CN111861022A - Method for optimizing electric vehicle charging station site selection based on big data analysis - Google Patents
Method for optimizing electric vehicle charging station site selection based on big data analysis Download PDFInfo
- Publication number
- CN111861022A CN111861022A CN202010736689.XA CN202010736689A CN111861022A CN 111861022 A CN111861022 A CN 111861022A CN 202010736689 A CN202010736689 A CN 202010736689A CN 111861022 A CN111861022 A CN 111861022A
- Authority
- CN
- China
- Prior art keywords
- charging station
- site selection
- charging
- cell
- decision tree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000007405 data analysis Methods 0.000 title claims abstract description 17
- 238000012360 testing method Methods 0.000 claims abstract description 41
- 238000012549 training Methods 0.000 claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 34
- 238000003066 decision tree Methods 0.000 claims abstract description 33
- 239000011159 matrix material Substances 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 230000005611 electricity Effects 0.000 claims abstract description 11
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 238000010276 construction Methods 0.000 claims description 20
- 230000002093 peripheral effect Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 238000011835 investigation Methods 0.000 claims description 4
- 230000032683 aging Effects 0.000 claims description 3
- 238000011160 research Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- CIWBSHSKHKDKBQ-JLAZNSOCSA-N Ascorbic acid Chemical compound OC[C@H](O)[C@H]1OC(=O)C(O)=C1O CIWBSHSKHKDKBQ-JLAZNSOCSA-N 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000004193 disodium 5'-ribonucleotide Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for optimizing electric vehicle charging station site selection based on big data analysis, which comprises the following steps: acquiring annual total electricity consumption data and position data of cells in an area and position data of public facilities; determining a power utilization total score weight parameter of a cell and a weight parameter of public facilities; calculating a weight parameter to form a parameter matrix X; determining a charging pile utilization rate evaluation standard to obtain a classification column vector Y; selecting a training set and a test set, and obtaining a charging station site selection rationality analysis model based on a parameter matrix X and a classification column vector Y by using a decision tree algorithm; inputting the longitude and latitude of a place of the charging station to be built into the model for rationality analysis; and outputting the report. According to the method, big data analysis is carried out by relying on the existing data, the rationality of the site selection of the charging station to be built is automatically judged by adopting a decision tree algorithm, a rationality analysis report is given, the site selection of the electric vehicle charging station is optimized, and the utilization rate of the charging station is further improved.
Description
Technical Field
The invention relates to the field of big data analysis, in particular to the technical field of new energy automobile charging pile construction site selection and electric power big data analysis, and particularly relates to a method for optimizing electric automobile charging station site selection based on big data analysis.
Background
With continuous breakthrough of modern information technologies such as 'big cloud thing moving intelligent chain' and the like, digital economy is prominent and becomes an important driving force for the development of the economic society of China. In early 3 months of 2020, the work deployment for accelerating the construction of novel infrastructures (called new infrastructure for short) is made by the center from the major bureau of promoting epidemic prevention and control and economic and social development, wherein the construction of the new energy automobile charging pile belongs to one of the key fields of the new infrastructure. According to the principle of moderate advance, a charging infrastructure service network system which takes self/special charging infrastructures configured at parking lots of special vehicles such as residential areas, unit internal parking lots, buses, environmental sanitation, logistics, postal service and the like as a main body, public charging infrastructures configured at parking lots, social public parking lots and in-road temporary parking places configured at urban public buildings as an auxiliary, urban quick charging stations, battery exchange stations and inter-city quick charging stations of expressway service areas which occupy independent areas as supplements and intelligent charging service platforms as supports and can meet the popularization and application requirements of new energy vehicles is established.
Under the background, the national grid company vigorously carries out the construction of electric vehicle charging stations (piles) in the national range, and the investment can be reduced as far as possible under the condition of meeting the charging requirements by reasonably planning the construction and site selection of the charging stations. According to the current situation investigation of the charging station site selection planning method, the current charging station site selection planning main means is to conduct some simple data statistical analysis by taking the electric vehicle traffic density of each region as guidance, and conduct planning according to local conditions. However, the utilization rate of the electric vehicle charging pile has many influencing factors, including peripheral facility distribution, peripheral population distribution, electric vehicle occupancy distribution, traffic conditions and the like, and the traditional site selection means has large limitation, so that the problem of insufficient utilization rate of part of charging stations after construction can be caused. Taking an urban area as an example, fig. 1 is a histogram of the total charge amount of non-public transportation charging stations in 2019 years in the area range of the urban area. As can be seen from fig. 1, about 60% of the charging stations have an annual charge of less than 10000 kw hours, and even nearly 50 charging stations have an annual charge of less than 5000 kw hours. The utilization rate of the charging stations is low, the construction investment return is insufficient, a more effective method is needed to assist in developing the site selection of the charging stations, and the goal that the newly-built charging stations have higher utilization rate is achieved.
At present, in the aspect of site selection planning of electric vehicle charging stations, some research has been carried out at home and abroad, and most of the research is around optimizing a charging station site selection model with the aim of maximum economic benefit or minimum construction cost, and partial progress is made. Zeng W et al propose that it is possible to increase the charging station utilization and reduce user waiting time by reasonably allocating users to different charging stations in consideration of the travel distance from the user to the charging station and congestion in the charging station. Hodgson et al propose that the location of the charging station may take into account that the charging station maximizes the number of roads surrounding the service. The invention discloses an electric taxi charging pile site selection method based on big data (patent application number 201711224096. X). The method is based on the big data. The invention patent of a charging pile site selection method and a charging pile site selection device (patent application number 201811467691.0): the method comprises the steps of dividing a map of a charging pile area to be laid into a plurality of grids, counting parking lots corresponding to the grids, counting traffic demand of the grids according to a pre-collected vehicle position data set, and selecting a corresponding number of parking lots from the parking lots as addresses for laying the charging piles according to attribute information of the parking lots, the traffic demand of the grids and the total number of the charging piles to be laid. The invention discloses a charging pile optimization layout method based on real driving data of electric automobiles (patent application number 201810048662.4), which analyzes real driving data of all electric automobiles by using a big data analysis method, screens out parking distribution of the electric automobiles, sets a time threshold, screens out a place with parking time exceeding the threshold from the parking distribution, fits the place with parking time exceeding the threshold as a candidate position for building a charging pile, and obtains a global optimal solution, namely an optimized layout scheme of the charging pile by using a meta-heuristic algorithm with the number of positions of the charging pile which are actually required to be built and the rated driving mileage of the electric automobiles as constraints.
Through comparison of the research, it can be found that most of the existing methods for site selection planning of electric vehicle charging stations need a large amount of real-time position data of electric vehicles, and as a construction department of the charging stations, the method cannot master the real-time position data of the electric vehicles in cities, and cannot master the data conveniently and quickly for any public organization in practice, so that the research methods are in many theoretical levels and are not suitable in practice.
Further analyzing the above problem, the main construction units of charging stations in cities are the respective electric power companies. An electric power company has a sufficient amount of data such as the position information of an existing charging station, the amount of charge, and the power consumption of a surrounding community at present, and it is easy to acquire the distribution data of surrounding public facilities based on the charging station position information. Therefore, the electric power company needs to invent a method for optimizing electric vehicle charging station site selection based on peripheral community power consumption and public facility distribution big data analysis on the basis of the existing charging pile information.
Disclosure of Invention
The invention aims to make up the defects of the prior art, provides a method for optimizing the site selection of an electric vehicle charging station based on big data analysis, and aims to perform big data analysis by depending on the data of the existing charging station, the site selection position of the charging station to be built, the energy consumption data of the surrounding communities of the charging station to be built and the public facility distribution data, automatically judge the rationality of the site selection of the charging station to be built by adopting a decision tree algorithm, give a rationality analysis report, optimize the site selection of the electric vehicle charging station and further improve the utilization rate of the charging station.
In order to solve the technical problems, the invention adopts the following technical scheme:
a method for optimizing electric vehicle charging station site selection based on big data analysis comprises the following steps:
and S1, acquiring annual total electricity consumption data and position data of all cells in a preset range around each existing charging station in the area and position data of all public facilities.
And S2, determining the total electricity consumption weight parameter of the cell and the weight parameter of the public facility by taking the annual total electricity consumption of the cell, the distance value between the cell and the existing charging station and the distance value between the public facility and the existing charging station as key influence factors.
And S3, calculating the total power consumption weight parameters of the cells corresponding to all the existing charging stations in the area and the weight parameters of the public facilities, and classifying and sorting to form a parameter matrix X.
And S4, determining the evaluation standard of the charging pile utilization rate, and using whether the charging station with the high utilization rate is used as the classification column vector Y of all the existing charging stations in the area.
S5, randomly and uniformly selecting part of the existing charging stations in the area as a training set, and using the rest of the existing charging stations as a test set; based on the parameter matrix X and the classification column vector Y, a decision tree algorithm training model is adopted on a training set, the model effect is verified on a test set, the decision tree algorithm parameters are repeatedly adjusted, the optimal parameters and the model are trained, the final decision tree is obtained, and the final decision tree is used as a charging station site selection rationality analysis model.
And S6, determining the longitude and latitude of the place of the charging station to be built, inputting the longitude and latitude into a charging station site selection rationality analysis model, and performing rationality analysis.
And S7, outputting a report of rationality analysis of site selection of the charging station to be built.
Further, in step S1, the specific process of acquiring data is as follows: taking the position of the existing charging station as a central point, calling a Goodpasts map open API through a requests library of python, acquiring the annual total power consumption of each cell in a first preset range around the central point and the distance value between each cell and the central point, and acquiring the distance value between each public facility and the central point in a second preset range around the central point.
Further, the first preset range is 4000 meters, and the second preset range is 3000 meters.
Further, in step S2, the calculation formula of the total power consumption weighting parameter of the cell is as follows:
wherein W is the annual total electricity consumption of the cell, D1Is the distance value between the cell and the center point, D2The value is 4000 m.
The weight parameter calculation formula of the public facility is as follows:
wherein D is3As a value of the distance between the public facility and the central point, D4The value is 600 m.
Further, in step S3, the parameter matrix X is formed as follows: calculating the total power consumption weight parameters of all cells in a first preset range and accumulating the total power consumption weight parameters to form total cell weight parameters, calculating the weight parameters of all public facilities in a second preset range, and accumulating the weight parameters of all public facilities in the same public building to form the weight parameters of the public building; and drawing the total cell weight parameters corresponding to all the existing charging stations in the area, the weight parameters of all public buildings and the weight parameters of all the independently existing public facilities into a parameter matrix X.
Further, in step S4, an existing charging station with an annual charge amount greater than 10000 kwh is defined as a high-utilization charging station, and if the existing charging station is a high-utilization charging station, the classification list vector is counted as 1, otherwise, it is counted as 0.
Further, in step S5, the concrete process of establishing the charging station address rationality analysis model is as follows: randomly and uniformly selecting 40% of the existing charging stations in the area as a training set, and using the rest 60% of the existing charging stations as a testing set; according to the training set and the test set, dividing the parameter matrix X into a training set parameter matrix X1 and a test set parameter matrix X2, and dividing the classification column vector Y into a training set classification column vector Y1 and a test set actual classification column vector Y3; inputting a training set parameter matrix X1 and a training set classification column vector Y1 into a decision tree algorithm, training a model by adopting the decision tree algorithm, verifying the model effect on a test set, inputting a test set parameter matrix X2 to obtain a test set prediction column vector Y2, judging the rationality of the decision tree algorithm by adopting a classification judgment standard based on the comparison between the test set prediction column vector Y2 and a test set actual value Y3, repeatedly adjusting the parameters of the decision tree algorithm, training optimal parameters and a model to obtain a final decision tree, and taking the final decision tree as a charging station site selection rationality analysis model.
Further, the classification judgment standard comprises an ROC curve, precision ratio and recall ratio.
Further, in step S6, the specific process of determining the longitude and latitude of the location of the charging station to be built is as follows: preliminarily determining an address selection range: according to the distribution condition of the existing charging stations in the area, the weak area is covered by combining the charging network distribution according to the charging requirements in the area, the construction area of the charging stations to be built is preliminarily determined, each charging station is ensured to have a reasonable service range or density, reasonable contact is kept between the adjacent charging stations, and balanced layout is realized on the whole; considering the practical factors of the service life aging of the battery and traffic jam, and starting from the aspect of ensuring the continuous running of the electric automobile user, the service radius of the charging station is calculated by the running mileage of the electric automobile charged once being 100 kilometers; site selection and fixed point selection: and in the preliminarily determined site selection range, comprehensively considering the principle of land intensification and peripheral public facilities for power supply, traffic and fire control according to local conditions, determining the specific site of the charging station to be built by combining region construction planning and road network planning, and acquiring the longitude and latitude of the specific site.
Further, in step S6, the concrete procedure of the rationality analysis is as follows: inputting the longitude and latitude of a place of a charging station to be built into a charging station site selection rationality analysis model; directly determining the position of a charging station to be built for a reasonable site selection place; and searching possible charging station positions within 200 meters around the unreasonable site selection location for the unreasonable site selection location, inputting the longitude and latitude coordinates into a charging station site selection reasonableness analysis model in a continuous iteration mode to obtain a plurality of reasonable positions, performing targeted field investigation and comprehensive judgment on the reasonable positions, and determining the suggested and modified positions of the charging stations to be built.
Compared with the prior art, the method has the obvious effect that the rationality of the site selection of the charging station to be established can be judged by performing big data analysis according to the existing data of the charging station, such as the position information, the charging amount and the like of the power company and combining the data of peripheral public facilities. The invention prejudges the rationality of the charging station site selection on the basis of only manually judging the site selection position of the charging station conventionally, solves the problem of low utilization rate of the charging station and provides scientific basis for the site selection of the charging station. Based on this, the present invention mainly has the following advantages.
1. Provides a site selection basis for the construction department of the charging pile, and is consistent with the strategic location of the national 'new capital construction'.
2. The charging station is built at a proper place to bring convenience for the owner of the new energy automobile to charge.
3. The utilization rate of the charging stations is improved, the number of the charging stations which are required to be built and meet the charging requirements of the new energy vehicles within a certain range is reduced, and the construction cost of the charging stations is saved.
Tests prove that the method has the analysis accuracy rate of over 70 percent.
Drawings
In order that the advantages of the invention will be readily understood, a more particular description of the invention briefly described above will be rendered by reference to specific embodiments that are illustrated in the appended drawings. Understanding that these drawings depict only typical embodiments of the invention and are not therefore to be considered to be limiting of its scope, the invention will be described and explained with additional specificity and detail through the use of the accompanying drawings.
FIG. 1 is a histogram of the total charge of non-public transportation charging stations throughout the year 2019 in a certain urban area;
FIG. 2 is a ROC curve for the optimal parameters and model of the present invention;
fig. 3 is a final decision tree in the present invention.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art, that embodiments of the invention may be practiced without one or more of these specific details. In other instances, well-known features have not been described in detail so as not to obscure the embodiments of the invention.
In the following description, a detailed structure will be presented for a thorough understanding of embodiments of the invention. It is apparent that the implementation of the embodiments of the present invention is not limited to the specific details familiar to those skilled in the art. The following detailed description of preferred embodiments of the invention, however, the invention is capable of other embodiments in addition to those detailed.
In order to explain the method for optimizing the site selection of the electric vehicle charging station based on big data analysis disclosed by the invention in detail, the following description is further provided with the accompanying drawings and a specific application example of a certain urban area.
And step 1, acquiring related data.
(1) Charging data of 104 existing charging stations 2019 in a certain urban area are obtained, wherein part of the data is shown in table 1.
TABLE 1 charging data table of 2019 charging stations in urban area
| Station name | Number of piles | Year of construction | Charge (kw/h) | Number of charges | Charging amount (Yuan) |
| XX district A charging station in district XX city | 10 | 2018 | 191748.99 | 4412 | 321233.76 |
| XX urban district XX district B charging station | 10 | 2018 | 127184.39 | 7644 | 213037.84 |
| XX urban district XX district C charging station | 10 | 2015 | 106912.17 | 6385 | 179093.32 |
| XX urban area XX district D charging station | 10 | 2016 | 97385.89 | 8056 | 163130.39 |
| XX downtown XX district E charging station | 12 | 2016 | 92349.48 | 6462 | 154662.55 |
| XX downtown XX district F charging station | 7 | 2017 | 83744.46 | 5577 | 140248.29 |
| XX downtown XX district G charging station | 25 | 2018 | 83393.54 | 5900 | 139707.79 |
| XX urban area XXDistrict H charging station | 8 | 2011 | 78147.27 | 6939 | 130912.68 |
| XX urban district XX district I charging station | 3 | 2011 | 72318.36 | 1443 | 121147.66 |
| XX urban district XX district J charging station | 10 | 2016 | 67375.72 | 5369 | 112862.82 |
| XX district K charging station in city district XX | 42 | 2017 | 66810.76 | 3469 | 111921.85 |
| XX downtown XX district L charging station | 6 | 2016 | 65595.88 | 4475 | 109763.94 |
| XX district M charging station in district XX city | 18 | 2011 | 54588.51 | 4200 | 91435.91 |
| XX urban district XX district N charging station | 20 | 2017 | 51970.06 | 4021 | 87054.49 |
| XX urban area XX district O charging station | 20 | 2018 | 48420.92 | 3653 | 81104.23 |
| XX urban district XX district P charging station | 6 | 2016 | 47251.47 | 3238 | 79153.02 |
| XX urban district XX district Q charging station | 6 | 2016 | 47229.96 | 4018 | 79117.55 |
| XX urban district XX district R charging station | 10 | 2016 | 46762.88 | 4155 | 78326.04 |
| XX urban area XX district S charging station | 8 | 2015 | 39724.14 | 3015 | 66541.14 |
(2) And acquiring longitude and latitude information of the geographic position of the existing charging station in a certain urban area.
(3) Annual power consumption data (annual total power consumption) of each cell in a certain urban area are obtained, and part of the data is shown in table 2.
TABLE 2 annual electricity consumption data table for some subdistricts in a certain urban area
| Name of cell | Number of households | 2019 electric power consumption (kilowatt hour) |
| Cell A | 192 | 1601667 |
| Cell B | 705 | 2992249 |
| Cell C | 757 | 1256756 |
| Cell D | 1701 | 3762010 |
| Cell E | 635 | 1721007 |
| Cell F | 172 | 261536 |
| Cell G | 1531 | 3200789 |
| Cell H | 164 | 2049277 |
| Cell I | 1266 | 2275741 |
| Cell J | 210 | 1069092 |
| Cell K | 715 | 1773059 |
| Cell L | 967 | 1717048 |
| Cell M | 586 | 1725189 |
| Cell N | 1163 | 2458914 |
| Cell O | 751 | 2494074 |
| Cell P | 3317 | 5627131 |
| Cell Q | 2079 | 2378966 |
| Cell R | 3460 | 7870599 |
| Cell S | 2453 | 6139727 |
| Cell T | 1323 | 3092797 |
(4) The position of each existing charging station is taken as a central point, a Goodpasts open API is called through a requests library of python, the distribution condition of cells and the distance value from the cells to the central point within the range of 4000 meters around the central point are obtained, the type of public facilities and the distance value from the public facilities (including the cells) to the central point within the range of 3000 meters around the central point are obtained, and part of data are shown in Table 3. Wherein cells and utilities around 93 existing charging stations can be obtained.
TABLE 3 summary of the types and distances of the public facilities around the existing charging stations in a certain urban area
And 2, establishing a site selection rationality analysis model of the charging station in a certain urban area.
(1) And (4) determining a weight parameter based on the peripheral cell and public facility data acquired in the step (1).
The method comprises the following steps of taking the total power consumption score of a peripheral cell and the type of peripheral public facilities as classification fields, respectively taking the annual total power consumption of the cell, the distance value between the cell and the existing charging station and the distance value between the public facilities and the existing charging station as key influence factors, determining the total power consumption score weight parameter of the cell and the weight parameter of the public facilities, and adopting the following calculation formulas:
wherein W is the annual total electricity consumption of the cell, D1Is the distance value between the cell and the center point, D2The value is 4000 m;
wherein D is3As a value of the distance between the public facility and the central point, D4The value is 600 m.
(2) And calculating the parameters of each label according to the weight parameter calculation formula, and forming a parameter matrix X.
The parameter matrix X is formed as follows: aiming at an existing charging station, calculating the total power consumption weight parameters of all cells within 4000 meters around the charging station, accumulating to form total cell weight parameters, calculating the weight parameters of all public facilities within 3000 meters around the charging station, and accumulating the weight parameters of all public facilities in the same public building to form the weight parameters of the public building; calculating total cell weight parameters corresponding to all the existing charging stations in a certain urban area, weight parameters of public buildings and weight parameters of public facilities which independently exist; and (3) taking the name or type of each public building, the name or type of each independently existing public facility, the total cell and the like as transverse tags, representing all the existing charging stations in the area by using numerical numbers and taking the numerical numbers as longitudinal tags, and drawing together to form a parameter matrix X, wherein part of data is shown in a table 4.
Table 4 parameter matrix X part data table
(3) Determining a charging pile utilization rate evaluation standard, wherein the standard is related to the number of charging stations in each region and the actual new energy automobile possession, and the existing charging stations with annual charge amount larger than 10000 kilowatt hours are defined as high-utilization charging stations; and taking whether the charging stations with high utilization rate are used as the classified column vector Y of all the existing charging stations in the area, wherein if the existing charging stations are the charging stations with high utilization rate, the classified column vector is 1, and if not, the classified column vector is 0. Wherein part of the data of the classification column vector Y is shown in table 5.
TABLE 5 Classification column vector Y section data sheet
(4) Randomly and uniformly selecting 37 charging stations (accounting for 40 percent of the total number) in a certain urban area as a training set, and selecting 56 charging stations (accounting for 60 percent of the total number) as a testing set. According to the training set and the test set, the parameter matrix X is divided into a training set parameter matrix X1 and a test set parameter matrix X2, and the classification column vector Y is divided into a training set classification column vector Y1 and a test set actual classification column vector Y3. Wherein, part of the data of the training set parameter matrix X1 and the training set classification column vector Y1 are shown in Table 6; part of the data for the test set parameter matrix X2 is shown in table 7.
TABLE 6 partial data summary of training set parameter matrix X1 and training set classification column vector Y1
Table 7 partial data table for test set parameter matrix X2
Inputting a training set parameter matrix X1 and a training set classification column vector Y1 into a decision tree algorithm, training a model by adopting the decision tree algorithm, verifying the model effect on a test set, inputting a test set parameter matrix X2 to obtain a test set prediction column vector Y2, judging the rationality of the decision tree algorithm by adopting classification judgment standards such as ROC curve, precision ratio and recall ratio and repeatedly adjusting the decision tree algorithm parameters (including the kernel of the decision tree algorithm, the maximum depth of the decision tree and the like) based on the comparison between the test set prediction column vector Y2 and the actual value Y3 of the test set (shown in Table 8), obtaining the optimal parameters and the model, obtaining a final decision tree, and taking the final decision tree as a charging station address selection rationality analysis model as shown in figure 3.
TABLE 8 partial data comparison Table of test set predicted column vector Y2 and test set actual value Y3
| Charging station number | Test set prediction value Y2 | True value of test set Y3 |
| 3 | 1 | 1 |
| 5 | 0 | 1 |
| 6 | 1 | 1 |
| 7 | 1 | 1 |
| 9 | 1 | 1 |
| 11 | 1 | 1 |
| 12 | 1 | 1 |
| 13 | 0 | 1 |
| 14 | 1 | 1 |
| 16 | 0 | 1 |
| 17 | 1 | 1 |
| 18 | 1 | 1 |
| 20 | 1 | 1 |
In this example, the ROC curve of the optimal parameters and model is shown in fig. 2, and it can be seen from this curve that the corner point a closest to the upper left is the optimal critical point, and the value at this point is the optimal critical value, because the sensitivity and specificity at this point are both high, and the number of false positives and false negatives is minimal; the accuracy of the test set in the model verification is shown in table 9, and it can be seen that the accuracy of the reasonable point locations and the unreasonable point locations judged according to the charging station site selection rationality analysis model is about 70%, and the charging station (pile) site selection rationality analysis work can be assisted.
Table 9 summary of accuracy of test set in model verification
| Charging station utilization classification | Precision ratio | Recall ratio of | F1 score | Number of |
| 0 | 0.76 | 0.74 | 0.75 | 35 |
| 1 | 0.59 | 0.62 | 0.6 | 21 |
And step 3, determining a place of the charging station to be built.
(1) Preliminarily determining an address selection range: according to the distribution situation of the existing charging stations in a certain urban area, the weak area is covered by combining the charging demand distribution charging network in the area, the construction area of the charging stations to be built is preliminarily determined, each charging station is guaranteed to have a reasonable service range or density, reasonable connection is kept between the adjacent charging stations, and balanced layout is achieved on the whole. Considering the practical factors of the service life aging of the battery, traffic jam and the like, and starting from the aspect of ensuring the continuous running of the electric automobile user, the service radius of the charging station is calculated by the running mileage of the electric automobile charged once being 100 kilometers.
(2) Site selection and fixed point selection: in the preliminarily determined site selection range, the land intensification principle and peripheral public facilities such as power supply, traffic, fire fighting and the like are comprehensively considered according to local conditions, and the specific sites of a plurality of charging stations to be built are determined by combining region construction planning and road network planning, wherein the specific sites of 9 charging stations to be built are selected in the example.
And 4, carrying out rationality analysis on the site of the charging station to be built.
(1) And determining the longitude and latitude of the specific place of the charging station to be built.
(2) And inputting the longitude and latitude of the specific place of the charging station to be built into a charging station site selection rationality analysis model.
(3) The charging station site selection rationality analysis model outputs analysis results, and the rationality of the site selection of the charging station to be established is determined, as shown in table 10. Wherein, the recommended value of 1 indicates that the address selection of the charging station to be built is reasonable, and the address selection of 2 charging stations to be built in the table 10 meets the condition; a recommended value of 0 indicates that the address selection of the charging station to be built is not reasonable, and the address selection of 7 charging stations to be built in table 10 conforms to the situation.
Table 10 summary table of rationality of site selection for charging station to be built
(4) And aiming at 7 unreasonable site locations, searching possible charging station positions to be built in a unit of 200 meters, inputting longitude and latitude coordinates into a charging station site selection rationality analysis model in a continuous iteration mode to obtain a plurality of reasonable positions, performing targeted field investigation and comprehensive judgment on the reasonable positions, and determining the suggested and modified charging station positions to be built.
(5) And giving a charging station site selection rationality analysis report on the basis of the result.
The method for optimizing the site selection of the electric vehicle charging station based on the big data analysis provided by the invention is characterized in that the big data analysis is carried out by depending on the data of the existing charging station, the site selection position of the charging station to be built, the energy consumption data of the surrounding communities of the charging station to be built and the public facility distribution data, the rationality of the site selection of the charging station to be built is automatically judged by adopting a decision tree algorithm, a rationality analysis report is given, the site selection of the electric vehicle charging station is optimized, and the utilization rate of the charging station is further improved.
In summary, the present invention is not limited to the above-mentioned embodiments, and those skilled in the art can propose other embodiments within the technical teaching of the present invention, but these embodiments are included in the scope of the present invention.
Claims (10)
1. A method for optimizing electric vehicle charging station site selection based on big data analysis is characterized by comprising the following steps:
s1, acquiring annual total electricity consumption data and position data of all cells in a preset range around each existing charging station in an area and position data of all public facilities;
s2, determining the total electricity consumption weight parameter of the cell and the weight parameter of the public facility by taking the annual total electricity consumption of the cell, the distance value between the cell and the existing charging station and the distance value between the public facility and the existing charging station as key influence factors;
s3, calculating the total power consumption weight parameters of the cells corresponding to all the existing charging stations in the area and the weight parameters of the public facilities, and forming a parameter matrix X after classification and arrangement;
s4, determining the evaluation standard of the charging pile utilization rate, and taking whether the charging station with high utilization rate is used as a classified column vector Y of all the existing charging stations in the area;
s5, randomly and uniformly selecting part of the existing charging stations in the area as a training set, and using the rest of the existing charging stations as a test set; based on the parameter matrix X and the classification column vector Y, training a model on a training set by adopting a decision tree algorithm, verifying the model effect on a test set, repeatedly adjusting the decision tree algorithm parameters, training optimal parameters and a model to obtain a final decision tree, and taking the final decision tree as a charging station site selection rationality analysis model;
s6, determining the longitude and latitude of the place of the charging station to be built, inputting the longitude and latitude into a charging station site selection rationality analysis model, and performing rationality analysis;
and S7, outputting a report of rationality analysis of site selection of the charging station to be built.
2. The method according to claim 1, wherein in step S1, the specific process of acquiring data is as follows: taking the position of the existing charging station as a central point, calling a Goodpasts map open API through a requests library of python, acquiring the annual total power consumption of each cell in a first preset range around the central point and the distance value between each cell and the central point, and acquiring the distance value between each public facility and the central point in a second preset range around the central point.
3. The method according to claim 2, characterized in that said first predetermined range is 4000 meters and said second predetermined range is 3000 meters.
4. The method according to claim 3, wherein in step S2, the calculation formula of the total power consumption weighting parameter of the cell is as follows:
wherein W is the annual total electricity consumption of the cell, D1Is the distance value between the cell and the center point, D2The value is 4000 m;
the weight parameter calculation formula of the public facility is as follows:
wherein D is3As a value of the distance between the public facility and the central point, D4The value is 600 m.
5. The method according to claim 4, wherein in step S3, the parameter matrix X is formed as follows:
calculating the total power consumption weight parameters of all cells in a first preset range and accumulating the total power consumption weight parameters to form total cell weight parameters, calculating the weight parameters of all public facilities in a second preset range, and accumulating the weight parameters of all public facilities in the same public building to form the weight parameters of the public building;
and drawing the total cell weight parameters corresponding to all the existing charging stations in the area, the weight parameters of all public buildings and the weight parameters of all the independently existing public facilities into a parameter matrix X.
6. The method of claim 5, wherein in step S4, the existing charging stations with an annual charge greater than 10000 kW are defined as high-utilization charging stations, and the classification column vector is 1 if the existing charging stations are high-utilization charging stations, otherwise, the classification column vector is 0.
7. The method according to claim 6, wherein in step S5, the concrete process of establishing the charging station siting rationality analysis model is as follows:
randomly and uniformly selecting 40% of the existing charging stations in the area as a training set, and using the rest 60% of the existing charging stations as a testing set; according to the training set and the test set, dividing the parameter matrix X into a training set parameter matrix X1 and a test set parameter matrix X2, and dividing the classification column vector Y into a training set classification column vector Y1 and a test set actual classification column vector Y3;
inputting a training set parameter matrix X1 and a training set classification column vector Y1 into a decision tree algorithm, training a model by adopting the decision tree algorithm, verifying the model effect on a test set, inputting a test set parameter matrix X2 to obtain a test set prediction column vector Y2, judging the rationality of the decision tree algorithm by adopting a classification judgment standard based on the comparison between the test set prediction column vector Y2 and a test set actual value Y3, repeatedly adjusting the parameters of the decision tree algorithm, training optimal parameters and a model to obtain a final decision tree, and taking the final decision tree as a charging station site selection rationality analysis model.
8. The method of claim 7, wherein the classification criteria comprises a ROC curve, precision, recall.
9. The method according to claim 8, wherein in step S6, the specific process of determining the longitude and latitude of the charging station location to be established is as follows:
preliminarily determining an address selection range: according to the distribution condition of the existing charging stations in the area, the weak area is covered by combining the charging network distribution according to the charging requirements in the area, the construction area of the charging stations to be built is preliminarily determined, each charging station is ensured to have a reasonable service range or density, reasonable contact is kept between the adjacent charging stations, and balanced layout is realized on the whole; considering the practical factors of the service life aging of the battery and traffic jam, and starting from the aspect of ensuring the continuous running of the electric automobile user, the service radius of the charging station is calculated by the running mileage of the electric automobile charged once being 100 kilometers;
site selection and fixed point selection: and in the preliminarily determined site selection range, comprehensively considering the principle of land intensification and peripheral public facilities for power supply, traffic and fire control according to local conditions, determining the specific site of the charging station to be built by combining region construction planning and road network planning, and acquiring the longitude and latitude of the specific site.
10. The method according to claim 9, wherein in step S6, the rationality analysis is performed as follows:
inputting the longitude and latitude of a place of a charging station to be built into a charging station site selection rationality analysis model;
directly determining the position of a charging station to be built for a reasonable site selection place;
and searching possible charging station positions within 200 meters around the unreasonable site selection location for the unreasonable site selection location, inputting the longitude and latitude coordinates into a charging station site selection reasonableness analysis model in a continuous iteration mode to obtain a plurality of reasonable positions, performing targeted field investigation and comprehensive judgment on the reasonable positions, and determining the suggested and modified positions of the charging stations to be built.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010736689.XA CN111861022B (en) | 2020-07-28 | 2020-07-28 | Method for optimizing electric vehicle charging station site selection based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010736689.XA CN111861022B (en) | 2020-07-28 | 2020-07-28 | Method for optimizing electric vehicle charging station site selection based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111861022A true CN111861022A (en) | 2020-10-30 |
| CN111861022B CN111861022B (en) | 2022-05-13 |
Family
ID=72948755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010736689.XA Active CN111861022B (en) | 2020-07-28 | 2020-07-28 | Method for optimizing electric vehicle charging station site selection based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111861022B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112686468A (en) * | 2021-01-14 | 2021-04-20 | 浙江工商大学 | Public facility stability optimization method |
| CN113139150A (en) * | 2021-04-02 | 2021-07-20 | 清华大学深圳国际研究生院 | Method for improving layout of electric vehicle charging facilities and computer readable storage medium |
| CN113609209A (en) * | 2021-08-12 | 2021-11-05 | 上海氢枫能源技术有限公司 | System and method for building station area and scale of hydrogen station |
| CN113822497A (en) * | 2021-10-27 | 2021-12-21 | 深圳市数字城市工程研究中心 | Method for selecting addresses in garbage land deployment |
| CN114862018A (en) * | 2022-05-05 | 2022-08-05 | 南京理工大学 | Electric vehicle charging station site selection and constant volume planning method considering charging travel distance |
| CN115271268A (en) * | 2022-09-27 | 2022-11-01 | 国网浙江省电力有限公司宁波供电公司 | Electric vehicle charging station site selection planning method and device and terminal equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180240047A1 (en) * | 2015-08-19 | 2018-08-23 | Tianjin University | Planning method of electric vehicle fast charging stations on the expressway |
| CN109711630A (en) * | 2018-12-28 | 2019-05-03 | 郑州大学 | A kind of electric car fast charge station addressing constant volume method based on trip probability matrix |
| CN110288212A (en) * | 2019-06-14 | 2019-09-27 | 石家庄铁道大学 | Electric taxi based on improved MOPSO creates charging station site selecting method |
-
2020
- 2020-07-28 CN CN202010736689.XA patent/CN111861022B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180240047A1 (en) * | 2015-08-19 | 2018-08-23 | Tianjin University | Planning method of electric vehicle fast charging stations on the expressway |
| CN109711630A (en) * | 2018-12-28 | 2019-05-03 | 郑州大学 | A kind of electric car fast charge station addressing constant volume method based on trip probability matrix |
| CN110288212A (en) * | 2019-06-14 | 2019-09-27 | 石家庄铁道大学 | Electric taxi based on improved MOPSO creates charging station site selecting method |
Non-Patent Citations (2)
| Title |
|---|
| 王萌等: "电动汽车充电站选址决策与评价研究", 《物流技术》 * |
| 田贺平等: "基于使用效率的充电设施选址评价方法研究", 《电工电能新技术》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112686468A (en) * | 2021-01-14 | 2021-04-20 | 浙江工商大学 | Public facility stability optimization method |
| CN112686468B (en) * | 2021-01-14 | 2023-05-26 | 浙江工商大学 | Public facility stability optimization method |
| CN113139150A (en) * | 2021-04-02 | 2021-07-20 | 清华大学深圳国际研究生院 | Method for improving layout of electric vehicle charging facilities and computer readable storage medium |
| CN113139150B (en) * | 2021-04-02 | 2022-11-08 | 清华大学深圳国际研究生院 | Method for improving layout of electric vehicle charging facilities and computer readable storage medium |
| CN113609209A (en) * | 2021-08-12 | 2021-11-05 | 上海氢枫能源技术有限公司 | System and method for building station area and scale of hydrogen station |
| CN113609209B (en) * | 2021-08-12 | 2024-02-20 | 上海氢枫能源技术有限公司 | System and method for judging building area and scale of hydrogen adding station |
| CN113822497A (en) * | 2021-10-27 | 2021-12-21 | 深圳市数字城市工程研究中心 | Method for selecting addresses in garbage land deployment |
| CN114862018A (en) * | 2022-05-05 | 2022-08-05 | 南京理工大学 | Electric vehicle charging station site selection and constant volume planning method considering charging travel distance |
| CN114862018B (en) * | 2022-05-05 | 2023-08-04 | 南京理工大学 | Electric vehicle charging station site selection and constant volume planning method considering charging driving distance |
| CN115271268A (en) * | 2022-09-27 | 2022-11-01 | 国网浙江省电力有限公司宁波供电公司 | Electric vehicle charging station site selection planning method and device and terminal equipment |
| CN115271268B (en) * | 2022-09-27 | 2023-01-13 | 国网浙江省电力有限公司宁波供电公司 | Electric vehicle charging station site selection planning method and device and terminal equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111861022B (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111861022B (en) | Method for optimizing electric vehicle charging station site selection based on big data analysis | |
| Yi et al. | Research on the spatial-temporal distribution of electric vehicle charging load demand: A case study in China | |
| Csonka et al. | Determination of charging infrastructure location for electric vehicles | |
| CN110288212B (en) | Improved MOPSO-based electric taxi newly-built charging station site selection method | |
| CN109711630A (en) | A kind of electric car fast charge station addressing constant volume method based on trip probability matrix | |
| CN114297809A (en) | Electric vehicle charging station site selection and volume fixing method | |
| CN110674975B (en) | Spatial layout method and device for reducing carbon emission in urban planning | |
| Qu et al. | Location optimization for urban taxi stands based on taxi GPS trajectory big data | |
| Morro-Mello et al. | Fast charging stations placement methodology for electric taxis in urban zones | |
| CN114418300B (en) | Multi-type electric vehicle charging facility planning method based on urban functional partitions and resident trip big data | |
| CN112036757A (en) | Parking transfer parking lot site selection method based on mobile phone signaling and floating car data | |
| CN117035185A (en) | Electric vehicle charging station layout optimization method and system based on dynamic charging demand | |
| CN114819633A (en) | Traffic facility layout evaluation method applied to homeland space planning | |
| Cai et al. | Evaluation of external costs in road transport under the openness of a gated community | |
| Li et al. | The effects of low-carbon city construction on bus trips | |
| Tsigdinos et al. | Transit Oriented Development (TOD). Challenges and Perspectives; The Case of Athens’ Metro Line 4 | |
| CN111429166A (en) | Electric vehicle charging demand spatial distribution prediction method based on maximum contour clustering | |
| CN115345351A (en) | Electric vehicle charging load prediction method based on user behaviors | |
| Arya et al. | Strategic Placement of Electric Vehicle Charging Stations Using Grading Algorithm | |
| Ghamami et al. | Electric Vehicle Charger Placement Optimization in Michigan: Phase II-Urban | |
| CN113610276A (en) | Urban electric vehicle charging infrastructure planning method and system | |
| CN112700117B (en) | Data-based electric vehicle charging infrastructure service condition estimation method | |
| Shen et al. | Strategic Charging Infrastructure Deployment for Electric Vehicles | |
| Wang et al. | Optimization of charging-station location and capacity determination based on optical storage, charging integration, and multi-strategy fusion | |
| CN117973915B (en) | Urban green travel development level evaluation method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |