Electric vehicle adjustable potential calculation method and system considering user charging behavior characteristics

Abstract

The invention discloses an electric vehicle adjustable potential calculation method and system considering user charging behavior characteristics, and the method comprises the steps: building a detailed boundary model of different charging behavior characteristics of an electric vehicle through analyzing the charging behavior characteristics of different users, and carrying out the aggregation of the parameters of the electric vehicle based on the Minkowski summation theory; according to the detailed boundary model of different charging behavior characteristics of the electric vehicle, utilizing a PSO-LSTM algorithm to predict the aggregated electric vehicle parameters; a three-way decision model based on the regret theory is established according to the uncertainty of user willingness, a self-scheduling model is established by considering the user willingness, and the schedulable potential of the electric vehicle cluster is calculated based on predicted electric vehicle parameters and the self-scheduling model, so that the electric vehicle cluster can better realize load peak clipping and valley filling and provide standby capacity.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle adjustable potential calculation, and in particular to an electric vehicle adjustable potential calculation method and system taking into account user charging behavior characteristics. Background Art

[0002] Electric Vehicles (EVs), as an important part of modern transportation, not only help reduce the consumption of fossil fuels and reduce environmental pollution, but also become an indispensable part of smart grids because of their flexible power loads. Electric vehicles have significant advantages in achieving load peak shaving and valley filling and participating in the auxiliary service market of the power system. Especially during peak periods of electricity demand, electric vehicles can provide backup capacity to the power grid through orderly charging or discharging technology, thereby helping to stabilize the frequency and voltage of the power grid and improve the overall stability of the power grid.

[0003] However, it is not easy to fully realize the potential of electric vehicles as flexible loads, mainly because there is a high degree of uncertainty in the willingness of users to participate in different charging behaviors. This uncertainty is not only affected by factors such as personal habits and preferences, but also by external social factors such as policy orientation and public opinion. If the charging patterns and psychological factors of users are ignored when modeling the dispatchable potential of electric vehicles, it may lead to deviations in the model prediction results, which in turn affects the accuracy and effectiveness of scheduling decisions.

[0004] Although many methods have been proposed to evaluate and predict the dispatchable potential of electric vehicles, they still face many challenges in practical applications. On the one hand, the modeling of the boundary conditions of a single electric vehicle is not accurate enough, which means that the existing models may not accurately reflect the specific available capacity of each electric vehicle at a specific time and place; on the other hand, the prediction of the dispatchable potential of the entire electric vehicle group is not accurate enough, especially when considering the large-scale access of electric vehicles to the power grid. How to effectively integrate the diverse individual behaviors of electric vehicles to form an effective cluster dispatch strategy is still an urgent problem to be solved. Therefore, in order to overcome the above limitations and further improve the utilization efficiency of electric vehicles as flexible loads, it is necessary to develop a new calculation method and dispatch system that can fully consider the characteristics of user charging behavior, so as to more accurately calculate the dispatchable potential of electric vehicles. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method and system for calculating the adjustable potential of electric vehicles taking into account the characteristics of user charging behavior, with the purpose of accurately quantifying the dispatchable potential of electric vehicle clusters based on predicting electric vehicle parameters and distinguishing the charging behavior of electric vehicle users.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for calculating the adjustable potential of electric vehicles taking into account the charging behavior characteristics of users, comprising: establishing a detailed boundary model of different charging behavior characteristics of electric vehicles by analyzing the charging behavior characteristics of different users, and aggregating electric vehicle parameters based on the Minkowski sum theory; predicting the aggregated electric vehicle parameters using the PSO-LSTM algorithm based on the detailed boundary model of different charging behavior characteristics of the electric vehicles; establishing a three-branch decision model based on the regret theory for the uncertainty of user willingness and establishing a self-scheduling model taking into account the user willingness, and calculating the dispatchable potential of an electric vehicle cluster based on the predicted electric vehicle parameters and the self-scheduling model.

[0009] As a preferred solution of the electric vehicle adjustable potential calculation method considering the user charging behavior characteristics of the present invention, wherein: the detailed boundary model of different charging behavior characteristics of electric vehicles is established, including:

[0010] Users who adopt charging and discharging behaviors after arriving at the station are represented as Class I users, users who adopt charging behaviors after arriving at the station but only change the charging time are represented as Class II users, and users who directly charge without order after arriving at the station are represented as Class III users. By analyzing the charging behavior characteristics of different users, a detailed boundary model of different charging behavior characteristics of electric vehicles is established, and the formula is expressed as follows:

[0011]

[0012] in, represents the maximum state of charge boundary of the i-th electric vehicle of Class I and Class II users at time t, represents the minimum state of charge boundary of the i-th electric vehicle of Class I user at time t, represents the minimum state of charge boundary of the i-th electric vehicle of Class II user at time t, P i + (t), P i - (t) represent the charge and discharge power boundaries, E0 represents the initial state of charge, E d represents the expected charge capacity of the battery, E + (t-1) and E - (t-1) represent the maximum and minimum charge state boundaries of the electric vehicle at time t-1, t a,t d They represent the time when the electric vehicle enters the grid and the time when it leaves the station, P ch , P dis They represent the maximum charging and discharging power of electric vehicles, η represents the charging and discharging efficiency, E min Indicates the lower limit of battery discharge, and They represent the maximum and minimum state of charge boundaries of the electric vehicle at time t+1 respectively.

[0013] As a preferred solution of the electric vehicle adjustable potential calculation method considering the user charging behavior characteristics of the present invention, wherein: the aggregation of electric vehicle parameters based on the Minkowski summation theory includes:

[0014] Based on the Minkowski summation theory, the parking matrix X is introduced to make electric vehicles have the same definition domain, and then the maximum and minimum power and capacity of N electric vehicles are aggregated to form a generalized energy storage model, that is, the electric vehicle parameters are aggregated into the parameters of the generalized energy storage model The formula is:

[0015]

[0016] Among them, x it represents the parking coefficient of the i-th electric vehicle at time t. The value is 1 when the electric vehicle is parked at the charging station and 0 when it leaves the charging station. They represent the maximum charge and discharge power of the generalized energy storage model at time t, They are the maximum and minimum power of the generalized energy storage model at time t respectively.

[0017] As a preferred solution of the electric vehicle adjustable potential calculation method considering the user charging behavior characteristics of the present invention, wherein: the prediction of the aggregated electric vehicle parameters using the PSO-LSTM algorithm includes:

[0018] Preprocessing the input electric vehicle network access time, electric vehicle departure time, and initial battery charge state, filtering out data that cannot be scheduled due to short parking time, and dividing the preprocessed data into a training set and a test set;

[0019] The particle swarm algorithm is used to initialize and assign values ​​to the four parameters of the LSTM model, and the LSTM model is trained according to the training set and the test set. When the loss value of the LSTM model meets the requirements, the result is output, otherwise the parameters are updated until the LSTM model meets the requirements and outputs the final result.

[0020] As a preferred solution of the electric vehicle adjustable potential calculation method considering the user charging behavior characteristics of the present invention, the three-branch decision model based on regret theory is established for the uncertainty of user willingness, including:

[0021] The user's willingness model for participating in different charging behaviors is expressed as:

[0022]

[0023] Where Pu(o1) represents the perceived utility function of user o1, u(r 11 ) and u(r 12 ) represent actions r 11 and r 12 The utility value obtained, u(r * ) indicates behavior r * The utility function of , γ represents the risk aversion coefficient of the decision maker, Δu represents the difference in utility values ​​of different behaviors, R(Δu) represents the regret-delight function, and η represents the regret aversion coefficient of the decision maker;

[0024] The flexible vehicle anxiety W borne by electric vehicle users is calculated based on the user willingness model for participating in different charging behaviors. T and the user's expected cost-benefit W c , the formula is:

[0025]

[0026] Among them, k1 represents the maximum value of the decision factor used to describe the anxiety of flexible car use, k2 represents the degree of change of flexible car use anxiety over time, and f E It means that the user expects to provide the maximum dispatchable capacity to obtain benefits, Indicates the loss of electric vehicle batteries due to additional charging and discharging. and Respectively represent the power loss under unit charging and discharging power, t c With t d Represent the additional charging and discharging time, t c0 With t d0 Respectively represent the initial charge and discharge time within the additional charge and discharge time, P i exc (t), P i exd (t) respectively represent the additional charging and discharging power of the i-th electric vehicle at time t, Δt c With Δt d Respectively represent the charging and discharging time periods within the additional charging and discharging time, p up (t) and p down (t) represents the compensation electricity price for the upward and downward regulation capacity, and Indicates the maximum upper scheduling capacity and the maximum lower scheduling capacity.

[0027] As a preferred solution of the method for calculating the adjustable potential of electric vehicles taking into account the user's charging behavior characteristics of the present invention, it also includes:

[0028] The flexible use anxiety of electric car users T and the user's expected cost-benefit W c Normalize and select each user and As an attribute to evaluate the user's willingness to participate;

[0029] The deviation maximization method is used to assign weights to the attributes that affect user participation in regulation. The calculation method is:

[0030]

[0031]

[0032] Among them, ω j represents the weight of attribute j, N represents the total number of users, i and k represent different users, and a ij -a kj represents the evaluation values ​​of different users under the same attribute, Pu(a ij ) represents the perceived utility value of user i under attribute j, u ij represents the utility value of user i under attribute j, Indicates u ij Relative to u kj The overall regret-delight value;

[0033] After the weights are assigned, the perceived utility values ​​of an object under each attribute are summarized using the weighted arithmetic mean method to obtain the overall perceived utility value of the object, and the overall perceived utility values ​​are sorted in descending order to obtain the ranking result of the target;

[0034] According to the ranking results, the user with the highest willingness to participate in regulation is obtained based on the classic multi-criteria analysis method. T1 and users with the lowest willingness to participate in regulation T2 , the calculation formula is:

[0035]

[0036] Will be with o T1 Users with high similarity are classified as type I users. T2 Users with high similarity are classified as Class III users, and other users are classified as Class II users. Among them, users who are hesitant to participate in regulation are also classified as Class II users.

[0037] As a preferred solution of the method for calculating the adjustable potential of electric vehicles considering the user charging behavior characteristics of the present invention, the calculation of the dispatchable potential of electric vehicle clusters includes:

[0038] Taking the optimal user economy as the objective function and the aggregated generalized energy storage model as the constraint condition, the self-dispatching load of the electric vehicle cluster is calculated considering the probability of different charging behaviors. The formula is expressed as:

[0039]

[0040] Among them, F obj represents the objective function of user economic optimization, C(t) represents the electricity price, P i,ch (t), P i,dis (t) respectively represent the charging and discharging power of the i-th vehicle at time t, P i (t) represents the charge and discharge power, E i (t) represents the battery charge, E i (t+1) means the amount of electricity at time t+1 is equal to the sum of the amount of electricity at the previous time and the charge and discharge power at the previous time;

[0041] Travel anxiety is calculated according to the parameters of a single electric vehicle, and cost anxiety is calculated by economically optimal self-scheduling of charging and discharging. Users are classified based on the three-branch decision model of regret theory, and economically optimal self-scheduling of charging is performed for Class II electric vehicles, while disorderly charging is performed for Class III electric vehicles. The three types of electric vehicles together constitute the self-scheduling load of the electric vehicle cluster through different self-scheduling. The difference between the boundary of the generalized energy storage model and the self-scheduling load of the electric vehicle cluster is the dispatchable potential of the electric vehicle cluster.

[0042] In a second aspect, the present invention provides an electric vehicle adjustable potential calculation system taking into account user charging behavior characteristics, comprising:

[0043] An electric vehicle capacity boundary modeling unit, used to establish a detailed boundary model of different charging behavior characteristics of the electric vehicle by analyzing the charging behavior characteristics of different users, wherein the charging behaviors of different users include charging and discharging, charging with changing charging time, and disordered charging;

[0044] An automobile parameter aggregation prediction unit, used for aggregating electric vehicle parameters based on the Minkowski summation theory, and predicting the aggregated electric vehicle parameters using a PSO-LSTM algorithm according to a detailed boundary model of different charging behavior characteristics of the electric vehicle;

[0045] The electric vehicle self-dispatching load modeling unit is used to establish a three-branch decision model based on regret theory for the uncertainty of user willingness and to establish a self-dispatching model considering user willingness;

[0046] An electric vehicle dispatchable potential calculation unit is used to calculate the dispatchable potential of an electric vehicle cluster based on the predicted electric vehicle parameters and the self-dispatching model, wherein the self-dispatching load curve reaches the boundary of the generalized energy storage model through the upper adjustment capacity, the lower adjustment capacity, the upper adjustment power, and the lower adjustment power, and the upper adjustment capacity, the lower adjustment capacity, the upper adjustment power, and the lower adjustment power together constitute the dispatchable potential of the electric vehicle cluster.

[0047] In a third aspect, the present invention provides a computing device, comprising:

[0048] Memory and processor;

[0049] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method are implemented.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which implement the steps of the method when executed by a processor.

[0051] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention first establishes a detailed boundary model of different charging behavior characteristics of electric vehicles, and then predicts the aggregation parameters of electric vehicles based on PSO-LSTM, accurately predicts the power boundary and capacity boundary of the GES model, and then characterizes the user's willingness based on the three-way decision (T-WD) model of regret theory (RT) to establish an electric vehicle self-dispatching load model, calculates the dispatchable potential of electric vehicles, and enables electric vehicle clusters to better achieve load peak shaving and valley filling and provide spare capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0053] Figure 1 This is an overall flow chart of a method for calculating the adjustable potential of an electric vehicle taking into account the charging behavior characteristics of a user according to an embodiment of the present invention;

[0054] Figure 2 A schematic diagram of a boundary model under different charging behavior characteristics of a method for calculating an adjustable potential of an electric vehicle taking into account the charging behavior characteristics of a user according to an embodiment of the present invention;

[0055] Figure 3A block diagram of electric vehicle parameter prediction based on PSO-LSTM of an electric vehicle adjustable potential calculation method considering user charging behavior characteristics according to an embodiment of the present invention;

[0056] Figure 4 A schematic diagram of the prediction result of the EV1 parking start time of the electric vehicle adjustable potential calculation method considering the user charging behavior characteristics according to an embodiment of the present invention;

[0057] Figure 5 A schematic diagram of the prediction result of the parking end time of EV1 according to the electric vehicle adjustable potential calculation method considering the user charging behavior characteristics according to an embodiment of the present invention;

[0058] Figure 6 A schematic diagram of the prediction result of the initial state of charge of EV1 of the method for calculating the adjustable potential of an electric vehicle taking into account the charging behavior characteristics of a user according to an embodiment of the present invention;

[0059] Figure 7 A flow chart of a T-WD model based on RT for calculating an adjustable potential of an electric vehicle taking into account the charging behavior characteristics of a user according to an embodiment of the present invention;

[0060] Figure 8 A user willingness ranking diagram of a method for calculating adjustable potential of electric vehicles considering user charging behavior characteristics according to an embodiment of the present invention;

[0061] Fig. 9 A user willingness classification diagram of a method for calculating adjustable potential of an electric vehicle considering user charging behavior characteristics according to an embodiment of the present invention;

[0062] Fig.10 A flow chart of an electric vehicle self-dispatching load model considering user willingness of a method for calculating an electric vehicle adjustable potential considering user charging behavior characteristics according to an embodiment of the present invention;

[0063] Fig.11 A schematic diagram of the number of charging and discharging electric vehicles according to a method for calculating the adjustable potential of electric vehicles taking into account the charging behavior characteristics of users according to an embodiment of the present invention;

[0064] Fig.12 A schematic diagram of an electric vehicle cluster self-dispatching result of an electric vehicle adjustable potential calculation method considering user charging behavior characteristics according to an embodiment of the present invention;

[0065] Fig.13 A schematic diagram of quantifying the dispatchable power of an electric vehicle cluster according to a method for calculating the adjustable potential of electric vehicles taking into account the charging behavior characteristics of users according to an embodiment of the present invention;

[0066] Fig.14A schematic diagram of quantifying the dispatchable capacity of an electric vehicle cluster according to a method for calculating the adjustable potential of electric vehicles taking into account user charging behavior characteristics according to an embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0068] Example 1

[0069] Reference Figures 1 to 3 , Figure 7 , Fig.10 As an embodiment of the present invention, a method for calculating the adjustable potential of an electric vehicle taking into account the charging behavior characteristics of a user is provided, which specifically includes the following steps:

[0070] S100: Establish a detailed boundary model of different charging behavior characteristics of electric vehicles by analyzing the charging behavior characteristics of different users, and aggregate electric vehicle parameters based on the Minkowski summation theory;

[0071] In the embodiment of the present application, establishing a detailed boundary model of different charging behavior characteristics of electric vehicles includes:

[0072] like Figure 2 As shown in (a), the electric vehicle a Always drive to the charging station to charge. l When driving away from the charging station, E0 represents the initial state of charge, E d is the expected charge capacity of the battery, E min Indicates the lower limit of battery discharge, the solid line represents the battery capacity boundary value that the electric vehicle battery can reach during the charging and discharging process, and the slope represents the maximum charging and discharging power of the electric vehicle. During the period from t2-1 to t2, the slope of the solid line represents the smaller charging and discharging power used to achieve the expected battery capacity. Figure 2 (b) indicates that the user chooses different charging times to charge and does not discharge. Both of these electric vehicle charging behaviors have the potential to be dispatched. In addition, the third type of electric vehicle charging behavior is disorderly charging. Figure 2 The figure can be seen as an ACD curve, that is, the expected battery capacity is achieved by charging at the maximum charging power, and it does not have the potential for dispatchability. The dotted line represents the battery capacity boundary value that can be achieved by electric vehicle batteries during the charging and discharging process under traditional methods.

[0073] In this embodiment, users who adopt charging and discharging behaviors after arriving at the station are represented as Class I users, users who adopt charging behaviors after arriving at the station but only change the charging time are represented as Class II users, and users who directly perform disorderly charging after arriving at the station are represented as Class III users. By analyzing the charging behavior characteristics of different users, a detailed boundary model of different charging behavior characteristics of electric vehicles is established, and the formula is expressed as follows:

[0074]

[0075] in, represents the maximum state of charge boundary of the i-th electric vehicle of Class I and Class II users at time t, represents the minimum state of charge boundary of the i-th electric vehicle of Class I user at time t, represents the minimum state of charge boundary of the i-th electric vehicle of Class II user at time t, P i + (t), P i - (t) represent the charge and discharge power boundaries, E0 represents the initial state of charge, E d represents the expected charge capacity of the battery, E + (t-1) and E - (t-1) represent the maximum and minimum charge state boundaries of the electric vehicle at time t-1, t a ,t d They represent the time when the electric vehicle enters the grid and the time when it leaves the station, P ch , P dis They represent the maximum charging and discharging power of electric vehicles, η represents the charging and discharging efficiency, E min Indicates the lower limit of battery discharge, and They represent the maximum and minimum state of charge boundaries of the electric vehicle at time t+1 respectively;

[0076] In the embodiment of the present application, the parking matrix X is introduced based on the Minkowski summation theory to make the electric vehicles have the same definition domain, so that the rechargeable power and capacity of a single electric vehicle are additive, and then the maximum and minimum power and capacity of N electric vehicles are aggregated to form a generalized energy storage model, that is, the electric vehicle parameters are aggregated into the parameters of the generalized energy storage model The formula is:

[0077]

[0078] Among them, x it represents the parking coefficient of the i-th electric vehicle at time t. The value is 1 when the electric vehicle is parked at the charging station and 0 when it leaves the charging station. They represent the maximum charge and discharge power of the generalized energy storage model at time t, They are the maximum and minimum power of the generalized energy storage model at time t respectively.

[0079] S200: Predict aggregated electric vehicle parameters using the PSO-LSTM algorithm based on a detailed boundary model of different charging behavior characteristics of electric vehicles;

[0080] In the embodiment of the present application, the input electric vehicle network access time, electric vehicle departure time, and initial battery charge state are preprocessed to filter out data that cannot be scheduled due to short parking time, and the preprocessed data is divided into a training set and a test set; the particle swarm algorithm is used to initialize and assign values ​​to the four parameters of the LSTM model, and the LSTM model is trained according to the training set and the test set. When the loss value of the LSTM model meets the requirements, the result is output, otherwise the parameters are updated until the LSTM model meets the requirements and the final result is output. The overall process is as follows: Figure 3 As shown, the indicator of the prediction effect is expressed as:

[0081]

[0082] Among them, N represents the amount of historical data of the test group, which is equal to the amount of data of the prediction result, and y test,g ,y pre,g Respectively represent the g-th historical data in the test group and its corresponding prediction result data;

[0083] It should be noted that R RMSE Measures the average difference between the predicted value and the true value. The smaller the value, the closer the predicted result is to the true value. MAPE It measures the average percentage error between the predicted value and the true value. The smaller the value, the more accurate the prediction result.

[0084] S300: A three-branch decision model based on regret theory is established to address the uncertainty of user willingness and a self-dispatching model is established considering user willingness. The dispatchable potential of the electric vehicle cluster is calculated based on the predicted electric vehicle parameters and the self-dispatching model.

[0085] In the embodiment of the present application, a three-branch decision model based on regret theory is established for the uncertainty of user intention, including:

[0086] The user's willingness model for participating in different charging behaviors is expressed as:

[0087]

[0088] Where Pu(o1) represents the perceived utility function of user o1, u(r 11 ) and u(r 12 ) represent actions r 11 and r 12The utility value obtained, u(r * ) indicates behavior r * The utility function of , γ represents the risk aversion coefficient of the decision maker, Δu represents the difference in utility values ​​of different behaviors, R(Δu) represents the regret-delight function, and η represents the regret aversion coefficient of the decision maker;

[0089] It should be noted that the core content of RT is the regret-delight function, which considers regret and delight by comparing other electric vehicle users under each attribute, which reflects that the willingness of electric vehicle users is influenced by other social members.

[0090] Furthermore, the flexible vehicle anxiety W borne by electric vehicle users is calculated based on the user willingness model to participate in different charging behaviors. T and the user's expected cost-benefit W c , the formula is:

[0091]

[0092] Among them, k1 represents the maximum value of the decision factor used to describe the anxiety of flexible car use, k2 represents the degree of change of flexible car use anxiety over time, and f E It means that the user expects to provide the maximum dispatchable capacity to obtain benefits, Indicates the loss of electric vehicle batteries due to additional charging and discharging. and Respectively represent the power loss under unit charging and discharging power, t c With t d Represent the additional charging and discharging time, t c0 With t d0 Respectively represent the initial charge and discharge time within the additional charge and discharge time, P i exc (t), P i exd (t) respectively represent the additional charging and discharging power of the i-th electric vehicle at time t, Δt c With Δt d Respectively represent the charging and discharging time periods within the additional charging and discharging time, p up (t) and p down (t) represents the compensation electricity price for the upward and downward regulation capacity, and Indicates the maximum upper scheduling capacity and the maximum lower scheduling capacity.

[0093] Furthermore, the flexible use anxiety of electric vehicle users T and the user's expected cost-benefit W c Normalize and select each user and As an attribute to evaluate the user's willingness to participate, it is expressed as:

[0094]

[0095] in, represents the maximum flexible use anxiety of the i-th electric vehicle, represents the expected cost-benefit of the user of the i-th electric car;

[0096] Furthermore, in order to prevent the influence of the subjective preferences of decision makers on the attributes, the deviation maximization method is used to assign weights to the attributes that affect user participation in regulation. The calculation method is:

[0097]

[0098]

[0099] Among them, ω j represents the weight of attribute j, N represents the total number of users, i and k represent different users, and a ij -a kj represents the evaluation values ​​of different users under the same attribute, Pu(a ij ) represents the perceived utility value of user i under attribute j, u ij represents the utility value of user i under attribute j, Indicates u ij Relative to u kj The overall regret-delight value;

[0100] Furthermore, after the weights are assigned, the perceived utility values ​​of an object under each attribute are summarized using the weighted arithmetic mean method to obtain the overall perceived utility value of the object, and the overall perceived utility values ​​are sorted in descending order to obtain the ranking result of the target; based on the sorting result, the user with the highest willingness to participate in the regulation is obtained based on the classic multi-criteria analysis method. T1 and users with the lowest willingness to participate in regulation T2 , the calculation formula is:

[0101]

[0102] Will be with o T1 Users with high similarity are classified as type I users. T2 Users with high similarity are classified as Class III users, and other users are classified as Class II users. Most users who hesitate to participate in the regulation are because they are worried about the damage to the battery caused by discharge, but at the same time they want to save charging costs. Therefore, users who hesitate to participate in the regulation are also classified as Class II users. The specific flow chart is as follows: Figure 7 shown.

[0103] In the embodiments of the present application, Fig.10As shown, calculating the dispatchable potential of electric vehicle clusters includes:

[0104] Taking the optimal user economy as the objective function and the aggregated generalized energy storage model as the constraint condition, the self-dispatching load of the electric vehicle cluster is calculated considering the probability of different charging behaviors. The formula is expressed as:

[0105]

[0106] Among them, F obj represents the objective function of user economic optimization, C(t) represents the electricity price, P i,ch (t), P i,dis (t) respectively represent the charging and discharging power of the i-th vehicle at time t, P i (t) represents the charge and discharge power, E i (t) represents the battery charge, E i (t+1) means the amount of electricity at time t+1 is equal to the sum of the amount of electricity at the previous time and the charge and discharge power at the previous time;

[0107] It should be explained that travel anxiety is calculated based on the parameters of a single electric vehicle, and cost anxiety is calculated by economically optimal self-scheduling of charging and discharging. Users are classified based on the three-branch decision model of regret theory, and economically optimal self-scheduling of charging is performed for Class II electric vehicles, while disorderly charging is performed for Class III electric vehicles. The three types of electric vehicles together constitute the self-scheduling load of the electric vehicle cluster through different self-scheduling. Among them, the difference between the boundary of the generalized energy storage model and the self-scheduling load of the electric vehicle cluster is the dispatchable potential of the electric vehicle cluster.

[0108] From the above, it can be seen that the present invention first establishes a detailed boundary model of different charging behavior characteristics of electric vehicles, and then predicts the aggregation parameters of electric vehicles based on PSO-LSTM, accurately predicts the power boundary and capacity boundary of the GES model, and then characterizes the user's willingness based on the three-way decision (T-WD) model of regret theory (RT) to establish an electric vehicle self-dispatching load model, calculate the dispatchable potential of electric vehicles, so that the electric vehicle cluster can better realize load peak shaving and valley filling and provide spare capacity.

[0109] The above is a schematic scheme of the method for calculating the adjustable potential of an electric vehicle considering the charging behavior characteristics of the user in this embodiment. It should be noted that the technical scheme of the system for calculating the adjustable potential of an electric vehicle considering the charging behavior characteristics of the user and the technical scheme of the method for calculating the adjustable potential of an electric vehicle considering the charging behavior characteristics of the user belong to the same concept. For details not described in detail in the technical scheme of the system for calculating the adjustable potential of an electric vehicle considering the charging behavior characteristics of the user in this embodiment, please refer to the description of the technical scheme of the method for calculating the adjustable potential of an electric vehicle considering the charging behavior characteristics of the user.

[0110] This embodiment also provides an electric vehicle adjustable potential calculation system that takes into account the user's charging behavior characteristics, including:

[0111] An electric vehicle capacity boundary modeling unit is used to establish a detailed boundary model of different charging behavior characteristics of electric vehicles by analyzing the charging behavior characteristics of different users, where the charging behaviors of different users include charging and discharging, charging with changing charging time, and disordered charging;

[0112] The vehicle parameter aggregation prediction unit is used to aggregate the electric vehicle parameters based on the Minkowski summation theory, and use the PSO-LSTM algorithm to predict the aggregated electric vehicle parameters according to the detailed boundary model of different charging behavior characteristics of electric vehicles;

[0113] The electric vehicle self-dispatching load modeling unit is used to establish a three-branch decision model based on regret theory for the uncertainty of user willingness and to establish a self-dispatching model considering user willingness;

[0114] The electric vehicle dispatchable potential calculation unit is used to calculate the dispatchable potential of the electric vehicle cluster based on the predicted electric vehicle parameters and the self-dispatching model, wherein the self-dispatching load curve reaches the boundary of the generalized energy storage model through the upper adjustment capacity, the lower adjustment capacity, the upper adjustment power, and the lower adjustment power, and the upper adjustment capacity, the lower adjustment capacity, the upper adjustment power, and the lower adjustment power together constitute the dispatchable potential of the electric vehicle cluster.

[0115] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0116] This embodiment also provides a computing device, which includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for calculating the adjustable potential of an electric vehicle taking into account the characteristics of the user's charging behavior is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0117] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method proposed in the above embodiment is implemented.

[0118] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0119] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0120] Example 2

[0121] Reference Figures 4 to 6 , Figures 8-9 , Figure 11 to Figure 14 This embodiment provides an application example of a method and system for calculating the adjustable potential of an electric vehicle taking into account the characteristics of user charging behavior, in order to verify and illustrate the technical effects adopted in this method.

[0122] In order to obtain the boundary of the maximum dispatchable potential of electric vehicles, this embodiment needs to accurately predict the parameters of the GES model. In order to verify the effect of the proposed GES model parameter prediction method based on PSO-LSTM, it is compared with the BP neural network model and LSTM model commonly used for data prediction. The prediction errors of different models are shown in Table 1; 100 vehicles include 40 official vehicles charged during the day and 60 private cars charged at night, which are recorded as EV1 and EV2 respectively. Taking an EV1 as an example, the data of the first 48 days are used as the training set, and the data of the last 12 days are used as the test set. The loss value of using the LSTM model alone is 0.2027, so the loss value is set to 0.2.

[0123] Table 1: Prediction errors of different models.

[0124]

[0125] As shown in Table 1, for the parameter prediction of different types of electric vehicles, the prediction accuracy based on the PSO-LSTM algorithm is higher than that of the BP neural network algorithm and the LSTM algorithm. Figure 4 The figure shows the prediction result of the parking start time of an EV1. Figure 5 This is the prediction result of the parking end time of an EV1. Figure 6 This is the prediction result of the initial state of charge of an EV1. The prediction results of the test set show that the parameter prediction method based on PSO-LSTM accurately predicts the three parameters, thereby improving the prediction accuracy of the GES model parameters, namely the power and capacity boundaries, which is of great significance for the prediction and calculation of the dispatchable potential of electric vehicle clusters.

[0126] Furthermore, considering the influence of other electric vehicle users in society, a three-branch decision model based on regret theory is used to rank and classify the users’ willingness to participate in regulation, such as Figure 8 , Fig. 9 As shown. Set η = 0.65, γ = 0.3. In the sorting results, the 22nd user is the one with the strongest willingness to participate, and the 75th user is the one with the least willingness to participate. In the classification results, Class I users account for 38%, Class II users account for 35%, and Class III users account for 27%. The proposed model can achieve the sorting and classification results of users' willingness to participate in regulation. The error rate index ER is used to prove the classification performance of the proposed model. The formula is:

[0127]

[0128] Among them, E1 indicates that users participating in charge and discharge regulation are classified as Class III users, and E2 indicates that users not participating in regulation are classified as Class I users and Class II users.

[0129] The error rate index ER = 2%, which proves that the model has good classification performance.

[0130] Further, such as Fig.11 The figure shows the number of charging and discharging electric vehicles after scheduling. The number of discharging electric vehicles is concentrated in the period with high electricity prices, while the number of charging electric vehicles is mostly concentrated in the period with low electricity prices. Fig.12As shown, the Class I vehicles charged during the day are concentrated in the morning from 8 to 10 am and the afternoon from 2 to 6 pm when the electricity price is low, and discharge during the period from 10 to 2 pm when the electricity price is high. The Class I vehicles charged at night are concentrated in the period from 6 to 9 pm when the electricity price is the highest, and the remaining electricity is discharged to the lower limit of the battery discharge during the period from 9 to 11 pm when the electricity price is high. At 11 pm, when the electricity price is the lowest, the battery is charged until it is fully charged. The charging period of Class II vehicles is the same as that of Class I vehicles. Class III vehicles are charged as soon as they are connected to the grid and do not have the potential for dispatch; therefore, the optimized load curve is compared with the load curve before optimization to reduce peaks and fill valleys, and smooth out load fluctuations.

[0131] Further, such as Fig.13 and Fig.14 As shown in the figure, the GES capacity boundary predicted by PSO-LSTM forms an envelope, in which the capacity of the electric vehicle cluster after self-scheduling is sandwiched. The self-scheduling load curve can reach the capacity boundary through upward and downward regulation. The upward regulation capacity, downward regulation capacity, upward regulation power, and downward regulation power together constitute the dispatchable potential of the electric vehicle cluster. Accurately quantifying the dispatchable potential of the electric vehicle cluster provides a reference for the electric vehicle cluster to participate in the auxiliary service market.

[0132] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0133] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0134] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0135] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0137] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0138] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for calculating the adjustable potential of electric vehicles considering the characteristics of user charging behavior, characterized in that: include: By analyzing the charging behavior characteristics of different users, a detailed boundary model of different charging behavior characteristics of electric vehicles is established, and the electric vehicle parameters are aggregated based on the Minkowski summation theory; Predicting the aggregated electric vehicle parameters using a PSO-LSTM algorithm based on a detailed boundary model of different charging behavior characteristics of the electric vehicles; A three-branch decision model based on regret theory is established in view of the uncertainty of user willingness, and a self-scheduling model is established considering user willingness. The dispatchable potential of the electric vehicle cluster is calculated based on the predicted electric vehicle parameters and the self-scheduling model.

2. The method for calculating the adjustable potential of electric vehicles considering the user charging behavior characteristics as claimed in claim 1, characterized in that: The detailed boundary model for establishing different charging behavior characteristics of electric vehicles includes: Users who adopt charging and discharging behaviors after arriving at the station are represented as Class I users, users who adopt charging behaviors after arriving at the station but only change the charging time are represented as Class II users, and users who directly charge without order after arriving at the station are represented as Class III users. By analyzing the charging behavior characteristics of different users, a detailed boundary model of different charging behavior characteristics of electric vehicles is established, and the formula is expressed as follows: in, represents the maximum state of charge boundary of the i-th electric vehicle of Class I and Class II users at time t, represents the minimum state of charge boundary of the i-th electric vehicle of Class I user at time t, represents the minimum state of charge boundary of the i-th electric vehicle of Class II user at time t, P i + (t), P i - (t) represent the charge and discharge power boundaries, E0 represents the initial state of charge, E d represents the expected charge capacity of the battery, E + (t-1) and E - (t-1) represent the maximum and minimum charge state boundaries of the electric vehicle at time t-1, t a ,t d They represent the time when the electric vehicle enters the grid and the time when it leaves the station, P ch , P dis They represent the maximum charging and discharging power of electric vehicles, η represents the charging and discharging efficiency, E min Indicates the lower limit of battery discharge, and They represent the maximum and minimum state of charge boundaries of the electric vehicle at time t+1 respectively.

3. The method for calculating the adjustable potential of electric vehicles considering the user charging behavior characteristics as claimed in claim 2, characterized in that: The aggregating of electric vehicle parameters based on the Minkowski summation theory includes: Based on the Minkowski summation theory, the parking matrix X is introduced to make electric vehicles have the same definition domain, and then the maximum and minimum power and capacity of N electric vehicles are aggregated to form a generalized energy storage model, that is, the electric vehicle parameters are aggregated into the parameters of the generalized energy storage model The formula is: Among them, x it represents the parking coefficient of the i-th electric vehicle at time t. The value is 1 when the electric vehicle is parked at the charging station and 0 when it leaves the charging station. They represent the maximum charge and discharge power of the generalized energy storage model at time t, They are the maximum and minimum power of the generalized energy storage model at time t respectively.

4. The method for calculating the adjustable potential of electric vehicles considering the user charging behavior characteristics as claimed in claim 3, characterized in that: The method of using the PSO-LSTM algorithm to predict the aggregated electric vehicle parameters includes: Preprocessing the input electric vehicle network access time, electric vehicle departure time, and initial battery charge state, filtering out data that cannot be scheduled due to short parking time, and dividing the preprocessed data into a training set and a test set; The particle swarm algorithm is used to initialize and assign values ​​to the four parameters of the LSTM model, and the LSTM model is trained according to the training set and the test set. When the loss value of the LSTM model meets the requirements, the result is output, otherwise the parameters are updated until the LSTM model meets the requirements and outputs the final result.

5. The method for calculating the adjustable potential of electric vehicles considering the user charging behavior characteristics as claimed in claim 1, characterized in that: The three-branch decision model based on regret theory established for the uncertainty of user willingness includes: The user's willingness model for participating in different charging behaviors is expressed as: Where Pu(o1) represents the perceived utility function of user o1, u(r 11 ) and u(r 12 ) represent actions r 11 and r 12 The utility value obtained, u(r * ) indicates behavior r * The utility function of , γ represents the risk aversion coefficient of the decision maker, Δu represents the difference in utility values ​​of different behaviors, R(Δu) represents the regret-delight function, and η represents the regret aversion coefficient of the decision maker; The flexible vehicle anxiety W borne by electric vehicle users is calculated based on the user willingness model for participating in different charging behaviors. T and the user's expected cost-benefit W c , the formula is: Among them, k1 represents the maximum value of the decision factor used to describe the anxiety of flexible car use, k2 represents the degree of change of flexible car use anxiety over time, and f E It means that the user expects to provide the maximum dispatchable capacity to obtain benefits, Indicates the loss of electric vehicle batteries due to additional charging and discharging. and Respectively represent the power loss under unit charging and discharging power, t c With t d Represent the additional charging and discharging time, t c0 With t d0 Respectively represent the initial charge and discharge time within the additional charge and discharge time, P i exc (t), P i exd (t) respectively represent the additional charging and discharging power of the i-th electric vehicle at time t, Δt c With Δt d Respectively represent the charging and discharging time periods within the additional charging and discharging time, p up (t) and p down (t) represents the compensation electricity price for the upward and downward regulation capacity, and Indicates the maximum upper scheduling capacity and the maximum lower scheduling capacity.

6. The method for calculating the adjustable potential of electric vehicles considering the user charging behavior characteristics as claimed in claim 5, characterized in that: Also includes: The flexible use anxiety of electric car users T and the user's expected cost-benefit W c Normalize and select each user and As an attribute to evaluate the user's willingness to participate; The deviation maximization method is used to assign weights to the attributes that affect user participation in regulation. The calculation method is: Among them, ω j represents the weight of attribute j, N represents the total number of users, i and k represent different users, and a ij -a kj represents the evaluation values ​​of different users under the same attribute, Pu(a ij ) represents the perceived utility value of user i under attribute j, u ij represents the utility value of user i under attribute j, Indicates u ij Relative to u kj The overall regret-delight value; After the weights are assigned, the perceived utility values ​​of an object under each attribute are summarized using the weighted arithmetic mean method to obtain the overall perceived utility value of the object, and the overall perceived utility values ​​are sorted in descending order to obtain the ranking result of the target; According to the ranking results, the user with the highest willingness to participate in regulation is obtained based on the classic multi-criteria analysis method. T1 and users with the lowest willingness to participate in regulation T2 , the calculation formula is: Will be with o T1 Users with high similarity are classified as type I users. T2 Users with high similarity are classified as Class III users, and other users are classified as Class II users. Among them, users who are hesitant to participate in regulation are also classified as Class II users.

7. The method for calculating the adjustable potential of electric vehicles considering the user charging behavior characteristics as claimed in claim 6, characterized in that: The calculated dispatchable potential of electric vehicle clusters includes: Taking the optimal user economy as the objective function and the aggregated generalized energy storage model as the constraint condition, the self-dispatching load of the electric vehicle cluster is calculated considering the probability of different charging behaviors. The formula is expressed as: Among them, F obj represents the objective function of user economic optimization, C(t) represents the electricity price, P i,ch (t), P i,dis (t) respectively represent the charging and discharging power of the i-th vehicle at time t, P i (t) represents the charge and discharge power, E i (t) represents the battery charge, E i (t+1) means the amount of electricity at time t+1 is equal to the sum of the amount of electricity at the previous time and the charge and discharge power at the previous time; Travel anxiety is calculated according to the parameters of a single electric vehicle, and cost anxiety is calculated by economically optimal self-scheduling of charging and discharging. Users are classified based on the three-branch decision model of regret theory, and economically optimal self-scheduling of charging is performed for Class II electric vehicles, while disorderly charging is performed for Class III electric vehicles. The three types of electric vehicles together constitute the self-scheduling load of the electric vehicle cluster through different self-scheduling. The difference between the boundary of the generalized energy storage model and the self-scheduling load of the electric vehicle cluster is the dispatchable potential of the electric vehicle cluster.

8. A system using the method for calculating the adjustable potential of electric vehicles taking into account the user charging behavior characteristics as described in any one of claims 1 to 7, characterized in that: include: An electric vehicle capacity boundary modeling unit, used to establish a detailed boundary model of different charging behavior characteristics of the electric vehicle by analyzing the charging behavior characteristics of different users, wherein the charging behaviors of different users include charging and discharging, charging with changing charging time, and disordered charging; An automobile parameter aggregation prediction unit, used for aggregating electric vehicle parameters based on the Minkowski summation theory, and predicting the aggregated electric vehicle parameters using a PSO-LSTM algorithm according to a detailed boundary model of different charging behavior characteristics of the electric vehicle; The electric vehicle self-dispatching load modeling unit is used to establish a three-branch decision model based on regret theory for the uncertainty of user willingness and to establish a self-dispatching model considering user willingness; An electric vehicle dispatchable potential calculation unit is used to calculate the dispatchable potential of an electric vehicle cluster based on the predicted electric vehicle parameters and the self-dispatching model, wherein the self-dispatching load curve reaches the boundary of the generalized energy storage model through the upper adjustment capacity, the lower adjustment capacity, the upper adjustment power, and the lower adjustment power, and the upper adjustment capacity, the lower adjustment capacity, the upper adjustment power, and the lower adjustment power together constitute the dispatchable potential of the electric vehicle cluster.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images