CN111401627A - Electric vehicle charging scheduling method and device - Google Patents

Abstract

The embodiment of the present invention discloses a method and device for scheduling electric vehicle charging, wherein the method includes: obtaining a first scheduling scheme for electric vehicles in a preset electric vehicle set respectively, The first scheduling scheme is evaluated to obtain a first fitness value; a mixed variable mutation process is performed on the first scheduling scheme according to a preset operation rule to obtain a variable variation value, and a variable variation value is obtained according to the first scheduling scheme and the variable variation value Perform cross operation processing to obtain a second scheduling scheme; evaluate the second scheduling scheme under the condition of satisfying the target constraint to obtain a second fitness value; select a target from the first scheduling scheme and the second scheduling scheme Optimize the scheduling scheme for charging scheduling. The method of the invention can effectively optimize the travel time and charging cost, improve the efficiency of electric vehicle charging scheduling in the overall road network, and have stronger global optimization performance.

Description

Electric vehicle charging scheduling method and device

technical field

Embodiments of the present invention relate to the field of intelligent transportation, in particular to a method and device for scheduling electric vehicle charging, and also to an electronic device and a computer-readable storage medium.

Background technique

In recent years, with the rapid development of science and technology, electric vehicle-related technologies have gradually matured. Electric car rental companies usually have a large number of electric cars and several charging station resources at the same time. When the electric car completes the journey, the charging state needs to be close to the expectation, so that it will not be too low and affect the development of the next journey, and will not be too high. In addition, the current journey time and charging cost are increased, so in terms of decision variables, it is not only necessary to optimize the selection of charging stations during electric vehicle scheduling, but also to optimize the specific charging amount at each charging station. The realization of electric vehicle charging scheduling has actually become a complex scheduling optimization problem. Solving this problem requires determining the specific charging scheme of each electric vehicle in the traffic network. The charging scheme may include information such as the number of charging times, the selection of charging stations, and the amount of charging.

At present, due to the limitation of the number of hardware facilities such as charging stations, it is necessary to meet the needs of use by sharing. During the specific implementation process, changing the charging scheme of a single electric vehicle will likely affect the implementation of other electric vehicle charging schemes, and thus affect the implementation of other electric vehicle charging schemes. Therefore, it is necessary to optimize the charging scheduling of electric vehicles globally, so as to realize the intelligent charging scheduling of electric vehicles. Starting from the interests of electric vehicle rental companies, how to quickly and effectively realize the charging and scheduling of electric vehicles has gradually become the focus of research by those skilled in the art.

SUMMARY OF THE INVENTION

To this end, the embodiments of the present invention provide a charging scheduling method for electric vehicles, so as to solve the problem in the prior art that the scheduling optimization process for charging vehicles is inefficient, resulting in the inability to meet the actual use requirements of users.

In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:

In a first aspect, an embodiment of the present invention provides an electric vehicle charging scheduling method, including: obtaining a corresponding first scheduling scheme for electric vehicles in a preset electric vehicle set, wherein the first scheduling scheme includes corresponding to the electric vehicles the initial charging station sequence and initial charging rate sequence; under the condition that the preset target constraints are met, the first scheduling scheme is evaluated to obtain the corresponding first adaptation value; the first scheduling scheme is evaluated according to the preset operation rules The scheme performs mixed variable mutation processing to obtain corresponding variable variation values; performs cross operation processing according to the first scheduling scheme and the variable variation values to obtain a second scheduling scheme; The second scheduling scheme is evaluated to obtain a corresponding second fitness value; based on the first fitness value and the second fitness value, a target optimal scheduling scheme is selected from the first scheduling scheme and the second scheduling scheme, according to The target optimal scheduling scheme manages and controls the electric vehicle to perform charging scheduling.

Further, the electric vehicle charging scheduling method further includes: presetting a target optimization iteration number; after selecting the target optimization scheduling scheme, judging whether the current optimization iteration number corresponding to the target optimization scheduling scheme is less than a predetermined number of iterations. The set number of target optimization iterations, if not, control the electric vehicle to perform charging scheduling according to the target optimization scheduling scheme.

Further, obtaining the corresponding first scheduling scheme for the electric vehicles in the preset electric vehicle set, specifically includes: constructing an initial charging station sequence for each electric vehicle in the electric vehicle set, and according to the set of electric vehicles. The initial charging station sequence selects a charging station for each electric vehicle, sets the charging rate for the selected charging station, and then forms the initial charging rate sequence; obtains the initial charging station sequence and the initial charging rate sequence according to the initial charging station sequence and the initial charging rate sequence The first scheduling scheme.

Further, performing mixed variable mutation processing on the first scheduling scheme according to preset operation rules to obtain a corresponding variable variation value specifically includes: according to the initial value corresponding to each electric vehicle in the electric vehicle set. The sequence of charging stations is subjected to discrete mutation operation processing, and further, continuous mutation operation processing is performed according to the charging rate set for the selected charging station for each electric vehicle in the electric vehicle set to obtain corresponding variable variation values.

Further, the performing crossover operation processing according to the first scheduling scheme and the variable variation value to obtain the second scheduling scheme specifically includes: using a preset binomial crossover algorithm to perform the crossover operation on the first scheduling scheme and the all The variation value of the above variable is subjected to cross operation processing to obtain the second scheduling scheme.

Further, the electric vehicle charging scheduling method further includes: if so, continuing to perform mixed variable mutation processing on the first scheduling scheme according to preset operation rules to obtain corresponding variable variation values; according to the first scheduling The scheme and the variable variation value are subjected to cross operation processing to obtain a new second scheduling scheme.

Further, the electric vehicle charging scheduling method further includes: predetermining a set of electric vehicles that need to be charged and scheduled.

In a second aspect, an embodiment of the present invention further provides an electric vehicle charging scheduling device, including: a first scheduling scheme obtaining unit, configured to obtain a corresponding first scheduling scheme for the electric vehicles in the preset electric vehicle set respectively, the The first scheduling scheme includes an initial charging station sequence and an initial charging rate sequence corresponding to the electric vehicle; the first evaluation unit is configured to evaluate the first scheduling scheme to obtain a corresponding a first fitness value; a second scheduling scheme obtaining unit, configured to perform mixed variable mutation processing on the first scheduling scheme according to a preset operation rule to obtain a corresponding variable variation value; according to the first scheduling scheme and the variable The variation value is subjected to cross operation processing to obtain a second scheduling scheme; a second evaluation unit is configured to evaluate the second scheduling scheme to obtain a corresponding second fitness value under the condition that the target constraint condition is satisfied; the optimization scheduling unit, is used to select a target optimal dispatch scheme from the first dispatch scheme and the second dispatch scheme based on the first fitness value and the second fitness value, and to manage and control the electric vehicle according to the target optimal dispatch scheme Perform charging scheduling.

Further, the electric vehicle charging scheduling device further includes: a unit for presetting the number of iterations, which is used for presetting the number of iterations for the target optimization; a first judgment processing unit, which is used for judging and matching after selecting the target optimization scheduling scheme. Whether the current optimization iteration number corresponding to the target optimization scheduling scheme is less than the preset target optimization iteration number, if not, the electric vehicle is managed and controlled to perform charging scheduling according to the target optimization scheduling scheme.

Further, the first scheduling scheme obtaining unit is specifically configured to: construct an initial charging station sequence for each electric vehicle in the electric vehicle set, and select charging for each electric vehicle according to the initial charging station sequence. station, set the charging rate for the selected charging station, and then form the initial charging rate sequence; obtain the first scheduling scheme according to the initial charging station sequence and the initial charging rate sequence.

Further, the second scheduling scheme obtaining unit is specifically configured to: perform discrete mutation operation processing according to the initial charging station sequence corresponding to each electric vehicle in the electric vehicle set, and further according to the electric vehicle set The charging rate set by the selected charging station of each electric vehicle in the CV is processed by continuous mutation operation, and the corresponding variable variation value is obtained.

Further, the second scheduling scheme obtaining unit is specifically configured to: use a preset binomial cross algorithm to perform cross operation processing on the first scheduling scheme and the variable variation value to obtain the second scheduling scheme.

Further, the electric vehicle charging scheduling device further includes: a second judgment processing unit, configured to continue to perform mixed variable mutation processing on the first scheduling scheme according to preset operation rules to obtain corresponding variable variation. value; perform cross operation processing according to the first scheduling scheme and the variable variation value to obtain a new second scheduling scheme.

Further, the electric vehicle charging scheduling device further includes: pre-determining a set of electric vehicles for which charging scheduling needs to be performed.

In a third aspect, an embodiment of the present invention further provides an electronic device, including: a processor and a memory; wherein, the memory is used to store a program of an electric vehicle charging scheduling method, the electronic device is powered on and passes the processor After running the program of the electric vehicle charging scheduling method, any one of the above-mentioned electric vehicle charging scheduling methods is executed.

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer storage medium contains one or more program instructions, and the one or more program instructions are used by a server to execute any one of the foregoing The described electric vehicle charging scheduling method.

Using the electric vehicle charging scheduling method of the present invention can effectively optimize the travel time and charging cost, and ensure that the charging state when the electric vehicle reaches the end point is as close to the expected state value as possible, which greatly improves the efficiency of electric vehicle charging scheduling. , thereby improving the user experience.

Description of drawings

In order to illustrate the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that are required to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, other implementation drawings can also be derived from the provided drawings without any creative effort.

FIG. 1 is a flowchart of an electric vehicle charging scheduling method provided by an embodiment of the present invention;

FIG. 2 is a schematic diagram of an electric vehicle charging scheduling device according to an embodiment of the present invention;

3 is a schematic diagram of an electronic device according to an embodiment of the present invention;

FIG. 4 is a complete flowchart of an electric vehicle charging scheduling method according to an embodiment of the present invention.

Detailed ways

The technical solutions of the present invention are described below by specific embodiments, and those who are familiar with the technology can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the embodiments described below are some, but not all, embodiments of the present invention. Based on the embodiments described below, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the protection scope of the present invention.

At present, electric vehicle charging scheduling has become an emerging complex scheduling optimization problem in the field of intelligent transportation. The technical solution disclosed in the present invention applies the differential evolution algorithm to the charging scheduling of electric vehicles, and uses the differential evolution algorithm to search for the optimal solution of all charging scheduling schemes for electric vehicles. It comprehensively considers the global optimization objectives in terms of journey time, charging cost, and the state of charge at the destination, using a charging station sequence composed of discrete charging station numbers and a continuous charging rate (the charging amount is normalized The latter value) sequence, which is more in line with the needs of practical applications. On the one hand, the generation and update operations of the solution are simplified by obtaining the charging rate by normalizing the charging amount, and then the fitness value evaluation method that satisfies the constraints is adopted to ensure the validity of the charging scheduling solution during the operation; The mutation mechanism of variables includes a set-based discrete mutation operator specially dealing with charging station sequences and a traditional continuous mutation operator specially dealing with charging rate sequences.

Based on the charging scheduling method for an electric vehicle according to the present invention, the embodiments thereof will be described in detail below. As shown in FIG. 1 , which is a flowchart of an electric vehicle charging scheduling method provided by an embodiment of the present invention, the specific implementation process includes the following steps:

Step S101 : respectively obtaining a corresponding first scheduling scheme for the electric vehicles in the preset electric vehicle set, where the first scheduling scheme includes an initial charging station sequence and an initial charging rate sequence corresponding to the electric vehicles.

Before step S101 is performed, a set of electric vehicles to be scheduled for charging may be predetermined, and a random first scheduling scheme is generated for the electric vehicles in the set of electric vehicles based on a preset rule. In the embodiment of the present invention, the corresponding first scheduling scheme is obtained for the electric vehicles in the preset electric vehicle set, and the specific implementation process may include: constructing a corresponding first scheduling scheme for each electric vehicle in the electric vehicle set an initial charging station sequence, and selecting a charging station for each electric vehicle according to the initial charging station sequence, setting a charging rate for the selected charging station, and then forming the initial charging rate sequence; according to the initial charging station sequence and the The initial charge rate sequence obtains the first scheduling scheme.

For example, in the operation implementation process, it is assumed that the charging scheduling scheme si of the _ith electric vehicle in the electric vehicle set (hereinafter referred to as A) consists of a charging station sequence _ci and an equal-length charging rate sequence _ei . It should be noted that since the electric vehicles in A have different journey start and end points, it is necessary to limit the length of the charging station sequence of each electric vehicle in advance to be J; if the actual length of the charging station sequence of an electric vehicle is less than J, then It can be filled by adding an empty number after it.

Specifically, initialize an electric vehicle charging scheduling solution S={s _i |i=1, 2, . n) A random dispatch scheme _si = ( _{ci, e i )} is generated for n electric vehicles. First, it is necessary to randomly select at most J non-repetitive charging station numbers to generate the charging station sequence c _i ={c _ij |j=1,2,...,J}, and it is required that the distance between c _i0 and the starting point of the journey shall not exceed the ith The initial cruising range of the vehicle, the distance between any two adjacent charging stations in the sequence of charging stations, and the distance between the last charging station and the end of the journey must not exceed the maximum cruising range of the i-th vehicle; then generate the length and c _i equal charge rate sequence e _i ={e _ij |j=1, 2, . . . , J}. where e _ij is a random number in the range [0,1].

When constructing the charging scheduling solution S={s _i |i=1,2,...,n}, the charging scheduling scheme si of the _i -th vehicle in A includes the charging station sequence c _i ={ c _ij |j=1,2,...} and an isometric sequence e _i ={e _ij |j=1,2,...} reflecting the corresponding charge amounts. Among them, the discrete variable c _ij represents the number of a charging station in B, and the continuous variable e _ij reflects the actual charging amount Δβ _{ij of the i-th vehicle at c ij .} Since the maximum charge β _i ^max that can be stored by the i-th vehicle may be different from other vehicles, and the minimum charge Δβ _ij ^min of the i-th vehicle at c _ij also needs to be determined according to the distance between c _ij and c _i(j+1) . Therefore, in order to unify the definition domain of e _ij , the present invention defines e _ij as the charging rate and limits its value range to [0, 1]. The calculation formula of _eij is as follows:

Step S102: Evaluate the first scheduling scheme to obtain a corresponding first adaptation value under the condition that a preset target constraint condition is satisfied.

After the scheduling scheme set S is constructed and obtained in step S101, in this step, the first scheduling scheme in S can be evaluated and the corresponding first fitness value f(S) can be obtained under the condition that the preset target constraint condition is satisfied. In the embodiment of the present invention, the target constraints include constraints of two conditions, and each electric vehicle charging scheduling solution S needs to satisfy the constraints of the two conditions during specific implementation, namely: a. The power at any time shall not be empty or overcharged; b. The number of charging electric vehicle books that each charging station can accommodate at any time shall not be greater than the number of charging piles in it.

Specifically, each electric vehicle charging scheduling solution S can be evaluated through the following three steps, and the corresponding fitness value can be obtained: S1: Arrange the charging scheduling scheme of each electric vehicle according to the charging scheduling solution S, in the case of satisfying the constraint condition a , get the time, charging time and charging cost of each electric vehicle to each charging station, and get the time to reach the end of the journey and the remaining power. S2: The relevant vehicle charging scheduling scheme obtained in each charging station arrangement S1, under the constraint of satisfying condition b, increase the waiting time for some vehicles at busy charging stations, and adjust the arrival time of these vehicles at subsequent charging stations accordingly. , charging time and charging cost, and finally update the arrival time and remaining power at the end of the journey; S3: The charging cost of all vehicles obtained in S2 at each charging station, the time at the start and end of the journey, and the arrival at the end of the journey. The time is applied to the fitness value calculation formula of the preset electric vehicle charging scheduling solution (for example, the following formulas (2) and (6)), and finally the first fitness value f(S) is obtained.

前到达各自终点，那么f_time(S)的计算公式就可以如下所示：Further description will be given in conjunction with the example in step S101. In the specific implementation process, the adaptive value f(S) corresponding to the optimized charging scheduling scheme of the present invention is to minimize the journey time, charging cost and arrival destination of all vehicles in A. The average value of the global optimization objectives for various aspects such as state of charge. Among them, the journey time is f _time (S), the charging cost is f _expense (S), and the charging state is f _SoC (S). The journey time of the i-th vehicle in A is the total time spent by the vehicle from the start of the journey to the end of the journey, so it includes the vehicle's travel time on the road, charging time at the charging station and possible additional waiting time. Suppose that all vehicles in A depart after time t=1 and are expected to arrive at time

reach their respective end points before, then the calculation formula of f _time (S) can be as follows:

则是为使车辆尽量在

前到达终点而定义如下的时间惩罚函数：where: t _i ^ori and t _i ^des represent the departure time and arrival time of the i-th vehicle, respectively,

is to keep the vehicle as far as possible

before reaching the end point, the time penalty function is defined as follows:

是充电价格计算函数，而

是充电费用计算函数，那么f_expense(S)的计算公式就可以如下所示：The charging cost of the i-th vehicle in A refers to the total cost of charging the vehicle at all the charging stations in the constructed charging station sequence. Assuming that Δβ _ij represents the power added by the i-th vehicle at the j-th charging station c _ij in its sequence,

is the charging price calculation function, and

is the charging cost calculation function, then the calculation formula of f _expense (S) can be as follows:

The state of charge of the i-th vehicle in A can be understood as the difference between the remaining power β _i ^des and the expected remaining power β ^exp when the vehicle reaches the end point. Considering that the maximum value β _i ^max that can be stored in the i-th vehicle may be different from other vehicles, the present invention uses the remaining battery rate ρ _i ^des =β _i ^des /β _i ^max to compare with the expected remaining battery rate ρ ^exp , and define the state-of-charge calculation formula of the i-th vehicle as follows:

Therefore, in order to make the state of charge of each electric vehicle at the end point not less than the expected state of charge and keep the reserve ratio as small as possible, the calculation formula of f _SoC (S) can be as follows:

和

作归一化处理，之后再进行求和，因此电动汽车充电调度解的适应值计算公式可表示如下：Finally, in order to balance multiple optimization objectives, the present invention divides the average value of all vehicles in A in terms of travel time, charging cost, and charging state by the corresponding maximum value.

and

It is normalized and then summed, so the calculation formula of the fitness value of the electric vehicle charging scheduling solution can be expressed as follows:

Step S103: Perform mixed variable mutation processing on the first scheduling scheme according to preset operation rules to obtain corresponding variable variation values; perform cross operation processing according to the first scheduling scheme and the variable variation values to obtain a second scheduling scheme Program.

After the first scheduling scheme is obtained in step S101, in this step, mixed variable mutation processing may be performed on the first scheduling scheme to obtain the corresponding variable variation value, and according to the first scheduling scheme and the variable variation value The interleave operation process obtains the second scheduling scheme.

In the embodiment of the present invention, performing mixed variable mutation processing on the first dispatching scheme according to preset operation rules to obtain a corresponding variable variation value, a specific implementation process may include: according to each vehicle in the electric vehicle set The initial charging station sequence corresponding to the electric vehicle is processed by discrete mutation operation using a preset discrete mutation operator; further according to the charging rate set for the selected charging station for each electric vehicle in the electric vehicle set, Use the preset continuous mutation operator to perform continuous mutation operation processing to obtain the corresponding variable mutation value. Further, performing crossover operation processing according to the first scheduling scheme and the variable variation value to obtain a second scheduling scheme, specifically, using a preset binomial crossover algorithm to perform a crossover operation on the first scheduling scheme and the variable variation value. The variation value of the variable is subjected to cross operation processing to obtain a second scheduling scheme. It should be noted that the first scheduling scheme and the second scheduling scheme are sets including at least one specific scheduling scheme; wherein, the first scheduling scheme refers to an initial scheduling scheme randomly generated before iterative optimization, The second scheduling scheme may refer to several scheduling schemes generated during the iterative optimization process, or may refer to the final scheduling scheme output after satisfying the number of iterative optimization times, which is not specifically limited herein.

原理如下所示：For further description in conjunction with the example in step S102, in the implementation process, the specific process of the variation mechanism of the mixed variable may be as follows: the _kth solution Sk of the electric vehicle charging scheduling is represented as a two-dimensional vector ( c _k , e _k ), and correspondingly designed a mutation mechanism supporting mixed variables to obtain

The principle is as follows:

Among them: r ₁ , r ₂ , and r ₃ represent any three non-repeating and non-k individual solution numbers in the differential evolution algorithm population, and F is the variation factor.

When specifically implemented, the present invention uses the following two mutation operators to deal with discrete variables and continuous variables in individual solutions respectively:

a. A discrete mutation operator, which redefines the key mathematical operation relation of formula (7) using a set-based discretization technique.

和

的差距，需要将两个序列相同位置上充电站编号的减法运算重定义为如下公式：①Subtraction operation. Since the purpose of the subtraction operation in formula (7) is to obtain the difference between the two solutions, the corresponding sequence of two charging stations is obtained.

and

The difference between the two sequences needs to be redefined as the following formula:

表示一个空充电站编号；*表示满足预设的目标约束条件的任一充电站的编号。in:

Indicates the number of an empty charging station; * indicates the number of any charging station that satisfies the preset target constraints.

②Addition operation with multiplication, where the multiplication factor is redefined as a probability value, which is used to select the two addends as follows:

Where: F∈[0,1] is the variation factor; q is a random number in the range of [0,1].

In short, the discrete mutation operator uses the following formula to process the jth charging station number c _kij of the charging station sequence of the ith vehicle in the _kth solution Sk:

b. Continuous mutation operator, which uses the following formula to process the charging rate e _kij of the i-th vehicle at its j-th charging station in the _k -th solution Sk:

The parameters of the present invention are set as: population size N=30, maximum generation ^gmax =100, variation factor F=0.5, crossover factor C=0.1. The final result shows that the algorithm of the present invention can be applied to both synthetic road network and real road network, and its average optimization effect is better than the traditional priority algorithm, which shows that the present invention is very effective to solve the electric vehicle charging scheduling problem.

Step S104: Evaluate the second scheduling scheme to obtain a corresponding second adaptation value under the condition that the target constraint condition is satisfied.

Step S105: Based on the first fitness value and the second fitness value, select a target optimal dispatch scheme from the first dispatch scheme and the second dispatch scheme, and manage and control the electric motor according to the target optimal dispatch scheme. Cars for charging scheduling.

After the first fitness value and the second fitness value are obtained in step S102 and step S104 respectively, in this step, a target optimal scheduling scheme can be selected based on the fitness value, and the electric vehicle can be charged according to the target optimal scheduling scheme. schedule.

In the specific implementation process, the number of preset target optimization iterations is also included; after the target optimization scheduling scheme is selected, it is determined whether the current optimization iteration number corresponding to the target optimization scheduling scheme is less than the preset target optimization iteration number, If not, the electric vehicle is managed and controlled to perform charging scheduling according to the target optimal scheduling scheme. In addition, if yes, continue to perform mixed variable mutation processing on the first scheduling scheme according to the preset operation rules to obtain corresponding variable variation values; perform cross operation processing according to the first scheduling scheme and the variable variation values to obtain New second scheduling scheme.

As shown in FIG. 4 , it is a complete flowchart of an electric vehicle charging scheduling method provided by an embodiment of the present invention. In order to facilitate the understanding of the technical solution disclosed by the present invention, the following describes the specific implementation of the entire algorithm step by step based on the content of the complete flowchart:

The first step: for the current set of electric vehicles (hereinafter referred to as A) that need to arrange a scheduling scheme, define each individual solution S in the population as a set containing the charging scheduling scheme of each electric vehicle in A. Initialize each individual solution S, first construct a random charging station sequence for each electric vehicle in A, and then set a random value for the charging rate of each electric vehicle in A at each charging station in the constructed charging station sequence, A charging rate sequence with the same length as the charging station sequence is constructed, and then a scheduling scheme set S is obtained. Under the condition that the preset target constraint conditions are met, S is evaluated to obtain a corresponding first fitness value f(S).

Step 2: To solve S for each individual in the iterative evolutionary population, set the initial algebra g=1, first perform different mutation operations on the discrete variables and continuous variables contained in S to obtain S ^mutant , that is, first The set-based discrete mutation operation is performed for the charging station sequence of each vehicle in A, and the traditional continuous mutation operation is performed for the charging rate of each charging station in the sequence after mutation; S ^mutant performs crossover operation to obtain the second scheduling scheme S ^trial , that is, select the charging scheduling scheme of each vehicle in A from S or S ^mutant with a certain probability to generate S ^trial ; then, under the condition of satisfying the preset target constraints Evaluate S ^trial and obtain the corresponding second fitness value f(S ^trial ); finally select the better one between S and S ^trial by comparing the first fitness value f(S) and the second fitness value f(S ^trial ) As the individual solution of the next generation population, the scheduling scheme is optimized for the target of electric vehicles. Incremental algebra g.

Step 3: If the algebra g is not less than the preset maximum algebra g ^max , terminate the algorithm, and arrange the charging scheduling scheme of each electric vehicle in A according to the historical optimal individual solution (ie, the target optimal scheduling scheme), otherwise go to The second step continues the loop execution.

Using the electric vehicle charging scheduling method of the present invention can effectively optimize the travel time and charging cost, and ensure that the charging state when the electric vehicle reaches the end point is as close to the expected state value as possible, which greatly improves the electric vehicle in the global road network. The efficiency of charging scheduling improves the user experience.

Corresponding to the electric vehicle charging scheduling method provided above, the present invention also provides an electric vehicle charging scheduling device. Since the embodiment of the device is similar to the above method embodiment, the description is relatively simple. For related details, please refer to the description of the above method embodiment part. The embodiment of the electric vehicle charging scheduling device described below is only schematic. . Please refer to FIG. 2 , which is a schematic diagram of an electric vehicle charging scheduling device according to an embodiment of the present invention.

An electric vehicle charging scheduling device according to the present invention includes the following parts:

The first dispatching scheme obtaining unit 201 is configured to respectively obtain a corresponding first dispatching scheme for the electric vehicles in the preset electric vehicle set, where the first dispatching scheme includes an initial charging station sequence and an initial charging rate corresponding to the electric vehicles sequence.

The first evaluation unit 202 is configured to evaluate the first scheduling scheme to obtain a corresponding first adaptation value under the condition that a preset target constraint condition is satisfied.

The second scheduling scheme obtaining unit 203 is configured to perform mixed variable mutation processing on the first scheduling scheme according to a preset operation rule to obtain a corresponding variable variation value; perform crossover according to the first scheduling scheme and the variable variation value The operation is processed to obtain the second scheduling scheme.

The second evaluation unit 204 is configured to evaluate the second scheduling scheme to obtain a corresponding second adaptation value under the condition that the target constraint condition is satisfied.

An optimization scheduling unit 205, configured to select a target optimal scheduling scheme from the first scheduling scheme and the second scheduling scheme based on the first fitness value and the second fitness value, and optimize the scheduling scheme according to the target The electric vehicle is controlled to perform charging scheduling.

The use of the electric vehicle charging scheduling device of the present invention can effectively optimize the travel time and charging cost, and ensure that the charging state when the electric vehicle reaches the end point is as close to the expected state value as possible, which greatly improves the electric vehicle in the global road network. The efficiency of charging scheduling improves the user experience.

Corresponding to the electric vehicle charging scheduling method provided above, the present invention also provides an electronic device. Since the embodiment of the electronic device is similar to the above-mentioned method embodiment, the description is relatively simple, and for related details, please refer to the description of the above-mentioned method embodiment part, and the electronic device described below is only illustrative. As shown in FIG. 3 , it is a schematic diagram of an electronic device provided by an embodiment of the present invention.

The electronic device specifically includes: a processor 301 and a memory 302; wherein, the memory 302 is used for running one or more program instructions, and is used for storing the program of the electric vehicle charging scheduling method, the server is powered on and runs the process through the processor 301. After the program of the electric vehicle charging scheduling method is executed, the electric vehicle charging scheduling method described in any one of the above is executed.

Corresponding to the electric vehicle charging scheduling method provided above, the present invention also provides a computer storage medium. Since the embodiment of the computer storage medium is similar to the foregoing method embodiment, the description is relatively simple, and for related details, please refer to the description of the foregoing method embodiment, and the computer storage medium described below is only illustrative.

The computer storage medium contains one or more program instructions, and the one or more program instructions are used by the server to execute the above-mentioned electric vehicle charging scheduling method. The server may refer to a background server corresponding to the above electronic device.

In this embodiment of the present invention, the processor or the processor module may be an integrated circuit chip, which has signal processing capability. The processor may be a general-purpose processor, a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field programmable gate array (FPGA for short), or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

Various methods, steps, and logical block diagrams disclosed in the embodiments of the present invention can be implemented or executed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art. The processor reads the information in the storage medium, and completes the steps of the above method in combination with its hardware.

The storage medium may be memory, eg, may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory.

Among them, the non-volatile memory may be a read-only memory (Read-Only Memory, referred to as ROM), a programmable read-only memory (Programmable ROM, referred to as PROM), an erasable programmable read-only memory (Erasable PROM, referred to as EPROM) , Electrically Erasable Programmable Read-Only Memory (Electrically EPROM, EEPROM for short) or flash memory.

The volatile memory may be a random access memory (Random Access Memory, RAM for short), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic RAM (DRAM), Synchronous DRAM, referred to as SDRAM), double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, referred to as DDRSDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, referred to as ESDRAM), synchronous connection dynamic random access memory (Synch link DRAM, referred to as SLDRAM) and direct memory bus random access memory (Direct Ram bus RAM, referred to as DRRAM).

The storage medium described in the embodiments of the present invention is intended to include, but not limited to, these and any other suitable types of memory.

Those skilled in the art should appreciate that, in one or more of the above examples, the functions described in the present invention may be implemented by a combination of hardware and software. When the software is applied, the corresponding functions may be stored in or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage medium can be any available medium that can be accessed by a general purpose or special purpose computer.

The specific embodiments described above further describe the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above descriptions are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made on the basis of the technical solution of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. an electric vehicle charging scheduling method, is characterized in that, comprises: A corresponding first scheduling scheme is obtained respectively for the electric vehicles in the preset electric vehicle set, where the first scheduling scheme includes an initial charging station sequence and an initial charging rate sequence corresponding to the electric vehicles; Evaluate the first scheduling scheme to obtain a corresponding first fitness value under the condition that a preset target constraint condition is satisfied; Perform mixed variable mutation processing on the first scheduling scheme according to a preset operation rule to obtain a corresponding variable variation value; perform cross operation processing according to the first scheduling scheme and the variable variation value to obtain a second scheduling scheme; Under the condition that the target constraint is satisfied, evaluating the second scheduling scheme to obtain a corresponding second fitness value; Based on the first fitness value and the second fitness value, a target optimal dispatch scheme is selected from the first dispatch scheme and the second dispatch scheme, and the electric vehicle is controlled to be charged according to the target optimal dispatch scheme schedule. 2. The electric vehicle charging scheduling method according to claim 1, further comprising: Preset target optimization iteration times; After selecting the target optimization scheduling scheme, determine whether the current optimization iteration number corresponding to the target optimization scheduling scheme is less than the preset target optimization iteration number, and if not, manage and control the electric motor according to the target optimization scheduling scheme. Cars for charging scheduling. 3 . The electric vehicle charging scheduling method according to claim 1 , wherein the obtaining a corresponding first scheduling scheme for the electric vehicles in the preset electric vehicle set respectively comprises: 3 . An initial charging station sequence is constructed for each electric vehicle in the electric vehicle set, and a charging station is selected for each electric vehicle according to the initial charging station sequence, and a charging rate is set for the selected charging station, thereby forming the an initial charging rate sequence; the first scheduling scheme is obtained according to the initial charging station sequence and the initial charging rate sequence. 4 . The electric vehicle charging scheduling method according to claim 1 , wherein, performing mixed variable mutation processing on the first scheduling scheme according to a preset operation rule to obtain a corresponding variable variation value, which specifically includes: 5 . Discrete mutation operation processing is performed according to the initial charging station sequence corresponding to each electric vehicle in the electric vehicle set, and further continuous processing is performed according to the charging rate set for the selected charging station for each electric vehicle in the electric vehicle set Type mutation operation processing to obtain the corresponding variable mutation value. 5 . The electric vehicle charging scheduling method according to claim 1 , wherein the cross operation processing is performed according to the first scheduling scheme and the variable variation value to obtain a second scheduling scheme, which specifically comprises: 6 . Using a preset binomial crossover algorithm, a crossover operation process is performed on the first scheduling scheme and the variable variation value to obtain a second scheduling scheme. 6. The electric vehicle charging scheduling method according to claim 2, further comprising: If yes, continue to perform mixed variable mutation processing on the first scheduling scheme according to the preset operation rules to obtain the corresponding variable variation value; perform cross operation processing according to the first scheduling scheme and the variable variation value to obtain a new Second schedule. 7 . The electric vehicle charging scheduling method according to claim 1 , further comprising: pre-determining a set of electric vehicles for which charging scheduling needs to be performed. 8 . 8. An electric vehicle charging scheduling device, comprising: A first dispatching scheme obtaining unit, configured to respectively obtain a corresponding first dispatching scheme for the electric vehicles in the preset electric vehicle set, where the first dispatching scheme includes an initial charging station sequence and an initial charging rate sequence corresponding to the electric vehicles ; a first evaluation unit, configured to evaluate the first scheduling scheme to obtain a corresponding first fitness value under the condition that a preset target constraint condition is met; A second scheduling scheme obtaining unit, configured to perform mixed variable mutation processing on the first scheduling scheme according to preset operation rules to obtain corresponding variable variation values; perform crossover operation according to the first scheduling scheme and the variable variation values processing to obtain a second scheduling scheme; a second evaluation unit, configured to evaluate the second scheduling scheme to obtain a corresponding second fitness value under the condition that the target constraint condition is satisfied; An optimization scheduling unit, configured to select a target optimal scheduling scheme from the first scheduling scheme and the second scheduling scheme based on the first fitness value and the second fitness value, and manage and control according to the target optimal scheduling scheme The electric vehicle performs charging scheduling. 9. An electronic device, characterized in that, comprising: processor; and The memory is used to store the program of the electric vehicle charging scheduling method. After the electronic device is powered on and the program of the electric vehicle charging scheduling method is run through the processor, the electric vehicle charging according to any one of the above claims 1-7 is executed. scheduling method. 10. A computer-readable storage medium, characterized in that, the computer-readable storage medium contains one or more program instructions, and the one or more program instructions are used to be executed by a server according to any one of claims 1-7. The one described electric vehicle charging scheduling method.

Images