CN108876052A - Electric car charging load forecasting method, device and computer equipment - Google Patents
Electric car charging load forecasting method, device and computer equipment Download PDFInfo
- Publication number
- CN108876052A CN108876052A CN201810690887.XA CN201810690887A CN108876052A CN 108876052 A CN108876052 A CN 108876052A CN 201810690887 A CN201810690887 A CN 201810690887A CN 108876052 A CN108876052 A CN 108876052A
- Authority
- CN
- China
- Prior art keywords
- model
- charging
- charge
- electric car
- load
- 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
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
This application involves a kind of electric automobile load prediction techniques, device, computer equipment.The method includes：Obtain the operating parameter of any classification electric car；Operating parameter includes standard power consumption and charge power；According to initiation of charge moment model and charging duration model, charging probabilistic model is obtained；Charging duration model is the product and the ratio of charge power and the product of charge efficiency of daily travel model and standard power consumption；Using the product of charge probabilistic model and charge power as charging load model, and the charging load prediction amount of classification electric car is obtained according to charging load model.The present invention sufficiently analyzes the charging behavior of user, more objectively predicts the charging load of all kinds of electric cars, and then provides for the construction of smart grid and intelligent transportation and forcefully support.
Description
Technical field
This application involves electric car field of intelligent control technology, more particularly to a kind of electric automobile load prediction side
Method, device, computer equipment.
Background technique
Now with the aggravation of energy crisis and environmental pollution, the intelligent transportation that people seek a kind of more scientific environmental protection goes out
Line mode, and intelligent transportation needs the strong support by smart grid.Electric car is as intelligent transportation and smart grid
Crucial tie will become irreplaceable trip tool in following social life, therefore to electric car charging load
Prediction will bring important leverage for the health operation and development of intelligent transportation and smart grid.
In recent years, related scholar proposes all multi-methods and predicts come the charging load to electric car, but mostly
Number prediction technique is filled by the electric car inidial charge amount (state of charge, SOC) of artificial subjective setting
Electric load predicts mathematical modeling, and extracts electric car charge period by Monte Carlo Analogue Method and just determine this period memory
In charging behavior, and then calculate the charging load in this period, but during realization, inventor is had found in traditional technology
At least there are the following problems：Traditional technology does not analyze the charging behavior of user sufficiently, leads to the charging load to electric car
Prediction can not objectively reflect the actual charging load of electric car.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of charging load for capableing of objective prediction electric car
Electric automobile load prediction technique, device, computer equipment.
A kind of electric car charging load forecasting method, includes the following steps：
Obtain the operating parameter of any classification electric car；Operating parameter includes standard power consumption and charge power；
According to initiation of charge moment model and charging duration model, charging probabilistic model is obtained；Charging duration model is day
The ratio of the product of the product of mileage travelled model and standard power consumption and charge power and charge efficiency；
Using the product of charge probabilistic model and charge power as charging load model, and obtained according to charging load model
The charging load prediction amount of category electric car.
In one of the embodiments,
Electric car is classified according to ride characteristic, obtains the classification of electric car；Ride characteristic includes electric car
It leaves home moment, the moment of getting home, daily stroke distances and single stroke distances.
In one of the embodiments, using the product of charge probabilistic model and charge power as charging load model, and
After the step of obtaining the charging load prediction amount of classification electric car according to charging load model, further include：
The charging load model of electric car of all categories is added up, total charging load of electric car of all categories is obtained
Model.
Operating parameter further includes initiation of charge moment and daily travel in one of the embodiments,；
The initiation of charge moment is fitted using maximum likelihood algorithm, obtains initiation of charge moment model；
Daily travel is fitted using maximum likelihood algorithm, obtains daily travel model.
It is based on following formula in one of the embodiments, obtains charging duration model：
Wherein, TcIndicate charging duration model；fD(S) daily travel model is indicated；S indicates daily travel；WStandardTable
The quasi- power consumption of indicating；PcIndicate charge power；η indicates charge efficiency.
It is based on following formula in one of the embodiments, obtains charging probabilistic model：
Wherein,Indicate charging probabilistic model；t0Indicate a certain moment；Indicate t0Moment is electronic
Automobile is charging；TcIndicate charging duration；T indicates the initiation of charge moment；
Based on following formula, obtain
Wherein, fs(t) initiation of charge moment model is indicated；Indicate charging duration model.
It is based on following formula in one of the embodiments, obtains charging load model：
Wherein, PcIndicate charge power；Indicate probabilistic model；.
A kind of electric car charging load prediction device, including：
Operating parameter obtains module, for obtaining the operating parameter of any classification electric car；Operating parameter includes standard
Power consumption and charge power；
The probabilistic model that charges obtains module, for being charged according to initiation of charge moment model and charging duration model
Probabilistic model；Charging duration model is the product and charge power and charge efficiency of daily travel model and standard power consumption
The ratio of product；
The load prediction amount that charges obtains module, and the product for will charge probabilistic model and charge power is as charging load
Model, and the charging load prediction amount of classification electric car is obtained according to charging load model.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes following steps when executing the computer program：
The probabilistic model that charges obtains module, for being charged according to initiation of charge moment model and charging duration model
Probabilistic model；The charging duration model is the product of daily travel model and the standard power consumption and the charge power
Ratio；
Charge load prediction amount obtain module, for using it is described charging probabilistic model and the charge power product as
Charge load model, and obtains the charging load prediction amount of the classification electric car according to the charging load model.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Following steps are realized when row：
Obtain the operating parameter of any classification electric car；Operating parameter includes standard power consumption and charge power；
According to initiation of charge moment model and charging duration model, charging probabilistic model is obtained；Charging duration model is day
The ratio of the product and charge power of mileage travelled model and standard power consumption；
Using the product of charge probabilistic model and charge power as charging load model, and obtained according to charging load model
The charging load prediction amount of classification electric car.
A technical solution in above-mentioned technical proposal has the following advantages that and beneficial effect：
Obtain the operating parameters of all kinds of electric cars wherein, operating parameter includes standard power consumption and charge power, tool
Body, any classification electric car obtains corresponding charging load model by following steps and exists；It is risen according to the category is electronic
Beginning charging moment model and the electronic charging duration model of the category obtain charging probabilistic model, and wherein charging duration model is day
The ratio of the product of the product of mileage travelled model and standard power consumption and charge power and charge efficiency；Obtain charging probabilistic model
With the product of charge power, and using product as charging load model, finally according to charging load model obtain the electronic vapour of classification
The charging load prediction amount of vehicle.The present invention is according to the charging behavior for sufficiently analyzing user, more objectively prediction category electricity
The charging load of electrical automobile, and then provide for the construction of smart grid and intelligent transportation and forcefully support.
Detailed description of the invention
Fig. 1 is the first step flow chart of electric car charging load forecasting method in one embodiment；
Fig. 2 is the second step flow chart of electric car charging load forecasting method in one embodiment；
Fig. 3 is the curve pair that the present invention predicts separate unit private car day charging load with traditional technology respectively in one embodiment
Than figure；
Fig. 4 is the curve that the present invention predicts separate unit electric car day charging load with traditional technology respectively in one embodiment
Comparison diagram；
Fig. 5 is the structural block diagram of electric car of the present invention charging load prediction device in one embodiment；
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
In order to solve the charging behavior that traditional technology does not analyze user sufficiently, lead to the pre- of the charging load to electric car
The problem of survey can not objectively reflect the actual charging load of electric car, in one embodiment, as shown in Figure 1,
A kind of electric automobile load prediction technique is provided, is included the following steps：
Step S110 obtains the operating parameter of any classification electric car；Operating parameter includes standard power consumption and fills
Electrical power.
Wherein, any classification refers to electric car according to the one type after certain regular partition classification.For example, one
In a specific embodiment.Electric car is classified according to ride characteristic, obtains the classification of the electric car；Ride characteristic packet
Include moment of leaving home, the moment of getting home, daily stroke distances and the single stroke distances of electric car.For example, can be by electronic vapour
Vehicle is divided into private car, officer's car, bus etc. classification.
Operating parameter refers to the system data of electric car, and in a specific implementation, operating parameter includes standard consumption
Electricity and charge power.Specifically, standard power consumption can be 100 kilometers of electric automobile during traveling of standard power consumption, certainly
It can be for using other modules.Charge power refers to the power of transmission line of electricity.In one example, it standard power consumption and fills
Electrical power can obtain to be acquired statistics in data of the previous year to all kinds of electric cars.
Step S120 obtains charging probabilistic model according to initiation of charge moment model and charging duration model；Charging duration
Model is the product and the ratio of charge power and the product of charge efficiency of daily travel model and standard power consumption.
It should be noted that operating parameter further includes initiation of charge moment and daily travel.Specifically, initiation of charge
At the time of moment is that electric car last time trip terminates.Daily travel is the mileage sum travelled in electric car one day
Charge power refers to the output power of transmission line of electricity.
Wherein, beginning charging moment model is to carry out emulation fitting at the initiation of charge moment counted to any classification electric car
The corresponding beginning charging moment model of the category is obtained, i.e., is emulated by the initiation of charge moment to each classification electric car
Simulation obtains corresponding initiation of charge moment model.Initiation of charge moment model is used to simulate starting to charge for electric car
Moment.For example, in one example, establishing starting charging moment model to the initiation of charge moment using Estimation of Distribution Algorithm.Tool
Body, an Estimation of Distribution Algorithm simulation is what the initiation of charge moment all to a classification electric car carried out.Another
In a example, the initiation of charge moment is fitted using maximum likelihood algorithm, obtains initiation of charge moment model.One secondary maximum
Likelihood algorithm simulation is to carry out at the initiation of charge moment all to a classification electric car.Specifically, utilizing maximum likelihood
The step of algorithm is fitted the initiation of charge moment include：(1) according to the initiation of charge moment, likelihood function is established；(2) to upper
It states likelihood function and takes logarithm, and arrange；(3) function obtained to above-mentioned steps (2) is differentiated；(4) above-mentioned steps (3) are obtained
Function carry out likelihood function request.
In a specific embodiment, the initiation of charge moment model that the initiation of charge moment is fitted is met
The normal distribution of following formula：
Wherein, t indicates last time trip finish time, is the initiation of charge moment；μsIndicate last time trip knot
The expectation at beam moment；σsFor the standard deviation for finish time of going on a journey for the last time.μsAnd σsWith different types of electric automobile during traveling
Characteristic and change.
Daily travel model is to carry out emulation fitting to the daily travel that any classification electric car counts to be somebody's turn to do
The corresponding beginning charging moment model of classification carries out analogue simulation by the daily travel to each classification electric car and obtains
Corresponding daily travel model.Daily travel model is used to simulate the daily travel of electric car.It will be to all kinds of electricity
The daily travel of electrical automobile statistics establishes daily travel mould corresponding with all kinds of electric cars by Mathematical Modeling Methods
Type.Daily travel model is used to simulate the total mileage travelled in one day of electric car.For example, in one example,
Daily travel model is established to daily travel using Estimation of Distribution Algorithm.In another example example, maximum likelihood is utilized
Algorithm is fitted daily travel, obtains daily travel model.
In a specific embodiment, the daily travel model that daily travel is fitted is met following
The normal distribution of formula：
Wherein, s is daily travel, and unit is km (km)；μDThe expectation of logarithm is taken for daily travel；σDFor day row
Sail the standard deviation that mileage takes logarithm.μDAnd σDChange with the ride characteristic of different type electric car.
Charging duration model can simulate the charging duration of electric car.Charging duration model be daily travel model and
The product of standard power consumption and the ratio of charge power.
In a specific embodiment, it is based on following formula, obtains charging duration model：
Wherein, fD(s) daily travel model is indicated；S indicates daily travel；WStandardExpression standard power consumption；PcIt indicates
Charge power；η indicates charge efficiency.Further, in a specific embodiment, η takes 0.9；C indicates English word
The initial of charge；The initial of D expression English word distance.
Further, by charging duration model it is found that charging duration model is daily travel fD(s) linear combination,
Therefore charging duration model can be indicated by following normal distribution：
Based on following formula, obtain in above-mentioned formula
Based on following formula, obtain in above-mentioned formula
Wherein,For the expectation of charging duration；For the standard deviation of charging duration；η indicates efficiency.
Charging probabilistic model is to simulate electric car in the probability of charging behavior sometime, i.e., sometime charges
Probability.
In a specific embodiment, it is based on following formula, obtains charging probabilistic model：
Wherein, t0Indicate a certain moment；Indicate t0Moment electric car is charging；TcIndicate charging duration；t
Indicate the initiation of charge moment；
Based on following formula, obtain
Wherein, ftIndicate initiation of charge moment model；Indicate charging duration model.I.e.Die sinking when for initiation of charge
Type fs(t) and charging durationJoint probability distribution function；；The initial of s expression English word start.
Further, t0Moment electric car is not obtained in the probability of charging by following formula：
Wherein,Indicate t0Moment electric car is not charging.
Step S130 using the product of charge probabilistic model and charge power as charging load model, and is born according to charging
Lotus model obtains the charging load prediction amount of category electric car.
Specifically, being based on following formula, charging load model is obtained：
Wherein, PcIndicate charge power；Indicate t0The probability that moment electric car is charging；C is indicated
The initial of English word charge.
Pass through the charging load of the predictable category electric car out of the charging load model.
In each embodiment of electric automobile load prediction technique of the present invention, the operating parameters of all kinds of electric cars is obtained wherein,
Operating parameter includes standard power consumption and charge power, specifically, any classification electric car passes through following steps acquisition pair
The charging load model answered exists；According to the electronic charging duration model of the electronic initiation of charge moment model of the category and the category
Charging probabilistic model is obtained, wherein charging duration model is the product and charge power of daily travel model and standard power consumption
Ratio；The product of charging probabilistic model and charge power is obtained, and using product as charging load model, it is finally negative according to charging
Lotus model obtains the charging load prediction amount of classification electric car.The present invention is according to the charging behavior for sufficiently analyzing user, more
Add the charging load for objectively predicting category electric car, and then provides for the construction of smart grid and intelligent transportation and have by force
Support to power.
In one embodiment, the load forecasting method as shown in Fig. 2, electric car of the present invention charges, includes the following steps：
Step 210, the operating parameter of any classification electric car is obtained；Operating parameter includes standard power consumption and charging
Power；
Step 220, according to initiation of charge moment model and charging duration model, charging probabilistic model is obtained；Charging duration
Model is the product of daily travel model and standard power consumption and the ratio of charge power；
Step 230, using the product of charge probabilistic model and charge power as charging load model, and according to charging load
Model obtains the charging load prediction amount of category electric car；
Step 240, the charging load model of electric car of all categories is added up, obtains the total of electric car of all categories
Charge load model.
Wherein, step 210 has been described in detail in the above-described embodiments to step 230, and details are not described herein again.
In step 240, following formula specifically can be described as：
Wherein, P indicates total charging load of all kinds of electric cars, unit kW；N is electric car sum, and unit is；
1440 indicate for be divided into 1440 minutes for 24 hours；fijIt is i-th electric car in jth minute charging probability；PcijFor i-th electricity
Charge power of the electrical automobile in jth minute, unit kW.
To further illustrate bring beneficial effect of the present invention, different types of electric car is given as shown in table 1
Ride characteristic situation is given as shown in Figures 3 and 4 with conventional method and the result of the invention to electric car charging load prediction
Comparison.
The setting of 1 electric automobile during traveling characterisitic parameter of table
By Fig. 3,4 it is found that the charging that the amplitude for the charging load predicted using the present invention is respectively less than conventional method prediction is born
The amplitude of lotus, the charging load that the present invention predicts is obtained by charge power and charging probabilistic model product, so that the present invention is more
Add the charging load of objectively reflection electric car.Conventional method and curve of the invention have a similar changing rule, it is qualitative on
The variation characteristic of charging load can be described rationally, but caused by the present invention is according to objective avoid during prediction because of subjectivity
Influence.The present invention pushes over to obtain each including charge period using the probability density at initiation of charge moment and charging duration
The charging probability at moment, confirmation electric car have certain probability that charging behavior occurs within the period.And traditional technology is to pass through
Extract charge period, default electric car charging behavior centainly occurs within the period, do not fully consider user charging with
Machine.The present invention is that the charging load at each moment can be accurately calculated based on charging moment；And traditional technology is to be based on
Charge period, the charging process shorter for charge period cannot accurately describe its load that charges.As shown in figure 3, energy of the present invention
It is enough that private car afternoon 14 is accurately depicted:00 or so charging behavior, and traditional technology could not embody moment appearance
Charge load peak, and the charging probability at each moment is influenced by adjacent moment in the present invention, and it is each in traditional technology when
The charging situation at quarter is that initiation of charge moment for being given by prognosticator, charging duration equiprobability model determine.Therefore, this hair
The bright charging behavior for capableing of the more scientific randomness that must predict all kinds of electric cars.
In electric car of the present invention charging each embodiment of load forecasting method, through this embodiment in method and step obtain
The charging load model of all kinds of electric cars, and the charging load model of all kinds of electric cars is added up and obtains the load mould that always charges
Type, by always charge load model more can integrated forecasting always charge influence of the load to entire power grid, mentioned for related technical personnel
For it is more objective, more intuitive, more fully for improving the data reference of power grid.
It should be understood that although each step in the flow chart of Fig. 1 and 2 is successively shown according to the instruction of arrow,
It is these steps is not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
There is no stringent sequences to limit for rapid execution, these steps can execute in other order.Moreover, in Fig. 1 and 2 at least
A part of step may include that perhaps these sub-steps of multiple stages or stage are not necessarily in same a period of time to multiple sub-steps
Quarter executes completion, but can execute at different times, the execution in these sub-steps or stage be sequentially also not necessarily according to
Secondary progress, but in turn or can replace at least part of the sub-step or stage of other steps or other steps
Ground executes.
In one embodiment, as shown in figure 5, providing a kind of electric car charging load prediction device, including：
Operating parameter obtains module 510, for obtaining the operating parameter of any classification electric car；Operating parameter includes mark
Quasi- power consumption and charge power；
The probabilistic model that charges obtains module 520, for being filled according to initiation of charge moment model and charging duration model
Electric probabilistic model；Charging duration model is the product and charge power and charge efficiency of daily travel model and standard power consumption
Product ratio；
The load prediction amount that charges obtains module 530, and the product for will charge probabilistic model and charge power is as charging
Load model, and the charging load prediction amount of classification electric car is obtained according to charging load model.
Specific restriction about electric car charging load prediction device may refer to charge above for electric car
The restriction of load forecasting method, details are not described herein.Modules in above-mentioned electric car charging load prediction device can be complete
Portion or part are realized by software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independently of calculating
In processor in machine equipment, it can also be stored in a software form in the memory in computer equipment, in order to processor
It calls and executes the corresponding operation of the above modules.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing the data such as initiation of charge moment, daily travel, standard power consumption and charge power.It should
The network interface of computer equipment is used to communicate with external terminal by network connection.The computer program is executed by processor
When to realize a kind of electric car charging load forecasting method.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor realize following steps when executing computer program：
Obtain the operating parameter of any classification electric car；Operating parameter includes standard power consumption and charge power；
According to initiation of charge moment model and charging duration model, charging probabilistic model is obtained；Charging duration model is day
The ratio of the product of the product of mileage travelled model and standard power consumption and charge power and charge efficiency；
Using the product of charge probabilistic model and charge power as charging load model, and obtained according to charging load model
The charging load prediction amount of classification electric car.
In one embodiment, following steps are also realized when processor executes computer program：
Electric car is classified according to ride characteristic, obtains the classification of electric car；Ride characteristic includes electric car
It leaves home moment, the moment of getting home, daily stroke distances and single stroke distances.
In one embodiment, following steps are also realized when processor executes computer program：
The charging load model of electric car of all categories is added up, total charging load of electric car of all categories is obtained
Model.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes following steps when being executed by processor：
Obtain the operating parameter of any classification electric car；Operating parameter includes standard power consumption and charge power；
According to initiation of charge moment model and charging duration model, charging probabilistic model is obtained；Charging duration model is day
The ratio of the product of the product of mileage travelled model and standard power consumption and charge power and charge efficiency；
Using the product of charge probabilistic model and charge power as charging load model, and obtained according to charging load model
The charging load prediction amount of classification electric car.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes following steps when being executed by processor：
Electric car is classified according to ride characteristic, obtains the classification of electric car；Ride characteristic includes electric car
It leaves home moment, the moment of getting home, daily stroke distances and single stroke distances.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes following steps when being executed by processor：
The charging load model of electric car of all categories is added up, total charging load of electric car of all categories is obtained
Model.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
- The load forecasting method 1. a kind of electric car charges, which is characterized in that include the following steps：Obtain the operating parameter of any classification electric car；The operating parameter includes standard power consumption, charge power and fills Electrical efficiency；According to initiation of charge moment model and charging duration model, charging probabilistic model is obtained；The charging duration model is day The ratio of the product of the product of mileage travelled model and the standard power consumption and the charge power and the charge efficiency；Using the product of the charging probabilistic model and the charge power as charging load model, and according to the charging load Model obtains the charging load prediction amount of the classification electric car.
- The load forecasting method 2. electric car according to claim 1 charges, which is characterized in thatElectric car is classified according to ride characteristic, obtains the classification of the electric car；The ride characteristic includes the electricity Moment of leaving home, the moment of getting home, daily stroke distances and the single stroke distances of electrical automobile.
- The load forecasting method 3. electric car according to claim 2 charges, which is characterized in that by the charging probability mould The product of type and the charge power is as charging load model, and it is electronic according to the charging load model to obtain the classification After the step of charging load prediction amount of automobile, further include：The charging load model of electric car of all categories is added up, total charging load of the electric car of all categories is obtained Model.
- 4. according to claim 1 to the charging load forecasting method of electric car described in 3 any one, which is characterized in that described Operating parameter further includes initiation of charge moment and daily travel；The initiation of charge moment is fitted using maximum likelihood algorithm, obtains the initiation of charge moment model；The daily travel is fitted using maximum likelihood algorithm, obtains the daily travel model.
- 5. according to claim 1 to the charging load forecasting method of electric car described in 3 any one, which is characterized in that be based on Following formula obtains the charging duration model：Wherein, TcIndicate the charging duration model；fD(S) the daily travel model is indicated；S is indicated in the day traveling Journey；WStandardIndicate the standard power consumption；PcIndicate the charge power；η indicates charge efficiency.
- The load forecasting method 6. electric car according to claim 5 charges, which is characterized in that be based on following formula, obtain Take the charging probabilistic model：Wherein,Indicate the charging probabilistic model；T0Indicate a certain moment；Indicate T0Moment is electronic Automobile is charging；TcIndicate charging duration；T indicates the initiation of charge moment；Based on following formula, described in acquisitionWherein, fs(t) the initiation of charge moment model is indicated；Indicate the charging duration model.
- The load forecasting method 7. electric car according to claim 6 charges, which is characterized in that be based on following formula, obtain Take the charging load model：Wherein, PcIndicate the charge power；Indicate the probabilistic model.
- The load prediction device 8. a kind of electric car charges, which is characterized in that including：Operating parameter obtains module, for obtaining the operating parameter of any classification electric car；The operating parameter includes standard Power consumption and charge power；The probabilistic model that charges obtains module, for obtaining charging probability according to initiation of charge moment model and charging duration model Model；The charging duration model is the product of daily travel model and the standard power consumption and the charge power and institute State the ratio of the product of charge efficiency；The load prediction amount that charges obtains module, for using the product of the charging probabilistic model and the charge power as charging Load model, and the charging load prediction amount of the classification electric car is obtained according to the charging load model.
- 9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
- 10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810690887.XA CN108876052A (en) | 2018-06-28 | 2018-06-28 | Electric car charging load forecasting method, device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810690887.XA CN108876052A (en) | 2018-06-28 | 2018-06-28 | Electric car charging load forecasting method, device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108876052A true CN108876052A (en) | 2018-11-23 |
Family
ID=64296505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810690887.XA Pending CN108876052A (en) | 2018-06-28 | 2018-06-28 | Electric car charging load forecasting method, device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108876052A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110310046A (en) * | 2019-07-09 | 2019-10-08 | 珠海格力电器股份有限公司 | Method of supplying power to, unit, system and computer readable storage medium |
| CN110401259A (en) * | 2019-08-07 | 2019-11-01 | 珠海格力电器股份有限公司 | A kind of photovoltaic bus intelligent charge management and control method and system |
| CN113094907A (en) * | 2021-04-15 | 2021-07-09 | 天津大学 | Combined scheduling method for air conditioner load and electric vehicle charging load |
| CN114274800A (en) * | 2021-12-31 | 2022-04-05 | 同济大学 | Group aggregation charging behavior prediction method for commercial electric vehicle and related device |
| DE102022126777A1 (en) | 2022-10-13 | 2024-04-18 | E.On Se | Method for controlling a plurality of charging stations in a charging system, central unit and charging system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013045449A2 (en) * | 2011-09-29 | 2013-04-04 | Nec Europe Ltd. | Method and system for charging electric vehicles |
| CN103065199A (en) * | 2012-12-18 | 2013-04-24 | 广东电网公司电力科学研究院 | Electric vehicle charging station load forecasting method |
| CN103870888A (en) * | 2014-03-10 | 2014-06-18 | 国家电网公司 | Load forecasting method for electric vehicle |
| CN105260807A (en) * | 2015-11-30 | 2016-01-20 | 江苏省电力公司苏州供电公司 | Electric automobile charging load estimation method considering random characteristics |
| CN107742038A (en) * | 2017-10-30 | 2018-02-27 | 广东电网有限责任公司惠州供电局 | Charging electric vehicle load forecasting method and device |
-
2018
- 2018-06-28 CN CN201810690887.XA patent/CN108876052A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013045449A2 (en) * | 2011-09-29 | 2013-04-04 | Nec Europe Ltd. | Method and system for charging electric vehicles |
| CN103065199A (en) * | 2012-12-18 | 2013-04-24 | 广东电网公司电力科学研究院 | Electric vehicle charging station load forecasting method |
| CN103870888A (en) * | 2014-03-10 | 2014-06-18 | 国家电网公司 | Load forecasting method for electric vehicle |
| CN105260807A (en) * | 2015-11-30 | 2016-01-20 | 江苏省电力公司苏州供电公司 | Electric automobile charging load estimation method considering random characteristics |
| CN107742038A (en) * | 2017-10-30 | 2018-02-27 | 广东电网有限责任公司惠州供电局 | Charging electric vehicle load forecasting method and device |
Non-Patent Citations (2)
| Title |
|---|
| 庄怀东等: "含电动汽车的微网系统多目标经济调度", 《电工技术学报》 * |
| 田立亭等: "电动汽车充电功率需求的统计学建模方法", 《电网技术》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110310046A (en) * | 2019-07-09 | 2019-10-08 | 珠海格力电器股份有限公司 | Method of supplying power to, unit, system and computer readable storage medium |
| CN110310046B (en) * | 2019-07-09 | 2021-02-09 | 珠海格力电器股份有限公司 | Power supply method, equipment, device, system and computer readable storage medium |
| CN110401259A (en) * | 2019-08-07 | 2019-11-01 | 珠海格力电器股份有限公司 | A kind of photovoltaic bus intelligent charge management and control method and system |
| CN113094907A (en) * | 2021-04-15 | 2021-07-09 | 天津大学 | Combined scheduling method for air conditioner load and electric vehicle charging load |
| CN114274800A (en) * | 2021-12-31 | 2022-04-05 | 同济大学 | Group aggregation charging behavior prediction method for commercial electric vehicle and related device |
| CN114274800B (en) * | 2021-12-31 | 2024-04-12 | 同济大学 | Method and related device for predicting group aggregation charging behavior of operating electric automobile |
| DE102022126777A1 (en) | 2022-10-13 | 2024-04-18 | E.On Se | Method for controlling a plurality of charging stations in a charging system, central unit and charging system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876052A (en) | Electric car charging load forecasting method, device and computer equipment | |
| CN110570014B (en) | Electric vehicle charging load prediction method based on Monte Carlo and deep learning | |
| Lojowska et al. | From transportation patterns to power demand: Stochastic modeling of uncontrolled domestic charging of electric vehicles | |
| Gan et al. | A probabilistic evaluation method of household EVs dispatching potential considering users’ multiple travel needs | |
| CN112865190A (en) | Optimal scheduling method and system for photovoltaic and charging demand-based optical storage charging station | |
| Bashash et al. | On the aggregate grid load imposed by battery health-conscious charging of plug-in hybrid electric vehicles | |
| WO2023221587A1 (en) | Method for determining state of health of power battery of electric vehicle, and server | |
| CN109711870A (en) | A kind of prediction of residential block electric car charging load and configuration method | |
| Wang et al. | Analysis of multi-location PEV charging behaviors based on trip chain generation | |
| CN111400662A (en) | Space load prediction method considering electric vehicle charging demand | |
| CN112994092B (en) | Independent wind-solar storage micro-grid system size planning method based on power prediction | |
| CN109713674A (en) | Meter and the off-network type micro-capacitance sensor reliability estimation method of the orderly charge and discharge of electric car | |
| CN114219214A (en) | Power grid comprehensive risk assessment system considering new energy and electric automobile access | |
| Gao et al. | Charging load forecasting of electric vehicle based on Monte Carlo and deep learning | |
| Su et al. | Operating status prediction model at EV charging stations with fusing spatiotemporal graph convolutional network | |
| Darabi et al. | Extracting probability distribution functions applicable for PHEVs charging load profile | |
| Nespoli et al. | User behavior clustering based method for ev charging forecast | |
| CN113435663A (en) | CNN-LSTM combined load prediction method considering electric vehicle charging load influence | |
| CN109359784A (en) | The electric automobile load time forecasting methods and system of meter and operator | |
| Grahn et al. | Plug-in-vehicle mobility and charging flexibility Markov model based on driving behavior | |
| Boulakhbar et al. | Electric vehicles arrival and departure time prediction based on deep learning: the case of Morocco | |
| CN110648013A (en) | Electric vehicle charging load prediction method based on dual-mode maximum entropy | |
| CN109878370A (en) | A kind of charging method and device of electric car cluster | |
| CN110852378A (en) | Road condition kinematics segment extraction method based on navigation system | |
| CN110492509A (en) | A kind of distributed generation resource equivalent method based on electric car electric discharge behavior |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181123 |