CN109858676A - Electric car electric charging demand for services model prediction method based on clustering algorithm - Google Patents
Electric car electric charging demand for services model prediction method based on clustering algorithm Download PDFInfo
- Publication number
- CN109858676A CN109858676A CN201811640079.9A CN201811640079A CN109858676A CN 109858676 A CN109858676 A CN 109858676A CN 201811640079 A CN201811640079 A CN 201811640079A CN 109858676 A CN109858676 A CN 109858676A
- Authority
- CN
- China
- Prior art keywords
- electric car
- electric
- charging demand
- sample
- electric charging
- 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
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/7072—Electromobility specific charging systems or methods for batteries, ultracapacitors, supercapacitors or double-layer capacitors
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/12—Electric charging stations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/14—Plug-in electric vehicles
Landscapes
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The electric car electric charging demand for services model prediction method based on clustering algorithm that the present invention relates to a kind of, technical characterstic are: the following steps are included: step 1, inquiry electric car information, regional planning information and it is built, building the element with built in advance charge station information as electric car electric charging demand model;Step 2, the element results inquired according to step 1, establish electric car electric charging demand model.The present invention forms the demand model of the electric car charging of meter and power grid bearing capacity by research automobile user electricity consumption behavioral trait, provides reliable reference for the addressing constant volume planning of electric car charging and conversion electric facility.
Description
Technical field
The invention belongs to electric power facility planning technology fields, are related to electric car electric charging demand for services model prediction side
Method is based especially on the electric car electric charging demand for services model prediction method of clustering algorithm.
Background technique
Currently, new-energy automobile has the features such as environmental-friendlyization, the energy is using high efficiency as new industry.New energy
Source automobile is a significant industry of the New Economy in industrial circle.China for the support that new-energy automobile develops will be just like
The past, the encouragement of electric car charging and conversion electric facility development is only increased, the prospect to electric car overall development is
Good for a long time.For the charge requirement for meeting electric car, each province is all in the construction for carrying forward vigorously charging station and charging pile.
Want scientific and reasonable planning and build the needs that electric car electric charging service network meets masses, just needs first
Have the accurate Demand Forecast Model of science, as guiding plan construction electric car electric charging service network it is important according to
The influence of numerous practical factors such as electric car is considered according to, the foundation of Demand Forecast Model, the influence in region, built filled
The influence etc. in power station, the influences such as there are also the trips of numerous uncontrollable factors such as user to influence, the electric charging rule of user.It can
The Demand Forecast Model that these factors are integrally formed a set of science there is into great meaning to the development of new-energy automobile industry.
In conclusion being badly in need of forming the Demand Forecast Model of a set of science, it can assist or instruct optimization planning electronic
The addressing constant volume of automobile charging and conversion electric service network pushes new-energy automobile industry actively to advance.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, proposes that a kind of electric car based on clustering algorithm fills and change
Electric demand for services model prediction method forms meter and power grid bearing capacity by analyzing automobile user electricity consumption behavioral trait
Electric car charging demand model, for electric car charging and conversion electric facility addressing constant volume plan reliable reference is provided.
The present invention solves its realistic problem and adopts the following technical solutions to achieve:
A kind of electric car electric charging demand for services model prediction method based on clustering algorithm, comprising the following steps:
Step 1, inquiry electric car information, regional planning information and it is built, building and built in advance charge station information conduct
The element of electric car electric charging demand model;
Step 2, the element results inquired according to step 1, establish electric car electric charging demand model.
Moreover, the step 2 method particularly includes: according to the element results that step 1 is inquired, established by K clustering algorithm
Electric car electric charging demand model, specific steps include:
(1) planning region is divided into several net regions, by the electric car electric charging demand of each net region
Property is expressed as n-dimensional spaceOn vector x (a1,a2,a3……an), wherein each component of vector x is being somebody's turn to do for quantization means
The electric car electric charging demand property information of net region;
(2) several vector x are chosen as training sample { x(1),x(2)……x(m), sample size m;
(3) k cluster center of mass point is randomly selected from sample
(4) for each sample i, its class that should belong to is calculated:
For each class j, such mass center is recalculated:
(5) step 4 is repeated until canonical measure function convergence.
Moreover, the step 2 method particularly includes: according to the element results that step 1 is inquired, pass through K central cluster algorithm
Establish electric car electric charging demand model;
Its specific steps includes:
(1) planning region is divided into several net regions, by the electric car electric charging demand of each net region
Property is expressed as n-dimensional spaceOn vector x (a1,a2,a3……an), wherein each component of vector x is being somebody's turn to do for quantization means
The electric car electric charging demand property information of net region;
(2) several vector x are chosen as training sample { x(1),x(2)……x(m), sample size m;
(3) k center of mass point is randomly selected from sample
(4) point for concentrating sample point to be clustered is assigned to nearest center of mass point, forms k race;
(5) calculate all sample points in each race to one of sample point manhatton distance with;
(6) selecting makes in the race manhatton distance and the smallest sample point as mass center;
(7) step 4 is repeated to step 6 until meeting the number of iterations or error range.
The advantages of the present invention:
The present invention assigns its attribute by dividing to region, and by each region with actual conditions, based on trip
Chain theory determines automobile passage situation in region, the letter such as ownership of space-time characterisation and electric car referring again to user's charging
Breath, (including electric car information data, electric charging station information data and planning region information data), and based on scale
The background for changing electric car access ultra-large type urban distribution network, studies automobile user electricity consumption behavioral trait, while considering power grid
Bearing capacity finally show that optimal electric car fills by successive ignition calculating using K central cluster algorithm (K-medoids)
Electric demand for services model is changed, Accurate Prediction scientifically is carried out to the electric charging demand of electric car charging and conversion electric service network, thus
Reliable reference and effectively guidance can be provided the addressing constant volume of subsequent optimization planning electric car charging and conversion electric service network, in turn
New-energy automobile industry is pushed actively to advance.
Detailed description of the invention
Fig. 1 is that the present invention establishes electric car electric charging demand model flow chart;
Fig. 2 is that the present invention uses K clustering algorithm to establish electric car electric charging demand model flow chart;
Fig. 3 is that the present invention uses K central cluster algorithm to establish electric car electric charging demand model flow chart.
Specific embodiment
The embodiment of the present invention is described in further detail below in conjunction with attached drawing:
A kind of electric car electric charging demand for services model prediction method based on clustering algorithm, as shown in Figure 1, include with
Lower step:
Step 1, inquiry electric car information, regional planning information and it is built, building and built in advance charge station information conduct
The element of electric car electric charging demand model;
Key element is as shown in table 1:
1 electric car electric charging demand model element table of table
Embodiment one: step 2, the element results inquired according to step 1 are established electronic by K clustering algorithm (K-means)
Automobile electric charging demand model;
As shown in Fig. 2, the specific steps of the step 2 include:
(1) planning region is divided into several net regions, by the electric car electric charging demand of each net region
Property is expressed as n-dimensional spaceOn vector x (a1,a2,a3……an), wherein each component of vector x is being somebody's turn to do for quantization means
The electric car electric charging demand property information of net region;
(2) several vector x are chosen as training sample { x(1),x(2)……x(m), sample size m;
(3) k cluster center of mass point is randomly selected from sample
(4) for each sample i, its class that should belong to is calculated:
For each class j, such mass center is recalculated:
(5) step S4 is repeated until canonical measure function convergence.
In the present embodiment, canonical measure function is mean square deviation.
Using k clustering algorithm, preferable Clustering Effect can be reached within the shorter calculating time, and is easy to explain;But
It is more sensitive to abnormal data, and needs artificial determining k value, to determine that k value needs many experiments.
Embodiment two: step 2, the element results inquired according to step 1 are built by K central cluster algorithm (K-medoids)
Vertical electric car electric charging demand model;
The specific steps of the step 2 include:
(1) planning region is divided into several net regions, by the electric car electric charging demand of each net region
Property is expressed as n-dimensional spaceOn vector x (a1,a2,a3……an), wherein each component of vector x is being somebody's turn to do for quantization means
The electric car electric charging demand property information of net region;
(2) several vector x are chosen as training sample { x(1),x(2)……x(m), sample size m;
(3) k center of mass point is randomly selected from sample
(4) point for concentrating sample point to be clustered is assigned to nearest center of mass point, forms k race;
(5) calculate all sample points in each race to one of sample point manhatton distance with;
(6) selecting makes in the race manhatton distance and the smallest sample point as mass center;
(7) step 4 is repeated to step 6 until meeting the number of iterations or error range.
It is less sensitive to abnormal data using K central cluster algorithm compared with K clustering algorithm, but due to being in
The mode of heart point selection is calculated, and the time complexity of algorithm also rises O (n) than K clustering algorithm.
It is emphasized that embodiment of the present invention be it is illustrative, without being restrictive, therefore the present invention includes
It is not limited to embodiment described in specific embodiment, it is all to be obtained according to the technique and scheme of the present invention by those skilled in the art
Other embodiments, also belong to the scope of protection of the invention.
Claims (3)
1. a kind of electric car electric charging demand for services model prediction method based on clustering algorithm, it is characterised in that: including with
Lower step:
Step 1, inquiry electric car information, regional planning information and it is built, building with built in advance charge station information as electronic
The element of automobile electric charging demand model;
Step 2, the element results inquired according to step 1, establish electric car electric charging demand model.
2. a kind of electric car electric charging demand for services model prediction side based on clustering algorithm according to claim 1
Method, it is characterised in that: the step 2 method particularly includes: according to the element results that step 1 is inquired, established by K clustering algorithm
Electric car electric charging demand model, specific steps include:
(1) planning region is divided into several net regions, by the electric car electric charging demand property of each net region
It is expressed as n-dimensional spaceOn vector x (a1,a2,a3……an), wherein each component of vector x is the grid of quantization means
The electric car electric charging demand property information in region;
(2) several vector x are chosen as training sample { x(1),x(2)……x(m), sample size m;
(3) k cluster center of mass point is randomly selected from sample
(4) for each sample i, its class that should belong to is calculated:
For each class j, such mass center is recalculated:
(5) step 4 is repeated until canonical measure function convergence.
3. a kind of electric car electric charging demand for services model prediction side based on clustering algorithm according to claim 1
Method, it is characterised in that: the step 2 method particularly includes: according to the element results that step 1 is inquired, pass through K central cluster algorithm
Electric car electric charging demand model is established, specific steps include:
(1) planning region is divided into several net regions, by the electric car electric charging demand property of each net region
It is expressed as n-dimensional spaceOn vector x (a1,a2,a3……an), wherein each component of vector x is the grid of quantization means
The electric car electric charging demand property information in region;
(2) several vector x are chosen as training sample { x(1),x(2)……x(m), sample size m;
(3) k center of mass point is randomly selected from sample
(4) point for concentrating sample point to be clustered is assigned to nearest center of mass point, forms k race;
(5) calculate all sample points in each race to one of sample point manhatton distance with;
(6) selecting makes in the race manhatton distance and the smallest sample point as mass center;
(7) step 4 is repeated to step 6 until meeting the number of iterations or error range.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811640079.9A CN109858676A (en) | 2018-12-29 | 2018-12-29 | Electric car electric charging demand for services model prediction method based on clustering algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811640079.9A CN109858676A (en) | 2018-12-29 | 2018-12-29 | Electric car electric charging demand for services model prediction method based on clustering algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109858676A true CN109858676A (en) | 2019-06-07 |
Family
ID=66893262
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811640079.9A Pending CN109858676A (en) | 2018-12-29 | 2018-12-29 | Electric car electric charging demand for services model prediction method based on clustering algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109858676A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111591152A (en) * | 2020-05-19 | 2020-08-28 | 浙江秦欧控股集团有限公司 | Battery pack power change decision method, device and system in charge and change separation mode |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102903037A (en) * | 2011-07-28 | 2013-01-30 | 上海拉手信息技术有限公司 | Siting method of distribution centers |
CN103793750A (en) * | 2012-10-30 | 2014-05-14 | 国际商业机器公司 | Method and apparatus for disposing charging/replacing station in area |
CN106951978A (en) * | 2017-02-20 | 2017-07-14 | 国网天津市电力公司 | A kind of city concentrated charging station planing method based on improvement K means algorithms |
CN107169605A (en) * | 2017-05-18 | 2017-09-15 | 东南大学 | City electric car charging station site selecting method based on vehicle location information |
CN109066663A (en) * | 2018-08-31 | 2018-12-21 | 国网上海市电力公司 | Consider the price competing method of electric car cluster grouping |
-
2018
- 2018-12-29 CN CN201811640079.9A patent/CN109858676A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102903037A (en) * | 2011-07-28 | 2013-01-30 | 上海拉手信息技术有限公司 | Siting method of distribution centers |
CN103793750A (en) * | 2012-10-30 | 2014-05-14 | 国际商业机器公司 | Method and apparatus for disposing charging/replacing station in area |
CN106951978A (en) * | 2017-02-20 | 2017-07-14 | 国网天津市电力公司 | A kind of city concentrated charging station planing method based on improvement K means algorithms |
CN107169605A (en) * | 2017-05-18 | 2017-09-15 | 东南大学 | City electric car charging station site selecting method based on vehicle location information |
CN109066663A (en) * | 2018-08-31 | 2018-12-21 | 国网上海市电力公司 | Consider the price competing method of electric car cluster grouping |
Non-Patent Citations (1)
Title |
---|
张洁等: ""基于二次聚类的大规模电动汽车有序充电调度策略优化"", 《计算机应用》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111591152A (en) * | 2020-05-19 | 2020-08-28 | 浙江秦欧控股集团有限公司 | Battery pack power change decision method, device and system in charge and change separation mode |
CN111591152B (en) * | 2020-05-19 | 2021-11-09 | 浙江秦欧控股集团有限公司 | Battery pack power change decision method, device and system in charge and change separation mode |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109272176B (en) | Calculation method is predicted to platform area line loss per unit using K-means clustering algorithm | |
CN106203720B (en) | A kind of schedulable capacity prediction methods of Multiple Time Scales electric car cluster | |
CN106651059B (en) | Optimal configuration method for electric vehicle charging station | |
CN105787588B (en) | Dynamic peak-valley time-of-use electricity price method for improving new energy consumption capability | |
CN105512745A (en) | Wind power section prediction method based on particle swarm-BP neural network | |
CN105787600A (en) | Electric taxi charging station planning method based on adaptive quantum genetic algorithm | |
CN103049651A (en) | Method and device used for power load aggregation | |
CN102682219A (en) | Method for forecasting short-term load of support vector machine | |
CN104992244A (en) | Airport freight traffic prediction analysis method based on SARIMA and RBF neural network integration combination model | |
CN102938562B (en) | Prediction method of total wind electricity power in area | |
CN114707292B (en) | Analysis method for voltage stability of distribution network containing electric automobile | |
CN115796393B (en) | Energy management optimization method, system and storage medium based on multi-energy interaction | |
CN107451686A (en) | Consider the micro-capacitance sensor energy source optimization method of the genetic algorithm of stochastic prediction error | |
CN117272850B (en) | Elastic space analysis method for safe operation scheduling of power distribution network | |
CN111428766B (en) | Power consumption mode classification method for high-dimensional mass measurement data | |
Chen et al. | Many-objective optimal power dispatch strategy incorporating temporal and spatial distribution control of multiple air pollutants | |
CN110543976A (en) | Charging station layout optimization method based on genetic algorithm | |
Miraftabzadeh et al. | K-means and alternative clustering methods in modern power systems | |
CN110111001B (en) | Site selection planning method, device and equipment for electric vehicle charging station | |
CN114611842A (en) | Whole county roof distributed photovoltaic power prediction method | |
CN109858676A (en) | Electric car electric charging demand for services model prediction method based on clustering algorithm | |
Panda et al. | Applications of machine learning in the planning of electric vehicle charging stations and charging infrastructure: A review | |
CN111985691B (en) | Site selection method for wind power plant booster station | |
CN109214610A (en) | A kind of saturation Methods of electric load forecasting based on shot and long term Memory Neural Networks | |
CN111914900B (en) | User electricity utilization mode classification 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 |