Fast charging station space-time pricing method, device and system, and storage medium

Abstract

The invention discloses a fast charging station space-time pricing method, device and system, and a storage medium. The method comprises the following steps: constructing a fast charging load space-time distribution model based on vehicle owner preference; according to the fast charging load space-time distribution model, a fast charging station space-time pricing model oriented to transformer area balance is obtained; and iteratively solving the time-space pricing model of the fast charging station by using a multi-objective optimization algorithm SPEA2. By adopting the technical scheme of the invention, the problem that the voltage of the terminal power grid node is obviously reduced during peak load is solved, and the voltage supporting capability of the fast-charging electric vehicle is effectively exerted.

Description

Technical Field

[0001] The present invention belongs to the technical field of power systems, and in particular relates to a method and device, a system, and a storage medium for time-space pricing of a fast charging station. Background Art

[0002] With the advancement of low-carbon economic construction, electric vehicles (EVs) are rapidly replacing fuel vehicles. Large-scale EV access to the distribution network has become an inevitable trend that can be predicted in the short term. The huge charging demand of EVs will cause the regional load to grow rapidly and unbalanced in a short period of time, which has a significant impact on the safe and economic operation of the distribution network. Under the disorderly access of EVs, the distribution network often needs to carry out super-redundant expansion and transformation of some distribution transformer substations to ensure the peak charging demand of EVs. However, due to reasons such as urban road construction, the distribution of EV charging loads shows serious uneven characteristics, which has caused redundant construction of some substations and incomplete capacity utilization of some substations, resulting in inefficiency. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and device, system and storage medium for time-space pricing of a fast charging station.

[0004] To achieve the above object, the present invention adopts the following technical solution:

[0005] A fast charging station spatiotemporal pricing method, comprising:

[0006] Construct a spatiotemporal distribution model of fast charging load based on car owner preferences;

[0007] According to the spatiotemporal distribution model of fast charging load, a spatiotemporal pricing model of fast charging stations for area balance is obtained;

[0008] The multi-objective optimization algorithm SPEA2 is used to iteratively solve the spatiotemporal pricing model of fast charging stations.

[0009] As a preferred method, constructing a fast charging load spatiotemporal distribution model based on the owner's preference includes:

[0010] Simulate EV dynamic driving process;

[0011] According to the EV dynamic driving process, the EV owner's path selection preference model is obtained;

[0012] According to the EV owner's route selection preference model, the Monte Carlo method is used to realize the random simulation of the influence of electricity price on the spatiotemporal distribution of regional fast charging load, and the spatiotemporal distribution model of fast charging load based on owner's preference is obtained.

[0013] Preferably, iteratively solving the spatiotemporal pricing model of the fast charging station includes:

[0014] Obtain the road network information of the regional transportation system and the topology information of the power system, and initialize the day-ahead spatiotemporal electricity price population;

[0015] The EV start and end points and charge states are randomly generated, and the individuals with spatiotemporal electricity price information in the population are imported into the EV load spatiotemporal distribution simulation model considering the owner's preference to obtain the node load distribution under the current spatiotemporal electricity price.

[0016] According to the node load corresponding to each time and space electricity price in the current population, the power flow distribution of each time and space electricity price is calculated;

[0017] Based on the power flow results of each time and space electricity price, the voltage balance degree f under each electricity price is calculated V and the spatiotemporal load balance f P ;

[0018] The Pareto surface is updated according to the results, and it is determined whether the maximum number of iterations has been reached; if so, the space-time electricity price with the smallest sum of the two targets in the current Pareto surface is selected as the output; if not, the SPEA2 algorithm updates the population and enters a new round of iterations.

[0019] The present invention also provides a fast charging station time-space pricing device, comprising:

[0020] A construction module for building a spatiotemporal distribution model of fast charging load based on vehicle owner preferences;

[0021] A processing module, used to obtain a fast charging station spatiotemporal pricing model for area balance according to the fast charging load spatiotemporal distribution model;

[0022] The calculation module is used to iteratively solve the spatiotemporal pricing model of fast charging stations using the multi-objective optimization algorithm SPEA2.

[0023] Preferably, the building blocks include:

[0024] Simulation unit, used to simulate the dynamic driving process of EV;

[0025] A first calculation unit is used to obtain a path selection preference model of an EV owner according to an EV dynamic driving process;

[0026] The second calculation unit is used to realize the random simulation of the influence of electricity price on the spatiotemporal distribution of regional fast charging load according to the EV owner's route selection preference model through the Monte Carlo method, so as to obtain the spatiotemporal distribution model of fast charging load based on the owner's preference.

[0027] The present invention also provides a fast charging station spatiotemporal pricing system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a fast charging station spatiotemporal pricing method when executed by the processor.

[0028] The present invention also provides a storage medium, on which a computer program is stored, and the computer program executes the spatiotemporal pricing method for a fast charging station when running.

[0029] By building and solving the fast charging load spatiotemporal distribution model and the fast charging load spatiotemporal distribution model, the balance of the uneven spatial distribution of the power grid load is achieved to a certain extent. The use of spatiotemporal pricing takes into account the spatial sensitivity of the fast charging load. By guiding the selection of electric vehicle charging stations, the peak-to-valley difference of the power grid is effectively optimized, reducing the problem of obvious voltage drop at the terminal power grid node during peak load, and effectively exerting the voltage support capacity of fast-charging electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0031] Figure 1 is a flow chart of a method for time-space pricing of a fast charging station according to an embodiment of the present invention;

[0032] Figure 2 It is a schematic diagram of space-time pricing;

[0033] Figure 3 It is a flow chart of the Monte Carlo-based simulation of the spatiotemporal distribution of electric vehicle loads of the present invention;

[0034] Figure 4 It is a flow chart of the present invention for solving the spatiotemporal pricing problem. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0037] Embodiment 1:

[0038] like Figure 1 As shown, an embodiment of the present invention provides a fast charging station spatiotemporal pricing method, including:

[0039] Step S1: Constructing the time-space pricing structure of fast charging stations

[0040] The spatiotemporal pricing problem of fast charging stations is essentially a power system optimization problem based on dynamic traffic flow, which can be decomposed into the upper-level power system pricing optimization problem and the lower-level traffic flow solution problem considering the influence of electricity prices, such as Figure 2 As shown. In terms of solving the lower-level traffic flow, the traffic flow model is introduced to characterize the EV driving path cost, and the owner preference model is used to describe the subjectivity of EV travel path selection, so as to incorporate the pricing strategy into the traffic flow solution problem. In terms of algorithms, the random Monte Carlo probability sampling method is used to ensure the randomness of EV travel selection, and the shortest path method is used to solve the final EV single-unit driving path, forming the spatiotemporal distribution of EV fast charging load in the day before. In terms of the upper-level power system pricing optimization, the distribution network operator relies on the SPEA2 algorithm to generate a spatiotemporal electricity price population and sends it to the lower-level problem. After obtaining the corresponding charging load, the second-order cone programming is used to solve the optimal power flow in the active distribution network, and then the overall spatiotemporal imbalance of the voltage and load in the substation area is calculated. The spatiotemporal electricity price population is updated according to the results obtained, and the above process is repeated to obtain acceptable spatiotemporal electricity price results.

[0041] Step S2: Establishing a fast charging load spatiotemporal distribution model considering the car owner's preference

[0042] Step 2.1, explore the EV travel pattern and speed modeling method. First, in order to simulate the travel pattern and dynamic driving process of these EVs, the EV travel return probability distribution, EV destination dynamic selection and EV dynamic speed calculation models are constructed respectively.

[0043] In terms of the probability distribution of EV travel return, according to the statistical fitting results of travel rules, the statistical data of EV travel time on typical working days approximately obeys the normal distribution, and the statistical data of EV return time approximately obeys the Cauchy distribution. The corresponding time distribution probability density function distribution function is shown as follows:

[0044]

[0045]

[0046]

[0047] Among them, private cars have commuting needs, which are obtained from the probability distribution of t1 and t2 respectively; operating vehicles have operation start time and operation end time, which are obtained from the probability distribution of t1 and t3 respectively.

[0048] In terms of dynamic EV destination selection, it is necessary to determine the EV "origin-destination" path pair (origin-destination, OD) at different times. According to the functional division in the government control plan, urban areas can be roughly divided into three types: residential areas, work areas, and commercial areas. Set the residential area node set , Workspace node collection , Commercial District Node Set Specifically, after the OD pair is completed, the operating vehicle needs to select the next destination according to the passenger demand. In order to reflect the time distribution characteristics of regional function selection and the randomness of passenger selection, the weight w of node i selected as the new destination at time t is i,t Described as the sum of the discrete probability values ​​of the node function attributes and white noise. And the probability P of node i being selected is calculated based on the obtained weight. i,t .

[0049]

[0050]

[0051]

[0052]

[0053] 0≤W i,t ≤1 (8)

[0054]

[0055] in, They represent the discrete probability values ​​of different functional attribute nodes being selected, and their sum is 1; W i,t is a white noise with a value between 0 and 1, representing the randomness of the selection of node i. i,t is the probability that node i is selected as the new starting point, which is equal to the ratio of the weight of node i selected to the total weight of all nodes.

[0056] After clarifying the EV travel choice, it is also necessary to consider the speed of the road network to dynamically simulate the EV's driving conditions. In fact, the EV driving speed is affected by the road grade and traffic volume of the road section, which can be characterized by the speed-flow practical model as follows:

[0057] v ij (t) = v ij,m / (1+(q ij (t) / C ij ) β ) (10)

[0058] β=a+b(q ij (t) / Cij ) n (11)

[0059] Among them, v ij,m represents the zero flow velocity of EV on the direct link (i, j); C ij represents the traffic capacity of the road section (i, j), which depends on the road grade; q ij (t) represents the flow rate of the road section (i, j) at time t; q ij (t) and C ij The ratio of represents the saturation of the road section at time t; a, b, and n represent the adaptive coefficients under different road grades.

[0060] Step 2.2, establish the EV owner’s route selection preference model;

[0061] For the simulation of the route selection of operating vehicles, the influencing factors can be summarized into three aspects: route travel time and charging cost. The route travel time is decomposed into the travel time of multiple sections, which depends on the length of the section and the driving speed of the section. Among them, the section length is represented by D(i,j), and the driving speed of the section can be calculated by formula (4). Therefore, the section travel delay matrix T can be formed at any time t t , the travel time of the road section (i, j) is calculated as follows:

[0062] T t (i,j)=D(i,j) / v ij (t) (12)

[0063] Passing time C t (O EV,t ,D EV,t ) is characterized as follows:

[0064]

[0065] Among them, O EV,t represents the starting node of the EV owner at time t (if in the road section, it is the end point of the road section); D EV,t It represents the destination of the EV owner at time t; x EV,t (i, j) represents the path selection of the EV owner at time t, which is a 01 variable. When the owner chooses the road section from i to j, its value is 1, otherwise it is 0. At the same time, the path selection of the owner's EV must also meet the following constraints.

[0066]

[0067]

[0068]

[0069]

[0070]

[0071] EV route selection requires solving the global shortest path problem of multiple OD pairs and calculating their travel time and charging cost. c Let’s take the c fast charging station at the node as an example. First, according to equations (13)-(18), its travel time C can be calculated: t (O t ,D c )as follows:

[0072]

[0073] The charging cost is further calculated based on the results as follows:

[0074]

[0075]

[0076]

[0077] E exp,c =(l SOC,pre -l SOC,c )×E max (twenty three)

[0078] l SOC,c = l SOC,t -C t (O t ,D c )×E per / E max (twenty four)

[0079]

[0080] Among them, C p (O t ,D c ) represents the charging cost of EV choosing fast charging station c; t c This is the charging time at the fast charging station c at this time; Respectively represent t c Time in D c The charging price of the node and the charging power of the EV; t a,c is the time when EV arrives at the fast charging station c; t c,max E is the end time of charging at fast charging station c; exp,c A is the expected charging capacity of EV after reaching c; c is the charging capacity per unit time of the fast charging station c; l SOC,pre ,lSOC,c are the expected and charge states of the EV when it reaches c, respectively; l SOC,t is the charge state of EV at time t; E max is the EV capacity; E per is the power consumption per unit time of EV driving; Δt is the simulation time interval; This is a round-up operation.

[0081] Considering that different car owners have different sensitivities to time and electricity prices, the distance loss weight ω1 and charging electricity price weight ω2 are set to measure the willingness of different car owners to choose charging stations. At this time, the fast charging station selection method of each EV owner is as follows:

[0082]

[0083] Among them, C represents the set of fast charging stations to be selected; The node where the selected fast charging station is located.

[0084] Step 2.3, simulation of spatiotemporal distribution of electric vehicle load based on Monte Carlo.

[0085] After completing the construction of the relevant models for EV travel dynamic simulation, the random simulation of the influence of electricity price on the spatiotemporal distribution of regional fast charging load is realized based on the Monte Carlo method. The steps are as follows: Figure 3 As shown, the specific summary can be as follows:

[0086] (1) First, initialize time t to 0 and assign an initial position O to each EV based on the vehicle type using random sampling. i , initial travel return time t1, t2, t3, initial charge state l SOC,t And related parameters such as time and space electricity prices.

[0087] (2) Traverse the state of each EV at time t and form OD pairs according to the EV type. For private cars, they have fixed OD pairs, and it is only necessary to determine whether their time is t1, t2; for commercial vehicles, based on private cars, it is also necessary to determine whether they have completed the current order trip, that is, whether they have reached the end of the current OD pair. If so, take the current node as the starting point and randomly sample its travel destination according to the result obtained in formula (9) to update the OD pair.

[0088] (3) If the OD pair of the EV has been confirmed, its path selection is dynamically updated at time t, and equations (13)-(18) and (19)-(26) are solved respectively to formulate the optimal driving path for different EVs with sufficient power and charging demand.

[0089] (4) At the same time, all EVs are traversed and the speed-flow model (10)-(11) is combined to calculate and update the state of each EV at time t.

[0090] (5) Determine whether time t reaches the maximum simulation time. If not, update t = t + 1 and re-enter step (2); if yes, end the calculation, output the driving behavior of each EV at the simulation time, and output the spatiotemporal distribution of the fast charging load according to the connection of each fast charging station to the distribution network node.

[0091] Step S3: Establishing a spatiotemporal pricing model for fast charging stations for regional balance

[0092] The time-space electricity price will affect the time-space distribution of load and be reflected in the time-space voltage balance degree f V and the spatiotemporal load balance f P , which can be expressed as follows:

[0093]

[0094]

[0095]

[0096]

[0097] Where H represents the number of scheduling intervals; P i,t With V i,t is the injected power and node voltage of node i at time t, where P i,t A positive number indicates that the node is a load node, and a negative number indicates that it is a power generation node; S indicates that it is a power supply node of the upper power grid. In the power distribution system, most of them are radial networks. In order to solve the possible bidirectional power flow problem, the absolute value |P i,t | Expand analysis; and They represent the average absolute values ​​of all node voltages and node powers during the scheduling time. The distribution system is represented as a strongly connected graph in Represented as a set of nodes in the power distribution system, Represents a branch (i, j) between two nodes.

[0098] In fact, the time-space electricity price will affect the time-space distribution of load. The matrix ρ=[ρ i,t ] represents the time-space electricity price vector, and the time-space distribution of fast charging load will be obtained by random simulation of the model established in Section 2, then P i,t It can be expressed as a function of electricity price and random parameters:

[0099] P i,t =P i,t (ρ,γ)=M(ρ,γ)+P i,t,Base(ρ),γ∈Γ (31)

[0100] Among them, the parameters determined by random sampling such as the starting point of the electric vehicle in the charging load distribution model are defined as the vector γ; Γ represents the distribution space of the random parameter γ; M(ρ,γ) represents the spatiotemporal distribution of the fast charging load under the electricity price ρ and the random parameter γ (a simplified expression of the Monte Carlo calculation in Section 2); for the basic node load of non-EV, P is used i,t,Base (ρ) indicates that, in fact, the distribution of node time and space electricity prices will also affect the user's load, but this is not the focus of discussion here, so this part is only treated as a constant.

[0101] After the time-space electricity price affects the load, it changes the power flow distribution and causes the time-space distribution of voltage to change. Among them, considering the economic requirements of the distribution system operation, the node voltage is proposed to be calculated based on the distribution optimal power flow (DOPF). The most widely used DistFlow model in the distribution system is adopted here, and convexification is realized based on the second-order cone. DOPF can be expressed as follows, which is the solution to the following optimization problem.

[0102]

[0103]

[0104]

[0105] U j,t =U i,t -2(r ij p ij,t +x ij q ij,t ) (35)

[0106]

[0107]

[0108] U i,min ≤U i,t ≤U i,max (38)

[0109] p ij,min ≤p ij,t ≤p ij,max (39)

[0110] q ij,min ≤q ij,t ≤q ij,max (40)

[0111] Among them, p ij,t ,qij,t They represent the active and reactive power flows of the branch between nodes i and j at time t respectively; r ij , x ij It is defined as the square of the resistance, reactance and current of the corresponding branch; P j,t , Q j,t , U j,t , l ij,t It is defined as the active power, reactive power, voltage and current square of node j at time t; U ref It is expressed as the square of the reference voltage at the upper grid access point. In this paper, the per-unit value of the reference voltage is set to 1.05; U i,min with U i,max represents the upper and lower bounds of the voltage square of node i; P ij,m i n , P ij,max , Q ij,min With Q ij,max Represents the active and reactive power boundary of branch ij. l, p, q, U are vector expressions of relevant variables.

[0112] Combining equations (1)-(6), the optimization problem of space-time electricity prices can be expressed as the solution process of the following equation.

[0113]

[0114] Step S4: Use the classic multi-objective optimization algorithm SPEA2 to iteratively solve the spatiotemporal pricing problem

[0115] The solution steps are as follows Figure 4 As shown, the details are as follows:

[0116] Step 4.1, import the road network information of the regional transportation system and the topology information of the power system, and initialize the day-ahead spatiotemporal electricity price population;

[0117] Step 4.2, enter the traffic system simulation phase. Generate EV starting and ending points and charge states randomly according to probability, and import the individuals with spatiotemporal electricity price information in the population into the EV load spatiotemporal distribution simulation model considering the owner's preference to obtain the node load distribution under the current spatiotemporal electricity price;

[0118] Step 4.3, enter the phase of solving the optimal power flow of the power system. Take the node load corresponding to each time and space electricity price in the current population as the input of DOPF in formula (32), and calculate the power flow distribution of each electricity price respectively;

[0119] Step 4.4, enter the unbalance calculation link of the substation area. Based on the power flow results of each time and space electricity price, the voltage balance degree f under each electricity price is obtained by calculating equations (27)-(30) V and the spatiotemporal load balance f P .

[0120] Step 4.5, update the Pareto surface according to the obtained results, and determine whether the maximum number of iterations has been reached. If so, select the time-space electricity price with the smallest sum of the two targets in the current Pareto surface as the output; if not, the SPEA2 algorithm updates the population and enters a new round of iterations, repeating steps 4.2-4.5.

[0121] By constructing a spatiotemporal distribution model of fast-charging electric vehicle (EV) load considering the owner's preference, the EV driving path and its fast-charging station selection process are dynamically simulated. The optimal power flow model considering the distribution network resource support is introduced to realize the calculation of the regional voltage and load rate imbalance of the power grid under the electricity price-guided EV charging access. Furthermore, through the pricing of fast-charging stations for regional load balance, the interaction between the EV charging load model and the distribution network optimal power flow model is completed by improving the strengthpareto evolutionary algorithm (SPEA2), and the iterative search of spatiotemporal electricity prices is realized.

[0122] Embodiment 2:

[0123] The embodiment of the present invention further provides a fast charging station spatiotemporal pricing device, comprising:

[0124] A construction module for building a spatiotemporal distribution model of fast charging load based on vehicle owner preferences;

[0125] A processing module, used to obtain a fast charging station spatiotemporal pricing model for area balance according to the fast charging load spatiotemporal distribution model;

[0126] The calculation module is used to iteratively solve the spatiotemporal pricing model of fast charging stations using the multi-objective optimization algorithm SPEA2.

[0127] As an implementation of an embodiment of the present invention, the building block includes:

[0128] Simulation unit, used to simulate the dynamic driving process of EV;

[0129] A first calculation unit is used to obtain a path selection preference model of an EV owner according to an EV dynamic driving process;

[0130] The second calculation unit is used to realize the random simulation of the influence of electricity price on the spatiotemporal distribution of regional fast charging load according to the EV owner's route selection preference model through the Monte Carlo method, so as to obtain the spatiotemporal distribution model of fast charging load based on the owner's preference.

[0131] Embodiment 3:

[0132] An embodiment of the present invention also provides a fast charging station spatiotemporal pricing system with integrated photovoltaic storage and orderly charging regulation, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes the fast charging station spatiotemporal pricing method when executed by the processor.

[0133] Embodiment 4:

[0134] An embodiment of the present invention further provides a storage medium, on which a computer program is stored, and when the computer program is run, the method for spatiotemporal pricing of a fast charging station is executed.

[0135] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A fast charging station spatiotemporal pricing method, characterized in that: include: Construct a spatiotemporal distribution model of fast charging load based on car owner preferences; According to the spatiotemporal distribution model of fast charging load, a spatiotemporal pricing model of fast charging stations for area balance is obtained; The multi-objective optimization algorithm SPEA2 is used to iteratively solve the spatiotemporal pricing model of fast charging stations.

2. The spatiotemporal pricing method for fast charging stations according to claim 1, characterized in that: Building a fast charging load spatiotemporal distribution model based on car owner preferences includes: Simulate EV dynamic driving process; According to the EV dynamic driving process, the EV owner's path selection preference model is obtained; According to the EV owner's route selection preference model, the Monte Carlo method is used to realize the random simulation of the influence of electricity price on the spatiotemporal distribution of regional fast charging load, and the spatiotemporal distribution model of fast charging load based on owner's preference is obtained.

3. The spatiotemporal pricing method for fast charging stations according to claim 2, characterized in that: The iterative solution of the spatiotemporal pricing model of fast charging stations includes: Obtain the road network information of the regional transportation system and the topology information of the power system, and initialize the day-ahead spatiotemporal electricity price population; The EV start and end points and charge states are randomly generated, and the individuals with spatiotemporal electricity price information in the population are imported into the EV load spatiotemporal distribution simulation model considering the owner's preference to obtain the node load distribution under the current spatiotemporal electricity price. According to the node load corresponding to each time and space electricity price in the current population, the power flow distribution of each time and space electricity price is calculated; Based on the power flow results of each time and space electricity price, the voltage balance degree f under each electricity price is calculated V and the spatiotemporal load balance f P ; The Pareto surface is updated according to the results, and it is determined whether the maximum number of iterations has been reached; if so, the space-time electricity price with the smallest sum of the two targets in the current Pareto surface is selected as the output; if not, the SPEA2 algorithm updates the population and enters a new round of iterations.

4. A fast charging station time-space pricing device, characterized in that: include: A construction module for building a spatiotemporal distribution model of fast charging load based on vehicle owner preferences; A processing module, used to obtain a fast charging station spatiotemporal pricing model for area balance according to the fast charging load spatiotemporal distribution model; The calculation module is used to iteratively solve the spatiotemporal pricing model of fast charging stations using the multi-objective optimization algorithm SPEA2.

5. The fast charging station spatiotemporal pricing device as claimed in claim 4, characterized in that: The building blocks include: Simulation unit, used to simulate the dynamic driving process of EV; A first calculation unit is used to obtain a path selection preference model of an EV owner according to an EV dynamic driving process; The second calculation unit is used to realize the random simulation of the influence of electricity price on the spatiotemporal distribution of regional fast charging load according to the EV owner's route selection preference model through the Monte Carlo method, so as to obtain the spatiotemporal distribution model of fast charging load based on the owner's preference.

6. A fast charging station time-space pricing system, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the spatiotemporal pricing method for a fast charging station as described in any one of claims 1 to 4 is executed.

7. A storage medium, characterized in that: The storage medium stores a computer program, which, when running, executes the spatiotemporal pricing method for a fast charging station as described in any one of claims 1 to 4.

Images