CN110111001A - A kind of Site planning method of electric automobile charging station, device and equipment - Google Patents

Abstract

The invention discloses a location planning method, device, equipment and computer-readable storage medium for electric vehicle charging stations, comprising: determining the number of target charging stations in a preset planning area and the initial value of each charging station by using a preselected clustering algorithm station site; according to the number of the target charging piles and the initial site address of each charging station, respectively determine the number of particles of the linear decreasing weight particle swarm algorithm and the initial position of each particle; using the linear decreasing weight particle swarm algorithm and the The overall social cost of the initial position of each particle determines the target site of each charging station. The method, apparatus, device and computer-readable storage medium provided by the present invention greatly reduce the running time of determining the optimal number of charging stations. It solves the problem that the traditional particle swarm algorithm is prone to "premature convergence" and local optimality.

Description

Site selection planning method, device and equipment for electric vehicle charging station

technical field

The present invention relates to the technical field of electric vehicles, and in particular, to a method, device, device and computer-readable storage medium for site selection and planning of an electric vehicle charging station.

Background technique

At present, the world's fossil energy is gradually depleting, and environmental problems are also aggravating. Among them, the use of fuel vehicles accounts for a large proportion of the damage to the environment. Therefore, out of consideration for energy use and environmental friendliness, my country, The development of electric vehicles has been vigorously promoted. However, there will be some battery life problems in the process of developing electric vehicles. Compared with fuel vehicles, the battery life of electric vehicles is much smaller than that of fuel vehicles. The battery life of electric vehicles depends on its internal battery. The technology has yet to improve, so the range of electric vehicles is determined by the charging stations in the area.

The steps of the planning method for the electric vehicle charging station in the prior art are as follows: taking the maximum annual operating profit of the charging station as the objective function, establishing a planning model of the electric vehicle charging station; introducing a weighted Vronoi diagram to analyze the service area of the charging station; Using the traditional particle swarm (PS0) optimization algorithm to solve the optimal value of the charging station planning Through the continuous optimization process of particles representing the location and capacity of the charging station, the optimization selection of various charging station planning schemes is simulated.

The electric vehicle charging station planning method in the prior art adopts the traditional particle swarm optimization algorithm to plan the electric vehicle charging station, which has the advantages of easy to understand, fast iterative optimization speed and few adjustment parameters. However, it also has the following disadvantages: the number K of electric vehicle charging stations needs to be manually set, and the set value K is not equal to the optimal value K. In order to obtain the optimal K value, the optimization algorithm needs to be run many times, which takes up a lot of operation. time; the traditional particle swarm optimization algorithm is easily affected by the selection of weights and learning factors, and is prone to the phenomenon of "premature convergence"; the traditional particle swarm optimization algorithm is easy to fall into the local optimum, resulting in the output result not being the optimal solution and convergence. Accuracy is not high.

In summary, it can be seen that how to quickly determine the optimal number of charging stations under the current traffic flow, so as to select the optimal charging station site is a problem to be solved at present.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide a location planning method, device, equipment and computer-readable storage medium for electric vehicle charging stations, so as to solve the problem that the planning method of electric vehicle charging stations in the prior art needs to occupy a large amount of electricity to determine the optimal number of charging stations. run time issue.

In order to solve the above technical problems, the present invention provides a method for site selection and planning of electric vehicle charging stations, including: determining the number of target charging stations in a preset planning area and the initial site location of each charging station by using a preselected clustering algorithm; According to the number of target charging piles and the initial site of each charging station, the number of particles and the initial position of each particle in the linear decreasing weight particle swarm algorithm are determined respectively; using the linear decreasing weight particle swarm algorithm and the initial position of each particle. At the cost of the whole society, determine the target site of each charging station.

Preferably, the use of a preselected clustering algorithm to determine the number of target charging stations in the preset planning area and the initial site location of each charging station includes:

The K-means clustering algorithm is used to determine the number of target charging stations in the preset planning area and the initial site location of each charging station.

Preferably, the determining the number of target charging stations in the preset planning area and the initial site location of each charging station by using a K-means clustering algorithm includes:

determining the maximum number and the minimum number of charging stations that can be set in the preset planning area according to the traffic network structure in the preset planning area and the information on the charging demand points of the transportation network;

Respectively take the number of charging stations from the minimum number to the maximum number as the cluster number K value, input it into the K-means clustering algorithm, and randomly assign the positions of the K cluster center points;

Calculate the Euclidean distance from each charging demand point in the preset planning area to the K cluster center points in a loop, and classify each charging demand point into the cluster with the smallest Euclidean distance and update it The operation of the positions of the K cluster center points, until the positions of the K cluster center points no longer change;

The target number of charging stations and the initial site location of each of the charging stations are determined according to the Davidson Potting index of the number of charging stations.

Preferably, the determining of the target number of charging stations and the initial site address of each charging station according to the Davidson Potting index of the number of charging stations includes:

The number of charging stations corresponding to the smallest Davidson-Boldding index is selected as the target number of charging stations, and the initial site location of each charging station is determined.

Preferably, the determining the target site of each charging station by using the linear decreasing weight particle swarm algorithm and the whole society cost of the initial position of each particle includes:

Set the total social cost of the initial position of each particle of the linear decreasing weight particle swarm algorithm as the individual optimal fitness value of each particle, and set the minimum value of the individual optimal fitness value as the group optimal fitness value ;

Iteratively update the exploration speed of each particle, recycle the updated exploration speed to update the current position of each particle, and record the fitness value of the current position of each particle;

According to the preset judgment condition, determine whether the fitness value of the current particle in the current number of cycles is smaller than the individual optimal fitness value of the current particle, and if it is smaller than the individual optimal fitness value of the current particle is updated;

Judging whether the fitness value of each particle in the current number of cycles is less than the optimal fitness value of the group, and if it is smaller than the optimal fitness value of the group, update the optimal fitness value of the group;

Judging whether the number of times of iterative updating of the exploration speed reaches a preset number of iterations, and if the number of iterations reaches the preset number of iterations, outputting the updated individual optimal fitness value and the group optimal fitness value;

According to the individual optimal fitness value and the group optimal fitness value, the target site of each charging station and the target total social cost are determined.

The invention also provides a site selection planning device for an electric vehicle charging station, comprising:

The module for determining the number of charging stations is used to determine the number of target charging stations in the preset planning area and the initial site location of each charging station by using a preselected clustering algorithm;

A particle number determination module, configured to determine the particle number of the linear decreasing weight particle swarm algorithm and the initial position of each particle respectively according to the number of the target charging piles and the initial site location of each charging station;

A target site determination module, configured to use the linear decreasing weight particle swarm algorithm and the whole social cost of the initial position of each particle to determine the target site of each charging station.

Preferably, the module for determining the number of charging stations is specifically used for:

The K-means clustering algorithm is used to determine the number of target charging stations in the preset planning area and the initial site location of each charging station.

Preferably, the module for determining the number of charging stations includes:

a quantity range determination unit, configured to determine the maximum number and the minimum number of charging stations that can be set in the preset planning area according to the traffic network structure in the preset planning area and the information on the charging demand points of the transportation network;

The allocation unit is used to respectively use the number of charging stations from the minimum number to the maximum number as the cluster number K value, input it into the K-means clustering algorithm, and randomly assign the positions of the K cluster center points ;

A circulation unit, configured to cyclically calculate the Euclidean distance from each charging demand point in the preset planning area to the K cluster center points, and classify each charging demand point to the one with the smallest Euclidean distance from the charging demand point. The operation of updating the positions of the K cluster center points after clustering, until the positions of the K cluster center points no longer change;

A unit for determining the number of target charging stations, configured to determine the number of target charging stations and the initial site locations of each charging station according to the Davidson Burging index of the number of charging stations.

The present invention also provides a site selection planning device for an electric vehicle charging station, including:

The memory is used for storing a computer program; the processor is used for implementing the steps of the above-mentioned method for site selection and planning of an electric vehicle charging station when the computer program is executed.

The present invention also provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned method for site selection and planning of an electric vehicle charging station are implemented .

The method for site selection and planning of electric vehicle charging stations provided by the present invention only needs to preselect a clustering algorithm to quickly determine the optimal number of charging stations under the current traffic flow. However, in the prior art, the number of electric vehicle charging stations needs to be set manually, and the artificially set value does not necessarily equal the optimal number of charging stations, and in order to obtain the optimal number of charging stations, the optimization algorithm needs to be run multiple times. , which takes up a lot of runtime. The present invention uses the preselected clustering algorithm to determine the optimal number of charging stations under the traffic flow in the preset planning area, which can be used as the particle number of the linear recursive weight reduction example swarm algorithm; the determined initial station location can be used as the linear recursive reduction The initial position of each particle of the weighted example swarm algorithm. The target site of each charging station is determined by using the linear decreasing weight particle swarm algorithm and the whole social cost of the initial position of each particle. The method provided by the present invention greatly reduces the running time for determining the optimal number of charging stations. In addition, the linear decreasing weight particle swarm algorithm is used to determine the optimal location of the charging station, which solves the problem that the traditional particle swarm algorithm is prone to "premature convergence" and local optimization.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following will briefly introduce the accompanying drawings used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only For some embodiments of the present invention, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

1 is a flowchart of a first specific embodiment of a method for site selection and planning for an electric vehicle charging station provided by the present invention;

2 is a flowchart of a second specific embodiment of a method for site selection and planning for an electric vehicle charging station provided by the present invention;

3 is a flowchart of a third specific embodiment of a method for site selection and planning for an electric vehicle charging station provided by the present invention;

FIG. 4 is a structural block diagram of an apparatus for site selection and planning for an electric vehicle charging station according to an embodiment of the present invention.

Detailed ways

The core of the present invention is to provide a location planning method, device, equipment and computer-readable storage medium for electric vehicle charging stations, which utilizes a clustering algorithm to quickly determine the optimal number of charging stations under the current traffic flow, thereby improving the running speed. .

In order to make those skilled in the art better understand the solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Please refer to FIG. 1, which is a flowchart of a first specific embodiment of a method for site selection and planning for an electric vehicle charging station provided by the present invention; the specific operation steps are as follows:

Step S101: use a preselected clustering algorithm to determine the number of target charging stations in the preset planning area and the initial site location of each charging station;

Step S102: According to the number of the target charging piles and the initial site addresses of the charging stations, respectively determine the number of particles and the initial position of each particle in the linear decreasing weight particle swarm algorithm;

Step S103: Determine the target site of each charging station by using the linear decreasing weight particle swarm algorithm and the whole social cost of the initial position of each particle.

In order to solve the problem that the method of electric vehicle charging station planning in the prior art needs to take up a lot of running time to determine the optimal number of charging stations, and the traditional PSO algorithm is prone to "premature convergence" and the phenomenon of local optimization, this embodiment uses a clustering algorithm. Determine the optimal value of the number of charging stations; and combine the linear decreasing weight particle swarm algorithm to determine the optimal location of charging stations.

Based on the above-mentioned embodiment, in this embodiment, the K-means clustering algorithm is used to determine the number of target charging stations in the preset planning area and the initial site location of each charging station. Please refer to FIG. 2 , which is a flowchart of a second specific embodiment of a method for site selection and planning for an electric vehicle charging station provided by the present invention; the specific operation steps are as follows:

Step S201: Determine the maximum number and the minimum number of charging stations that can be set in the preset planning area according to the traffic network structure in the preset planning area and the information on the charging demand points of the transportation network;

The maximum number and minimum number of charging stations that can be set in the preset planning area are:

Among them, Q _total is the demand for centralized charging of electric vehicles in the planning area; are the maximum and minimum number of charging devices allowed in the charging station, respectively; S _ch is the capacity of a single charging device.

Step S202: Take the number of each charging station from the minimum number to the maximum number as the cluster number K value, input it into the K-means clustering algorithm, and randomly assign the positions of the K cluster center points;

The number between N _{ch_min} and N _{ch_max} is input cyclically as the K value of the number of clusters, and the positions of K cluster centers are randomly assigned.

Step S203: Calculate the Euclidean distance from each charging demand point in the preset planning area to the K cluster center points respectively, and classify each charging demand point into the cluster with the smallest Euclidean distance from it. The operation of updating the positions of the K cluster center points until the position of the K cluster center points no longer changes;

Calculate the Euclidean distance from each charging demand point to the cluster center point And based on the minimum distance, each charging demand point is classified into the nearest cluster; where Op is the Euclidean distance between the cluster center point x ₁ and the charging demand point x ₂ ;

Use zhongxin _K =((x _1x +x _2x +...x _ix )/i,(x _1y +x _2y +...x _iy )/i) to update the positions of the K cluster centers; where zhongxin _K is the K cluster center Class center point, x _ix is the x coordinate in the i-th data in the data set, and x _iy is the y-coordinate in the i-th data in the data set;

The above steps are performed cyclically until the positions of the K cluster center points no longer change, that is, the convergence condition is satisfied.

Step S204: Determine the target number of charging stations and the initial site location of each charging station according to the Davidson Pottinger index of the number of charging stations;

Calculate the Davidson Burging Index DBI for the respective number of charging stations:

Among them, DBI is the evaluation index of the clustering algorithm. The smaller the DBI, the better the clustering effect. and is the intra-class average distance of any two classes, and W _i and W _j are the cluster centers of the two classes.

Step S205: according to the number of the target charging piles and the initial site addresses of the charging stations, respectively determine the number of particles of the linear decreasing weight particle swarm algorithm and the initial position of each particle;

After the cycle is completed, the Davidson Burging Index DBI under the number of charging stations is obtained, and based on the Davidson Burging Index DBI, the number of charging stations K corresponding to the minimum Davidson Burging Index DBI is found, which is what we need. The optimal number of charging stations. In this process, in addition to obtaining the optimal number of charging stations K, we also obtained the initial site locations of K charging stations and the number of charging piles in each station.

Step S206: Determine the target site of each charging station and the target total social cost of the charging station by using the linear decreasing weight particle swarm algorithm and the social cost of the initial position of each particle.

In this embodiment, the K-means clustering algorithm is used to determine the number of target charging stations in the preset planning area and the initial site location of each charging station. The maximum number to the minimum number of charging stations that can be set in the preset planning area is used as the cluster center, and the clustering operation is performed until the convergence condition is satisfied. Calculate the Davidson Potting index of the number of charging stations, select the number K of charging stations corresponding to the minimum Davidson Potting index as the optimal number of charging stations, and obtain the initial site locations of K charging stations and the number of charging piles in each site. The linear decreasing weight particle swarm algorithm is used to obtain the optimal location under the optimal number of charging stations and the total cost of the whole society.

Based on the above embodiment, in this embodiment, the optimal number of charging stations K is used as the particle number of the linear decreasing weight particle swarm algorithm, and the total social cost of the initial position of the K particles is used as their respective individual optimal fitness values, The smallest one of the individual optimal fitness values is taken as the group optimal fitness value, and the linear decreasing weight particle swarm algorithm is used for iterative calculation to obtain the target site of each charging station and the target total social cost. Please refer to FIG. 3 , which is a flowchart of a third specific embodiment of the method for site selection and planning of an electric vehicle charging station provided by the present invention; the specific operation steps are as follows:

Step S301: use the K-means clustering algorithm to determine the number of target charging stations in the preset planning area and the initial site location of each charging station;

Step S302: According to the target number of charging piles and the initial site addresses of each charging station, respectively determine the number of particles and the initial position of each particle in the linear decreasing weight particle swarm algorithm;

Step S303: Set the overall social cost of the initial position of each particle of the linear decreasing weight particle swarm algorithm as the individual optimal fitness value of each particle, and set the minimum value of the individual optimal fitness value as the group's maximum fitness value. optimal fitness value;

Step S304: iteratively update the exploration speed of each particle, recycle the updated exploration speed to update the current position of each particle, and record the fitness value of the current position of each particle;

Each particle first explores the surroundings at an exploration speed v, and in the process of each iteration, the exploration speed v will be to update;

Among them, the number of iterations t, r ₁ , and r ₂ are random constants between [0, 1]; X is the position of each particle; P _i , i=1, 2, ...... K is the position of each particle Individual optimal fitness value; G _i is the group optimal fitness value.

After each particle has updated its position by the said exploration speed, the fitness value of each position, the position update function and the fitness value function are recorded.

Wherein, the position update function is

The fitness function is:

Among them, C is the total social cost, _C1i is the construction investment cost of the ith charging station (i=1, 2,...,K), C2i is the operating cost of the ith charging station, and C3i is the electric vehicle user to the ith charging station. The average annual loss cost of i charging stations on the road, K is the number of charging stations, m is the number of transformers in the charging station, F is the unit price of the transformer, a is the number of chargers in the charging station, B is the infrastructure cost of the charging station, r ₀ is the discount rate of the charging station, z is the operating years of the charging station, λ is the proportional coefficient, L is the distance from the electric vehicle user to the corresponding charging station, g is the driving distance of the electric vehicle per unit of electricity, and p is the charging electricity price of the electric vehicle.

Step S305: According to a preset judgment condition, determine whether the fitness value of the current particle in the current number of cycles is smaller than the individual optimal fitness value of the current particle, and if it is smaller than the individual optimal fitness value of the current particle is updated;

Step S306: judging whether the fitness value of each particle in the current number of cycles is smaller than the optimal fitness value of the group, and if it is smaller than the optimal fitness value of the group, update the optimal fitness value of the group;

by As a judgment condition, if the fitness value of the i-th particle at the t-th time is smaller than its individual optimal fitness value, the individual optimal fitness value is updated, otherwise it remains unchanged. If the optimal fitness value of the K particle population in the t-th iteration is smaller than the optimal fitness value of the group in the t-1-th iteration, update the optimal fitness value of the group and record the position of the K charging stations at this time, otherwise it will remain unchanged. .

Steps S304 to S306 are executed cyclically until the specified number of iterations is satisfied, and the optimal fitness value of the group is output.

Step S307: judging whether the number of times of iterative update of the exploration speed reaches a preset number of iterations, and if it reaches the preset number of iterations, outputting the updated individual optimal fitness value and the group optimal fitness value;

Step S308: Determine the target site of each charging station and the target total social cost according to the individual optimal fitness value and the group optimal fitness value.

In this embodiment, the K-means clustering algorithm can be used to quickly determine the optimal number of charging stations under the current traffic flow; it solves the problem that obtaining the optimal number of charging stations in the prior art requires multiple runs of the optimization algorithm, which takes up a lot of time. runtime issues. In this embodiment, the optimal number of charging stations in the preset planning area determined by the K-means clustering algorithm can be used as the particle number of the linear recursive weight reduction example swarm algorithm in combination with the linear recursive weight reduction example swarm algorithm. ; Determine the target site of each charging station by using the linear decreasing weight particle swarm algorithm and the total social cost of the initial position of each particle. The method provided in this embodiment greatly reduces the running time of determining the optimal number of charging stations. In addition, the linear decreasing weight particle swarm algorithm is used to determine the optimal location of the charging station, which solves the problem that the traditional particle swarm algorithm is prone to "premature convergence" and local optimization.

Please refer to FIG. 4. FIG. 4 is a structural block diagram of a site selection planning device for an electric vehicle charging station provided by an embodiment of the present invention; the specific device may include:

The number of charging stations determination module 100 is used for determining the number of target charging stations in the preset planning area and the initial site location of each charging station by using a preselected clustering algorithm;

The particle number determination module 200 is configured to determine the particle number of the linear decreasing weight particle swarm algorithm and the initial position of each particle respectively according to the target number of charging piles and the initial site location of each charging station;

The target site determination module 300 is configured to determine the target site of each charging station by using the linear decreasing weight particle swarm algorithm and the whole society cost of the initial position of each particle.

The site selection and planning device for an electric vehicle charging station in this embodiment is used to implement the foregoing method for site selection and planning for an electric vehicle charging station. Therefore, the specific implementation of the site selection and planning device for an electric vehicle charging station can be found in the aforementioned Electric Vehicle Charging The embodiment part of the site selection planning method for the station, for example, the charging station quantity determination module 100, the particle number determination module 200, and the target site location determination module 300 are respectively used to realize step S101 in the above-mentioned electric vehicle charging station site selection planning method , S102 and S103, therefore, for the specific implementation manner, reference may be made to the descriptions of the corresponding respective partial embodiments, which will not be repeated here.

A specific embodiment of the present invention also provides a location planning device for an electric vehicle charging station, including: a memory for storing a computer program; a processor for implementing the above-mentioned electric vehicle charging station when the computer program is executed. Steps of a site planning method.

A specific embodiment of the present invention also provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the above-mentioned location planning for an electric vehicle charging station is implemented steps of the method.

The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments may be referred to each other. As for the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method.

Professionals may further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two, in order to clearly illustrate the possibilities of hardware and software. Interchangeability, the above description has generally described the components and steps of each example in terms of functionality. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.

The steps of a method or algorithm described in conjunction with the embodiments disclosed herein may be directly implemented in hardware, a software module executed by a processor, or a combination of the two. A software module can be placed in random access memory (RAM), internal memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other in the technical field. in any other known form of storage medium.

The method, device, device, and computer-readable storage medium for site selection and planning for an electric vehicle charging station provided by the present invention have been described in detail above. The principles and implementations of the present invention are described herein by using specific examples, and the descriptions of the above embodiments are only used to help understand the method and the core idea of the present invention. It should be pointed out that for those skilled in the art, without departing from the principle of the present invention, several improvements and modifications can also be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

Claims (10)

1. a kind of Site planning method of electric automobile charging station characterized by comprising

The initial location of the target charging station quantity and each charging station in default planning region is determined using pre-selection clustering algorithm；

According to the initial location of the target charging pile quantity and each charging station, linear decrease weight particle is determined respectively The population of group's algorithm and each particle initial position；

Using whole society's cost of the linear decrease weight particle swarm algorithm and each particle initial position, determine described in The target site of each charging station.

2. Site planning method as described in claim 1, which is characterized in that the benefit is determined default using pre-selection clustering algorithm The initial location of target charging station quantity and each charging station in planning region includes:

Using K- means clustering algorithm determine target charging station quantity in the default planning region and each charging station just Initial station location.

3. Site planning method as claimed in claim 2, which is characterized in that described in the utilization K- means clustering algorithm determines The initial location of target charging station quantity and each charging station in default planning region includes:

According to the traffic web frame and network of communication lines charge requirement point information in the default planning region, the default planning is determined The maximum quantity and minimum number of settable charging station in region；

Respectively using each charging station quantity in the minimum number to the maximum quantity as cluster numbers K value, described in input In K- means clustering algorithm, it is randomly assigned the position of K cluster centre point；

Circulation, which executes, calculates separately in the default planning region each charge requirement point to the European of the K cluster centre point Each charge requirement point is referred to and updates the K cluster centre with rear in the smallest cluster of its Euclidean distance by distance The operation of the position of point, until the position of the K cluster centre point is no longer changed；

According to the Dai Weisenbaoding index of each charging station quantity, determines the target charging station quantity and described each fill The initial location in power station.

4. Site planning method as claimed in claim 3, which is characterized in that the wearing according to each charging station quantity Wei Senbaoding index determines that the initial location of the target charging station quantity and each charging station includes:

The corresponding charging station quantity of the smallest Dai Weisenbaoding index is selected, as the target charging station quantity, and determines institute State the initial location of each charging station.

5. Site planning method as claimed in claim 4, which is characterized in that described to utilize the linear decrease weight population Whole society's cost of algorithm and each particle initial position determines that the target site of each charging station includes:

Set described each for whole society's cost of each particle initial position of the linear decrease weight particle swarm algorithm The minimum value in the individual adaptive optimal control value is set group's adaptive optimal control value by the individual adaptive optimal control value of particle；

Iteration updates the exploration speed of each particle, recycles updated exploration speed update each particle and works as Front position, and record the adaptive value of each particle current location；

According to default decision condition, judge whether the adaptive value of current particle in current cycle time is less than the current particle Individual adaptive optimal control value updates the individual adaptive optimal control value of the current particle if being less than；

Judge whether the adaptive value of each particle described in the current cycle time is less than group's adaptive optimal control value, if small In then updating group's adaptive optimal control value；

Whether the number for judging that the exploration speed iteration updates reaches default the number of iterations, if reaching the default iteration time Number then exports the individual adaptive optimal control value and group's adaptive optimal control value for completing to update；

According to the individual adaptive optimal control value and group's adaptive optimal control value, determine each charging station target site and Target whole society totle drilling cost.

6. a kind of siteselecting planning device of electric automobile charging station characterized by comprising

Charging station quantity determining module, for determining the target charging station quantity in default planning region using pre-selection clustering algorithm With the initial location of each charging station；

Population determining module, for the initial location according to the target charging pile quantity and each charging station, respectively Determine linear decrease weight particle swarm algorithm population and each particle initial position；

Target site determining module, for utilizing the linear decrease weight particle swarm algorithm and each particle initial position Whole society's cost, determine the target site of each charging station.

7. siteselecting planning device as claimed in claim 6, which is characterized in that the charging station quantity determining module is specifically used In:

Using K- means clustering algorithm determine target charging station quantity in the default planning region and each charging station just Initial station location.

8. siteselecting planning device as claimed in claim 7, which is characterized in that the charging station quantity determining module includes:

Quantitative range determination unit, for according to the traffic web frame and network of communication lines charge requirement point in the default planning region Information determines the maximum quantity and minimum number of settable charging station in the default planning region；

Allocation unit, for respectively using each charging station quantity in the minimum number to the maximum quantity as cluster numbers K value inputs in the K- means clustering algorithm, is randomly assigned the position of K cluster centre point；

It is poly- to the K to calculate separately each charge requirement point in the default planning region for circulation execution for cycling element Each charge requirement point is referred to and updates institute with rear in the smallest cluster of its Euclidean distance by the Euclidean distance of class central point The operation of the position of K cluster centre point is stated, until the position of the K cluster centre point is no longer changed；

Target charging station quantity determination unit determines institute for the Dai Weisenbaoding index according to each charging station quantity State the initial location of target charging station quantity and each charging station.

9. a kind of siteselecting planning equipment of electric automobile charging station characterized by comprising

Memory, for storing computer program；

Processor realizes that a kind of electric car as described in any one of claim 1 to 5 fills when for executing the computer program The step of Site planning method in power station.

10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium Program realizes a kind of electric car charging as described in any one of claim 1 to 5 when the computer program is executed by processor The step of Site planning method stood.