CN111709662A - Electric automobile charging station capacity fixing method based on big data - Google Patents

Electric automobile charging station capacity fixing method based on big data Download PDF

Info

Publication number
CN111709662A
CN111709662A CN202010585291.0A CN202010585291A CN111709662A CN 111709662 A CN111709662 A CN 111709662A CN 202010585291 A CN202010585291 A CN 202010585291A CN 111709662 A CN111709662 A CN 111709662A
Authority
CN
China
Prior art keywords
station
charging
urban
data
capacity
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.)
Pending
Application number
CN202010585291.0A
Other languages
Chinese (zh)
Inventor
谢士明
唐强
安飞虎
岳毫
傅世勇
李念念
潘勇
李小山
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siji Xingneng Technology Sichuan Co ltd
Original Assignee
Aostar Information Technologies Co ltd
State Grid Information and Telecommunication Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Aostar Information Technologies Co ltd, State Grid Information and Telecommunication Co Ltd filed Critical Aostar Information Technologies Co ltd
Priority to CN202010585291.0A priority Critical patent/CN111709662A/en
Publication of CN111709662A publication Critical patent/CN111709662A/en
Pending legal-status Critical Current

Links

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
    • G06Q10/06—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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/951—Indexing; Web crawling techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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"
    • 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
    • G06Q10/067—Enterprise or organisation modelling
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • 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
    • G06Q50/06—Energy or water supply
    • 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
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Databases & Information Systems (AREA)
  • Accounting & Taxation (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Quality & Reliability (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Finance (AREA)
  • Operations Research (AREA)
  • Educational Administration (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Remote Sensing (AREA)
  • Water Supply & Treatment (AREA)

Abstract

The invention discloses a big data-based electric vehicle charging station capacity determining method, which comprises the steps of obtaining the number of used vehicles of charging guns of peripheral stations, station demand prediction data and station land information, and calculating the maximum charging capacity max _ count of the station according to the station land information; the average number of times of using the charging guns is calculated according to the number of using the charging guns of the peripheral stations, the number of the charging guns needed to meet the demand, namely, the needed _ count, is calculated by combining with station demand prediction data, and then the station capacity min (max _ count, needed _ count) is obtained by combining with the maximum charging capacity of the station. The method calculates the maximum charging gun capacity of the station based on the accurate station demand prediction data, so that the urban demand estimation is more accurate, and the urban charging station planning is more reasonable on the basis.

Description

Electric automobile charging station capacity fixing method based on big data
Technical Field
The invention belongs to the technical field of capacity fixing of charging stations, and particularly relates to a capacity fixing method of an electric vehicle charging station based on big data.
Background
At present, the site selection and volume fixing method of the urban charging station is based on an urban road network structure, traffic flow and resident gathering points, and the data of operation big data (such as price, order quantity and the like), passenger and truck holding capacity, new energy automobile policy and the like of the existing charging station are not brought into the site selection method for a moment. The site selection not only can directly influence improper constant volume of the charging station, but also can influence planning layout of an urban traffic network and travel convenience of electric automobile users, further influence wide application of the electric automobile, and also can cause remarkable increase of electric energy loss and obvious reduction of voltage of certain nodes. The current method for site selection of urban charging stations is as follows:
1) site selection and station size are determined according to municipal planning requirements: and determining the number of the electric vehicle charging stations in the planning area according to the total power demand of the electric vehicles in the planning area. However, site selection and station sizing are determined by the needs of municipal planning: the site selection thought is guided by municipal planning, the actual charging requirements of users are not considered, and the waste of charging station resources can be caused.
2) And planning the site selection of the charging station by the optimal path based on the road network. However, the method only considers the convenience of vehicle charging, and the station is not planned according to the actual charging requirement and the number of charging guns, so that the situation of insufficient charging stations is caused.
Disclosure of Invention
The invention aims to provide a capacity determining method for an electric vehicle charging station based on big data, which is used for calculating the maximum charging gun capacity of the station based on accurate station demand prediction data, so that the urban demand estimation is more accurate, and the urban charging station planning is more reasonable on the basis.
The invention is mainly realized by the following technical scheme: a capacity determining method for an electric vehicle charging station based on big data comprises the steps of obtaining the number of vehicles used by charging guns of peripheral stations, station demand prediction data and station land information, and calculating the maximum charging capacity max _ count of the station according to the station land information; the average number of times of using the charging guns is calculated according to the number of using the charging guns of the peripheral stations, the number of the charging guns needed to meet the demand, namely, the needed _ count, is calculated by combining with station demand prediction data, and then the station capacity min (max _ count, needed _ count) is obtained by combining with the maximum charging capacity of the station.
In order to better implement the present invention, further, the station maximum charging capacity max _ count is equal to (area of station parking lot-area of station aisle)/area of average parking space; the required number of charging guns needed to meet the requirement need _ count is equal to the station required vehicle number/average used vehicle number of the charging guns.
In order to better realize the invention, further, the number of stations to be built and the regional distribution thereof are calculated through a charging station distribution model to form an alternative station library; if the peripheral charging stations meet the charging requirements, site selection is not abandoned, otherwise, the charging station requirements are estimated through the site requirement prediction model, if the estimated charging station requirements are larger than or equal to the station building threshold value, site selection is determined, and site requirement prediction data are estimated through the site requirement prediction model.
In order to better implement the method, the charging station distribution model is further obtained by establishing a constraint function according to the charging prediction demand, the urban POI distribution and the urban road network data, taking the total distance from the station to the road network trunk road as an objective function and based on an MOPSO algorithm.
In order to better realize the method, the charging demand forecasting model is used for forecasting the overall charging demand of a single city, the influence factor of the new energy automobile inventory of the city is introduced, and the urban charging demand is forecasted by establishing the BP network model.
In order to better implement the invention, further, the influence factor of the new energy automobile holding capacity of the city comprises the new energy automobile holding capacity of the city, new energy automobile policy of the city, and city passenger/freight index city public transportation data.
In order to better realize the invention, the station demand prediction model predicts the charging demand of a single proposed station, introduces POI data around the station and daily average train number influence factors around the station, and predicts the charging demand of the proposed station by establishing a BP network model.
In order to better implement the invention, further, the station day-average train number influence factors around the station include station peripheral POI data, station train number data around the station, station peripheral traffic situation data, and station basic information.
In order to better realize the method, further, urban charging station distribution and operation big data, urban road network structure and traffic situation, urban POI distribution, urban fuel passenger-truck and new energy passenger-truck holding capacity, urban new energy automobile policy, urban traffic policy, urban public traffic data and urban land renting and selling information are captured through a distributed real-time data crawler technology.
Data acquisition, namely acquiring distribution and operation big data of each urban charging station, an urban road network structure and traffic situation thereof, urban POI (Key interest site) distribution, urban fuel passenger-truck and new energy passenger-truck holding capacity, urban new energy automobile policies, urban traffic policies, urban public traffic data and urban land renting and selling information by a distributed real-time data crawler technology, and storing the data by using a distributed big data storage system; and performing data fusion, cleaning, processing and storage on the data through a big data technology. The invention can utilize python and tensorflow to establish and train a big data algorithm model: the method comprises the steps of establishing a city charging demand model, a city charging station big data network planning model, a charging station site selection model and a charging operation model of the charging station.
After data is crawled, processing is required. For example: taking each station as a sample, calculating POI classification in the range of 1/3/5/10 kilometers around the station and summing up the POI classification to form the sample.
The invention has the beneficial effects that:
(1) the method calculates the maximum charging gun capacity of the station based on the accurate station demand prediction data, so that the urban demand estimation is more accurate, and the urban charging station planning is more reasonable on the basis.
(2) The invention fully considers the data of the holding capacity of the urban fuel passenger-truck and the new energy passenger-truck, the urban new energy automobile policy, the urban traffic policy, the urban public traffic data and the like, so that the urban demand estimation is more accurate, and the urban charging station planning is more reasonable on the basis.
(3) The invention fully considers the distribution of the charging stations and the operation big data thereof, the urban road network structure and the traffic situation thereof, and the distribution of the urban POI (key interest site), so that the estimation of the station requirements is more accurate.
(4) The invention fully considers the distributed practical use of the existing charging station, can effectively avoid the over-construction and insufficient construction coverage of the charging station, and improves the return on investment of the charging station.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a functional block diagram of a charging station distribution model;
FIG. 3 is a functional block diagram of a site demand prediction model;
fig. 4 is a functional block diagram of a charging demand prediction model.
FIG. 5 is a functional block diagram of a MOPSO optimization algorithm;
FIG. 6 is a flow chart for establishing a site volume;
FIG. 7 is a functional block diagram of a distributed data acquisition system.
Detailed Description
Example 1:
a capacity determining method for an electric vehicle charging station based on big data is disclosed, as shown in FIG. 6, the number of used vehicles of charging guns of peripheral stations, station demand prediction data and station land information are obtained, and the maximum charging capacity max _ count of the station is calculated according to the station land information; the average number of times of using the charging guns is calculated according to the number of using the charging guns of the peripheral stations, the number of the charging guns needed to meet the demand, namely, the needed _ count, is calculated by combining with station demand prediction data, and then the station capacity min (max _ count, needed _ count) is obtained by combining with the maximum charging capacity of the station. The station maximum charging capacity max _ count is equal to (station parking area-station aisle area)/average parking space area; the required number of charging guns needed to meet the requirement need _ count is equal to the station required vehicle number/average used vehicle number of the charging guns.
Example 2:
in this embodiment, optimization is performed on the basis of implementation 1, and as shown in fig. 1, the number of stations to be built and the regional distribution thereof are calculated by a charging station distribution model to form an alternative station library; if the peripheral charging stations meet the charging requirements, site selection is not abandoned, otherwise, the charging station requirements are estimated through the site requirement prediction model, if the estimated charging station requirements are larger than or equal to the station building threshold value, site selection is determined, and site requirement prediction data are estimated through the site requirement prediction model. The station building threshold is the minimum amount of orders required to achieve a balance of profit and loss for the station during the planned operation period. Below the threshold demand, the total revenue coverage meets the construction and operational costs, and therefore the station building is not considered. The invention fully considers the distributed practical use of the existing charging station and can effectively avoid the over-construction and insufficient construction coverage of the charging station.
Other parts of this embodiment are the same as embodiment 1, and thus are not described again.
Example 3:
in this embodiment, optimization is performed on the basis of embodiment 2, and the charging station distribution model is obtained by establishing a constraint function according to the charging prediction demand, the urban POI distribution and the urban road network data, taking the total distance from a station to a road network trunk road as an objective function, and based on an MOPSO algorithm.
The MOPSO (multi-objective particle swarm optimization) adopted by the invention is a variant of the PSO (particle swarm optimization).
1. Urban charging station distribution model based on MOPSO optimization algorithm
And (3) establishing a constraint function according to the urban charging prediction demand (see 2 in (8), an urban charging demand prediction model), urban POI distribution and urban road network data, taking the total distance from the station to the road network trunk road as an objective function, establishing an MOPSO optimization algorithm model, and calculating the urban station distribution result.
2. The MOPSO optimization algorithm flow chart is shown in the figure;
3. MOPSO optimization algorithm steps and calculation formula
1) Initialization population and Archive set: giving initial values to the parameters to generate an initial group P1And is combined with P1Copying the non-inferior solution of (1) to Archive to obtain A1. And (4) finishing the contents of 2) to 4) when the current evolution algebra is set as t and the t is less than the total evolution algebra.
2) Evolution produces the next generation population: and (4) setting the currently evolved particle j, and finishing the contents of a to c when j is smaller than the population scale.
a calculating the density information of Archive concentrated particles
The target space is divided into small regions by a grid, and the number of particles included in each region is used as density information of the particles. The larger the number of particles contained in the grid in which the particles are located, the larger the density value of the particles, and vice versa. Taking the problem of minimizing optimization of a two-dimensional target space as an example, the specific implementation process of the density information estimation algorithm is as follows:
step1 calculating the boundary of t generation target space
(min F1 t,max F1 t) And
Figure BDA0002553724580000041
step2 calculation of the modulus of the network:
Figure BDA0002553724580000042
step3 traversal AtCalculating the number of the grid where the particle is located; for particle i, the numbering is as follows:
Figure BDA0002553724580000043
step4, grid information and ion density estimation are calculated.
Wherein, G ═ M × M is the number of grids to be divided into the target space, Int (·) is an integer function, F1 iAnd
Figure BDA0002553724580000051
is the value of the objective function of the particle i.
b is the particle P in the populationj,tIn AtIn which g is selectedBestParticle gj,t，gj,tThe quality of the particles determines the convergence performance of the MOPSO algorithm and the diversity of the non-inferior solution sets, and the selection is based on the density information of the particles in the Archive set. Specifically, for particles in Archive, the lower the density value, the greater the probability of selection, and vice versa; the search potential is evaluated by the number of particles in the Archive set which are superior to the number of particles in the population, and the more the number of particles in the population is superior, the stronger the search potential is, and the weaker the search potential is. The specific implementation of the algorithm is as follows:
step1 calculation of AtHas a mean of better than Pj,tParticle set A ofj
Fork＝1TO|At|
Aj＝Aj+{Ak,t|Ak,tp Pj,t,Ak,t∈At}
NEXT
Step2 calculation of AjParticle set G with the lowest medium densityj
Gj＝min{Density(Ak),k＝1,2,K,|Aj|,Ak∈Aj}
Step2:IF|Gj|＞1THENgj,t＝Rand(Gj)
Wherein, | AtI represents AtThe number of particles contained; a. thejFor storing AtHas a medium to superior particle Pj,tMember of (A)jThe particles with the smallest intermediate density are stored in GjPerforming the following steps; density (A)k) Calculating particle Ak(ii) a density estimate of; rand (G)j) Represents from GjWherein a member is randomly selected.
c updating the position of the particles in the population and the velocity of the particles in the population at gBestAnd pBestThe optimal solution is searched under the guidance of the algorithm, and the specific implementation of the algorithm is as follows:
Fori＝1TOD
a calculating the position range
Figure BDA0002553724580000052
And speed range
Figure BDA0002553724580000053
Figure BDA0002553724580000054
Figure BDA0002553724580000055
Figure BDA0002553724580000056
Out of bounds handling
NEXT
Wherein D is a decision variable dimension; rand (·) is a random function; w is the inertial weight; c. C1，c2Is a learning factor; x is a contraction factor; r1、R2Is [0,1 ]]A random number in between;
Figure BDA0002553724580000061
and
Figure BDA0002553724580000062
is g of particle jBestAnd pBestThe ith decision component of (1).
3) Updating an Archive set: evolving to obtain a new generation of clusters Pt+1Then, handle Pt+1The non-inferior solution in (1) is saved to Archive set.
The concrete implementation is as follows:
IFAt＝ΦTHEN
FORk＝1TO|Pt+1|
At+1＝At+1+{Pk,t+1|Pk,t+1p Pi,t+1orPk,t+1p f Pi,t+1,i＝1,2,K,|Pt+1|,i≠k}
NEXT
ELSE
FORk＝1TO|Pt+1|
At+1＝At+1+{Pk,t+1|Pk,t+1p Ai,t+1orPk,t+1p f Ai,t+1,i＝1,2,K,|Pt+1|,i≠k}
NEXT
ENDIF
wherein, Pk,t+1Represents Pt+1The kth particle in (1); the symbol p f indicates that the two vectors have no precedence relationship. When Archive set is empty, P is addedt+1The non-inferior solution in (1) is directly copied into an Archive set; when the Archive set is not empty, as long as Pt+1A medium particle is superior to or independent of a particle in the Archive set, and the particle is inserted into the Archive set.
4) Truncating operation of Archive set
When the number of particles in an Archive set exceeds a predetermined size, it is necessary to delete extra individuals to maintain a stable Archive set size. For a grid k with more than 1 particle number, the particle number PN to be deleted in the grid is calculated according to the following formula, and then PN particles are randomly deleted in the grid k.
Figure BDA0002553724580000063
Where Grid [ k,2] represents the number of particles included in Grid k.
5) And outputting the particle information concentrated by the Archive.
The other parts of this embodiment are the same as those of embodiment 2, and thus are not described again.
Example 4:
in this embodiment, optimization is performed on the basis of embodiment 2 or 3, as shown in fig. 3, a station demand prediction model: the charging requirement of a single proposed station is predicted by establishing a model, a BP neural network model is selected and used in the method, and the schematic diagram is as follows: and introducing POI data around the station, influence factors such as daily average vehicle number of stations around the station and the like, and predicting the charging requirement of the proposed station by establishing a BP network model. The daily average train number influence factors of the stations around the stations comprise POI data around the stations, train number data of the stations around the stations, traffic situation data around the stations and basic information of the stations.
As shown in fig. 4, the urban charging demand prediction model: the model is established to predict the overall charging demand of a single city, and a BP neural network model is selected and used in the method, and the schematic diagram is as follows: influence factors such as the holding capacity of the urban new energy automobile are introduced, and urban charging requirements are predicted by establishing a BP network model. The influence factors of the urban new energy automobile holding capacity comprise the urban new energy automobile holding capacity, urban new energy automobile policies and urban passenger/freight index urban public transport data.
The invention fully considers the data of the holding capacity of the urban fuel passenger-truck and the new energy passenger-truck, the urban new energy automobile policy, the urban traffic policy, the urban public traffic data and the like, so that the urban demand estimation is more accurate, and the urban charging station planning is more reasonable on the basis. The invention fully considers the distribution of the charging stations and the operation big data thereof, the urban road network structure and the traffic situation thereof, and the distribution of the urban POI (key interest site), so that the estimation of the station requirements is more accurate. The invention fully considers the distributed practical use of the existing charging station and can effectively avoid the over-construction and insufficient construction coverage of the charging station.
The rest of this embodiment is the same as embodiment 2 or 3, and therefore, the description thereof is omitted.
Example 5:
in this embodiment, optimization is performed on the basis of any one of embodiments 2 to 4, and as shown in fig. 7, the distributed data acquisition system is used for data processing, and the system includes the following functional modules:
1) a task management module: the data acquisition system is responsible for managing and distributing data acquisition tasks;
2) a distributed acquisition module: the data analyzer is responsible for executing a data acquisition task and transmitting a data acquisition result to the data analyzer;
3) a data analysis module: the data return state is judged, the data result is analyzed, and the data result is stored in the database; simultaneously reporting data analysis and storage states to a task manager;
4) a data storage module: is responsible for storing data.
Other parts of this embodiment are the same as any of embodiments 2 to 4, and thus are not described again.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications and equivalent variations of the above embodiments according to the technical spirit of the present invention are included in the scope of the present invention.

Claims (9)

1. A capacity determining method of an electric vehicle charging station based on big data is characterized by comprising the steps of obtaining the number of vehicles used by charging guns of peripheral stations, station demand prediction data and station land information, and calculating the maximum charging capacity max _ count of the station according to the station land information; the average number of times of using the charging guns is calculated according to the number of using the charging guns of the peripheral stations, the number of the charging guns needed to meet the demand, namely, the needed _ count, is calculated by combining with station demand prediction data, and then the station capacity min (max _ count, needed _ count) is obtained by combining with the maximum charging capacity of the station.
2. In order to better implement the present invention, further, the station maximum charging capacity max _ count is equal to (area of station parking lot-area of station aisle)/area of average parking space; the required number of charging guns needed to meet the requirement need _ count is equal to the station required vehicle number/average used vehicle number of the charging guns.
3. The big data-based electric vehicle charging station capacity measuring method according to claim 1 or 2,
calculating the number of stations to be built and the regional distribution thereof through a charging station distribution model to form an alternative station library; if the peripheral charging stations meet the charging requirements, site selection is not abandoned, otherwise, the charging station requirements are estimated through the site requirement prediction model, if the estimated charging station requirements are larger than or equal to the station building threshold value, site selection is determined, and site requirement prediction data are estimated through the site requirement prediction model.
4. The electric vehicle charging station capacity determining method based on big data as claimed in claim 3, wherein the charging station distribution model is obtained by establishing a constraint function according to the charging prediction demand, the urban POI distribution and the urban road network data, taking the total distance from a station to a road network main road as an objective function and based on an MOPSO algorithm.
5. The electric vehicle charging station capacity determining method based on big data according to claim 4, wherein the charging demand prediction model is used for predicting the overall charging demand of a single city, introducing an urban new energy vehicle capacity influence factor, and predicting the urban charging demand by establishing a BP network model.
6. The electric vehicle charging station capacity determining method based on big data according to claim 5, wherein the urban new energy vehicle holding capacity influence factor comprises urban new energy vehicle holding capacity, urban new energy vehicle policy, and urban passenger/freight index urban public transportation data.
7. The electric vehicle charging station capacity measuring method based on the big data as claimed in claim 3, wherein the station demand prediction model predicts the charging demand of a single proposed station, introduces POI data around the station and daily average train number influence factors around the station, and predicts the charging demand of the proposed station by establishing a BP network model.
8. The electric vehicle charging station capacity determining method based on the big data as claimed in claim 7, wherein the station peripheral station daily average train number influence factor includes station peripheral POI data, station peripheral station train number data, station peripheral traffic situation data, and station basic information.
9. The electric vehicle charging station capacity fixing method based on big data according to any one of claims 3-8, characterized in that urban charging station distribution and operation big data, urban road network structure and traffic situation thereof, urban POI distribution, urban fuel passenger truck and new energy passenger truck holding capacity, urban new energy vehicle policy, urban traffic policy, urban public traffic data and urban land renting and selling information are captured through a distributed real-time data crawler technology.
CN202010585291.0A 2020-06-23 2020-06-23 Electric automobile charging station capacity fixing method based on big data Pending CN111709662A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010585291.0A CN111709662A (en) 2020-06-23 2020-06-23 Electric automobile charging station capacity fixing method based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010585291.0A CN111709662A (en) 2020-06-23 2020-06-23 Electric automobile charging station capacity fixing method based on big data

Publications (1)

Publication Number Publication Date
CN111709662A true CN111709662A (en) 2020-09-25

Family

ID=72542011

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010585291.0A Pending CN111709662A (en) 2020-06-23 2020-06-23 Electric automobile charging station capacity fixing method based on big data

Country Status (1)

Country Link
CN (1) CN111709662A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113191695A (en) * 2021-05-27 2021-07-30 四川中电启明星信息技术有限公司 Electric vehicle charging station demand response method based on competition map

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130057211A1 (en) * 2011-09-01 2013-03-07 Nec Corporation Charging control system and charging control method
TW201428511A (en) * 2013-01-07 2014-07-16 Univ Lunghwa Sci & Technology Optimized multi-stage rapid charging strategy for lithium battery
US20140277599A1 (en) * 2013-03-13 2014-09-18 Oracle International Corporation Innovative Approach to Distributed Energy Resource Scheduling
CN106887841A (en) * 2017-03-23 2017-06-23 东北大学 A kind of genetic particle group optimizing method on multiple populations of the capacity configuration of micro-capacitance sensor containing electric automobile
CN107153893A (en) * 2017-05-19 2017-09-12 东南大学 A kind of electric automobile charging station Site planning method based on city parking data
CN108288110A (en) * 2018-01-18 2018-07-17 武汉理工大学 A kind of charging pile Optimal Deployment Method based on the true running data of electric vehicle
CN108460487A (en) * 2018-03-07 2018-08-28 国网江苏省电力有限公司无锡供电分公司 Electric vehicle rapid charging station Optimizing Site Selection constant volume method based on APSO algorithms
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
CN110175780A (en) * 2019-05-28 2019-08-27 广东工业大学 A kind of electric automobile charging station site selecting method, system and relevant apparatus
CN111311122A (en) * 2020-03-23 2020-06-19 广东工业大学 Charging station construction method for smart city

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130057211A1 (en) * 2011-09-01 2013-03-07 Nec Corporation Charging control system and charging control method
TW201428511A (en) * 2013-01-07 2014-07-16 Univ Lunghwa Sci & Technology Optimized multi-stage rapid charging strategy for lithium battery
US20140277599A1 (en) * 2013-03-13 2014-09-18 Oracle International Corporation Innovative Approach to Distributed Energy Resource Scheduling
CN106887841A (en) * 2017-03-23 2017-06-23 东北大学 A kind of genetic particle group optimizing method on multiple populations of the capacity configuration of micro-capacitance sensor containing electric automobile
CN107153893A (en) * 2017-05-19 2017-09-12 东南大学 A kind of electric automobile charging station Site planning method based on city parking data
CN108288110A (en) * 2018-01-18 2018-07-17 武汉理工大学 A kind of charging pile Optimal Deployment Method based on the true running data of electric vehicle
CN108460487A (en) * 2018-03-07 2018-08-28 国网江苏省电力有限公司无锡供电分公司 Electric vehicle rapid charging station Optimizing Site Selection constant volume method based on APSO algorithms
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
CN110175780A (en) * 2019-05-28 2019-08-27 广东工业大学 A kind of electric automobile charging station site selecting method, system and relevant apparatus
CN111311122A (en) * 2020-03-23 2020-06-19 广东工业大学 Charging station construction method for smart city

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
刘自发等: "基于量子粒子群优化算法的城市电动汽车充电站优化布局", 《中国电机工程学报》 *
姚良: "《Python3爬虫实战 数据清洗、数据分析与可视化》", 31 October 2019, 中国铁道出版社 *
王利利等: "计算智能在电动车充电站规划的应用研究综述", 《计算机工程与应用》 *
贾斯佳等: "电动汽车基础设施选址定容研究――以南京市河西新城为例", 《科技管理研究》 *
马玉清等: "城市电动汽车充电站规划模型探析", 《皖西学院学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113191695A (en) * 2021-05-27 2021-07-30 四川中电启明星信息技术有限公司 Electric vehicle charging station demand response method based on competition map
CN113191695B (en) * 2021-05-27 2024-01-26 四川中电启明星信息技术有限公司 Electric vehicle charging station demand response method based on competition spectrum

Similar Documents

Publication Publication Date Title
Iacobucci et al. Optimization of shared autonomous electric vehicles operations with charge scheduling and vehicle-to-grid
Li et al. Price incentive-based charging navigation strategy for electric vehicles
James Two-stage request scheduling for autonomous vehicle logistic system
Fiedler et al. The impact of ridesharing in mobility-on-demand systems: Simulation case study in Prague
Bi et al. Logistical planning for electric vehicles under time-dependent stochastic traffic
Alesiani et al. Optimization of charging stops for fleet of electric vehicles: A genetic approach
Pan et al. Deploying public charging stations for electric taxis: A charging demand simulation embedded approach
CN110968837A (en) Method for locating and sizing electric vehicle charging station
Liu et al. Bus pooling: A large-scale bus ridesharing service
Su et al. Forecast of electric vehicle charging demand based on traffic flow model and optimal path planning
CN117077985B (en) Electric vehicle charging pile planning method and system according to charging requirements
Zeng et al. Optimization of future charging infrastructure for commercial electric vehicles using a multi-objective genetic algorithm and real travel data
CN111709663A (en) Electric vehicle charging station site selection method based on big data
Luo et al. Dynamic intra-cell repositioning in free-floating bike-sharing systems using approximate dynamic programming
Kumar et al. S2RC: A multi-objective route planning and charging slot reservation approach for electric vehicles considering state of traffic and charging station
Huang et al. An improved charging navigation strategy of electric vehicles via optimal time-of-use pricing
Miao et al. Highly Automated Electric Vehicle (HAEV)-based mobility-on-demand system modeling and optimization framework in restricted geographical areas
Su et al. Spatial-temporal distribution model of electric vehicle charging demand based on a dynamic evolution process
Dorokhova et al. Routing of electric vehicles with intermediary charging stations: A reinforcement learning approach
Zhang et al. The effect of nonlinear charging function and line change constraints on electric bus scheduling
Uribe et al. Discrete event simulation for battery-swapping station sizing for hybrid and electric motorcycles
CN112926800B (en) Logistics distribution area division method considering complex road network
CN111709662A (en) Electric automobile charging station capacity fixing method based on big data
Coninx et al. Anticipatory coordination of electric vehicle allocation to fast charging infrastructure
CN113222248B (en) Automatic taxi-driving charging pile selection method

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
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20210714

Address after: No.99-ol-10-202012005, west section of Hupan Road, Xinglong Street, Tianfu New District, Chengdu, Sichuan 610000

Applicant after: Siji Xingneng Technology (Sichuan) Co.,Ltd.

Address before: 610000 No. 2688 Xiyuan Avenue, Pixian Modern Industrial Port, Chengdu City, Sichuan Province

Applicant before: SICHUAN ZHONGDIAN AOSTAR INFORMATION TECHNOLOGIES Co.,Ltd.

Applicant before: STATE GRID INFORMATION & TELECOMMUNICATION GROUP Co.,Ltd.

RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20200925