A V2G Power Regulation Method for Electric Vehicles Based on Surrogate Model

Abstract

The present invention discloses a method for regulating the V2G power of electric vehicles based on a surrogate model. The method includes the following steps: First, construct a training sample set according to the historical V2G data of electric vehicles; then, use the training sample set to train a surrogate model based on a neural network to obtain a prediction model for the power flexibility of electric vehicles; next, obtain the electric vehicle parameters and behavior information corresponding to each user and input them into the prediction model, and the model outputs the power flexibility of the electric vehicle corresponding to the user. The power grid sends an actual regulation instruction for the electric vehicle to the corresponding charging pile according to the power flexibility of the electric vehicle, so as to control the charging and discharging power of the electric vehicle; finally, obtain the real-time battery SOC of the electric vehicle and perform a rolling prediction of the power flexibility of the electric vehicle to realize the dynamic regulation of the V2G power of the electric vehicle. The present invention realizes the rapid solution of the power flexibility of electric vehicles and can effectively improve the grid regulation ability.

Description

Technical Field

[0001] The present invention relates to an electric vehicle regulation method in the technical field of electric vehicles, and more particularly to an electric vehicle V2G power regulation method based on a surrogate model. Background Art

[0002] Existing electric vehicle regulation means are mainly divided into two categories: centralized control and distributed control. The centralized control method can achieve a global optimal solution, but there are also certain limitations. On the one hand, this method ignores the protection of user privacy; on the other hand, due to the high computational complexity, it is easy to bring a large computational burden and it is difficult to meet the high-efficiency requirements in practical applications. In contrast, the distributed control method makes up for the deficiencies of the centralized control to a certain extent. The distributed control method usually integrates the feasible power boundaries provided by users through an electric vehicle aggregator and submits them to the distribution system operator. Subsequently, the distribution system operator issues regulation instructions according to the real-time demand of the power grid, so as to achieve the efficient and reasonable regulation of electric vehicles.

[0003] However, neither the existing centralized control method nor the distributed control method takes into account and quantifies the power flexibility of electric vehicles. Therefore, it is necessary to propose an electric vehicle V2G power regulation method that considers the power flexibility of electric vehicles. Summary of the Invention

[0004] In order to solve the problems and requirements in the background art, the present invention provides an electric vehicle V2G power regulation method based on a surrogate model.

[0005] The technical solution of the present invention is as follows:

[0006] 1. An electric vehicle V2G power regulation method based on a surrogate model

[0007] S1: Calculate the power flexibility of the electric vehicle according to the historical V2G data of the electric vehicle, and then construct a training sample set;

[0008] S2: Use the training sample set to train a surrogate model based on a neural network to obtain an electric vehicle power flexibility prediction model;

[0009] S3: Obtain the electric vehicle parameters and behavior information corresponding to each user and input them into the electric vehicle power flexibility prediction model. The model outputs the power flexibility of the electric vehicle corresponding to the user. The power grid sends an actual regulation instruction for the electric vehicle to the corresponding charging pile according to the power flexibility of the electric vehicle, so as to control the charging and discharging power of the electric vehicle;

[0010] S4: Obtain the real-time battery SOC of the electric vehicle and perform a rolling prediction of the power flexibility of the electric vehicle to achieve dynamic regulation of the electric vehicle V2G power.

[0011] In S1, the power flexibility of the electric vehicle satisfies the following formula:

[0012] S = [P - i,1 , P + i,1 × [P - i,2 , P + i,2 × … × [P - i,t , P + i,t

[0013] Where S is the power flexibility of the electric vehicle; P - i,1 , P + i,1 are respectively the upper limit and lower limit of the charge-discharge power allowed for electric vehicle i at time 1; P - i,2 , P + i,2 are respectively the upper limit and lower limit of the charge-discharge power allowed for electric vehicle i at time 2; P - i,t , P + i,t are respectively the upper limit and lower limit of the charge-discharge power allowed for electric vehicle i at time t, and the time interval between adjacent two times is Δt.

[0014] In S1, the power flexibility of the electric vehicle is calculated according to the historical V2G data of the electric vehicle, specifically:

[0015] First, construct the electric vehicle V2G power optimization problem corresponding to each user, and the electric vehicle V2G power optimization problem satisfies the following formula:

[0016] maxP gap -σ·k

[0017] P gap = min(P + i,t - P - i,t ), t = t i a , …, t i ε

[0018] t i ε = min(t i a ​+ε, t i d )

[0019] σ = ∑abs(P + i,t -P + i,t+1 ) + abs(P - i,t -P - i,t+1 ), t = t i a , …, t i d -△t

[0020] P + i,t ≥ P - i,t , t = t i a ,..., t i d

[0021] where P gap is the minimum value of the flexibility of the electric vehicle power in each time period within the target time period; σ is the power fluctuation coefficient of the upper and lower limits of the electric vehicle power flexibility; k is the power fluctuation penalty coefficient; △t is the time interval between two adjacent moments; t i a is the arrival time of the i-th electric vehicle; t i d is the departure time of the i-th electric vehicle; ε is the duration of the target time period; t i ε is P gap the end time of the target time period; abs() is the absolute value symbol; P - i,t , P + i,t are respectively the upper limit and lower limit of the charge and discharge power allowed for the i-th electric vehicle at time t; P - i,t , P + i,t are respectively the upper limit and lower limit of the charge and discharge power allowed for the i-th electric vehicle at time t + 1;

[0022] Then, based on the historical V2G data of electric vehicles, as well as the capacity constraint of the battery itself, the initial energy state of the vehicle, the minimum demand power constraint when the user leaves, the maximum charge and discharge power constraint, and the energy balance constraint, use the optimization method to solve the V2G power optimization problem of the electric vehicle corresponding to each user, and obtain the power flexibility of the electric vehicle corresponding to this user.

[0023] The capacity constraint of the battery itself satisfies the formula e i,min ≤e i,t ≤e i,max ,t i a ≤t≤t i d , e i,min is the minimum energy of the battery of the i-th electric vehicle, e i,max is the maximum energy of the battery of the i-th electric vehicle, e i,t is the energy state of the i-th electric vehicle at time t.

[0024] The initial energy state of the vehicle and the minimum required power constraint when the user leaves satisfy the formula e i need ≤e i init +∑P i,t △t,t=t i a ,…,t i d , P i,t is the power of the i-th electric vehicle at time t, e i need is the minimum energy required by the electric vehicle battery when the i-th electric vehicle leaves; e i ini is the energy of the electric vehicle battery when the i-th electric vehicle arrives.

[0025] The energy balance constraint satisfies the formula e i,t+1 = e i,t + P i,t △t, e i,t is the energy state of the i-th electric vehicle at time t, e i,t+1 is the energy state of the i-th electric vehicle at time t+1, P i,t is the power of the i-th electric vehicle at time t.

[0026] II. An Electric Vehicle V2G Power Regulation Device Based on an Agent Model

[0027] A training sample set generation unit, configured to calculate the power flexibility of an electric vehicle according to the historical V2G data of the electric vehicle, and further construct a training sample set;

[0028] A model storage unit, configured to store an agent model based on a neural network and corresponding network parameters;

[0029] A training unit, configured to train the agent model based on the neural network by using the training sample set, obtain the trained network parameters, and send them to the prediction unit;

[0030] A prediction unit, configured to obtain the electric vehicle parameters and behavior information corresponding to each user and input them into a trained neural network-based proxy model, and the model outputs the power flexibility of the electric vehicle corresponding to the user.

[0031] A power grid regulation unit, configured to send an actual regulation instruction for the electric vehicle to the corresponding charging pile according to the power flexibility of the electric vehicle, so as to control the charging and discharging power of the electric vehicle.

[0032] III. A computer device

[0033] The device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method for regulating the V2G power of an electric vehicle based on a proxy model are implemented.

[0034] IV. A computer-readable storage medium

[0035] The medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for regulating the V2G power of an electric vehicle based on a proxy model are implemented.

[0036] V. A computer program product

[0037] The product includes a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps of the method for regulating the V2G power of an electric vehicle based on a proxy model are implemented.

[0038] The beneficial effects of the present invention are as follows:

[0039] The method proposed by the present invention is based on electric vehicle parameters and user behavior information, and uses a proxy model to quantitatively evaluate the adjustable power flexibility in future time periods, which can effectively aggregate electric vehicle resources for grid operators, improve the grid regulation ability, and is conducive to ensuring the operation and maintenance management of the grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a schematic flow chart of the method provided by an embodiment of the present invention.

[0041] Figure 2 is a schematic diagram of the quantization result of the V2G power flexibility of an electric vehicle provided by an embodiment of the present invention, where (a) is a schematic diagram of the quantization result of the V2G power flexibility of an electric vehicle provided by Embodiment 2, and (b) is a schematic diagram of the quantization result of the V2G power flexibility of an electric vehicle provided by Embodiment 1.

[0042] Figure 3 is a schematic diagram of the proxy model substitution process provided by an embodiment of the present invention.

[0043] Figure 4 It is a schematic diagram of the quantification result of V2G power flexibility provided by an embodiment of the present invention.

[0044] Figure 5 It is a schematic diagram of the rolling prediction result when the target period for maximizing the flexibility of an electric vehicle provided in Embodiment 1 is 1 h.

[0045] Figure 6 It is a schematic diagram of the rolling prediction result when the target period for maximizing the flexibility of an electric vehicle provided in Embodiment 2 is the entire stay time. Detailed implementation manners

[0046] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0047] In the description of the present invention, it should be understood that the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, the meaning of "plurality" is two or more.

[0048] Embodiment 1

[0049] As Figure 1 shown, a method for regulating the V2G power of an electric vehicle based on a surrogate model proposed by the present invention specifically includes the following steps:

[0050] S1: Calculate the power flexibility of the electric vehicle according to the historical V2G data of the electric vehicle, and then construct a training sample set; the historical V2G data includes the electric vehicle parameters and behavior information of the user, and each sample in the training sample set includes the electric vehicle parameters and behavior information of the user and the power flexibility.

[0051] The power flexibility of the electric vehicle satisfies the following formula:

[0052] S = [P - i,1 , P + i,1 × [P - i,2 , P + i,2 × … × [P - i,t , P +i,t

[0053] Among them, S is the power flexibility of the electric vehicle; P - i,1 , P + i,1 are respectively the upper limit and lower limit of the charge-discharge power allowed for electric vehicle i at time 1; P - i,2 , P + i,2 are respectively the upper limit and lower limit of the charge-discharge power allowed for electric vehicle i at time 2; P - i,t , P + i,t are respectively the upper limit and lower limit of the charge-discharge power allowed for electric vehicle i at time t. The time interval between two adjacent times is Δt, that is, the power state at each time will last for Δt time, and Δt takes 15 min.

[0054] The present invention quantifies the power flexibility S of electric vehicles in different time periods based on the inner box approximation method, and can realize the decoupling of the power feasible region in the time dimension.

[0055] Calculate the power flexibility of electric vehicles according to the historical V2G data of electric vehicles, specifically:

[0056] First, construct the electric vehicle V2G power optimization problem corresponding to each user. The electric vehicle V2G power optimization problem satisfies the following formula:

[0057] maxP gap -σ·k

[0058] P gap =min(P + i,t -P - i,t ), t = t i a ,…, t i ε

[0059] t i ε = min(t i a +ε, t i d )

[0060] σ=∑abs(P + i,t -P + i,t+1 )+ abs(P - ​i,t -P - i,t+1 ), t = t i a , …, t i d -Δt

[0061] P + i,t ≥P - i,t , t = t i a ,..., t i d

[0062] where P gap is the minimum value of the flexibility of the electric vehicle power at each time period within the target time period; σ is the power fluctuation coefficient of the upper and lower limits of the electric vehicle power flexibility; k is the power fluctuation penalty coefficient; t i a is the arrival time of the i-th electric vehicle; t i d is the departure time of the i-th electric vehicle; ε is the duration of the target time period in the objective function to be solved, which is taken as 1 h here; t i ε is for P gap the end moment of the target time period; abs( ) is the absolute value symbol; P - i,t , P + i,t are respectively the upper limit and lower limit of the charging and discharging power allowed for the i-th electric vehicle at time t; P - i,t , P + i,t are respectively the upper limit and lower limit of the charging and discharging power allowed for the i-th electric vehicle at time t + 1;

[0063] As Figure 2 shown in (b) of gap when the target time period is selected as the nearest target time period of the electric vehicle, the power flexibility of its nearest time period is greatly improved. Although the power flexibility in the subsequent several time periods is restricted within a very small area, through continuous prediction and evaluation by rolling optimization, its power flexibility can be continuously updated, so that the power flexibility at the nearest moment is always continuously increasing.

[0064] Then, according to the historical V2G data of electric vehicles, as well as the capacity constraint of the battery itself, the initial energy state of the vehicle, the minimum required power constraint when the user leaves, the maximum charge-discharge power constraint, and the energy balance constraint, an optimization method is used to solve the V2G power optimization problem of the electric vehicle corresponding to each user, and the power flexibility of the electric vehicle corresponding to the user is obtained.

[0065] The capacity constraint of the battery itself satisfies the formula e i,min ≤e i,t ≤e i,max ,t i a ≤t≤t i d ,e i,min is the minimum energy of the battery of the i-th electric vehicle, e i,max is the maximum energy of the battery of the i-th electric vehicle, e i,t is the energy state of the i-th electric vehicle at time t. The initial energy state of the vehicle and the minimum required power constraint when the user leaves satisfy the formula e i need ≤e i init +∑P i,t △t,t=t i a ,…,t i d ,P i,t is the power of the i-th electric vehicle at time t, e i need is the minimum energy required by the battery of the electric vehicle when user i leaves, e i ini is the energy of the battery of the electric vehicle when user i arrives. The maximum charge-discharge power constraint satisfies the formula P i,min ≤P i,t ≤P i,max ,P i,max is the maximum charging power allowed for the i-th electric vehicle, P i,min is the maximum discharging power allowed for the i-th electric vehicle. The energy balance constraint satisfies the formula e i,t+1 = e i,t + P i,t △t,e i,t+1 is the energy state of the i-th electric vehicle at time t+1.

[0066] S2: Use the training sample set to train the surrogate model based on the neural network so that it can effectively learn the mapping process of the original problem and obtain the electric vehicle power flexibility prediction model; the electric vehicle power flexibility prediction model replaces the original optimization method, and the process is as Figure 3 shown.

[0067] S3: Each user uploads their electric vehicle parameters and behavior information to the cloud. The electric vehicle parameters include the electric vehicle battery capacity, maximum charge and discharge power, minimum battery SOC required for travel, and the current battery SOC at the current moment. The behavior information includes the arrival time and departure time, where the current battery SOC is obtained by collecting through the charging pile. Obtain the electric vehicle parameters and behavior information corresponding to each user and input them into the electric vehicle power flexibility prediction model. The model outputs the power flexibility of the electric vehicle corresponding to this user. The power grid sends the actual electric vehicle regulation command to the corresponding charging pile according to the power flexibility of this electric vehicle, so as to control the charge and discharge power of this electric vehicle;

[0068] S4: Obtain the real-time battery SOC of the electric vehicle and conduct rolling prediction of the power flexibility of the electric vehicle, that is, input the real-time battery SOC of the electric vehicle together with other electric vehicle parameters and behavior information into the electric vehicle power flexibility prediction model. The model continuously predicts the power flexibility of the electric vehicle. The power grid sends the actual electric vehicle regulation command to the corresponding charging pile according to the power flexibility of this electric vehicle, so as to control the charge and discharge power of this electric vehicle, thereby realizing the dynamic regulation of the electric vehicle V2G power.

[0069] In this embodiment, 1000 electric vehicle charging events are selected as historical V2G data. Table 1 shows the performance of solving the power flexibility of electric vehicles using a surrogate model (specifically, an MLP multi-layer perceptron) and a mathematical optimization method (specifically, programming with yalmip and solving with the gurobi solver). Among them, the mean square error index is used to evaluate the accuracy of the surrogate model. It can be seen from the table that the accuracy of the surrogate model has achieved good results. Compared with the mathematical optimization method, the surrogate model has achieved a reduction of hundreds of times in calculation time, fully demonstrating the high efficiency and practical application potential of the method proposed in the present invention.

[0070] Table 1 is the performance table of the surrogate model and the optimization method

[0071]

[0072] From Figure 4 it can be seen that the electric vehicle V2G power regulation method based on the surrogate model proposed in the present invention is almost completely consistent with the results obtained through the mathematical optimization model. This result verifies the high accuracy of the method proposed in the present invention.

[0073] Figure 5It shows the feasible region of the rolling evaluation of the power flexibility of a typical electric vehicle. The range ε of the target time period is set to 1 h, and after every 1 h interval, the proposed electric vehicle V2G power regulation method of the present invention is used to re-evaluate the power feasible region. It can be clearly observed that for this device, the electric vehicle, which is highly coupled with time, its power flexibility is closely related to the current battery energy state and the historical power trajectory. Using rolling prediction can significantly expand the range of the power feasible region in the future time period.

[0074] Embodiment 2

[0075] As Figure 1 shown, a proxy model-based electric vehicle V2G power regulation method proposed by the present invention specifically includes the following steps:

[0076] S1: Calculate the power flexibility of the electric vehicle according to the historical V2G data of the electric vehicle, that is, the power flexibility during all the parking periods of the electric vehicle, and then construct a training sample set; the historical V2G data includes the electric vehicle parameters and behavior information of the user, and each sample in the training sample set includes the electric vehicle parameters and behavior information of the user and the power flexibility.

[0077] The power flexibility of the electric vehicle satisfies the following formula:

[0078] S = [P - i,1 , P + i,1 × [P - i,2 , P + i,2 × … × [P - i,t , P + i,t

[0079] where S is the power flexibility of the electric vehicle; P - i,1 , P + i,1 are respectively the upper limit and lower limit of the charge and discharge power allowed for electric vehicle i at time 1; P - i,2 , P + i,2 are respectively the upper limit and lower limit of the charge and discharge power allowed for electric vehicle i at time 2; P - i,t , P + i,t ​They are the upper and lower limits of the allowable charging and discharging power of electric vehicle i at time t, respectively. The time interval between two adjacent times is Δt, that is, the power state at each time will last for Δt, and Δt is taken as 15 minutes.

[0080] Based on the inner box approximation method, the present invention quantifies the power flexibility S of electric vehicles at different time periods, and can realize the decoupling of the power feasible region in the time dimension.

[0081] Calculate the power flexibility of electric vehicles according to the historical V2G data of electric vehicles, specifically:

[0082] First, construct the electric vehicle V2G power optimization problem corresponding to each user. The electric vehicle V2G power optimization problem satisfies the following formula:

[0083] maxP gap -σ·k

[0084] P gap =min(P + i,t -P - i,t ),t=t i a ,… , t i d

[0085] σ=∑abs(P + i,t -P + i,t+1 )+ abs(P - i,t -P - i,t+1 ) ,t=t i a ,…,t i d -△t

[0086] P + i,t ≥P - i,t ,t=t i a ,..., t i d

[0087] Among them, P gap is the minimum value of the flexibility of the electric vehicle power in each time period within the target time period; σ is the power fluctuation coefficient of the upper and lower limits of the electric vehicle power flexibility; k is the power fluctuation penalty coefficient; Δt is the time interval between two adjacent times; t i ais the arrival time of the \(i\)-th electric vehicle; \(t\) i d is the departure time of the \(i\)-th electric vehicle; abs( ) is the absolute value symbol; \(t\) i d is the departure time of the \(i\)-th electric vehicle; \(P\) - i,t , \(P\) + i,t are respectively the upper limit and lower limit of the allowable charging and discharging power of electric vehicle \(i\) at time \(t\); \(P\) - i,t , \(P\) + i,t are respectively the upper limit and lower limit of the allowable charging and discharging power of electric vehicle \(i\) at time \(t + 1\);

[0088] Figure 2 (a) of is \(P\) gap The target time period is selected as the power flexibility diagram obtained from the entire stay period of the electric vehicle. At this time, the power of the electric vehicle only needs to change within its power flexibility range to meet the operation constraints of the electric vehicle. The change range of its energy is shown in the upper diagram of (a) of Figure 2 The upper and lower boundaries respectively correspond to the regulation results of the electric vehicle power at the upper and lower limits of the power flexibility.

[0089] Then, according to the historical V2G data of the electric vehicle, as well as the capacity constraint of the battery itself, the initial energy state of the vehicle, the minimum demand power constraint when the user leaves, the maximum charging and discharging power constraint, and the energy balance constraint, an optimization method is used to solve the V2G power optimization problem of the electric vehicle corresponding to each user, and the power flexibility of the electric vehicle corresponding to the user is obtained.

[0090] The capacity constraint of the battery itself satisfies the formula \(e\) i,min ≤ \(e\) i,t ≤ \(e\) i,max , \(t\) i a ≤ \(t\) ≤ \(t\) i d , \(e\) i,min is the minimum energy of the battery of the \(i\)-th electric vehicle, \(e\) i,max is the maximum energy of the battery of the \(i\)-th electric vehicle, \(e\) i,t is the energy state of the \(i\)-th electric vehicle at time \(t\). The initial energy state of the vehicle and the minimum demand power constraint when the user leaves satisfy the formula \(e\) i need ≤ \(e\) i init + ∑ \(P\) i,t △ \(t\), \(t = t\) i a , …, \(t\) id , P i,t is the power of the \(i\)-th electric vehicle at time \(t\), \(e\) i need is the minimum energy required for the battery of the electric vehicle when user \(i\) leaves, \(e\) i ini is the energy of the battery of the electric vehicle when user \(i\) arrives. The maximum charge-discharge power constraint satisfies the formula \(P\) i,min ≤ \(P\) i,t ≤ \(P\) i,max , \(P\) i,max is the maximum charging power allowed for the \(i\)-th electric vehicle, \(P\) i,min is the maximum discharging power allowed for the \(i\)-th electric vehicle. The energy balance constraint satisfies the formula \(e\) i,t+1 = \(e\) i,t + \(P\) i,t △\(t\), \(e\) i,t+1 is the energy state of the \(i\)-th electric vehicle at time \(t + 1\).

[0091] S2: Use the training sample set to train the surrogate model based on the neural network so that it can effectively learn the mapping process of the original problem and obtain the electric vehicle power flexibility prediction model; the electric vehicle power flexibility prediction model replaces the original optimization method, and the process is as Figure 3 shown.

[0092] S3: Each user uploads their own electric vehicle parameters and behavior information to the cloud. The electric vehicle parameters include the electric vehicle battery capacity, the maximum charge-discharge power, the minimum battery SOC required for travel, and the current battery SOC. The behavior information includes the arrival time and the departure time. Among them, the current battery SOC is obtained by collecting through the charging pile. Obtain the electric vehicle parameters and behavior information corresponding to each user and input them into the electric vehicle power flexibility prediction model. The model outputs the power flexibility of the electric vehicle corresponding to this user. The power grid sends the actual regulation instruction of the electric vehicle to the corresponding charging pile according to the power flexibility of this electric vehicle, so as to control the charge-discharge power of this electric vehicle;

[0093] S4: Obtain the real-time battery SOC of the electric vehicle and conduct a rolling prediction of the power flexibility of the electric vehicle, that is, input the real-time battery SOC of the electric vehicle together with other electric vehicle parameters and behavior information into the electric vehicle power flexibility prediction model. The model continuously predicts the power flexibility of the electric vehicle. The power grid sends the actual regulation instruction of the electric vehicle to the corresponding charging pile according to the power flexibility of this electric vehicle, so as to control the charge-discharge power of this electric vehicle, so as to realize the dynamic regulation of the V2G power of the electric vehicle.

[0094] Figure 6It shows the feasible region of the rolling evaluation of the typical power flexibility of electric vehicles. The range ε of the target time period is set as the entire residence time of the electric vehicles. After every 1 h interval, the V2G power regulation method proposed in the present invention is used to re-evaluate the power feasible region.

[0095] In the above two embodiments, due to the different settings of the range ε of the target time period, the obtained flexibility intervals are also different. From Figure 5 and Figure 6 it can be seen that Figure 5 the power flexibility benefits achieved are more significant, and the obtained flexibility interval is larger. However, the rolling strategy has higher performance requirements in terms of calculation time. Different from the traditional mathematical method that only needs to calculate the power flexibility once, the rolling method needs to continuously evaluate new flexibility regions as time progresses, which poses a higher challenge to the calculation speed of the model. Therefore, the present invention introduces a surrogate model, which can significantly reduce the calculation time in the process of solving the power flexibility optimization problem, thus providing important help for practical engineering applications.

[0096] The above are the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A method for regulating the V2G power of an electric vehicle based on a surrogate model, characterized in that Including the following steps: S1: Calculate the power flexibility of the electric vehicle according to the historical V2G data of the electric vehicle, and then construct a training sample set; S2: Use the training sample set to train the surrogate model based on the neural network to obtain the electric vehicle power flexibility prediction model; S3: Obtain the electric vehicle parameters and behavior information corresponding to each user and input them into the electric vehicle power flexibility prediction model. The model outputs the power flexibility of the electric vehicle corresponding to the user. The power grid sends the actual regulation command of the electric vehicle to the corresponding charging pile according to the power flexibility of the electric vehicle, so as to control the charging and discharging power of the electric vehicle; S4: Obtain the real-time battery SOC of the electric vehicle and perform rolling prediction of the power flexibility of the electric vehicle to realize the dynamic regulation of the V2G power of the electric vehicle; In the S1, calculating the power flexibility of the electric vehicle according to the historical V2G data of the electric vehicle is specifically as follows: First, construct the electric vehicle V2G power optimization problem corresponding to each user, and the electric vehicle V2G power optimization problem satisfies the following formula: maxP gap -σ·k P gap = min(P + i,t -P - i,t ), t = t i a , …, t i ε t i ε = min(t i a + ε, t i d ) σ = ∑ abs(P + i,t -P + i,t+1 ) + abs(P - i,t -P - i,t+1 ), t = t i a , …, t i d -△t P + i,t ≥P - i,t ,t=t i a ,..., t i d Among them, P gap is the minimum value of the flexibility of each time period of the electric vehicle power within the target time period; σ is the power fluctuation coefficient of the upper and lower limits of the electric vehicle power flexibility; k is the power fluctuation penalty coefficient; △t is the time interval between two adjacent moments; t i a is the arrival time of the i-th electric vehicle; t i d is the departure time of the i-th electric vehicle; ε is the duration of the target time period; t i ε is P gap the end moment of the target time period; abs( ) is the absolute value symbol; P - i,t , P + i,t are respectively the lower limit and the upper limit of the charge and discharge power allowed for the i-th electric vehicle at the moment t; P - i,t+1 , P + i,t+1 are respectively the lower limit and the upper limit of the charge and discharge power allowed for the i-th electric vehicle at the moment t + 1; Then, according to the historical V2G data of the electric vehicle, as well as the capacity constraint of the battery itself, the initial energy state of the vehicle, the minimum required power consumption when the user leaves, the maximum charging and discharging power constraint, and the energy balance constraint, use the optimization method to solve the electric vehicle V2G power optimization problem corresponding to each user to obtain the power flexibility of the electric vehicle corresponding to the user.

2. The method for regulating the V2G power of an electric vehicle based on an agent model according to claim 1, wherein In the S1, the power flexibility of the electric vehicle satisfies the following formula: S = [P - i,1 , P + i,1 × [P - i,2 , P + i,2 × … × [P - i,t , P + i,t ​ Among them, S is the power flexibility of electric vehicle i; P - i,1 , P + i,1 are respectively the lower limit and upper limit of the allowable charging and discharging power of electric vehicle i at time 1; P - i,2 , P + i,2 are respectively the lower limit and upper limit of the allowable charging and discharging power of electric vehicle i at time 2; P - i,t , P + i,t are respectively the lower limit and upper limit of the allowable charging and discharging power of electric vehicle i at time t, and the time interval between two adjacent times is △t.

3. A method for regulating the V2G power of an electric vehicle based on an agent model according to claim 1, characterized in that, The capacity constraint of the battery itself satisfies the formula e i,min ≤e i,t ≤e i,max ,t i a ≤t≤t i d ,e i,min is the minimum energy of the battery of the i-th electric vehicle, e i,max is the maximum energy of the battery of the i-th electric vehicle, e i,t is the energy state of the i-th electric vehicle at time t.

4. A method for regulating the V2G power of an electric vehicle based on an agent model according to claim 1, characterized in that, The initial energy state of the vehicle and the minimum required power consumption constraint when the user leaves satisfy the formula e i need ≤e i init +∑P i,t △t,t=t i a ,…,t i d ,P i,t is the power of the i-th electric vehicle at time t, and e i need is the minimum energy required for the battery of the i-th electric vehicle when it leaves; e i ini is the energy of the battery of the i-th electric vehicle when it arrives.

5. A method for regulating the V2G power of an electric vehicle based on an agent model according to claim 1, characterized in that The energy balance constraint satisfies the formula e i,t+1 = e i,t + P i,t △t, where e i,t is the energy state of the i-th electric vehicle at time t, and e i,t+1 is the energy state of the i-th electric vehicle at time t+1, and P i,t is the power of the i-th electric vehicle at time t.

6. An electric vehicle V2G power regulation device based on a surrogate model, characterized in that, Including: A training sample set generation unit, which is used to calculate the power flexibility of the electric vehicle according to the historical V2G data of the electric vehicle, and then construct a training sample set; The calculating the power flexibility of the electric vehicle according to the historical V2G data of the electric vehicle is specifically as follows: First, construct the electric vehicle V2G power optimization problem corresponding to each user, and the electric vehicle V2G power optimization problem satisfies the following formula: maxP gap -σ·k P gap = min(P + i,t -P - i,t ), t = t i a , …, t i ε t i ε = min(t i a +ε,t i d ) σ=∑abs(P + i,t -P + i,t+1 )+ abs(P - i,t -P - i,t+1 ) ,t=t i a ,…,t i d -△t P + i,t ≥P - i,t ,t=t i a ,..., t i d Among them, P gap is the minimum value of the flexibility of each time period of the electric vehicle power within the target time period; σ is the power fluctuation coefficient of the upper and lower limits of the electric vehicle power flexibility; k is the power fluctuation penalty coefficient; △t is the time interval between two adjacent moments; t i a is the arrival time of the i-th electric vehicle; t i d is the departure time of the i-th electric vehicle; ε is the duration of the target time period; t i ε is P gap the end time of the target time period; abs( ) is the absolute value symbol; P - i,t , P + i,t are respectively the lower limit of the charge and discharge power and the upper limit of the charge and discharge power allowed for the i-th electric vehicle at time t; P - i,t+1 , P + i,t+1 are respectively the lower limit of the charge and discharge power and the upper limit of the charge and discharge power allowed for the i-th electric vehicle at time t + 1; Then, according to the historical V2G data of the electric vehicle, as well as the capacity constraint of the battery itself, the initial energy state of the vehicle, the minimum required power consumption when the user leaves, the maximum charging and discharging power constraint, and the energy balance constraint, use the optimization method to solve the electric vehicle V2G power optimization problem corresponding to each user to obtain the power flexibility of the electric vehicle corresponding to the user; A model storage unit, which is used to store the surrogate model based on the neural network and the corresponding network parameters; A training unit, which is used to train the surrogate model based on the neural network by using the training sample set, obtain the trained network parameters and send them to the prediction unit; A prediction unit, which is used to obtain the electric vehicle parameters and behavior information corresponding to each user and input them into the trained surrogate model based on the neural network. The model outputs the power flexibility of the electric vehicle corresponding to the user; A power grid regulation unit, which is used to send the actual regulation command of the electric vehicle to the corresponding charging pile according to the power flexibility of the electric vehicle, so as to control the charging and discharging power of the electric vehicle.

7. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for regulating the V2G power of an electric vehicle based on a surrogate model according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method for regulating the V2G power of an electric vehicle based on an agent model according to any one of claims 1 to 5 are implemented.

9. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by a processor, the steps of the method for regulating the V2G power of an electric vehicle based on an agent model according to any one of claims 1 to 5 are implemented.

Images