Transformer supply area selection method and system for an electric vehicle

Abstract

A transformer area selection method and system for electric vehicles. The method comprises: collecting traveling data of electric vehicles and transformer area data, and preprocessing the collected data to obtain a charging demand probability of each area (S1); selecting and optimizing a transformer area for electric vehicle charging (S2); and determining a weight in active transformer area selection, and formulating a dynamic weight adjustment policy (S3).

Description

[0001] This application claims priority to Chinese Patent Application No. 202510034843.1 filed with the China National Intellectual Property Administration on Jan. 9, 2025, the disclosure of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present disclosure relates to the technical field of electric vehicle charging network optimization, and for example, relates to a transformer supply area selection method and system for an electric vehicle. BACKGROUND

[0003] With the popularization of electric vehicles, the charging demand increases rapidly. The random mobility of electric vehicles and the high-power characteristics of the electric vehicle aggregators after large-scale connection of the electric vehicles will alter the load level of the existing power grid, posing a significant challenge to the voltage stability of the distribution network, especially to the voltage stability of the transformer supply area. After the electric vehicles are connected to charging piles, large-scale disorderly charging may further increase the peak-valley difference and even affect the power supply quality, which may have a certain degree of adverse impact on power grid security. Moreover, the random charging of a large number of electric vehicles generates a clustering effect that affects the operation of the power grid. Research of the distribution network at the transformer supply area level facilitates understanding and prediction of these changes, and data support can be provided for planning future charging infrastructure and upgrading the power grid.

[0004] The electric vehicles may be regarded as distributed energy storage devices with mobile characteristics. The new controllable load may supply energy to the distribution network by discharging the battery. For a city with a large geographical area, the distribution network in this city typically consists of hundreds of transformer supply areas, and it may be impractical to research and manage all transformer supply areas. A representative transformer supply area is proactively selected, thus simplifying the research and management and allowing efforts to focus on solving the most critical problems.

[0005] In the past, the demand response of the power grid in a large city was mainly carried out at the city-wide level, which could not accurately balance the local power supply and demand. Therefore, a selection method and system for the electric vehicle is urgently needed to solve the problem. SUMMARY

[0006] The present disclosure provides a transformer supply area selection method and a transformer supply area selection system for an electric vehicle. The key transformer supply area is selected and optimized according to the actual driving data and charging and discharging data of the electric vehicle, thus avoiding local load overload and ensuring the stability and reliability of the power grid.

[0007] In a first aspect, the present disclosure provides a transformer supply area selection method for an electric vehicle. The transformer supply area selection method includes the steps below.

[0008] Driving data and transformer supply area data of the electric vehicle are collected, and a charging demand probability of a region is obtained by preprocessing the collected data.

[0009] A transformer supply area for charging the electric vehicle is selected and optimized.

[0010] A weight in an active transformer supply area selection is determined, and a dynamic weight adjustment strategy is formulated.

[0011] In a second aspect, the present disclosure provides a transformer supply area selection system for the electric vehicle. The transformer supply area selection system includes a data acquisition and processing module, a transformer supply area selection and optimization module, and a dynamic weight adjustment strategy formulation module.

[0012] The data acquisition and processing module is configured to collect driving data and transformer supply area data of the electric vehicle, and obtain a charging demand probability of a region by preprocessing the collected data.

[0013] The transformer supply area selection and optimization module is configured to select and optimize a transformer supply area for charging the electric vehicle.

[0014] The dynamic weight adjustment strategy formulation module is configured to determine a weight in an active transformer supply area selection and formulate a dynamic weight adjustment strategy.

[0015] In a third aspect, the embodiments of the present disclosure further provide an electronic device. The electronic device includes one or more processors, and a storage device for storing one or more programs.

[0016] When executed by the one or more processors, the one or more programs cause the one or more processors to implement the transformer supply area selection method for the electric vehicle according to any embodiment of the present disclosure.

[0017] In a fourth aspect, the embodiments of the present disclosure further provide a storage medium including computer-executable instructions. The computer-executable instructions, when executed by the one or more processors, are used to implement the transformer supply area selection method for the electric vehicle according to any embodiment of the present disclosure.

[0018] In a fifth aspect, the embodiments of the present disclosure further provide a computer program product including a computer program. The computer program, when executed by the one or more processors, implements the transformer supply area selection method for the electric vehicle according to any embodiment of the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0019] FIG. 1 is a flowchart of a transformer supply area selection method for an electric vehicle of the present disclosure.

[0020] FIG. 2 is a schematic structural diagram of a transformer supply area selection system for the electric vehicle of the present disclosure.

[0021] FIG. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] The present disclosure is further described hereinafter in conjunction with specific embodiments. These embodiments are only intended to illustrate and not to limit the scope of the present disclosure. After reading the above described contents of the present disclosure, those skilled in the art can make various modifications or alterations to the present disclosure, and such equivalents also fall within the scope of the present disclosure.

[0023] In the present disclosure, orientations or position relations indicated by terms such as "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "side" and "bottom" are based on the drawings. These orientations or position relations are intended only to facilitate the description of the relational words determined by the structural relationships between the components or elements in the present disclosure, and not to specifically refer to any component or element in the present disclosure.

[0024] Embodiment one

[0025] As shown in FIG. 1, a transformer supply area selection method for an electric vehicle is provided by this embodiment and includes steps S1 to S3 below.

[0026] In S1, driving data and transformer supply area data of the electric vehicle are collected, and a charging demand probability of a region is obtained by preprocessing the collected data.

[0027] In S2, a transformer supply area for charging the electric vehicle is selected and optimized.

[0028] In S3, a weight in an active transformer supply area selection is determined, and a dynamic weight adjustment strategy is formulated.

[0029] In S1, the driving data of the electric vehicle includes a time stamp, a geographical location of the electric vehicle and a state of charge (SoC) of the electric vehicle. The driving data is stored as time series data D^, where Di t = {t, X^, SoC / J, Xt denotes a horizontal coordinate value of an i-th electric vehicle at time t, 7 / denotes a vertical coordinate value of the i-th electric vehicle at time t, and S()C, denotes the SOC of the i-th electric vehicle at time t.

[0030] Obtaining the charging demand probability of the region includes steps S11 and S12 below.

[0031] In S11, all transformer supply areas are divided proportionally. A size of each grid region G; is Ax X Ay, where Ax denotes a horizontal coordinate value corresponding to a division size of a transformer supply area, and Ay denotes a vertical coordinate value corresponding to a division size of the transformer supply area.

[0032] In S12, for each grid region G h the charging demand probability ?j of the region is calculated in one of the manners below.

[0033] The charging demand probability ?j of the region is determined according to the number of electric vehicles entering the region by the following formula: Lj P ------ rJ VM i , ^J = l where M denotes the total number of all divided transformer supply areas, and Lj denotes the total number of charging times in a transformer supply area j.

[0034] Alternatively, the charging demand probability ?j of the region is determined according to a proportion of low-battery electric vehicles entering the region by the following formula: N =          yd e Gj ’ SoCt - 0 t=i where N denotes the total number of electric vehicles in the transformer supply area.

[0035] Based on the charging demand probability Pj, a region G; with the largest charging demand probability is selected as a first transformer supply area J , where J is expressed by the following formula:

[0036] The S2 includes steps S21 and S22 below.

[0037] In S21, a charging demand probability of the electric vehicle is corrected. The charging demand probability of the electric vehicle is corrected as follows: for each transformer supply area Gj, a correction value Wj of charging demand probability of all electric vehicles in each transformer supply area is determined by the following formula: Uy = <tPf + )1(} - SoC,), where « and / ? are coefficients for adjusting a plurality of weights.

[0038] The charging possibility of the electric vehicle in a certain transformer supply area is not only related to historical data, but also related to the SoC of the electric vehicle when driving in the transformer supply area. The higher the SoC of the electric vehicle, the lower the charging possibility in the transformer supply area. The correction value of the charging possibility is calculated by comprehensively considering a charging demand frequency, the proportion of low-battery electric vehicles and a frequency of electric vehicles passing through the transformer supply area.

[0039] To calculate the charging possibility more accurately, the factors below need to be considered.

[0040] First, the historical data of charging provides a basic charging demand frequency. The basic charging demand frequency is obtained based on statistics of the past charging behaviors in the transformer supply area.

[0041] Second, the proportion of low-battery electric vehicles is a key factor, as vehicles are more likely to seek out charging piles to charge when the SoC of the electric vehicle is low.

[0042] Finally, the frequency of electric vehicles passing through the transformer supply area is also very important, as a higher frequency of electric vehicles passing through the transformer supply area corresponds to a greater charging demand.

[0043] In S22, a weighted K-center greedy algorithm is executed.

[0044] Oi denotes a point with a numerical value (_X(- - yLj ,      ■ yc) denotes a longitude value of the i-th electric vehicle and a latitude value of the i-th electric vehicle, 0 0 =         , and m denotes a total number of points in the original data set.

[0045] Executing the weighted K-center greedy algorithm includes the steps below.

[0046] 1 . A k-nearest neighbour indicator matrix P is constructed by the following formula: P = fPi / 1 , where Pij is used to indicate whether °j is a nearest neighbour to (y, in response to °j being the nearest neighbour to (y, p, / = 1 is determined, and in response to f)j being not the nearest neighbour to (y,      = 0 is determined.

[0047] Pij is replaced with a weight W[j of Gaussian kernel distance by the following formula: W = [w„] L JJmxn e [o, 1] where = p^ * exp ~dx(xif 2v2 , dx (X[, y^) denotes a Manhattan distance, and v denotes variance of distances between all points corresponding to (Xi, yi).

[0048] 2. Weights of edges corresponding to K nearest neighbours are normalized to distinguish a data point from a neighbour with a small weight. A normalized graph density vector is expressed by the following formula: T Grd(O) = [^(1^), •••, Gra^of), • •, Grd(om)] .

[0049] 3. A data point with a high density is selected by the following formula: neighbour(pi') {Oe}eeznde%(pi>o).

[0050] Density attenuation is implemented on a neighbour point °j by the following formula: Gra^Oj) = Gra(oj) - Gra(ot) ■ p^, Oj e neighbour^o^, where neighbour (Oj) is a set of neighbour points of tp obtained according to the k-nearest neighbour indicator matrix P, Pi is an i-th row of the k-nearest neighbour indicator matrix P, Index(p[ >0) provides an index set satisfying p( > 0, a point with the highest density is selected based on a graph density, and a density of the neighbour point is iteratively reduced.

[0051] The proactive transformer supply area selection may be described as follows: according to the driving historical data of large-scale electric vehicles and the current SoC of all electric vehicles, multiple transformer supply areas are identified to represent all transformer supply areas for simplification analysis.

[0052] For this goal, representative transformer supply areas need to be selected by the optimization algorithm below

[0053] First, a coverage radius is defined, and the coverage radius indicates that any transformer supply area in the coverage radius may be regarded as the same representative transformer supply area. Next, a set of transformer supply areas needs to be identified so that each transformer supply area is able to cover as many other transformer supply areas as possible while ensuring the maximum coverage area.

[0054] To solve this problem, an iterative optimization method is adopted. In each iteration, a new transformer supply area is selected, coverage of the new transformer supply area is calculated, and the set of covered transformer supply areas is updated. The specific steps include S221 to S223 below.

[0055] In S221, an initial transformer supply area is selected as a starting point, and the starting point is added into a marked data point set.

[0056] In S222, in each iteration, coverage of a current marked data point set is calculated, and a new transformer supply area is selected to maximize new coverage.

[0057] In S223, the new transformer supply area is added to the marked data point set, the new coverage is updated, and the objective formula is optimized by the following formula: arg where e0 is the current marked data point set, e1 is a selected marked data point set, and S illustrates a coverage radius of f 1 on e0, the formula                      e0 Ue1 indicates that a group of spheres centered on each member in e0 with a radius of 8 is capable of covering the entire f1 , and a minimization problem in the formula e° Ue1 is equivalent to the following minimax transformer supply area selection problem: min max min e1:|e1<B| ie[a]\(e°ue1) jee°ue1 where A denotes a calculation of Euclidean distance, the minimax transformer supply area selection problem is solved by using a 2-optimization (2-OPT) solution, and in the 2-OPT solution, the following equations are iterated: o = arg maxminA(ojX, i6[tz]\e Jee and e G e U {0} where O denotes a selected data point in an iteration.

[0058] The steps S221 to S223 are repeated until the calculation of all transformer supply areas is completed.

[0059] In the process of transformer supply area selection, the weight     serves as a key factor to reflect the charging demand and priority of each grid region. However, the charging demand is not the only factor to be considered, and external conditions such as load of the power grid and transformer supply area construction cost are also taken into account. To evaluate the value of each power transformer supply area more comprehensively, multiple influencing factors need to be introduced, and appropriate weights are assigned to each factor. These factors may include a load level of the existing power grid, a future demand forecast, the transformer supply area construction cost, a renewable energy integration capability and a policy guidance. The weight of each factor needs to be adjusted according to the actual situation to ensure that the final decision satisfies various needs and constraints to the greatest extent. Therefore, step S3 includes the step below.

[0060] is defined as a weight representing a comprehensive importance of the grid region G, by the following formula: where fj denotes a charging demand frequency of the region and is used to reflect a concentration degree of low-battery electric vehicles in the region, denotes transformer supply area construction cost of the area, the transformer supply area construction cost includes land cost and construction cost, Gj denotes a load condition of a power grid in the area and is used to consider load pressure of the power grid in the area when the power grid is connected to a new transformer supply area, and «, b and f are important coefficients for adjusting the plurality of weights.

[0061] To better adapt to changes in different regional needs and external conditions, the weights ^7 need to be dynamically adjusted periodically. This process includes the steps below.

[0062] 1. The charging demand frequency fj is periodically recalculated.

[0063] The charging demand frequency fj reflects the charging demand of each region and may be updated based on real-time driving data of the electric vehicle.

[0064] 2. The transformer supply area construction cost Cj is dynamically adjusted.

[0065] The transformer supply area construction cost C, is not fixed and fluctuates with the transformer supply area construction condition, the policy change, and the market condition. For example, the rising land price or the increased material cost affects the transformer supply area construction cost. The Cj is updated by performing a dynamic evaluation on the construction cost.

[0066] The load condition    of the power grid is dynamically monitored and adjusted.

[0067] The load condition     of the power grid directly affects the feasibility of transformer supply area access. If the load of the power grid in a certain region is close to the upper limit, selecting the region as the transformer supply area may lead to the overload of the power grid. Therefore, the load of the power grid needs to be monitored in real time to ensure that the selection result of the transformer supply area does not cause unnecessary pressure on the power grid, and the load condition is regularly updated to reflect the real-time status of the power grid, thereby dynamically adjusting the transformer supply area selection.

[0068] To further improve the rationality of the transformer supply area selection, an iterative optimization strategy needs to be introduced and includes the steps below.

[0069] Iteration is performed based on the historical data, and the iteration is performed based on the historical data in the steps below.

[0070] With continuous accumulation of electric vehicle data and demand data, the weight ^7 of each grid region is re-evaluated after each iteration.

[0071] The transformer supply area is re-selected based on new data to ensure that a layout of the transformer supply area satisfies the latest demand.

[0072] If the layout and weight of the transformer supply area do not change significantly after several iterations, it indicates that the layout of the transformer supply area has stabilized.

[0073] The transformer supply area selection strategy can implement the flexible response to the ever-changing demand environment by dynamically adjusting the weight ^7 , thus ensuring the rationality and sustainability of the layout of the transformer supply area.

[0074] Compared with the related art, the beneficial effects of the present disclosure are as follows.

[0075] 1. A method is provided to satisfy the dynamic charging demand of the electric vehicle and proactively select a to-be-researched transformer supply area. The operation characteristic of each electric vehicle in the large-scale electric vehicle dataset is considered, and the spatiotemporal characteristic of charging and discharging of large-scale electric vehicles are fully explored.

[0076] 2. The key transformer supply area is selected and optimized according to the actual driving data and charging and discharging data of the electric vehicle, so that local load overload can be avoided, and the stability and reliability of the power grid are ensured. The charging and discharging scheduling strategy of the electric vehicle is implemented in the selected transformer supply area, facilitating effective integration with renewable energy (such as solar energy), promoting the full utilization of green energy, and supporting the sustainable development goal.

[0077] 3. According to the real and effective driving data and charging and discharging data of the electric vehicle, an alternative selection method is provided, and the method utilizes the diversity exploration of the K-center greedy algorithm in graph density attenuation to solve the transformer supply area selection problem.

[0078] Embodiment two

[0079] As shown in FIG. 2, a transformer supply area selection system for an electric vehicle is provided in this embodiment and includes a data acquisition and processing module 210, a transformer supply area selection and optimization module 220, and a dynamic weight adjustment strategy formulation module 230.

[0080] The data acquisition and processing module 210 is configured to collect driving data and transformer supply area data of the electric vehicle, and obtain a charging demand probability of a region by preprocessing the collected data.

[0081] The transformer supply area selection and optimization module 220 is configured to select and optimize a transformer supply area for charging the electric vehicle.

[0082] The dynamic weight adjustment strategy formulation module 230 is configured to determine a weight in an active transformer supply area selection and formulate a dynamic weight adjustment strategy.

[0083] The transformer supply area selection system for the electric vehicle provided by the embodiments of the present disclosure can execute the transformer supply area selection method for the electric vehicle provided by any embodiment of the present disclosure, and has corresponding functional modules and beneficial effects of the execution method.

[0084] Embodiment three

[0085] Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. Fig. 3 shows a schematic structural diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. The electronic device 500 may include a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a personal digital assistant (PDA), a portable android device (PAD), a portable media player (PMP), and a vehicle-mounted terminal (e.g., a vehicle-mounted navigation terminal).

[0086] As shown in FIG. 3, the electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, and may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device 500. The processing device 501, the ROM 502 and the RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0087] Generally, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc., an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc., a storage device 508 including, for example, a magnetic tape, a hard disk, etc., and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although FIG. 3 shows an electronic device 500 with various devices, it is not required to implement or possess all the devices shown, and more or fewer devices may be implemented or possessed alternatively according to actual needs.

[0088] According to the embodiments of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, the embodiments of the present disclosure include a computer program product including a computer program carried on a transitory computer-readable medium. The computer program contains program code for executing the method shown in the flowchart. In such embodiments, the computer program may be downloaded and installed from a network via the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When executed by the processing device 501, the computer program executes the above functions defined in the transformer supply area selection method for the electric vehicle according to the embodiments of the present disclosure.

[0089] The electronic device provided by the embodiments of the present disclosure belongs to the same concept as the transformer supply area selection method for the electric vehicle provided by the above embodiments. For technical details not described in detail in this embodiment, references may be made to the above embodiments. This embodiment has the same beneficial effects as the above embodiments.

[0090] Embodiment four

[0091] The embodiment fourth of the present disclosure further provides a computer-readable storage medium storing a computer program. The computer program, when executed by a processor, implements the transformer supply area selection method for the electric vehicle provided by any embodiment of the present disclosure.

[0092] In the embodiments of the present disclosure, the computer storage medium may include any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may include, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any combination thereof. The computer-readable storage media include electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EEPROM), flash memory, optical fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, and the program may be used by, or in conjunction with, an instruction execution system, device, or apparatus.

[0093] The computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, and the data signal carries computer-readable program code. The propagated data signal may take various forms, including an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium. The computer-readable medium may send, propagate, or transmit the program for use by or in conjunction with the instruction execution system, device, or equipment.

[0094] The program code included in the computer-readable medium may be transmitted through any appropriate medium, including but not limited to wireless, wire, optical cable, radio frequency (RF), etc., or any appropriate combination thereof.

[0095] The computer program code for performing that operation of the present disclosure may be written in one or more programming languages or a combination of multiple programming languages, including object-oriented programming languages, such as Java, Smalltalk, and C++, as well as conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be entirely executed on the user's computer, partially executed on the user's computer, executed as a standalone software package, partially executed on the user's computer and partially executed on a remote computer, or entirely executed on a remote computer or server. In a case involving a remote computer, the remote computer may be connected to a user computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

Claims

1. A transformer supply area selection method for an electric vehicle, comprising:collecting driving data and transformer supply area data of the electric vehicle, and obtaining a charging demand probability of a region by preprocessing the collected data;selecting and optimizing a transformer supply area for charging the electric vehicle; anddetermining a weight in an active transformer supply area selection, and formulating a dynamic weight adjustment strategy.

2. The transformer supply area selection method according to claim 1, wherein the driving data of the electric vehicle comprises a time stamp, a geographical location of the electric vehicle and a state of charge (SoC) of the electric vehicle, the driving data is stored as time series data D[,t, wherein t = {t, x^ y^ SoQ}, Xt denotes a horizontal coordinate value of an i-th electric vehicle at time t, yi denotes a vertical coordinate value of the i-th electric vehicle at time t, and 5()C, denotes the SOC of the i-th electric vehicle at time t;obtaining the charging demand probability of the region comprises:dividing all transformer supply areas proportionally, wherein a size of each grid region G; is Ax X Ay, wherein Ax denotes a horizontal coordinate value corresponding to a division size of a transformer supply area, and Ay denotes a vertical coordinate value corresponding to a division size of the transformer supply area; andfor each grid region G y, calculating the charging demand probability ?j of the region in one of the following manner:determining the charging demand probability Pj of the region according to a number of electric vehicles entering the region by the following formula:J vM i ,wherein M denotes a total number of all divided transformer supply areas, and Lj denotes a total number of charging times in a transformer supply area j; ordetermining the charging demand probability ?j of the region according to a proportion of low-battery electric vehicles entering the region by the following formula:NPj ((a; ■ y{) e Gj ■ SoC} < 1),i=lwherein / V denotes a total number of electric vehicles in the transformer supply area.

3. The transformer supply area selection method according to claim 2, further comprising:based on the charging demand probability Pj, selecting a region Gy with a largest charging ■ *                    .*demand probability as a first transformer supply area J , wherein J is expressed by the following formula: / * = arg max P,•4. The transformer supply area selection method according to claim 2, wherein selecting and optimizing the transformer supply area for charging the electric vehicle comprises:correcting a charging demand probability of the electric vehicle; andexecuting a weighted K-center greedy algorithm, wherein 0( denotes a point with a numerical value (xp y;J, (A i ‘ )'[') denotes a longitude value of the i-th electric vehicle and a latitude value of the i-th electric vehicle, 0 denotes an original data set and is expressed by 0 =         , and m denotes a total number of points in the original data set;wherein correcting a charging demand probability of the electric vehicle comprises:for each transformer supply area Gj, determining a correction value ^7 of charging demand probability of all electric vehicles in each transformer supply area by the following formula: w^uPj+iki-SoC,) ,wherein « and ft are coefficients for adjusting a plurality of weights;wherein executing the weighted K-center greedy algorithm comprises:constructing a k-nearest neighbour indicator matrix P by the following formula;P = hi / 1 ,wherein Pij is used to indicate whether ()j is a nearest neighbour to Oj, in response to ()j being the nearest neighbour to Oj, p^ = 1 is determined, and in response to f)j being not the nearest neighbour to Oj,      = 0 is determined;replacing Pij with a weight W[j of Gaussian kernel distance by the following formula;W = [wj.l , wn e [0, 11,.                      dx(xf yd\ , z               ........wherein — p, / : • exp [ -----7^—;----- I, dx (Xj, y^) denotes a Manhattan distance,and v denotes variance of distances between all points corresponding to (Xj, yi).

5. The transformer supply area selection method according to claim 4, wherein executing the weighted K-center greedy algorithm further comprises:normalizing weights corresponding to K nearest neighbours, wherein a normalized graph density vector is expressed by the following formula:TGrd(O) = [^(1^), •••, Gra^of), • •, Grd(om)] ;selecting a data point with a high density by the following formula:neighbour (Oi) — {Oe}ee / ndex(pi>o);andimplementing density attenuation on a neighbour point ()j by the following formula:Gra^Oj) = Gra(oj) - Gra(ot) ■ p^, Oj e neighbour^o^;wherein neighbour (Oj) is a set of neighbour points of Oj obtained according to the k-nearest neighbour indicator matrix P, Pi is an i-th row of the k-nearest neighbour indicator matrix P, Index^Pi >0) provides an index set satisfying Pi > 0, a point with a highest density is selected based on a graph density, and a density of the neighbour point is iteratively reduced.

6. The transformer supply area selection method according to claim 5, wherein the density of the neighbour point is iteratively reduced in the following manners:selecting an initial transformer supply area as a starting point, and adding the starting point into a marked data point set;in each iteration, calculating coverage of a current marked data point set, and selecting a new transformer supply area to maximize new coverage;adding the new transformer supply area to the marked data point set, updating the new coverage, and optimizing the objective formula by the following formula:arg min  5e°uei,wherein e0 is the current marked data point set, f 1 is a selected marked data point set, and 8 illustrates a coverage radius of f1 on e0 , the formulaargindicates that a group of spheres centered on each memberin e 0 with a radius of 5 is capable of covering the entire cjl, and a minimizationproblem in the formula ^Pg Hl in  S eoUe1is equivalent to the followingminimax transformer supply area selection problem:min max min Mojr,e1:|e1<B| ie[a]\(e°ue1);Ge°ue1 v°jx);wherein A denotes a calculation of Euclidean distance, the minimax transformer supply area selection problem is solved by using a 2-optimization (2-OPT) solution, and in the 2-OPT solution, the following equations are iterated:o = arg maxminA(ojX,andwherein O denotes a selected data point in an iteration;repeating the above steps until the calculation of all transformer supply areas is completed.

7. The transformer supply area selection method according to claim 6, wherein determining the weight in the active transformer supply area selection comprises:defining Wj as a weight representing a comprehensive importance of the grid region G; by the following formula:Wj = afj + bCj + cLj,wherein fj denotes a charging demand frequency of the region and is used to reflect a concentration degree of low-battery electric vehicles in the region, Cj denotes transformer supply area construction cost of the area, the transformer supply area construction cost comprises land cost and construction cost, denotes a load condition of a power grid in the area and is used to consider load pressure of the power grid in the area when the power grid is connected to a new transformer supply area, and ^, b and c are important coefficients for adjusting the plurality of weights.

8. The transformer supply area selection method according to claim 7, wherein formulating the dynamic weight adjustment strategy comprises:periodically recalculating the charging demand frequency fj based on real-time driving data of the electric vehicle;dynamically adjusting the transformer supply area construction cost C, by performing a dynamic evaluation on the construction cost; anddynamically monitoring and adjusting the load condition of the power grid.

9. The transformer supply area selection method according to claim 8, wherein determining the weight in the active transformer supply area selection and formulating the dynamic weight adjustment strategy further comprises:performing iteration based on historical data, wherein performing iteration based on the historical data comprises: in response to continuous accumulation of electric vehicle data and demand data, re-evaluating the weight Wj of each grid region after each iteration; andre-selecting the transformer supply area based on new data to ensure that a layout of the transformer supply area satisfies a latest demand.

10. A transformer supply area selection system for an electric vehicle, comprising:a data acquisition and processing module, configured to collect driving data and transformer supply area data of the electric vehicle, and obtain a charging demand probability of a region by preprocessing the collected data;a transformer supply area selection and optimization module, configured to select and optimize a transformer supply area for charging the electric vehicle; anda dynamic weight adjustment strategy formulation module, configured to determine a weight in an active transformer supply area selection and formulate a dynamic weight adjustment strategy.

Images