determining the distances between the processed behavioral data points other than the initial data points and the initial cluster centers; determining the target data points whose distances are greater than a distance threshold as the next cluster centers of the initial cluster centers; and using the fuzzy clustering model to perform cluster analysis on the processed behavioral data to determine the third membership function, including: a ninth determination module, used to update the initial cluster centers based on the distances and the distances between the initial data points and the initial cluster centers to obtain the third membership function.

[0021] Optionally, the generation unit includes: an eleventh determining module, used to determine the response information of the target object in different time periods based on the first membership function, the second membership function, and the third membership function, wherein the response information is used to represent the degree of response of the target object to electricity price data, battery data, and behavioral data; and a generation module, used to generate a vehicle configuration strategy based on the response information.

[0022] According to another aspect of the present invention, a computer-readable storage medium is also provided, which stores a plurality of instructions adapted for loading by a processor and executing any of the methods described above.

[0023] According to another aspect of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform any of the methods described above.

[0024] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements any of the methods described above.

[0025] In this embodiment of the invention, to generate a vehicle configuration strategy, electricity price data of electrical equipment, battery data of the vehicle's battery, and behavioral data of the target object can be obtained within different time periods. The electricity price data represents the charging value attribute of the electrical equipment charging the vehicle and the discharging value attribute of the vehicle discharging the electrical equipment. The battery data represents the battery's state, and the behavioral data represents the target object's charging and discharging behaviors towards the vehicle. A membership function can be determined based on the electricity price data, battery data, and behavioral data, representing the degree of influence of these data on the target object. A vehicle configuration strategy can then be generated based on this membership function. In this embodiment, by constructing a membership function that considers electricity price data, battery data, and behavioral data, and introducing a time dimension (different time periods), the degree of influence of these data on the target object within different time periods can be dynamically reflected, thereby generating a vehicle configuration strategy. This solves the technical problem of low accuracy in generating vehicle configuration strategies and improves the accuracy of vehicle configuration strategy generation. Attached Figure Description

[0026] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0027] Figure 1 This is a flowchart of a method for generating a vehicle configuration strategy according to an embodiment of the present invention;

[0028] Figure 2 This is a schematic diagram of a V2G parameter configuration system based on user dynamic response and driving habits according to an embodiment of the present invention;

[0029] Figure 3 This is a schematic diagram of the dynamic change of a user's perception of charging prices and the membership function graph according to an embodiment of the present invention.

[0030] Figure 4 This is a schematic diagram of the dynamic changes in battery life and user acceptance with depth of discharge and current rate according to an embodiment of the present invention.

[0031] Figure 5 This is a schematic diagram of a vehicle configuration strategy generation device according to an embodiment of the present invention.

[0032] Figure 6 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0033] 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.

[0034] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] Example 1

[0036] According to an embodiment of the present invention, a method for generating a vehicle configuration strategy 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. Furthermore, 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.

[0037] Figure 1 This is a flowchart of a method for generating a vehicle configuration strategy according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0038] Step S102: Obtain electricity price data of electrical equipment, battery data of batteries in vehicles, and behavioral data of the target object within different time periods.

[0039] In the technical solution provided in step S102 of this embodiment of the invention, electricity price data is used to represent the charging value attribute of the power equipment charging the vehicle, and the discharging value attribute of the vehicle discharging the power equipment; battery data is used to represent the battery state; and behavioral data is used to represent the charging and discharging behavior of the target object towards the vehicle. The vehicle can be an electric vehicle, but this is only an example and is not specifically limited here.

[0040] In this embodiment, in V2G, electric vehicles can not only obtain electrical energy from the grid for charging, but also supply electrical energy from the vehicle battery back to the grid, thereby participating in demand-side management activities such as peak shaving and valley filling.

[0041] Optionally, since electricity price data varies over time, it is necessary to collect electricity price data according to different time periods (such as peak, off-peak, and off-peak periods), for example, charging and discharging prices, in order to understand the load conditions of the power grid and electricity price fluctuation patterns. Electricity price data when electrical equipment charges vehicles can be obtained; this data reflects the economic cost of charging and is an important factor in determining the charging behavior of the target (user).

[0042] Optionally, battery data may include depth of discharge, current rate, state of charge (SOC), battery temperature, and number of charge / discharge cycles. Depth of discharge refers to the proportion of a battery's total capacity that is discharged in one discharge cycle, and it has a significant impact on battery life; a shallower depth of discharge helps extend the battery's cycle life. Current rate represents the rate at which the battery's charging and discharging current is relative to its rated capacity. For example, a current rate of 1 means the battery can be fully charged and discharged within one hour. A high current rate can lead to battery overheating and accelerated battery aging, while a lower current rate can reduce battery wear and extend its lifespan.

[0043] Optionally, the target user's behavioral data, also known as user driving habit data, is used to record the frequency, time, and location of user charging to understand their charging preferences and routine patterns. By collecting user discharge behavior data under different discharge prices, the user's sensitivity to price changes can be assessed. By analyzing user driving habits, such as average daily driving distance and travel time distribution, the user's potential charging and discharging needs can be predicted; that is, the target user's charging or discharging behavior towards the vehicle.

[0044] Optionally, electricity price data can be obtained by connecting to real-time data interfaces of the electricity market or grid company. These interfaces typically provide Application Programming Interfaces (APIs), allowing for the automatic acquisition of electricity price data for different time periods. Historical electricity price databases can also be used to collect electricity price data for specific past periods. Electricity market analysis reports can also be consulted to understand seasonal fluctuations, holiday impacts, and long-term trends in electricity price data.

[0045] Optionally, battery data, such as SOC, depth of discharge, current rate, and battery temperature, can be obtained from the electric vehicle's Battery Management System (BMS). This can be achieved through the vehicle's communication interface, such as a Controller Area Network (CAN) bus. Alternatively, a remote monitoring system can be used to collect the battery's real-time operating status. This remote monitoring system can be a cloud-based service that communicates with the vehicle via wireless networks (such as 4G, 5G, or Wi-Fi) to acquire and store battery data.

[0046] Optionally, behavioral data of the target user can be collected through the vehicle's built-in Global Positioning System (GPS) and trip recorder, gathering information on the user's driving habits, including mileage and travel time. User interaction data with the vehicle, such as charging frequency, charging location, and charging time, can also be collected; this data can be obtained from the vehicle's application or charging station logs. Regular user surveys can also be conducted to collect user preferences and satisfaction feedback on charging strategies, as well as user sensitivity to charging and discharging prices.

[0047] It should be noted that the specific content and acquisition methods of the above-mentioned electricity price data, battery data, and target object behavior data are only illustrative examples and are not subject to specific restrictions.

[0048] Step S104: Determine the membership function based on electricity price data, battery data, and behavioral data.

[0049] In the technical solution provided by step S104 of this embodiment of the invention, after acquiring electricity price data of power equipment, battery data of vehicle batteries, and behavioral data of the target object within different time periods, a membership function can be determined based on the electricity price data, battery data, and behavioral data. The membership function represents the degree of influence of the electricity price data, battery data, and behavioral data on the target object.

[0050] In this embodiment, after acquiring electricity price data for electrical equipment, battery data for vehicles, and behavioral data of the target object within different time periods, data cleaning can be performed on the electricity price data, battery data, and behavioral data of the target object to eliminate outliers and missing data, ensuring the quality of the electricity price data, battery data, and behavioral data of the target object. Different data types can be converted to the same scale for easier comparison and analysis, thereby identifying which data features have a significant impact on user response intentions.

[0051] Optionally, based on the Weber-Fechner law, the impact of electricity price fluctuations on user psychology can be examined to determine user sensitivity to charging / discharging prices. A time-related reference price can be set based on historical data and real-time market conditions, thereby determining the membership function based on sensitivity and the reference price.

[0052] Optionally, the thermal effect model based on the Arrhenius equation can be used to quantify the impact of discharge depth and current rate on battery life. A Gaussian function can be used to simulate the user's perceived information about battery performance degradation. Based on the dynamic changes in battery life over time, the user's acceptance of battery performance at different time periods can be more accurately assessed, thereby determining the membership function based on perceived information.

[0053] Optionally, user behavior data on daily mileage and time distribution can be collected, normalized to ensure data comparability, and then fuzzy C-means clustering can be used to calculate the membership function of each user to different clusters and determine the membership function.

[0054] Step S106: Generate the vehicle configuration strategy based on the membership function.

[0055] In the technical solution provided by step S106 of this embodiment of the invention, after determining the membership function based on electricity price data, battery data, and behavioral data, a vehicle configuration strategy can be generated based on the membership function. The configuration strategy represents the rules for adjusting the vehicle's configuration information.

[0056] In this embodiment, after obtaining the first membership function of the influence of electricity price data on the target object in different time periods, the second membership function of the influence of battery data on the target object in different time periods, and the third membership function of the influence of behavioral data on the target object in different time periods, the Apriori algorithm or other association rule mining techniques can be used to analyze the correlation between the membership function output and the user response results, generating a series of fuzzy rules. These fuzzy rules describe the user's response tendency under different electricity price levels, battery states, and user behaviors. Based on the rule set in the fuzzy logic system, the fuzzy output can be transformed into clear numerical values ​​or decision suggestions. By weighted averaging the outputs of different fuzzy rules, the final configuration parameters are obtained, such as charging price, discharge incentive price, current rate, and depth of discharge. Based on the defuzzification results, appropriate V2G parameter configurations are determined to ensure that these parameters meet the needs of the power grid while also taking into account the user's response intentions and the battery's health status.

[0057] Optionally, after generating the configuration strategy, the parameters are sent to the battery management system (BMS) via the vehicle's communication system (such as the CAN bus). The BMS adjusts the charging and discharging operations based on the received information. After implementing the configuration strategy, user feedback and actual effect data can be collected and fed back into the fuzzy logic system for subsequent adjustments to the configuration strategy.

[0058] In steps S102 to S106 of this embodiment of the invention, if a vehicle configuration strategy needs to be generated, electricity price data of electrical equipment, battery data of the vehicle's battery, and behavioral data of the target object can be obtained within different time periods. The electricity price data represents the charging value attribute of the electrical equipment charging the vehicle and the discharging value attribute of the vehicle discharging the electrical equipment. The battery data represents the battery's state, and the behavioral data represents the target object's charging and discharging behaviors towards the vehicle. A membership function can be determined based on the electricity price data, battery data, and behavioral data, whereby the membership function represents the degree of influence of the electricity price data, battery data, and behavioral data on the target object. A vehicle configuration strategy can be generated based on this membership function. In this embodiment, by constructing a membership function that considers electricity price data, battery data, and behavioral data, and introducing a time dimension (different time periods), the degree of influence of electricity price data, battery data, and behavioral data on the target object within different time periods can be dynamically reflected, thereby generating a vehicle configuration strategy. This solves the technical problem of low accuracy in generating vehicle configuration strategies and achieves the technical effect of improving the accuracy of vehicle configuration strategy generation.

[0059] The embodiments of the present invention will now be described in detail with reference to the steps described above.

[0060] As an optional embodiment, the membership function includes a first membership function, which is used to represent the degree of influence of electricity price data on the target object in different time periods. Step S104, based on electricity price data, battery data, and behavioral data, determines the membership function, including: dividing different time periods to obtain division results; determining the target object's perception information on electricity price data based on electricity price data and division results, wherein the perception information is used to determine whether the target object performs charging or discharging behavior on the vehicle according to the electricity price data; and analyzing the perception information to determine the first membership function.

[0061] In this embodiment, different time periods can be divided to obtain the division results. For example, a day can be divided into multiple time periods, such as peak hours, off-peak hours, and low-peak hours. The psychological effects on users can be analyzed in different time periods. Based on the Weber-Fechner law, the psychological effects of charging prices and discharging incentive prices on electric vehicle users can be quantified to obtain perceived information, that is, the perceived intensity of users' perception of electricity price data. The perceived intensity can be determined by the following formula:

[0062]

[0063] Among them, S c It can be used to represent the intensity of a user's perceived price of charging, S c The smaller the value, the more affordable the current charging price is perceived by the user; S d It can be used to represent the intensity of a user's perceived price of electric discharge; P c 、P d These can be used to represent the current charging and discharging incentive prices, respectively. P0(t) can be used to represent the psychological reference price at time t (dynamically changing). The psychological reference price needs to be adjusted based on historical charging and discharging price data and real-time dynamics of the V2G market. The analysis of charging and discharging price fluctuations over a period of time, and the statistical analysis of price averages and trends for different time periods, are used as a basis for setting psychological reference prices for different time periods (peak, off-peak, and low-peak periods). c k d These can be used to represent the sensing coefficients for charging and discharging, respectively.

[0064] Optionally, This can be used to quantify users' perception of charging and discharging prices, thereby reflecting the intensity of the psychological impact of price changes on users. In V2G scenarios, users' perception of charging and discharging prices is not based on the absolute price value, but rather on a comparison with a pre-set reference price. When prices begin to rise from a low level, even small price changes can trigger a significant psychological reaction from users; conversely, when prices are at a high level, the same increase in price will elicit a relatively smaller psychological reaction. Price changes can be converted into relative proportions, which can more accurately reflect changes in the intensity of the stimulus.

[0065] Optionally, based on the above-mentioned perception intensity formula, a perception intensity variation curve can be plotted to determine the boundary point, divide the value interval, and determine the first membership function type according to the distribution. Membership function types can include triangular membership functions, trapezoidal membership functions, and S-shaped membership functions. The graphical representation of a triangular membership function is a triangle with its vertex in the middle and equal slopes on both sides. Triangular functions are suitable for describing fuzzy sets with concepts of "middle," "moderate," or "normal." The trapezoidal membership function is similar to a triangle, but its graphical representation is trapezoidal, meaning that the membership degree of elements remains constant over a wider range. Trapezoidal functions are more flexible than triangular functions and are often used to express extreme fuzzy concepts such as "very low" or "very high." The S-shaped function resembles the letter S. In the region of small input values, the membership degree is close to 0; in the middle region, the membership degree gradually increases from 0 to 1; and in the region of large input values, the membership degree is close to 1. S-shaped functions are suitable for expressing changes in membership degree that are "gradually increasing" or "gradually decreasing."

[0066] As an optional embodiment, the membership function includes a second membership function, which is used to represent the degree of influence of battery data on the target object within different time periods. Step S104, based on electricity price data, battery data, and behavioral data, determines the membership function, including: determining battery performance change information based on battery data, wherein the change information is used to represent the degree of performance degradation of the battery; determining the target object's acceptance information of the degradation, wherein the acceptance information is used to represent the target object's acceptance of the degradation; dividing the acceptance information into intervals to obtain interval division results; and determining the second membership function based on the interval division results.

[0067] In this embodiment, battery performance changes can be determined based on battery data, such as the combined impact of depth of discharge (D) and current rate (C) on battery cycle life during scheduling. A thermal effect model based on the Arrhenius equation, combined with a Gaussian function, can be used to characterize user acceptance. The Arrhenius model can be expressed by the following formula:

[0068]

[0069] Where k can be used to represent the aging rate constant; A can be used to represent the frequency factor, representing the baseline value of the aging rate; E a It can be used to represent activation energy (in J / mol) and describe the effect of temperature on aging rate; R can be used to represent gas constant (8.314 J / (mol·K)); T can be used to represent temperature (in K).

[0070] Optionally, the depth of discharge (D) and current rate (C) are the main factors affecting battery aging, and the aging rate can be described by the following extended formula:

[0071]

[0072] Among them, D α It can be used to represent the contribution factor of discharge depth D to aging rate; C β It can be used to represent the contribution factor of current ratio C to aging rate.

[0073] Optionally, the target object's acceptance of the degree of degradation, i.e., user acceptance μ(t), is a subjective representation of the battery performance degradation and can be described using a Gaussian function:

[0074]

[0075] Wherein, μ(t) can be used to represent user acceptance, ranging from [0,1]. The higher the user acceptance, the higher the user's acceptance of the current battery performance; L(t) can be used to represent the remaining battery life (which varies over time); σ can be used to represent the standard deviation, which represents the user's tolerance range for battery performance degradation.

[0076] Optionally, a time dimension can be introduced to determine the battery life L(t):

[0077]

[0078] L0 can be used to represent the initial battery life (normalized to 1 or the number of cycles).

[0079] Optionally, based on the user acceptance level, the region can be divided into a high acceptance interval, a medium acceptance interval (transition interval), and a low acceptance interval. Based on the distribution, the type of the second membership function can be determined.

[0080] As an optional embodiment, the membership function includes a third membership function, which is used to represent the degree of influence of behavioral data on the target object in different time periods. Step S104, based on electricity price data, battery data, and behavioral data, determines the membership function, including: standardizing the behavioral data to obtain processed behavioral data; using a fuzzy clustering model to perform cluster analysis on the processed behavioral data to determine the third membership function, wherein the fuzzy clustering model is obtained by training an initial fuzzy clustering model using behavioral data samples.

[0081] In this embodiment, behavioral data, including but not limited to daily mileage, driving time distribution, and charging / discharging frequency, reflects the user's lifestyle and usage habits. Standardizing the collected behavioral data, for example using normalization, can eliminate differences in dimensions and scales between different feature data, enabling the behavioral data to be compared and analyzed on the same scale.

[0082] Optionally, for the perceived intensity S c 、S d Normalization is performed:

[0083]

[0084] Among them, P c,max 、P c,min These can be used to represent the upper and lower limits of charging prices, respectively. d,max 、P d,min These can be used to represent the upper and lower limits of the discharge price, respectively.

[0085] Optionally, P may include P c 、P d When P = P0(t), the minimum perceived intensity S min All are 0, and the maximum perceived intensity is Further simplification yields the following formula:

[0086]

[0087]

[0088] Optionally, an appropriate fuzzy clustering model, such as the Fuzzy C-Means (FCM) algorithm, can be selected as the basis for the fuzzy clustering model. The processed behavioral data can be used as the model input for cluster analysis to determine the third membership function.

[0089] As an optional embodiment, analyzing the perceived information to determine a first membership function includes: normalizing the perceived information to obtain processed perceived information; acquiring perceived deviation information of the target object, wherein the perceived deviation information is used to represent the difference of the target object to the electricity price data; adjusting the processed perceived information based on the perceived deviation information, wherein the accuracy of the adjusted perceived information is higher than the accuracy of the perceived information before adjustment; and determining a first membership function corresponding to the distribution of the adjusted perceived information.

[0090] In this embodiment, the perceived bias information reflects the difference between a user's subjective perception of actual changes in electricity price data and the objective changes themselves. This means that even if the electricity price changes the same, different users may perceive the price change differently due to differences in their psychological expectations and past experiences. Perceived bias can be quantified through methods such as questionnaires, user behavior analysis, or comparison of historical transaction data to identify users' sensitivity to price changes and their personalized preferences.

[0091] Optionally, by introducing user perception bias, S can be... c 、S d After making corrections, we obtain S. sc 、S sd (Different users have different perceptions of charging and discharging prices, S) c With S d The value of S is affected by uncertainty caused by perceptual biases between individual users. c 、S d It can be expressed by the following formula:

[0092] S se =S e ±ΔS e

[0093] S sd =S d ±ΔS d

[0094] Where, ΔS c ΔS d These can be used to represent perceived price deviation for charging and perceived price deviation for discharging, respectively.

[0095] Optionally, for users with large perceptual biases, their sensitivity to price changes can be appropriately increased, and vice versa. Analyze the distribution of the adjusted perceptual information and select a matching function type as the first membership function, such as ramp, triangular, Gaussian, or S-shaped.

[0096] As an optional embodiment, the method further includes: classifying the type of the target object according to the processed behavioral data to obtain classification results; and determining the number of classification results as the number of cluster centers of the fuzzy clustering model.

[0097] In this embodiment, in the V2G scenario, users corresponding to daily driving mileage can be divided into three categories: short-distance, medium-distance, and long-distance. At this time, the number of clusters C=3, and C=3 data points can be randomly selected as the number of cluster centers of the fuzzy clustering model.

[0098] Optionally, the number of user groups obtained from the classification can be used as the number of cluster centers in the fuzzy clustering model. This means that if three main user types (such as short-distance commuters, long-distance travelers, and mixed types) are identified through preliminary classification, the number of cluster centers in the fuzzy clustering model should be set to 3. By setting the number of cluster centers to match the actual number of user groups, the fuzzy clustering model can capture the characteristics and preferences of different user groups more precisely, thereby improving the model's prediction accuracy and the effectiveness of parameter configuration strategies.

[0099] As an optional embodiment, a fuzzy clustering model is used to perform cluster analysis on the processed behavioral data to determine a third membership function. This includes: selecting initial data points from the processed behavioral data and defining these initial data points as the initial cluster centers of the fuzzy clustering model; determining the distances between the processed behavioral data points (excluding the initial data points) and the initial cluster centers; identifying target data points whose distances are greater than a distance threshold as the next cluster centers of the initial cluster centers; repeating the following steps until the number of selected target cluster centers equals the number of cluster centers: determining the distances between the processed behavioral data points (excluding the initial data points) and the initial cluster centers; identifying target data points whose distances are greater than a distance threshold as the next cluster centers of the initial cluster centers; and using the fuzzy clustering model to perform cluster analysis on the processed behavioral data to determine a third membership function, including: updating the initial cluster centers based on the distances and the distances between the initial data points and the initial cluster centers to obtain the third membership function.

[0100] In this embodiment, initial data points are selected from the processed behavioral data and determined as the initial cluster centers of the fuzzy clustering model. This selection can be based on the actual data distribution, such as choosing the median or mean of the dataset as the starting point, or randomly selecting representative data points using an improved K-means clustering (K-means++) algorithm. For each data point in the user behavior dataset, the distance to the current cluster center is calculated using the Euclidean distance equidistance metric. A distance threshold can be set to determine when to select a new cluster center. If the distance between a data point and any existing cluster center is greater than the threshold, the point may be selected as a candidate for the next cluster center. From the remaining data points, data points whose distance to existing cluster centers is greater than the threshold are selected as candidates for the next cluster center. This step helps ensure that the cluster centers can cover different subgroups in the dataset. The above distance calculation and cluster center selection steps are repeated until a preset number of cluster centers is reached or the distance between all remaining data points and existing cluster centers is less than the threshold. This process ensures the comprehensiveness and representativeness of the cluster centers.

[0101] Optionally, a fuzzy clustering algorithm (FCM) is used to calculate the membership degree of each data point to all cluster centers. This process involves quantifying the degree of membership of a data point, allowing a data point to belong to multiple clusters simultaneously, with the degree of membership represented by the membership degree. Based on the calculated membership degrees, the center position of each cluster is updated, for example, through a weighted average, where the weights are determined by the membership degrees of the data points. The membership degrees of data points to each cluster center can be recalculated until the cluster centers stabilize or the change in membership degrees is less than a predetermined threshold.

[0102] Optionally, the results of fuzzy clustering can be analyzed to identify the behavioral characteristics and preferences of different user groups. Based on the clustering analysis results, a third membership function is constructed to reflect the impact of user behavior habits on V2G parameter configuration. The third membership function can include Gaussian, triangular, etc., depending on the distribution shape of the clustering results.

[0103] For example, in a V2G scenario, users based on their daily mileage are categorized into three groups: short-distance, medium-distance, and long-distance, resulting in a cluster size of C=3. C=3 data points are randomly selected from the dataset as initial cluster centers. Then, the K-means++ clustering algorithm is used to randomly select one data point as the first cluster center. The next data point is selected as the one furthest from the selected cluster center, and this process is repeated until C cluster centers are selected. (The probability of each data point being selected as the next cluster center is proportional to the square of its nearest distance to the nearest selected cluster center.)

[0104] Optionally, the distance d(x,y) from each data point x to each cluster center y is calculated using Euclidean distance, with the following formula:

[0105] x = (x1, x2, ..., x n ), y = (y1, y2, ..., y n )

[0106]

[0107] Optionally, the membership degree calculation formula in the fuzzy C-means algorithm is used for data point x. i Membership degree u of cluster j ij for:

[0108]

[0109] Where d(x) i ,v j This can be used to represent the distance from data points to cluster centers (v). j The distance; d(x) i ,v k This can be used to represent the distance from data points to cluster centers (v). kThe distance; m can be used to represent the fuzzy weight index, m∈(1,+∞), and can take the value 2.

[0110] Optionally, the cluster center positions are updated based on the current membership matrix and data points, for the dataset {x1,x2,...,x...} n}, the number of clusters is C, the fuzzy weight exponent is m, and the j-th cluster center is v. j The update formula is as follows (i.e., each cluster center is a weighted average of all data points with weights equal to the power of m of their membership degrees):

[0111]

[0112] in, It can be used to represent the membership degree of the i-th data point to the j-th cluster.

[0113] Alternatively, the updated cluster centers can be used, following the previous membership calculation formula. The membership degree of each data point to each cluster is recalculated to further optimize the clustering results. Intervals are defined based on the cluster centers and boundaries obtained from fuzzy C-means clustering. Cluster centers represent typical behavioral characteristics of different user groups, and cluster boundaries define the range of different groups. Three user groups with different mileage characteristics are obtained through clustering. Using each cluster center as a benchmark, combined with the cluster boundaries, mileage intervals corresponding to different groups are defined, and the type of the third membership function is determined.

[0114] As an optional embodiment, step S106, generating a vehicle configuration strategy based on membership functions, includes: determining the response information of the target object in different time periods based on the first membership function, the second membership function, and the third membership function, wherein the response information is used to represent the degree of response of the target object to electricity price data, battery data, and behavioral data; and generating a vehicle configuration strategy based on the response information.

[0115] In this embodiment, user response information to electricity price data, battery performance data, and behavioral data is obtained from the membership function. This response information reflects the user's sensitivity and willingness to respond to these three types of data within a specific time period. Different weights are assigned to the response information for electricity price data, battery data, and behavioral data based on user group characteristics and system objectives. For example, if the objective is to maximize battery health, then the response information for battery data may be given a higher weight. Using a weighted average or a more complex comprehensive evaluation method, the three types of response information are combined to obtain a numerical value representing the user's overall willingness and ability to respond to V2G services.

[0116] Optionally, a framework for vehicle configuration strategies can be designed based on comprehensive response information. These strategies can include aspects such as charging time scheduling, discharge depth setting, and charging / discharging price optimization. V2G parameters are dynamically adjusted based on the level of comprehensive response information. For example, for high-response users, higher discharge incentive prices can be set during peak hours to encourage participation in grid ancillary services; for low-response users, more attractive charging prices need to be offered during off-peak or low-peak hours to incentivize charging while reducing instantaneous load on the grid. Configuration strategies can be customized based on the user's group (determined by a third membership function) to ensure that the strategies meet the needs of specific user groups, improving user satisfaction and engagement.

[0117] During the implementation of the strategy, user response data and battery status information are continuously collected to evaluate the effectiveness of the configuration strategy. Based on the feedback, the configuration strategy parameters are adjusted to adapt to the ever-changing user behavior and grid demands.

[0118] In this embodiment of the invention, to generate a vehicle configuration strategy, electricity price data of electrical equipment, battery data of the vehicle's battery, and behavioral data of the target object can be obtained within different time periods. The electricity price data represents the charging value attribute of the electrical equipment charging the vehicle and the discharging value attribute of the vehicle discharging the electrical equipment. The battery data represents the battery's state, and the behavioral data represents the target object's charging and discharging behaviors towards the vehicle. A membership function can be determined based on the electricity price data, battery data, and behavioral data, representing the degree of influence of these data on the target object. A vehicle configuration strategy can then be generated based on this membership function. In this embodiment, by constructing a membership function that considers electricity price data, battery data, and behavioral data, and introducing a time dimension (different time periods), the degree of influence of these data on the target object within different time periods can be dynamically reflected, thereby generating a vehicle configuration strategy. This solves the technical problem of low accuracy in generating vehicle configuration strategies and improves the accuracy of vehicle configuration strategy generation.

[0119] Example 2

[0120] The following describes in detail another optional implementation method.

[0121] Currently, quantitative models for V2G response intention mainly focus on factors such as incentive prices and battery SOC, neglecting the impact of factors like battery degradation and user driving habits on the quantification results. Most models employ single-dimensional or linear models, failing to fully consider the comprehensive response of users to multiple factors or reflect individual differences among users, resulting in poor model universality and low user engagement. Furthermore, the lack of research on inversely setting V2G parameters based on user response intention makes it difficult to further improve user response intention.

[0122] In related technologies, optimization is typically performed separately on charging / discharging prices or battery losses, lacking a comprehensive optimization mechanism. This fails to balance the relationship between user benefits, battery life, and grid demand, making it difficult to achieve a win-win situation for both users and the grid. When using fuzzy logic systems to quantify response intentions, the membership function construction relies on a simple assignment method, lacking theoretical support and resulting in a high risk of error in the quantification results, making it difficult to reflect reality. The evaluation of user response intentions is based on a fixed Mamdani fuzzy logic system. Although user intentions are quantified through a fuzzy rule base and membership functions, the dynamic changes in user response intentions over different time periods are not considered. This leads to the model's inability to accurately capture user response intentions at different times, affecting the rationality of parameter scheduling and the system optimization effect. Therefore, the technical problem of low accuracy in generating vehicle configuration strategies remains.

[0123] This invention proposes a V2G parameter configuration method based on user dynamic response and driving habits. It constructs membership functions considering user driving habits, charging and discharging costs, and battery degradation, and introduces a time dimension to enable the user response model to dynamically reflect behavior and preferences at different times. This solves the technical problem of low accuracy in generating vehicle configuration strategies and achieves the technical effect of improving the accuracy of vehicle configuration strategy generation.

[0124] The method will be further described below.

[0125] In this embodiment, Figure 2 This is a schematic diagram of a V2G parameter configuration system based on user dynamic response and driving habits according to an embodiment of the present invention, as shown below. Figure 2 As shown, the V2G parameter configuration system includes: Mamdani fuzzy logic module 201, membership function optimization module 202, and parameter setting module 203.

[0126] Mamdani Fuzzy Logic Module 201 utilizes the Mamdani fuzzy logic reasoning method, a reasoning approach for fuzzy control. Based on fuzzy logic, it performs reasoning and decision-making through fuzzification, fuzzy rules, and defuzzification. Input variables include charging / discharging prices, charging rates, discharge depth, and user behavior data. Membership function fuzzification is performed using a membership function constructed by Membership Function Optimization Module 202. Fuzzy rules are then used to perform cluster analysis on the input variables, dividing them into different fuzzy subsets. Charging / discharging prices are divided into low, medium, and high fuzzy subsets; discharge depth is divided into suitable and unsuitable fuzzy subsets; and daily mileage is clustered using FCM to categorize users into short-distance, medium-distance, and long-distance fuzzy subsets. The Apriori association rule mining algorithm is used to mine the associations between different fuzzy subsets in the data, setting support and confidence thresholds to filter fuzzy rules with practical significance. Finally, defuzzification is performed, outputting the quantitative results of user response intentions.

[0127] The membership function optimization module 202 includes the construction and optimization of the membership function of the charging and discharging incentive price (corresponding to the first membership function), the construction and optimization of the membership function of the discharge depth and current ratio (corresponding to the second membership function), and the construction and optimization of the membership function of the user driving habits (corresponding to the third membership function).

[0128] In this embodiment, the membership function for the charging and discharging incentive price is constructed using the Weber-Fechner law to characterize the relationship between changes in user psychology and changes in charging and discharging prices, thus determining the price distribution under different levels of user perception. The charging price P can be... c With discharge price P d As input variables, a day is divided into three periods: peak, off-peak, and low-peak. The psychological effects on users are analyzed at different times. Using the Weber-Fechner law, the psychological effects of charging prices and discharging incentive prices on electric vehicle users are quantified. The quantification formula can be determined as follows:

[0129]

[0130]

[0131] Among them, S c It can be used to represent the intensity of a user's perceived price of charging, S c The smaller the value, the more affordable the current charging price is perceived by the user; S d It can be used to represent the intensity of a user's perceived price of electric discharge; P c 、P dThese can be used to represent the current charging and discharging incentive prices, respectively. P0(t) can be used to represent the psychological reference price at time t (dynamically changing). The psychological reference price needs to be adjusted based on historical charging and discharging price data and real-time dynamics of the V2G market. The analysis of charging and discharging price fluctuations over a period of time, and the statistical analysis of price averages and trends for different time periods, are used as a basis for setting psychological reference prices for different time periods (peak, off-peak, and low-peak periods). c k d These can be used to represent the sensing coefficients for charging and discharging, respectively.

[0132] Optionally, This can be used to quantify users' perception of charging and discharging prices, thereby reflecting the intensity of the psychological impact of price changes on users. In V2G scenarios, users' perception of charging and discharging prices is not based on the absolute price value, but rather on a comparison with a pre-set reference price. When prices begin to rise from a low level, even small price changes can trigger a significant psychological reaction from users; conversely, when prices are at a high level, the same increase in price will elicit a relatively smaller psychological reaction. Price changes can be converted into relative proportions, which can more accurately reflect changes in the intensity of the stimulus.

[0133] Optionally, for the perceived intensity S c 、S d Normalization is performed:

[0134]

[0135] Among them, P c,max 、P c,min These can be used to represent the upper and lower limits of charging prices, respectively. d,max 、P d,min These can be used to represent the upper and lower limits of the discharge price, respectively.

[0136] Optionally, P may include P c 、P d When P = P0(t), the minimum perceived intensity S min All are 0, and the maximum perceived intensity is Further simplification yields the following formula:

[0137]

[0138] Optionally, by introducing user perception bias, S can be... c 、S d After making corrections, we obtain S. sc 、S sd (Different users have different perceptions of charging and discharging prices, S) c With S dThe value of S is affected by uncertainty caused by inter-individual perceptual bias. c 、S d It can be expressed by the following formula:

[0139]

[0140] Where, ΔS c ΔS d These can be used to represent perceived price deviation for charging and perceived price deviation for discharging, respectively.

[0141] Figure 3 This is a schematic diagram of the dynamic changes in a user's perception of charging prices and the membership function graph according to an embodiment of the present invention, such as... Figure 3 As shown, the intensity of users' perceived charging price changes over time or with price fluctuations. The shape and slope of the curve can reveal the sensitivity of user perception. For example, when prices rise rapidly, the curve slope is steeper, indicating that users are more sensitive to price changes. The curve may differ at different times. For instance, during peak electricity consumption periods, users may be more sensitive to charging prices, and the peak value of the curve may be higher, while during off-peak periods, the curve may be flatter, indicating that users are less sensitive to price changes. Based on the curve of perceived price change, a dividing point is determined, and the value interval is divided. The membership function type is then selected based on the distribution.

[0142] Optionally, the membership function type can include triangular membership functions, trapezoidal membership functions, and sigmoid membership functions. A triangular membership function is graphically represented as a triangle with its vertex in the middle and equal slopes on both sides. Triangular functions are suitable for describing fuzzy sets with concepts of "middle," "moderate," or "normal." A trapezoidal membership function is similar to a triangle, but its graph is trapezoidal, meaning that the membership degree of elements remains constant over a wider range. Trapezoidal functions are more flexible than triangular functions and are often used to express extreme fuzzy concepts such as "very low" or "very high." A sigmoid function resembles the letter S. In the region of small input values, the membership degree is close to 0; in the middle region, the membership degree gradually increases from 0 to 1; and in the region of large input values, the membership degree is close to 1. Sigmoid functions are suitable for expressing changes in membership degree that are "gradually increasing" or "gradually decreasing."

[0143] In this embodiment, to describe the combined impact of discharge depth D and current rate C on battery cycle life during scheduling (introducing a time dimension), a thermal effect model based on the Arrhenius equation is used, combined with a Gaussian function to characterize user acceptance. The Arrhenius model can be expressed by the following formula:

[0144]

[0145] Where k can be used to represent the aging rate constant; A can be used to represent the frequency factor, representing the baseline value of the aging rate; E a It can be used to represent activation energy (in J / mol) and describe the effect of temperature on aging rate; R can be used to represent gas constant (8.314 J / (mol·K)); T can be used to represent temperature (in K).

[0146] Optionally, the depth of discharge (D) and current rate (C) are the main factors affecting battery aging, and the aging rate can be described by the following extended formula:

[0147]

[0148] Among them, D α It can be used to represent the contribution factor of discharge depth D to aging rate; C β It can be used to represent the contribution factor of current ratio C to aging rate.

[0149] Optionally, user acceptance μ(t) is a subjective representation of battery performance degradation, which can be described using a Gaussian function:

[0150]

[0151] Wherein, μ(t) can be used to represent user acceptance, ranging from [0,1]. The higher the user acceptance value, the higher the user's acceptance of the current battery performance; L(t) can be used to represent the remaining battery life (which varies over time); σ can be used to represent the standard deviation, which represents the user's tolerance range for battery performance degradation.

[0152] Optionally, a time dimension can be introduced to determine the battery life L(t):

[0153]

[0154] L0 can be used to represent the initial battery life (normalized to 1 or the number of cycles).

[0155] Figure 4 This is a schematic diagram illustrating the dynamic changes in battery life and user acceptance with depth of discharge and current rate according to an embodiment of the present invention. Figure 4 As shown, the battery life varies with the depth of discharge (D) and current rate (C). Generally, as D and C increase, the battery's cycle life gradually decreases because deep discharge and high current rates cause greater damage to the battery's chemical and physical structure. Figure 4The shape of the curve reveals the rate of battery life decline under different D and C combinations. For example, the curve is flatter when D and C are low, indicating that battery life is less affected in this case; while when D and C are high, the slope of the curve increases significantly, indicating that battery life declines more rapidly. User acceptance is an indicator of user sentiment or satisfaction with V2G parameter configurations (such as charging and discharging strategies), typically represented by 1 for complete acceptance and 0 for complete rejection. Figure 4 The user acceptance curve reflects users' tolerance for battery performance degradation. User acceptance may decrease as D and C increase, because deep discharge and high current rates reduce battery life, thus affecting overall battery performance and lowering user satisfaction.

[0156] Optionally, based on the degree of acceptance, the intervals can be divided into high acceptance intervals, medium acceptance intervals (transition intervals), and low acceptance intervals, and the membership function type can be selected according to the distribution.

[0157] In this embodiment, user driving habit data mainly manifests as daily mileage and driving time distribution. Data is collected and cleaned daily, and outliers and noise are removed using statistical methods to prevent interference with clustering results and ensure the data reflects users' daily travel patterns. Finally, the processed data is normalized, mapping data with different features to the [0,1] interval to ensure consistent weights for each feature in the clustering analysis and improve clustering effectiveness. The normalization process uses max-min normalization, and its formula is shown below, where x represents the original data, x... min x max Let x be the minimum and maximum values ​​in the data. norm It is normalized data.

[0158]

[0159] Optionally, in the V2G scenario, users corresponding to daily mileage are divided into three categories: short-distance, medium-distance, and long-distance, with a cluster size C=3. C=3 data points are randomly selected from the dataset as initial cluster centers. Then, the K-means++ clustering algorithm is used to randomly select one data point as the first cluster center. Subsequently, the data point furthest from the selected cluster center is selected as the next cluster center, and this process is repeated until C cluster centers are selected. (The probability of each data point being selected as the next cluster center is proportional to the square of its nearest distance to the nearest selected cluster center).

[0160] Optionally, the distance d(x,y) from each data point x to each cluster center y is calculated using Euclidean distance, with the following formula:

[0161]

[0162] Optionally, the membership degree calculation formula in the fuzzy C-means algorithm is used for data point x. i Membership degree u of cluster j ij for:

[0163]

[0164] Where d(x) i ,v j This can be used to represent the distance from data points to cluster centers (v). j The distance; d(x) i ,v k This can be used to represent the distance from data points to cluster centers (v). k The distance; m can be used to represent the fuzzy weight index, m∈(1,+∞), and can take the value 2.

[0165] Optionally, the cluster center positions are updated based on the current membership matrix and data points, for the dataset {x1, x2, ..., x...} n}, the number of clusters is C, the fuzzy weight exponent is m, and the j-th cluster center is v. j The updated formula is as follows (that is, each cluster center is a weighted average of all data points with the membership degree raised to the power of m).

[0166]

[0167] in, It can be used to represent the membership degree of the i-th data point to the j-th cluster.

[0168] Optionally, using the updated cluster centers, the membership degree of each data point to each cluster is recalculated according to the previous membership degree calculation formula (14) to further optimize the clustering results. Intervals are divided based on the cluster centers and cluster boundaries obtained from fuzzy C-means clustering. Cluster centers represent typical behavioral characteristics of different user groups, and cluster boundaries define the range of different groups. Three user groups with different mileage characteristics are obtained through clustering. Based on each cluster center and combined with the cluster boundaries, mileage intervals corresponding to different groups are divided, and the membership function type is selected.

[0169] Optionally, the driving time distribution method is the same as the daily driving mileage method.

[0170] After obtaining the output user response willingness quantification results, the parameter setting module 203 can select the input corresponding to high response willingness and configure V2G parameters according to the user's psychological expectation range.

[0171] Optionally, cluster analysis is performed on the input variables to divide them into different fuzzy subsets. Charging and discharging prices can be divided into low, medium, and high fuzzy subsets, and discharge depth into suitable and unsuitable fuzzy subsets. Daily mileage is clustered using FCM to categorize users into short-distance, medium-distance, and long-distance fuzzy subsets. The Apriori association rule mining algorithm is used to mine the associations between different fuzzy subsets in the data. Support and confidence thresholds are set to filter fuzzy rules with practical significance. The collected data is divided into training and testing sets. Fuzzy rules are established on the training set, and their accuracy and generalization ability are tested on the testing set. Based on the validation results, the rules are adjusted and improved to enhance the predictive accuracy of fuzzy rules for user response intentions and their guiding value for V2G parameter configuration.

[0172] The weighted average method is used for deblurring, and the corresponding formula for the deblurred output result is as follows:

[0173]

[0174] Where y represents the user's willingness to respond, x i The value represents the input parameter, μ(x) i ) represents the membership function.

[0175] Optionally, during the scheduling process, for different vehicle users in the current time period, the parameter setting module selects the range of input variables corresponding to high response willingness, which can determine the range of user psychological expectations for each V2G parameter under the high response willingness state.

[0176] This invention provides a vehicle configuration strategy generation apparatus. It should be noted that this vehicle configuration strategy generation apparatus can be used to execute... Figure 1 This invention provides a method for generating vehicle configuration strategies. The following describes the apparatus for generating vehicle configuration strategies provided in this embodiment.

[0177] Figure 5 This is a schematic diagram of a vehicle configuration strategy generation device according to an embodiment of the present invention, as shown below. Figure 5 As shown, the vehicle configuration strategy generation device 500 may include: an acquisition unit 502, a determination unit 504, and a generation unit 506.

[0178] The acquisition unit 502 is used to acquire electricity price data of power equipment, battery data of battery in vehicle, and behavior data of target object within different time periods. Among them, electricity price data is used to represent the charging value attribute of power equipment charging vehicle and the discharging value attribute of vehicle discharging power equipment, battery data is used to represent battery state, and behavior data is used to represent the charging behavior and discharging behavior of target object to vehicle.

[0179] The determination unit 504 is used to determine the membership function based on electricity price data, battery data, and behavioral data, wherein the membership function is used to represent the degree of influence of electricity price data, battery data, and behavioral data on the target object.

[0180] The generation unit 506 is used to generate a vehicle configuration strategy based on a membership function, wherein the configuration strategy is used to represent the rules by which the target object adjusts the configuration information of the vehicle.

[0181] Optionally, the membership function includes a first membership function, which represents the degree of influence of electricity price data on the target object within different time periods. The determining unit includes: a first partitioning module, used to partition different time periods to obtain partitioning results; a first determining module, used to determine the target object's perception information of the electricity price data based on the electricity price data and the partitioning results, wherein the perception information is used to determine whether the target object performs charging or discharging behavior on the vehicle according to the electricity price data; and a second determining module, used to analyze the perception information to determine the first membership function.

[0182] Optionally, the membership function includes a second membership function, which represents the degree of influence of battery data on the target object within different time periods. The determination module includes: a third determination module, used to determine the performance change information of the battery based on the battery data, wherein the change information represents the degree of performance degradation of the battery; a fourth determination module, used to determine the target object's acceptance information of the degradation, wherein the acceptance information represents the target object's acceptance of the degradation; a second partitioning module, used to partition the acceptance information into intervals to obtain interval partitioning results; and a fifth determination module, used to determine the second membership function based on the interval partitioning results.

[0183] Optionally, the membership function includes a third membership function, which represents the degree of influence of behavioral data on the target object within different time periods. The determination module includes: a processing module, used to standardize the behavioral data to obtain processed behavioral data; and an analysis module, used to perform cluster analysis on the processed behavioral data using a fuzzy clustering model to determine the third membership function. The fuzzy clustering model is obtained by training an initial fuzzy clustering model using behavioral data samples.

[0184] Optionally, the second determining module includes: a processing module for normalizing the perceived information to obtain processed perceived information; an acquisition module for acquiring perceived deviation information of the target object, wherein the perceived deviation information represents the difference of the target object to the electricity price data; an adjustment module for adjusting the processed perceived information based on the perceived deviation information, wherein the accuracy of the adjusted perceived information is higher than the accuracy of the perceived information before adjustment; and a sixth determining module for determining a first membership function corresponding to the distribution of the adjusted perceived information.

[0185] Optionally, the generating apparatus further includes: a classification unit, used to classify the type of the target object according to the processed behavioral data to obtain a classification result; and a first determining unit, used to determine the number of classification results as the number of cluster centers of the fuzzy clustering model.

[0186] Optionally, the analysis module includes: a seventh determination module, used to select initial data points from the processed behavioral data and determine the initial data points as the initial cluster centers of the fuzzy clustering model; and to determine the target data points whose distances are greater than a distance threshold as the next cluster centers of the initial cluster centers; an eighth determination module, used to determine the distances between the processed behavioral data points other than the initial data points and the initial cluster centers; repeating the following steps until the number of selected target cluster centers equals the number of cluster centers: determining the distances between the processed behavioral data points other than the initial data points and the initial cluster centers; determining the target data points whose distances are greater than a distance threshold as the next cluster centers of the initial cluster centers; and using the fuzzy clustering model to perform cluster analysis on the processed behavioral data to determine the third membership function, including: a ninth determination module, used to update the initial cluster centers based on the distances and the distances between the initial data points and the initial cluster centers to obtain the third membership function.

[0187] Optionally, the generation unit includes: an eleventh determining module, used to determine the response information of the target object in different time periods based on the first membership function, the second membership function, and the third membership function, wherein the response information is used to represent the degree of response of the target object to electricity price data, battery data, and behavioral data; and a generation module, used to generate a vehicle configuration strategy based on the response information.

[0188] The vehicle configuration strategy generation device provided in this embodiment of the invention acquires electricity price data of electrical equipment, battery data of the vehicle's battery, and behavioral data of the target object within different time periods through an acquisition unit 502. The electricity price data represents the charging value attribute of the electrical equipment charging the vehicle and the discharging value attribute of the vehicle discharging the electrical equipment. The battery data represents the battery's state, and the behavioral data represents the target object's charging and discharging behaviors towards the vehicle. A determination unit 504 determines a membership function based on the electricity price data, battery data, and behavioral data, where the membership function represents the degree of influence of the electricity price data, battery data, and behavioral data on the target object. A generation unit 506 generates a vehicle configuration strategy based on the membership function, where the configuration strategy represents the rules by which the target object adjusts the vehicle's configuration information. This solves the technical problem of low accuracy in generating vehicle configuration strategies and achieves the technical effect of improving the accuracy of vehicle configuration strategy generation.

[0189] According to an embodiment of the present invention, a computer-readable storage medium is also provided, on which a program is stored, which, when executed by a processor, implements the method of the embodiments of the present invention.

[0190] According to an embodiment of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the method of the embodiment of the present invention during runtime.

[0191] Figure 6 This is a schematic diagram of an electronic device according to an embodiment of the present invention, such as... Figure 6 As shown in the embodiment of the present invention, an electronic device 600 is also provided. The device includes a processor 601, a memory 602, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the above steps.

[0192] The devices mentioned in this article can be servers, PCs, tablets (Portable Automated Devices, or PADs for short), mobile phones, etc.

[0193] The present invention also provides a computer program product that, when executed on a data processing device, is adapted to execute a program that initializes the above-described method steps.

[0194] 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, compact disc read-only memory (CD-ROM), optical storage, etc.) containing computer-usable program code.

[0195] 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 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0196] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0197] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0198] In a typical configuration, a computing device includes one or more central processing units (CPUs), input / output interfaces, network interfaces, and memory.

[0199] Memory may include non-persistent memory in computer-readable media, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0200] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0201] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0202] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0203] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for generating a vehicle configuration strategy, characterized in that, include: The system acquires electricity price data for electrical equipment, battery data for vehicles, and behavioral data for target objects within different time periods. The electricity price data represents the charging value attribute of the electrical equipment charging the vehicle and the discharging value attribute of the vehicle discharging the electrical equipment. The battery data represents the state of the battery. The behavioral data represents the charging and discharging behaviors of the target object towards the vehicle. Based on the electricity price data, the battery data, and the behavioral data, a membership function is determined, wherein the membership function is used to represent the degree of influence of the electricity price data, the battery data, and the behavioral data on the target object; Based on the membership function, a configuration strategy for the vehicle is generated, wherein the configuration strategy represents the rules for adjusting the configuration information of the vehicle.

2. The method for generating a vehicle configuration strategy according to claim 1, characterized in that, The membership function includes a first membership function, which represents the degree of influence of the electricity price data on the target object within different time periods. The membership function is determined based on the electricity price data, the battery data, and the behavioral data, including: The time periods were divided into different segments to obtain the segmentation results; Based on the electricity price data and the division result, the target object's perception information of the electricity price data is determined, wherein the perception information is used to determine whether the target object performs the charging behavior or the discharging behavior of the vehicle according to the electricity price data; The perceived information is analyzed to determine the first membership function.

3. The method for generating a vehicle configuration strategy according to claim 2, characterized in that, The membership function includes a second membership function, which represents the degree of influence of the battery data on the target object within different time periods. The membership function is determined based on the electricity price data, the battery data, and the behavioral data, including: Based on the battery data, information on changes in the battery's performance is determined, wherein the information on changes indicates the degree of performance degradation of the battery. Determine the target object's acceptance information regarding the degree of descent, wherein the acceptance information represents the target object's acceptance level of the degree of descent; The received information is divided into intervals to obtain interval division results; Based on the interval partitioning results, the second membership function is determined.

4. The method for generating a vehicle configuration strategy according to claim 2, characterized in that, The membership function includes a third membership function, which represents the degree of influence of the behavioral data on the target object within different time periods. The membership function is determined based on the electricity price data, the battery data, and the behavioral data, including: The behavioral data is standardized to obtain the processed behavioral data. The processed behavioral data is clustered using a fuzzy clustering model to determine the third membership function. The fuzzy clustering model is obtained by training an initial fuzzy clustering model using behavioral data samples.

5. The method for generating a vehicle configuration strategy according to claim 2, characterized in that, Analyzing the perceived information to determine the first membership function includes: The sensed information is normalized to obtain the processed sensed information; Obtain the perception deviation information of the target object, wherein the perception deviation information is used to represent the difference of the target object to the electricity price data; Based on the perception deviation information, the processed perception information is adjusted, wherein the accuracy of the adjusted perception information is higher than the accuracy of the perception information before adjustment. Determine the first membership function corresponding to the distribution of the adjusted perceived information.

6. The method for generating a vehicle configuration strategy according to claim 4, characterized in that, The method further includes: Based on the processed behavioral data, the target object is classified into different types to obtain a classification result. The number of the classification results is determined as the number of cluster centers of the fuzzy clustering model.

7. The method for generating a vehicle configuration strategy according to claim 6, characterized in that, Using a fuzzy clustering model, cluster analysis is performed on the processed behavioral data to determine the third membership function, including: Initial data points are selected from the processed behavioral data, and these initial data points are determined as the initial cluster centers of the fuzzy clustering model. Determine the distances between the processed behavioral data points other than the initial data points and the initial cluster center; Target data points whose distances are greater than the distance threshold are determined as the next cluster centers of the initial cluster centers; Repeat the following steps until the number of target cluster centers is equal to the stated number of cluster centers: Determine the distances between the processed behavioral data points other than the initial data points and the initial cluster center; Target data points whose distances are greater than the distance threshold are determined as the next cluster centers of the initial cluster centers; Using a fuzzy clustering model, cluster analysis is performed on the processed behavioral data to determine the third membership function, including: Based on the distance and the distance between the initial data point and the initial cluster center, the initial cluster center is updated to obtain the third membership function.

8. The method for generating a vehicle configuration strategy according to claim 7, characterized in that, Based on the membership function, the configuration strategy for the vehicle is generated, including: Based on the first membership function, the second membership function, and the third membership function, the response information of the target object in different time periods is determined, wherein the response information is used to represent the degree of response of the target object to the electricity price data, the battery data, and the behavioral data; Based on the response information, a configuration strategy for the vehicle is generated.

9. An apparatus for generating a vehicle configuration strategy, characterized in that, include: The acquisition unit is used to acquire electricity price data of power equipment, battery data of battery in vehicle, and behavior data of target object within different time periods. The electricity price data is used to represent the charging value attribute of the power equipment charging the vehicle and the discharging value attribute of the vehicle discharging the power equipment. The battery data is used to represent the state of the battery. The behavior data is used to represent the charging behavior and discharging behavior of the target object to the vehicle. The determining unit is configured to determine a membership function based on the electricity price data, the battery data, and the behavioral data, wherein the membership function is used to represent the degree of influence of the electricity price data, the battery data, and the behavioral data on the target object; The generation unit is used to generate a configuration strategy for the vehicle based on the membership function, wherein the configuration strategy is used to represent the rules by which the target object adjusts the configuration information of the vehicle.

10. The generating apparatus according to claim 9, characterized in that, The membership function includes a first membership function, which represents the degree of influence of the electricity price data on the target object within different time periods. The determining unit includes: The first segmentation module is used to segment different time periods and obtain the segmentation results; The first determining module is used to determine the target object's perception information of the electricity price data based on the electricity price data and the division result, wherein the perception information is used to determine whether the target object performs the charging behavior or the discharging behavior of the vehicle according to the electricity price data; The second determining module is used to analyze the perceived information and determine the first membership function.

11. The generating apparatus according to claim 10, characterized in that, The membership function includes a second membership function, which represents the degree of influence of the battery data on the target object within different time periods. The determining module includes: The third determining module is used to determine the performance change information of the battery based on the battery data, wherein the change information is used to indicate the degree of performance degradation of the battery; The fourth determining module is used to determine the target object's acceptance information regarding the degree of descent, wherein the acceptance information is used to represent the target object's acceptance level of the degree of descent; The second partitioning module is used to partition the received information into intervals to obtain interval partitioning results. The fifth determining module is used to determine the second membership function based on the interval partitioning result.

12. The generating apparatus according to claim 10, characterized in that, The membership function includes a third membership function, which is used to represent the degree of influence of the behavioral data on the target object within different time periods. The determining module includes: The processing module is used to standardize the behavioral data to obtain the processed behavioral data; The analysis module is used to perform cluster analysis on the processed behavioral data using a fuzzy clustering model to determine the third membership function, wherein the fuzzy clustering model is obtained by training an initial fuzzy clustering model using behavioral data samples.

13. The generating apparatus according to claim 10, characterized in that, The second determining module includes: The processing module is used to normalize the perceived information to obtain the processed perceived information; An acquisition module is used to acquire the perception deviation information of the target object, wherein the perception deviation information is used to represent the difference of the target object to the electricity price data; An adjustment module is used to adjust the processed perception information based on the perception deviation information, wherein the accuracy of the adjusted perception information is higher than the accuracy of the perception information before adjustment. The sixth determining module is used to determine the first membership function corresponding to the distribution of the adjusted perceived information.

14. The generating apparatus according to claim 12, characterized in that, The generating apparatus further includes: A classification unit is used to classify the type of the target object according to the processed behavioral data to obtain a classification result; The first determining unit is used to determine the number of the classification results as the number of cluster centers of the fuzzy clustering model.

15. The generating apparatus according to claim 14, characterized in that, The analysis module includes: The seventh determining module is used to select initial data points from the processed behavioral data and determine the initial data points as the initial cluster centers of the fuzzy clustering model; and to determine the target data points whose distances are greater than a distance threshold as the next cluster centers of the initial cluster centers. The eighth determining module is used to determine the distance between the processed behavioral data points other than the initial data points and the initial cluster center. Repeat the following steps until the number of target cluster centers is equal to the stated number of cluster centers: Determine the distances between the processed behavioral data points other than the initial data points and the initial cluster center; identify the target data points whose distances are greater than a distance threshold as the next cluster center of the initial cluster center; Using a fuzzy clustering model, cluster analysis is performed on the processed behavioral data to determine the third membership function, including: The ninth determining module is used to update the initial cluster center based on the distance and the distance between the initial data point and the initial cluster center to obtain the third membership function.

16. The generating apparatus according to claim 15, characterized in that, The generation unit includes: The eleventh determining module is used to determine the response information of the target object in different time periods based on the first membership function, the second membership function, and the third membership function, wherein the response information is used to represent the degree of response of the target object to the electricity price data, the battery data, and the behavior data; A generation module is used to generate a configuration strategy for the vehicle based on the response information.

17. A processor, characterized in that, The processor is used to run a program, wherein the program, when run by the processor, executes the method for generating a vehicle configuration strategy according to any one of claims 1 to 8.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method for generating a configuration strategy for a vehicle as described in any one of claims 1 to 8.

19. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method for generating a configuration strategy for a vehicle as described in any one of claims 1 to 8.

20. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method for generating a vehicle configuration strategy according to any one of claims 1 to 8.

Images