Generation method of energy scheduling strategy of vehicle, electronic equipment and storage medium

Abstract

The invention relates to a method for generating an energy scheduling strategy of a vehicle, electronic equipment and a storage medium, which are applied to the technical field of vehicles, and the method comprises the following steps: obtaining current operation data and power consumption limitation data of a vehicle battery; determining a constraint condition based on the power consumption limitation data; obtaining an optimization target of the vehicle battery, wherein the optimization target comprises maximization of a battery health state and minimization of power consumption cost; and by taking the optimization target as an optimization direction, optimizing an energy scheduling strategy of the vehicle battery based on the current operation data and the power consumption limitation data in the constraint condition to obtain a target energy scheduling strategy.

Description

Technical Field

[0001] The present application relates to the technical field of vehicles, and in particular, to a method for generating an energy scheduling strategy for a vehicle, an electronic device, and a storage medium. Background Art

[0002] With the transformation of the global energy structure and the rapid development of smart grid technology, the Home Energy Management System (HEMS) has gradually become an important part of modern smart homes. Especially in the context of the gradual popularization of time-of-use electricity price policies, HEMS plays an increasingly important role in reducing electricity costs and improving energy utilization efficiency by optimizing the use efficiency of household energy. At the same time, as a representative of clean energy transportation, Electric Vehicles (EVs) have been rapidly popularized globally. The bi-directional energy interaction technology between electric vehicles and the home power grid (Vehicle-to-Home, V2H) has also become a research hotspot. The V2H technology can not only realize the function of the electric vehicle supplying power to the home during peak grid load periods and charging during low load periods, but also provide backup power support for the home to ensure the basic electricity demand of the home during power outages.

[0003] However, in related technologies, most of the research on the scheduling strategy for the home energy system focuses on optimizing the matching relationship between electricity prices and household loads with the goal of minimizing electricity costs. However, a single optimization goal is likely to affect the long-term operation performance of the system and cause problems such as reduced system reliability. Summary of the Invention

[0004] The present application provides a method for generating an energy scheduling strategy for a vehicle, an electronic device, and a storage medium, so as to solve the problems in the prior art that a single optimization goal is likely to affect the long-term operation performance of the system and cause problems such as reduced system reliability.

[0005] According to a first aspect of an embodiment of the present application, there is provided a method for generating an energy scheduling strategy for a vehicle, including:

[0006] Obtaining current operation data and power consumption limit data of a vehicle battery;

[0007] Determining constraint conditions based on the power consumption limit data;

[0008] Obtaining an optimization goal of the vehicle battery, where the optimization goal includes maximizing the state of health of the battery and minimizing the electricity cost;

[0009] Taking the optimization goal as the optimization direction, optimizing the energy scheduling strategy of the vehicle battery based on the current operation data and the power consumption limit data within the constraint conditions to obtain a target energy scheduling strategy.

[0010] Optionally, taking the optimization objective as the optimization direction, within the constraint conditions, based on the current operating data and the power consumption limit data, optimize the energy scheduling strategy of the vehicle battery to obtain the target energy scheduling strategy, including:

[0011] Initialize a particle swarm based on the particle swarm optimization algorithm to obtain the initial velocity and initial position of each particle in the particle swarm. The position of the particle represents the energy scheduling strategy of the vehicle battery, and the velocity of the particle represents the change amount of the vehicle battery energy scheduling strategy;

[0012] Perform the following iterative process for each particle: Calculate the fitness value of the particle based on the power consumption limit data, the current operating data, and the current position of the particle. The initial value of the current position is the initial position, and the fitness value is calculated by the objective function constructed by the optimization objective; Based on the current velocity and current position of the particle, update the position and velocity of the particle to obtain the updated position and updated velocity. The updated position satisfies the constraint conditions. The initial value of the current velocity is the initial velocity, and the initial value of the current position is the initial position; Determine the best position of the particle based on the fitness value and the current position;

[0013] Determine the global best position of the particle swarm based on the best position of each particle;

[0014] Based on the best position, determine whether the iteration end condition is satisfied. If so, determine the energy scheduling strategy represented by the global best position as the target energy scheduling strategy; If not, update the current velocity to the updated velocity, and update the current position to the updated position, and then execute the iterative process again.

[0015] Optionally, the objective function is:

[0016] F = W1F1 +... + W n F n ;

[0017] Wherein, F n represents the nth optimization objective, W n represents the weight of the nth optimization objective, and n represents the number of optimization objectives.

[0018] Optionally, when the optimization objective includes minimizing the power consumption cost, the power consumption cost calculation formula is:

[0019] When the optimization objective includes maximizing the battery health state, the battery health state calculation formula is:

[0020] The optimization objectives include that, when the power grid stability is the strongest, the power grid stability calculation formula is:

[0021] The optimization objectives include that, when the satisfaction degree of household load demand is the highest, the satisfaction degree calculation formula of household load demand is:

[0022] Among them, P grid (t) represents the power purchase amount from the power grid in the t time period, P charge (t) represents the charging amount in the t time period, C elec (t) represents the real-time electricity price in the t time period, ΔSOH(t) represents the battery health state change rate in the t time period, T represents the optimization period; P battery (t) represents the battery power at the moment t, and L(t) represents the household load demand at the moment t.

[0023] Optionally, the weights of the optimization objectives are obtained in the following manner:

[0024] Normalize each of the optimization objectives to obtain a normalization result;

[0025] The weights of the optimization objectives are:

[0026]

[0027] Among them, s i (t) represents the normalization result of the i-th optimization objective, and the value of i ranges from 1 to n.

[0028] Optionally, taking the optimization objectives as the optimization directions, within the constraint conditions, based on the current operation data and power consumption limit data, after optimizing the energy scheduling strategy of the vehicle battery to obtain a target energy scheduling strategy, it further includes:

[0029] Obtain the target operation data of the vehicle battery after operating according to the target energy scheduling strategy;

[0030] Determine the target health state of the vehicle battery according to the target operation data;

[0031] Adjust the target energy scheduling strategy based on the target health state.

[0032] Optionally, determining the target health state of the vehicle battery according to the target operation data includes:

[0033] Extract the operation characteristic data from the target operation data;

[0034] Perform weighted processing on the operation characteristic data to obtain weighted operation data;

[0035] Based on the random forest model, make a decision on the weighted operation data to obtain the health status.

[0036] Optionally, it further includes:

[0037] Determine the power transmission direction of the vehicle based on the target operation data;

[0038] Adjust the target energy scheduling strategy based on the power transmission direction and the target health status.

[0039] Optionally, the training process of the random forest model includes:

[0040] Obtain a training data set, where the training data set includes multiple training samples, and each training sample includes the true health status of the sample battery and the sample weighted operation data;

[0041] Input the training samples into the original random forest model in sequence, and make a decision on the sample weighted operation data of the training samples through the original random forest model to obtain the sample health status;

[0042] Based on the true health status and the sample health status, determine whether the original random forest model is trained. If so, obtain the random forest model;

[0043] If not completed, optimize the model parameters in the original random forest model based on the cross-validation algorithm and input the training samples again.

[0044] According to the second aspect of the embodiments of the present application, there is provided a generating device for an energy scheduling strategy of a vehicle, including:

[0045] The first obtaining unit is used to obtain the current operation data and power consumption limit data of the vehicle battery;

[0046] The determining unit is used to determine the constraint conditions based on the power consumption limit data;

[0047] The second obtaining unit is used to obtain the optimization target of the vehicle battery, and the optimization target includes maximizing the battery health status and minimizing the power consumption cost;

[0048] The generating unit is used to optimize the energy scheduling strategy of the vehicle battery based on the current operation data and power consumption limit data within the constraint conditions with the optimization target as the optimization direction to obtain the target energy scheduling strategy.

[0049] According to the third aspect of the embodiments of the present application, there is provided an electronic device, including a memory and a processor;

[0050] The memory is connected to the processor and is used to store programs;

[0051] The processor is configured to implement the method for generating an energy scheduling strategy of a vehicle as described in the first aspect by running the programs stored in the memory.

[0052] According to a fourth aspect of the embodiments of the present application, a storage medium is provided. A computer program is stored on the storage medium. When the computer program is run by a processor, the method for generating an energy scheduling strategy of a vehicle as described in the first aspect is implemented.

[0053] According to a fifth aspect of the embodiments of the present application, a computer program product is provided, including computer program instructions. When the computer program instructions are run by a processor, the processor is caused to execute the method for generating an energy scheduling strategy of a vehicle as described in the first aspect.

[0054] The above technical solutions provided by the embodiments of the present application have the following advantages compared with the prior art: In the method provided by the embodiments of the present application, the current operating data and power consumption limit data of the vehicle battery are obtained; constraint conditions are determined based on the power consumption limit data; an optimization target of the vehicle battery is obtained, and the optimization target includes maximizing the battery health state and minimizing the power consumption cost; with the optimization target as the optimization direction, within the constraint conditions, based on the current operating data and power consumption limit data, the energy scheduling strategy of the vehicle battery is optimized to obtain a target energy scheduling strategy. In this way, by setting both maximizing the battery health state and minimizing the power consumption cost as optimization targets, the energy scheduling scheme of the battery is optimized using multiple optimization targets, optimizing the performance of the system and improving the reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0056] Figure 1 It is a flowchart of a method for generating an energy scheduling strategy of a vehicle provided by an embodiment of the present application;

[0057] Figure 2 It is a structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0058] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0059] Exemplary implementation environment

[0060] The method for generating the energy scheduling strategy of the vehicle according to the embodiments of the present application can be executed by an electronic device such as a terminal device or a server. The terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The server can be an independent physical server, a server cluster composed of multiple physical servers, or a cloud server capable of performing cloud computing. This method can be implemented by the processor calling the computer-readable program instructions stored in the memory. In the present application, the method for generating the energy scheduling strategy of the vehicle is taken as an example of being executed by the server for explanation, but it is not limited thereto.

[0061] Exemplary method

[0062] Please refer to Figure 1 , in an exemplary embodiment, a method for generating an energy scheduling strategy of a vehicle is provided, including:

[0063] Step 101, obtain the current operation data and power consumption limit data of the vehicle battery.

[0064] In some embodiments, the current operation data includes the remaining battery power E(t), charge and discharge current I(t), voltage V(t), charge and discharge depth DoD(t), charge and discharge power P(t), number of cycles C(t) of the vehicle battery, and ambient temperature T(t). The current operation data can be collected by relevant sensors.

[0065] Among them, the charge and discharge depth can be calculated by the ratio of the current battery power E(t) of the vehicle battery to the maximum value E of the battery power max , that is, the charge and discharge depth DoD(t) = 1 - E(t) / E max . The number of cycles is related to the charge and discharge depth, and the number of cycles C(t) = k·(DoD(t)) 2 , where k can be set according to experience.

[0066] After obtaining the current operating data of the vehicle battery, it can be stored in a database in the following data format: X(t) = [I(t), V(t), T(t), DoD(t), P(t), C(t)].

[0067] The power consumption limit data is used to indicate the power consumption limit of the vehicle battery, including the household load demand curve L(t), the time-of-use electricity price curve C elec (t), the battery capacity limit, and the charge and discharge power limit. The battery capacity limit includes the battery maximum capacity limit E max and the battery minimum capacity limit E min , and the charge and discharge power limit includes the maximum charging power P charge,max and the maximum discharge power P discharge,max .

[0068] Step 102: Determine the constraint conditions based on the power consumption limit data.

[0069] In some embodiments, the constraint conditions can be set according to different power consumption limit data. In this embodiment, the constraint conditions include energy balance constraint, battery capacity constraint, charge and discharge power constraint, and cycle number constraint.

[0070] Specifically, the energy balance constraint is: E(t + 1) = E(t) + P charge (t)·Δt - P discharge (t)·Δt - L(t));

[0071] Where: L(t) represents the household load demand in the time period (t), E(t) represents the battery power in the time period (t), P charge (t) represents the charging power in the time period (t),

[0072] P discharge (t) represents the discharge power in the time period (t), and Δt represents the time interval (such as 1 hour).

[0073] The battery capacity constraint is: E min ≤ E(t) ≤ E max ;

[0074] Where: E min is the battery minimum capacity limit, and E max is the battery maximum capacity limit.

[0075] The charge and discharge power constraint is: 0 ≤ P charge (t) ≤ P charge,max , 0 ≤ P discharge (t) ≤ P discharge,max ; The cycle number constraint is: C(t) = k·(DoD(t)) 2 .

[0076] Step 103: Obtain the optimization objectives of the vehicle battery, where the optimization objectives include maximizing the battery health state and minimizing the electricity consumption cost.

[0077] In some embodiments, taking minimizing the electricity consumption cost as the optimization objective can make full use of the time-of-use (TOU) electricity price policy by reasonably arranging the charging and discharging times, thereby reducing the overall household electricity consumption cost. Taking maximizing the battery health state (SOH) as the optimization objective can extend the battery service life by reducing charging and discharging behaviors harmful to the battery (such as deep charging and discharging, charging and discharging in high-temperature environments, etc.).

[0078] Furthermore, the strongest power grid stability and the highest household load demand satisfaction can also be taken as optimization objectives.

[0079] Taking the household load demand as the optimization objective can monitor the household electricity load (L(t)) in real time and predict the change in the load demand in the future period. Taking the power grid stability as the optimization objective can monitor the power grid operation status (such as frequency, voltage, etc.) and avoid large-power charging and discharging operations when the power grid is unstable.

[0080] Step 104: Taking the optimization objectives as the optimization direction, within the constraint conditions, optimize the energy scheduling strategy of the vehicle battery based on the current operation data and electricity consumption limit data to obtain the target energy scheduling strategy.

[0081] In some embodiments, the particle swarm optimization (PSO) algorithm can be used, but not limited to, to solve the multi-objective optimization problem. Considering two key factors, namely the electricity consumption cost and the battery health state, it avoids the "one-sidedness" problem that may be caused by traditional single-objective optimization. Taking the power grid stability and the household load demand satisfaction as the optimization objectives can avoid large-power operations when the power grid is unstable, increase the discharge power during high electricity price periods to reduce power purchase from the power grid, and increase the charging power during low electricity price periods to reduce the electricity consumption cost. Discharge is prioritized when the electricity price is high and the battery health state SOH is high, and charging is prioritized when the electricity price is low and SOH is low.

[0082] In an alternative embodiment, taking the optimization objectives as the optimization direction, within the constraint conditions, optimize the energy scheduling strategy of the vehicle battery based on the current operation data and electricity consumption limit data to obtain the target energy scheduling strategy, including:

[0083] Initialize the particle swarm based on the particle swarm optimization algorithm to obtain the initial velocity and initial position of each particle in the particle swarm. The position of the particle represents the energy scheduling strategy of the vehicle battery, and the velocity of the particle represents the change amount of the vehicle battery energy scheduling strategy;

[0084] The following iterative process is performed for each of the said particles: calculate the fitness value of the particle based on the electricity consumption limit data, the current operation data, and the current position of the particle, the initial value of the current position being the initial position, and the fitness value being calculated by an objective function constructed based on the optimization objective; update the position and velocity of the particle based on the current velocity and current position of the particle to obtain an updated position and an updated velocity; the updated position satisfies the constraint conditions, the initial value of the current velocity being the initial velocity, and the initial value of the current position being the initial position; determine the best position of the particle based on the fitness value and the current position;

[0085] Determine the global best position of the particle swarm based on the best position of each particle;

[0086] Judge whether the iteration end condition is satisfied based on the best position; if so, determine the energy scheduling strategy represented by the global best position as the target energy scheduling strategy; if not, update the current velocity to the updated velocity, and update the current position to the updated position, and perform the iterative process again.

[0087] In some embodiments, each particle in the particle swarm represents a complete home energy scheduling strategy, which includes, for each time period (such as 1 hour): charging power, discharging power, and remaining battery energy. Among them, the particle position dimension can be set according to the actual situation. For example, it can be set to 24, that is, the optimization period is 24 hours. For each particle in different time periods, multiple variables can be set respectively according to actual needs. For example, if 3 are set, then each particle contains 3 * 24 = 72 decision variables (3 variables for each time period).

[0088] Among them, the initial velocities and initial positions of the particles during the initialization of the particle swarm, the charging power and discharging power in the energy scheduling strategy represented by each initial position, are randomly generated within the power constraint conditions, and the battery power is the actual remaining power in the current operation data of the battery; the initial velocity can be set to 0.

[0089] After the particle initialization, it can be judged whether the randomly generated initial position satisfies the energy balance constraint condition based on the energy balance constraint condition; if not, regenerate it.

[0090] It can be understood that during initialization, the number of particles, learning factors, inertia weights, etc. will also be initialized. For example, the number of particles N p is initialized to 50, the learning factors c1 and c2 are both initialized to 2, and the inertia weight is initialized to 0.8. The above data can be adjusted according to the actual situation and are not limited here.

[0091] After the initialization is completed, the iterative process is entered. For each particle, the fitness value F is calculated through the objective function based on the current position.

[0092] Among them, the objective function is:

[0093] F = W1F1 +... + W n F n ; Formula (1)

[0094] Among them, F n represents the nth optimization objective, W n represents the weight of the nth optimization objective, and n represents the number of optimization objectives.

[0095] It can be understood that two, three, or four of them can be selected from multiple optimization objectives according to actual needs, and the calculation formulas of the corresponding optimization objectives and the weight calculation formulas are substituted into the above Formula (1).

[0096] Specifically, when the optimization objective includes minimizing the electricity consumption cost, the electricity consumption cost calculation formula is:

[0097] When the optimization objective includes maximizing the battery health state, the battery health state calculation formula is:

[0098] When the optimization objective includes the strongest power grid stability, the power grid stability calculation formula is:

[0099] When the optimization objective includes the highest satisfaction of household load demand, the household load demand satisfaction calculation formula is:

[0100] Among them, P grid (t) represents the electricity purchase amount from the power grid in the t time period, P charge (t) represents the charging amount in the t time period, C elec (t) represents the real-time electricity price in the t time period, ΔSOH(t) represents the battery health state change rate in the t time period, T represents the optimization period; P battery (t) represents the battery power at the t moment, and L(t) represents the household load demand at the t moment.

[0101] Among them, the above P grid (t) = L(t) + P discharge (t) - E(t). It is necessary to ensure that P grid (t) is greater than or equal to, otherwise purchase electricity from the power grid.

[0102] Among them, ΔSOH(t) can be obtained by calculating the difference between the SOH in the t time period and the SOH in the t - 1 time period. Or, SOH(t) - SOH(t - 1) = -f(C(t - 1), T(t - 1)) is obtained in the following way, where f is the health attenuation function, C(t) = k·(DoD(t)) 2 is the number of cycles, and T(t - 1) is the ambient temperature. Among them, the higher the temperature, the faster the battery health state decays, and the greater the depth of discharge DoD of the battery, the more damage to the battery.

[0103] The update process of the particle velocity and position is as follows:

[0104] Velocity update:

[0105] Among them, is the velocity of the i-th particle at the k-th iteration, is its historical best position, is the global best position, and (r1, r2) are random numbers in the interval [0, 1].

[0106] Position update:

[0107] After the position update, check whether the constraint conditions are satisfied (such as energy balance: η(t) is the charge-discharge efficiency; capacity limit: SOH min ≤SOH(t)≤SOH max ). If not, adjust P(t) to the feasible range (such as setting it to (-P max ) if it exceeds the discharge power upper limit).

[0108] Based on the above related embodiments, since multiple variables are set for each particle in the same time period, therefore, the best variable can be determined from multiple variables. The best variable in each time period constitutes the best position of the particle. Since there are multiple particles, similarly, the best variables are selected for each particle in the same time period, and then the global best position is constructed from the best variables of each particle in each time period.

[0109] By comparing the fitness value of the current position with the fitness of the best position of the most recently updated position, if the fitness value of the current position is small, update the best position obtained in this iteration to the current position. Furthermore, by comparing all particles, the global best position is obtained.

[0110] Among them, the iteration end condition can be that the iteration number reaches the maximum iteration number (such as 100 times) or when the global best position has not improved significantly for several consecutive times, terminate the iteration.

[0111] The final global optimal position p g The corresponding [P(1), P(2), …, P(24)] is the optimized target energy scheduling strategy.

[0112] When the iteration termination condition is the maximum number of iterations: For example, if 100 iterations are set, it terminates after reaching (to avoid excessive calculation time). When the iteration termination condition is fitness convergence: When the change in the global optimal F is less than 1% in five consecutive iterations (e.g., from 100 to 99.9), it is considered close to the optimal solution and terminates in advance.

[0113] After the iteration terminates, select the global optimal particle (i.e., the particle with the minimum F), and extract its decision variables, including: the optimal charging power for each time period, the optimal discharging power for each time period, and the remaining battery energy for each time period. This strategy simultaneously satisfies: the electricity cost is as low as possible (charging using time-of-use electricity prices), the battery health is as good as possible (avoiding behaviors that damage the battery such as deep discharging and high-temperature charging and discharging), the power grid is as stable as possible, and the household load demand is satisfied as much as possible.

[0114] Exemplarily, after iteration, if in p g when t = 8, P(8) = -5, that is, discharging 5 kW; when t = 23, P(23) = 3, that is, charging 3 kW, it means discharging at 8 o'clock and charging at 23 o'clock, and through the combination of P(t) in the overall 24 time periods, the comprehensive optimization of electricity cost and battery health is achieved.

[0115] In an alternative embodiment, the weights of the optimization objectives are obtained in the following manner:

[0116] Normalize each of the optimization objectives to obtain the normalization results; and sum up the normalization results, and take the ratio of each normalization result of the optimization objective to the sum value as the weight of each optimization objective.

[0117] Among them, the calculation formula for the weights of the optimization objectives is:

[0118]

[0119] Among them, s i (t) represents the normalization result of the i-th optimization objective, and the value of i ranges from 1 to n. It can be understood that the sum value of the weights of each optimization objective is 1.

[0120] Specifically, when the optimization objective includes minimizing the electricity cost, the calculation formula for the normalization result is:

[0121] When the optimization objective includes maximizing the battery health state, the calculation formula for the normalization result is:

[0122] The optimization objective includes that when the power grid stability is the strongest, the calculation formula for the normalization result is:

[0123] The optimization objective includes that when the satisfaction of household load demand is the highest, the calculation formula for the normalization result is:

[0124] Among them, the smaller the electricity cost and the smaller the state of health of the battery, the slower the battery attenuation, the better the objective function. The power grid stability formula can measure the fluctuation of the interactive power with the power grid, and the smaller the value, the better the stability. The smaller the value of the household load demand satisfaction, the smaller the deviation between the actual power supply and demand, and the higher the satisfaction.

[0125] Among them, the optimization objective comprehensively considers the real-time electricity price fluctuation, household load demand, power grid stability and the state of health of the battery (SOH). Through real-time data collection and analysis, while ensuring the household electricity demand, the charging and discharging mode with the least impact on the battery health and the best economy is preferentially selected.

[0126] The real-time electricity price information can be obtained from the power grid or power company. The household electricity consumption can be collected through a smart meter or sensor. The power grid stability data can be obtained through the power grid operation data provided by the power company or local sensors. The battery operation data such as current, voltage and temperature can be obtained through the battery management system (BMS). After obtaining the relevant data, the collected data can be denoised and smoothed to reduce interference.

[0127] Furthermore, the method for generating the energy scheduling strategy of the vehicle further includes:

[0128] Obtaining the target operation data of the vehicle battery after operating according to the target energy scheduling strategy;

[0129] Determining the target state of health of the vehicle battery according to the target operation data;

[0130] Adjusting the target energy scheduling strategy based on the target state of health.

[0131] In some embodiments, a state of health threshold can be set. By comparing with the target state of health threshold, the corresponding adjustment method is selected. In the case of a higher state of health, a larger charging and discharging power is allowed to make full use of the time-of-use electricity price discount. In the case of a lower state of health, the charging and discharging power is reduced or the number of charging and discharging times is reduced to extend the battery life. Therefore, the charging and discharging power and frequency can be dynamically adjusted by classifying the state of health. Among them, the state of health threshold can be set to 80% but is not limited thereto.

[0132] Specifically, it is adjusted in the following manner:

[0133] When the target health state is relatively high ((SOH(t)>80%)), a relatively large charge-discharge power is allowed:

[0134]

[0135] And the charge-discharge frequency is increased:

[0136] f charge (t) = f base +Δf1; f discharge (t) = f base +Δf1; When the target health state is relatively low (SOH(t)<80%), the charge-discharge power is reduced:

[0137] And the charge-discharge frequency is reduced:

[0138] f charge (t) = f base -Δf2; f discharge (t) = f base -Δf2; Where: P charge,base , P discharge,base is the basic charge-discharge power, f base is the basic charge-discharge frequency, (ΔP1, ΔP2, Δf1, Δf2) are adjustment amplitudes set according to actual requirements.

[0139] The basic charge-discharge power and the basic charge-discharge frequency are reference parameters of the battery management system and are fixed values preset during system design.

[0140] In an alternative embodiment, determining the target health state of the vehicle battery according to the target operation data includes:

[0141] Extracting operation characteristic data from the target operation data;

[0142] Performing weighted processing on the operation characteristic data to obtain weighted operation data;

[0143] Based on a random forest model, making a decision on the weighted operation data to obtain the target health state.

[0144] In some embodiments, the parameters included in the target operation data may include the parameters in the current operation data, such as the remaining battery power, charge-discharge current, voltage, charge-discharge depth, charge-discharge power, and number of cycles of the vehicle battery. Based on the above target operation data, the corresponding operation characteristic data can be determined by analyzing this data.

[0145] Among them, the operation characteristic data includes: the maximum charge-discharge current Imax , minimum charge and discharge current I min , average charge and discharge current I avg , voltage fluctuation amplitude V fluctuation , temperature change rate T rate , average value of charge and discharge depth DoD avg , standard deviation of charge and discharge depth DoD std , charge and discharge power change rate P change , the influence coefficient of ambient temperature on battery performance T effect , number of cycles C count . Then, the operating characteristic data can be expressed as:

[0146] X=[I max ,I min ,I avg ,V fluctuation ,T rate ,DoDavg,DoDstd,P change ,T effect ,C count ];

[0147] The above-mentioned operation characteristic data are weighted to obtain weighted operation data: X′=H·X, where H represents the weight of each operation characteristic data, and H=[H1, H2, ..., Hy], where y represents the number of operation characteristic data.

[0148] After obtaining the weighted operating data, the target health status is obtained by calculation through the random forest model.

[0149] Specifically, a random forest consists of multiple decision trees: Where: M represents the number of decision trees, f m (X') represents the output of the mth decision tree.

[0150] Each decision tree is generated by random sampling (Bootstrap Sampling) and random feature selection (Random Feature Selection).

[0151] When the random forest model predicts SOH, the model output is a continuous value between 0 and 1: SOH = F(X'); SOH = 1 indicates that the battery is in the best condition; SOH = 0 indicates that the battery is completely failed.

[0152] In addition, in order to ensure the real-time performance and accuracy of the model, the present invention introduces an adaptive update mechanism to update the random forest model. The model parameters can be dynamically adjusted using an online learning mechanism to ensure that the model can adapt to changes in battery performance.

[0153] Among them, the data samples for training the random forest model can be obtained through a sliding window. Define a sliding window W that contains the data samples of the most recent N time steps: W(t) = X(t - N + 1), X(t - N + 2), …, X(t); at fixed time intervals (such as 1 hour or 1 charging cycle), the sliding window moves forward by one time step: W(t + 1) = W(t) + X(t + 1) - X(t - N + 1); after obtaining the new data sample X(t + 1), it is added to the end of the window (W), and the data sample X(t - N + 1) that entered the window earliest is removed from the window, so that the updated window W(t + 1) contains the latest operating data of the battery.

[0154] Based on the latest data set W(t) obtained by the sliding window technique, train or optimize the random forest model. Input the latest data set W(t) in the sliding window into the random forest model, and use cross-validation to optimize the hyperparameters (such as the number of trees, node splitting conditions, etc.).

[0155] The updated model is expressed as:

[0156]

[0157] is the true health state value, and (F(X')) is the predicted value of the health state by the model.

[0158] It can be understood that the weight coefficient (W) and the feature selection strategy can be dynamically adjusted according to the change trend of the battery performance. If a significant change in the battery performance is detected (such as rapid capacity decay), a fast update process is triggered.

[0159] In an optional embodiment, the method for generating the energy scheduling strategy of the vehicle in this application further includes:

[0160] Determine the power transmission direction of the vehicle based on the target operating data; adjust the target energy scheduling strategy based on the power transmission direction and the target health state.

[0161] In some embodiments, in the vehicle-to-home (V2H) scenario, bidirectional energy flow can be achieved between an electric vehicle (EV) and a home energy system:

[0162] Power supply to the home: When the grid load is at a peak or the home electricity demand is high, the EV supplies power to the home.

[0163] Charging from the grid: During off-peak hours or when the grid load is low, the EV charges from the grid to reserve energy.

[0164] Therefore, by predefined power direction, it is stipulated that the power is negative when the battery discharges (supplying power to the household), and the power is positive when the battery charges (charging from the grid). Thus, by obtaining the real-time power P(t) of the battery. If P(t) < 0, it is determined as "supplying power to the household", at this time, the battery energy flows to the household load to meet the electricity demand. If P(t) > 0, it is determined as "charging from the grid", at this time, the grid energy flows to the battery to charge the battery.

[0165] Specifically, the power adjustment scheme when supplying power to the household is as follows:

[0166] During the peak period of grid load or when the household electricity demand is high:

[0167] Dynamically adjust the output power according to the real-time SOH value: P output (t) = k·SOH(t), where k represents the proportionality coefficient.

[0168] Ensure that the output power does not exceed the maximum allowable value of the battery: P output (t) ≤ P max . The power adjustment scheme when charging from the grid is as follows:

[0169] During the low valley period or when the grid load is low, use the low-power slow charging mode to extend the battery life: P charge (t) = P base ·(SOH(t) / 100)); where P base represents the basic charging power.

[0170] The basic charge-discharge power and the basic charge-discharge frequency are the reference parameters of the battery management system and are fixed values preset during system design.

[0171] The method for generating the energy scheduling strategy of the vehicle in this application incorporates a dynamic SOH evaluation model and a multi-objective optimization algorithm, taking the battery health state as an important constraint condition into the scheduling strategy. This design not only reduces the electricity cost but also effectively delays the battery aging process and extends the battery service life. Through the adaptive charge and discharge strategy and the intelligent decision-making mechanism, it can dynamically adjust the charge and discharge mode according to the current health state of the battery, electricity price fluctuations, and household load demand. This flexibility significantly improves the adaptability and reliability of the system. The multi-objective optimization algorithm, while ensuring the lowest electricity cost, preferentially selects the charge and discharge strategies with less impact on battery health. This balanced optimization significantly enhances the overall performance of the system. Through dynamic SOH evaluation and adaptive charge and discharge strategies, the charge and discharge power or the number of charge and discharges is appropriately reduced during high electricity price periods, thereby effectively delaying the battery aging process and extending its service life. Through the design of protecting the battery health state, the reliability of the system is improved while ensuring household electricity demand, and the long-term maintenance cost is reduced. A new type of bidirectional energy interaction control method is proposed, which dynamically adjusts the output power when supplying power to the household during the peak period of the grid load, and adopts a low-power slow charge mode during charging in the low valley period to extend the battery life.

[0172] Exemplary device

[0173] Correspondingly, the embodiment of this application further provides a device for generating an energy scheduling strategy of a vehicle, including:

[0174] A first acquisition unit for acquiring the current operation data and power consumption limit data of the vehicle battery;

[0175] A determination unit for determining the constraint conditions based on the power consumption limit data;

[0176] A second acquisition unit for acquiring the optimization objectives of the vehicle battery, where the optimization objectives include maximizing the battery health state and minimizing the electricity cost;

[0177] A generation unit for optimizing the energy scheduling strategy of the vehicle battery based on the current operation data and power consumption limit data within the constraint conditions with the optimization objectives as the optimization direction to obtain the target energy scheduling strategy.

[0178] The generating device of the vehicle's energy scheduling strategy is based on a dynamic SOH evaluation model that combines real-time data collection and machine learning algorithms. This model can monitor the state of the electric vehicle battery in real time and, considering factors such as charge and discharge history data, ambient temperature, and charge and discharge depth, accurately predict the changing trend of the battery's health state. By dynamically evaluating the SOH, the system can detect signs of battery aging in a timely manner and take corresponding protection measures (such as restricting charge and discharge power or adjusting charge and discharge frequency), thereby effectively delaying the battery aging process. A multi-objective optimization algorithm is provided, with electricity cost and battery health state protection as the dual optimization objectives. By weighing the relationship between electricity cost and battery life, this algorithm preferentially selects charge and discharge strategies that have less impact on battery health while meeting household electricity demand. For example, during periods when electricity prices are low but may accelerate battery aging, the system will appropriately reduce charge and discharge power or the number of charge and discharge times. An adaptive charge and discharge strategy based on real-time SOH evaluation results. This strategy can dynamically adjust charge and discharge power and frequency according to the current health state of the battery. Specifically, when the battery health state is relatively high, the system allows a larger charge and discharge power to make full use of time-of-use electricity price discounts; while when the battery health state is relatively low, the charge and discharge power will be reduced or the number of charge and discharge times will be decreased to extend the battery life. An intelligent decision-making mechanism is introduced, which can comprehensively consider multiple factors such as electricity price fluctuations, household load demand, grid stability, and battery health state to formulate an optimal household energy scheduling plan. Through real-time data collection and analysis, this mechanism preferentially selects a charge and discharge mode that has the least impact on battery health and is economically optimal while ensuring household electricity demand. For the energy interaction process in the V2H scenario, the present invention proposes a new energy control method. This method can dynamically adjust the energy flow direction and power magnitude according to the battery health state, minimizing damage to the battery while ensuring household power supply. For example, when supplying power to the household during peak grid load periods, the system will dynamically adjust the output power according to the battery SOH; when charging during off-peak periods, a low-power slow charge mode will be adopted to extend the battery life.

[0179] The generating device of the vehicle's energy scheduling strategy provided in this embodiment belongs to the same inventive concept as the vehicle's energy scheduling strategy generating method provided in the above embodiments of the present application, can execute the methods provided in any of the above embodiments of the present application, and has the corresponding functional modules and beneficial effects of the executed methods. For technical details not described in detail in this embodiment, reference can be made to the specific processing content of the vehicle's energy scheduling strategy generating method provided in the above embodiments of the present application, which will not be elaborated here.

[0180] The functions realized by each unit in the above generating device of the vehicle's energy scheduling strategy can be respectively realized by the same or different processors, which is not limited in the embodiments of the present application.

[0181] It should be understood that the acquisition unit, expansion unit, and generation unit in the above device can be implemented in the form of a processor invoking software. For example, the device includes a processor, the processor is connected to a memory, instructions are stored in the memory, and the processor invokes the instructions stored in the memory to implement any of the above methods or the functions of each unit of the device. The processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory inside the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units can be implemented through the design of the hardware circuits. The hardware circuits can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are implemented through the design of the logical relationships of the components in the circuit. Again, for example, in another implementation, the hardware circuit can be implemented through a PLD. Taking an FPGA as an example, it can include a large number of logic gate circuits, and the connection relationships between the logic gate circuits are configured through a configuration file, so as to implement the functions of some or all of the above units. All the units of the above device can be all implemented in the form of a processor invoking software, or all implemented in the form of hardware circuits, or some implemented in the form of a processor invoking software, and the remaining part implemented in the form of hardware circuits.

[0182] In the embodiments of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor can be a circuit with the ability to read and execute instructions, such as a CPU, a microprocessor, a GPU, or a DSP, etc. In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits, and the logical relationships of the hardware circuits are fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an ASIC or a PLD, such as an FPGA, etc. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as a type of ASIC, such as an NPU, a TPU, a DPU, etc.

[0183] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method. For example: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0184] In addition, each unit in the above device can be integrated in whole or in part, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of an SOC. The SOC may include at least one processor for implementing any of the above methods or the functions of each unit of the device. The types of the at least one processor may be different, such as including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0185] Exemplary electronic device

[0186] Another embodiment of this application also proposes an electronic device. Refer to Figure 2 As shown, the device includes:

[0187] A memory 200 and a processor 210;

[0188] Wherein, the memory 200 is connected to the processor 210 and is used for storing programs;

[0189] The processor 210 is used for implementing the method for generating the energy scheduling strategy of the vehicle disclosed in any of the above embodiments by running the program stored in the memory 200.

[0190] Specifically, the above device for generating the energy scheduling strategy of the vehicle may further include: a bus, a communication interface 220, an input device 230, and an output device 240.

[0191] The processor 210, the memory 200, the communication interface 220, the input device 230, and the output device 240 are interconnected through the bus. Among them:

[0192] The bus may include a path for transmitting information between various components of the computer system.

[0193] The processor 210 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or may be an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the solution of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0194] The processor 210 may include a main processor and may also include a baseband chip, a modem, etc.

[0195] The program for implementing the technical solution of the present invention is stored in the memory 200. The operating system and other key services may also be stored therein. Specifically, the program may include program codes, and the program codes include computer operation instructions. More specifically, the memory 200 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk memory, a flash memory, etc.

[0196] The input device 230 may include devices for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor, etc.

[0197] The output device 240 may include devices for allowing information to be output to a user, such as a display screen, a printer, a speaker, etc.

[0198] The communication interface 220 may include devices of any transceiver type for communicating with other devices or communication networks, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0199] The processor 210 executes the program stored in the memory 200 and calls other devices, and can be used to implement each step of the method for generating an energy scheduling strategy for any vehicle provided in the above embodiments of the present application.

[0200] Exemplary computer program product and storage medium

[0201] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions. When the computer program instructions are run by a processor, the processor is caused to execute the steps in the method for generating an energy scheduling strategy for a vehicle according to various embodiments of the present application described in any of the above embodiments of this specification.

[0202] The computer program product may be written in any combination of one or more programming languages for programming codes for performing the operations of the embodiments of the present application. The programming languages include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as the "C" language or similar programming languages. The program codes may be executed entirely on a user computing device, partially on a user device, executed as an independent software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0203] In addition, an embodiment of the present application may also be a storage medium, on which a computer program is stored. The computer program is executed by a processor to perform the steps in the method for generating an energy scheduling strategy of a vehicle according to various embodiments of the present application described in any of the above embodiments of the present specification, and specifically may implement the following steps:

[0204] Obtain the current operating data and power consumption limit data of the vehicle battery;

[0205] Determine the constraint conditions based on the power consumption limit data;

[0206] Obtain the optimization objectives of the vehicle battery, where the optimization objectives include maximizing the battery health state and minimizing the power consumption cost;

[0207] Taking the optimization objectives as the optimization direction, optimize the energy scheduling strategy of the vehicle battery within the constraint conditions based on the current operating data and power consumption limit data to obtain the target energy scheduling strategy.

[0208] For the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps may be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0209] It should be noted that the embodiments in this specification are all described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0210] The steps in the methods of the embodiments of the present application can be adjusted, combined, and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0211] The modules and sub-modules in the devices and terminals in the embodiments of the present application can be combined, divided, and deleted according to actual needs.

[0212] In several embodiments provided by the present application, it should be understood that the disclosed terminals, devices, and methods can be implemented in other ways. For example, the terminal embodiments described above are merely illustrative. For example, the division of modules or sub-modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple sub-modules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be an indirect coupling or communication connection through some interfaces, devices, or modules, and can be in electrical, mechanical, or other forms.

[0213] The modules or sub-modules described as separate components may or may not be physically separated. The components as modules or sub-modules may or may not be physical modules or sub-modules, that is, they can be located in one place, or can be distributed to multiple network modules or sub-modules. Some or all of the modules or sub-modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0214] In addition, each functional module or sub-module in various embodiments of the present application can be integrated in a processing module, or each module or sub-module can exist physically alone, or two or more modules or sub-modules can be integrated in one module. The above-mentioned integrated modules or sub-modules can be implemented in the form of hardware, or in the form of software functional modules or sub-modules.

[0215] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0216] The steps of the methods or algorithms described in combination with the embodiments disclosed in this article can be directly implemented by hardware, software units executed by a processor, or a combination of the two. The software units can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0217] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

[0218] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating an energy scheduling strategy for a vehicle, characterized in that, Including: Obtain the current operation data and power consumption limit data of the vehicle battery; Determine the constraint conditions based on the power consumption limit data; Obtain the optimization objectives of the vehicle battery, where the optimization objectives include maximizing the battery health state and minimizing the power consumption cost; Taking the optimization objectives as the optimization direction, within the constraint conditions, optimize the energy scheduling strategy of the vehicle battery based on the current operation data and power consumption limit data to obtain the target energy scheduling strategy.

2. The method according to claim 1, characterized in that, Taking the optimization objectives as the optimization direction, within the constraint conditions, optimize the energy scheduling strategy of the vehicle battery based on the current operation data and power consumption limit data to obtain the target energy scheduling strategy, including: Initialize the particle swarm based on the particle swarm optimization algorithm to obtain the initial velocity and initial position of each particle in the particle swarm. The position of the particle represents the energy scheduling strategy of the vehicle battery, and the velocity of the particle represents the change amount of the energy scheduling strategy of the vehicle battery; Perform the following iterative process for each particle: Calculate the fitness value of the particle based on the power consumption limit data, the current operation data, and the current position of the particle. The initial value of the current position is the initial position, and the fitness value is calculated by the objective function constructed by the optimization objective; Based on the current velocity and current position of the particle, update the position and velocity of the particle to obtain the updated position and updated velocity. The updated position satisfies the constraint conditions. The initial value of the current velocity is the initial velocity, and the initial value of the current position is the initial position; Determine the best position of the particle based on the fitness value and the current position; Determine the global best position of the particle swarm based on the best position of each particle; Based on the best position, determine whether the iteration end condition is satisfied. If so, determine the energy scheduling strategy represented by the global best position as the target energy scheduling strategy; If not, update the current velocity to the updated velocity, and update the current position to the updated position, and then execute the iterative process again.

3. The method according to claim 2, wherein The objective function is: F = W1F1 +... + W n F n ; Among them, F n represents the nth optimization objective, and W n represents the weight of the nth optimization objective, where n represents the number of optimization objectives.

4. The method according to claim 3, wherein When the optimization objective includes minimizing the power consumption cost, the power consumption cost calculation formula is: When the optimization objective includes maximizing the battery health state, the battery health state calculation formula is: When the optimization objective includes the strongest power grid stability, the power grid stability calculation formula is: When the optimization objective includes the highest satisfaction degree of household load demand, the household load demand satisfaction degree calculation formula is: Among them, P grid (t) represents the electricity purchased from the power grid during the time period t, P charge (t) represents the charging amount during the time period t, C elec (t) represents the real-time electricity price during the time period t, ΔSOH(t) represents the rate of change of the battery health state during the time period t, and T represents the optimization period; P battery (t) represents the battery power at the moment t, and L(t) represents the household load demand at the moment t.

5. The method according to claim 3, wherein The weight of the optimization objective is obtained by the following method: Normalize each optimization objective to obtain the normalization result; The weights of the optimization objectives are: Among them, s i (t) represents the normalized result of the i-th optimization objective, where i ranges from 1 to n.

6. The method according to claim 1, characterized in that, After optimizing the energy scheduling strategy of the vehicle battery based on the current operation data and power consumption limit data within the constraint conditions with the optimization objectives as the optimization direction to obtain the target energy scheduling strategy, it further includes: Obtain the target operation data after the vehicle battery operates according to the target energy scheduling strategy; Determine the target health state of the vehicle battery according to the target operation data; Adjust the target energy scheduling strategy based on the target health state.

7. The method according to claim 6, characterized in that Determine the target health state of the vehicle battery according to the target operation data, including: Extract the operation characteristic data from the target operation data; Perform weighted processing on the operation characteristic data to obtain weighted operation data; Based on the random forest model, make a decision on the weighted operation data to obtain the health state.

8. The method according to claim 6, characterized in that It further includes: Determine the power transmission direction of the vehicle based on the target operation data; Adjust the target energy scheduling strategy based on the power transmission direction and the target health state.

9. An electronic device, characterized in that, It includes a memory and a processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the method for generating the energy scheduling strategy of the vehicle according to any one of claims 1 to 8 by running the programs in the memory.

10. A storage medium, characterized in that, A computer program is stored on the storage medium, and when the computer program is run by the processor, the method for generating the energy scheduling strategy of the vehicle according to any one of claims 1 to 8 is implemented.

Images