CN115689028A - Electric vehicle charging prediction method, device and equipment - Google Patents
Electric vehicle charging prediction method, device and equipment Download PDFInfo
- Publication number
- CN115689028A CN115689028A CN202211379306.3A CN202211379306A CN115689028A CN 115689028 A CN115689028 A CN 115689028A CN 202211379306 A CN202211379306 A CN 202211379306A CN 115689028 A CN115689028 A CN 115689028A
- Authority
- CN
- China
- Prior art keywords
- model
- electric vehicle
- charging
- charging station
- selection
- 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
Images
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
Landscapes
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses a method, a device and equipment for predicting electric vehicle charging, relating to the technical field of electric vehicles, wherein an initial selection model for selecting a charging station for charging when a user drives an electric vehicle is constructed, and the trip will of the user is fully considered in the initial selection model; continuously optimizing the model coefficient of the initial selection model according to a theoretical charging selection result obtained by predicting the selection model and an actual charging selection result obtained based on actual measurement or research to obtain a target selection model; the charging station selected when the electric vehicle is charged is predicted based on the target selection model, so that the user's trip will be fully considered and the charging station to be selected for charging when the user drives the electric vehicle is accurately predicted when the electric vehicle is charged.
Description
Technical Field
The invention relates to the technical field of electric automobiles, in particular to an electric automobile charging prediction method, an electric automobile charging prediction device and electric automobile charging prediction equipment.
Background
At present, electric vehicles powered by clean energy are rapidly developing. In the practical application scenario of electric vehicles, the disordered access of large-scale electric vehicles brings adverse effects such as load increase, power quality reduction, increased difficulty in power grid operation optimization control and the like to a power system, and higher requirements are put forward on charging station planning.
Therefore, the above problems are generally solved by an ordered charging control method based on accurate prediction of the temporal and spatial distribution of the charging demand of the electric vehicle, and the research on the temporal and spatial distribution of the charging demand of the electric vehicle is mainly carried out from the operation rule of the electric vehicle and is combined with a trip chain and a trip desire of a user.
However, the related documents pay attention to energy consumption change caused by real-time dynamic traffic flow change so as to influence travel willingness of users; in addition, external factors such as different time periods, weather types and ambient temperatures can influence the trip willingness of the user. In other words, the user's will is a very subjective factor and is difficult to predict.
Disclosure of Invention
The invention mainly aims to provide an electric vehicle charging prediction method, an electric vehicle charging prediction device and electric vehicle charging prediction equipment, and aims to solve the technical problem that in the prior art, when electric vehicle charging prediction is carried out, the user trip will is difficult to be fully considered, so that the charging prediction of an electric vehicle is not accurate enough.
In order to achieve the above object, the present invention provides a method for predicting charging of an electric vehicle, comprising the following steps:
constructing an initial selection model for selecting a charging station for charging of the electric vehicle;
iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result of the initial selection model and the acquired actual selection result to obtain a target selection model;
and predicting the selected charging station when the electric vehicle is charged based on the target selection model.
Optionally, the step of constructing an initial selection model for selecting a charging station for charging by the electric vehicle includes:
constructing an original selection model for selecting a charging station for charging of the electric vehicle based on the gravity model;
and solving the initial model coefficient of the original selection model to obtain the initial selection model.
Optionally, before the step of constructing a raw selection model for selecting an electric vehicle to charge by a charging station based on the gravitation model, the method further comprises:
determining the performance of a charging station, the performance of an electric vehicle and the interaction information between the electric vehicle and the charging station;
the step of constructing an original selection model for selecting the electric vehicle to charge the charging station based on the gravitation model comprises the following steps:
constructing the raw selection model based on the charging station performance, the electric vehicle performance, the interaction information, and initial model coefficients of the raw selection model and with reference to the gravity model.
Optionally, the step of determining the charging station performance, the electric vehicle performance and the interaction information between the electric vehicle and the charging station includes:
determining the charging station performance based on the number of charging piles within a charging station and the charging efficiency of the charging station;
determining electric vehicle performance based on a state of charge of an electric vehicle;
and determining the comprehensive distance between the electric vehicle and the charging station based on the distance of each path between the electric vehicle and the charging station, the average speed of the electric vehicle to the charging station when the electric vehicle runs at the distance of each path, and the weight of each path between the electric vehicle and the charging station, and taking the comprehensive distance as the interactive information.
Optionally, the step of solving initial model coefficients of the originally selected model comprises:
substituting attribute information of the electric automobile and the charging station and interactive information between the electric automobile and the charging station into the original selection model;
and fitting to obtain the initial model coefficient based on the original selection model and the actual selection result of the electric vehicle for selecting the charging station for charging.
Optionally, the step of iteratively optimizing the model coefficients of the initially selected model to obtain a target selected model includes:
inputting attribute information, interaction information and initial model coefficients of the electric vehicle and the charging station in the current period into the initial selection model to obtain a theoretical selection result;
acquiring an actual selection result of the electric vehicle in the current period for selecting a charging station to charge;
and iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result to obtain the target selection model.
Optionally, the step of obtaining an actual selection result that the electric vehicle selects the charging station for charging in the current cycle includes:
collecting actual selection preference of each electric vehicle when the electric vehicle selects a charging station for charging in the current period;
and carrying out quantitative sorting based on the actual selection preference to obtain the actual selection result.
Optionally, the step of iteratively optimizing the model coefficients of the initial selection model based on the theoretical selection result and the actual selection result includes:
and dynamically correcting the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result, wherein the theoretical selection result obtained according to the model after dynamic correction is predicted to be close to or equal to the actual selection result.
Optionally, the step of iteratively optimizing a model coefficient of the initial selection model based on the theoretical selection result and the actual selection result to obtain the target selection model includes:
if the difference between the model coefficients before and after modification is smaller than a preset threshold value, determining the modified selection model as a target selection model, and taking the modified model coefficient as the model coefficient of the target selection model;
and if the difference between the model coefficients before and after correction is not less than a preset threshold value, circularly and dynamically correcting the model coefficients of the initially selected model until the difference between the model coefficients before and after correction is less than a preset difference value.
Optionally, the electric vehicle charging prediction method further includes:
constructing a first initial selection model for charging by selecting a charging station for the electric vehicle on a working day and a second initial selection model for charging by selecting the charging station for the electric vehicle on a non-working day;
optimizing the model coefficient of the first initial selection model to obtain a first target selection model, and optimizing the model coefficient of the second initial selection model to obtain a second target selection model;
and predicting the selected charging station when the electric vehicle is charged in a working day based on the first target selection model, and predicting the selected charging station when the electric vehicle is charged in a non-working day based on the second target selection model.
In addition, to achieve the above object, the present invention provides an electric vehicle charging prediction device, including:
the system comprises a construction module, a charging module and a charging module, wherein the construction module is used for constructing an initial selection model for selecting a charging station for charging the electric vehicle;
the optimization module is used for iteratively optimizing the model coefficient of the initial selection model to obtain a target selection model based on the theoretical selection result of the initial selection model and the acquired actual selection result;
and the prediction module is used for predicting the selected charging station when the electric automobile is charged based on the target selection model.
In addition, to achieve the above object, the present invention also provides an electric vehicle charging prediction apparatus, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the electric vehicle charging prediction method as described above.
The embodiment of the invention provides an electric vehicle charging prediction method, an electric vehicle charging prediction device and electric vehicle charging prediction equipment, which comprise the following steps: constructing an initial selection model for selecting a charging station for charging of the electric vehicle; iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result of the initial selection model and the acquired actual selection result to obtain a target selection model; and predicting the selected charging station when the electric vehicle is charged based on the target selection model.
In the method, an initial selection model for selecting a charging station for charging when a user drives an electric vehicle is constructed, and the trip will of the user is fully considered in the initial selection model; continuously optimizing the model coefficient of the initial selection model according to a theoretical charging selection result obtained by predicting the selection model and an actual charging selection result obtained based on actual measurement or research to obtain a target selection model; and predicting the charging station selected by the electric vehicle when the electric vehicle is charged based on the target selection model, so that the travel will of the user is fully considered and the charging station to be selected for charging when the user drives the electric vehicle is accurately predicted when the electric vehicle is charged.
Drawings
FIG. 1 is a schematic diagram of a hardware execution environment execution device according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an embodiment of a method for predicting charging of an electric vehicle according to the present invention;
FIG. 3 is a schematic flowchart illustrating a method for predicting charging of an electric vehicle according to another embodiment of the present invention;
FIG. 4 is a schematic flowchart illustrating a method for predicting charging of an electric vehicle according to another embodiment of the present invention;
fig. 5 is a flowchart illustrating a method for predicting charging of an electric vehicle according to another embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an operating device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the operation device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in FIG. 1 is not intended to be limiting as to the operating equipment and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, the memory 1005, which is a storage medium, may include therein an operating system, a data storage module, a network communication module, a user interface module, and a computer program.
In the operating device shown in fig. 1, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the execution device of the present invention may be provided in an execution device that calls the computer program stored in the memory 1005 by the processor 1001 and performs the following operations:
constructing an initial selection model for selecting a charging station for charging of the electric vehicle;
iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result of the initial selection model and the acquired actual selection result to obtain a target selection model;
and predicting the selected charging station when the electric vehicle is charged based on the target selection model.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
the step of constructing an initial selection model for selecting a charging station for charging of the electric vehicle comprises the following steps:
constructing an original selection model for selecting a charging station for charging of the electric vehicle based on the gravity model;
and solving the initial model coefficient of the original selection model to obtain the initial selection model.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
before the step of constructing an original selection model for selecting an electric vehicle to charge by a charging station based on the gravitation model, the method further comprises the following steps:
determining the performance of a charging station, the performance of an electric vehicle and the interaction information between the electric vehicle and the charging station;
the step of constructing an original selection model for selecting the electric vehicle to charge the charging station based on the gravitation model comprises the following steps:
and constructing the original selection model based on the charging station performance, the electric vehicle performance, the interaction information and the initial model coefficient of the original selection model and by referring to the gravity model.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
the step of determining the performance of the charging station, the performance of the electric vehicle and the interaction information between the electric vehicle and the charging station comprises the following steps:
determining the charging station performance based on the number of charging piles within a charging station and the charging efficiency of the charging station;
determining electric vehicle performance based on a state of charge of an electric vehicle;
and determining the comprehensive distance between the electric vehicle and the charging station based on the distance of each path between the electric vehicle and the charging station, the average speed of the electric vehicle to the charging station when the electric vehicle runs at the distance of each path, and the weight of each path between the electric vehicle and the charging station, and taking the comprehensive distance as the interactive information.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
the step of solving initial model coefficients for the originally selected model comprises:
substituting attribute information of the electric automobile and the charging station and interactive information between the electric automobile and the charging station into the original selection model;
and fitting to obtain the initial model coefficient based on the original selection model and the actual selection result of the electric vehicle for selecting the charging station for charging.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
the step of iteratively optimizing the model coefficients of the initial selection model to obtain a target selection model includes:
inputting attribute information, interaction information and initial model coefficients of the electric vehicle and the charging station in the current period into the initial selection model to obtain a theoretical selection result;
acquiring an actual selection result of the electric vehicle in the current period for selecting a charging station to charge;
and iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result to obtain the target selection model.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
the step of obtaining the actual selection result of the electric vehicle in the current period selecting the charging station for charging includes:
collecting actual selection preference of each electric vehicle when the electric vehicle selects a charging station for charging in the current period;
and carrying out quantitative sorting based on the actual selection preference to obtain the actual selection result.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
the step of iteratively optimizing model coefficients of the initial selection model based on the theoretical selection result and the actual selection result includes:
and dynamically correcting the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result, wherein the theoretical selection result obtained according to the model after dynamic correction is predicted to be close to or equal to the actual selection result.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
the step of iteratively optimizing the model coefficients of the initial selection model based on the theoretical selection result and the actual selection result to obtain the target selection model comprises:
if the difference between the model coefficients before and after modification is smaller than a preset threshold value, determining the modified selection model as a target selection model, and taking the modified model coefficient as the model coefficient of the target selection model;
and if the difference between the model coefficients before and after correction is not less than a preset threshold value, circularly and dynamically correcting the model coefficients of the initially selected model until the difference between the model coefficients before and after correction is less than a preset difference value.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
the electric vehicle charging prediction method further comprises the following steps:
constructing a first initial selection model for charging by selecting a charging station for the electric vehicle on a working day and a second initial selection model for charging by selecting the charging station for the electric vehicle on a non-working day;
optimizing the model coefficient of the first initial selection model to obtain a first target selection model, and optimizing the model coefficient of the second initial selection model to obtain a second target selection model;
and predicting the selected charging station when the electric vehicle is charged in a working day based on the first target selection model, and predicting the selected charging station when the electric vehicle is charged in a non-working day based on the second target selection model.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating an embodiment of a charging prediction method for an electric vehicle according to the present invention. The embodiment of the invention provides an electric vehicle charging prediction method, which comprises the following steps:
step S10: and constructing an initial selection model for selecting a charging station for charging the electric vehicle.
The initial selection model is a model which fully considers the trip willingness of the user, wherein the trip willingness of the user comprises but is not limited to the charging station performance represented by the number of charging piles in the charging station and the charging efficiency of each charging pile; electric vehicle performance characterized using a state of charge of the electric vehicle; and determining the interaction information between the electric vehicle and the charging station represented by the comprehensive distance between the electric vehicle and the charging station by using the path distance between the electric vehicle and the charging station, the average speed of the electric vehicle for driving the path distance to reach the charging station, the path weight between the electric vehicle and the charging station, and the like.
Further, referring to fig. 3, step S10 includes:
step S101: constructing an original selection model for selecting a charging station for charging the electric vehicle based on the gravitation model;
the original selection model between the ith electric vehicle and the charging station j constructed based on the gravitation model is as follows:
wherein M is j For charging station j performance, m i For the performance of the ith electric vehicle, R ij For the interaction between the ith electric vehicle and charging station j, k ij Are the model coefficients.
Optionally, referring to fig. 3, before step S101, the method further includes:
step S100: determining the performance of a charging station, the performance of an electric vehicle and the interaction information between the electric vehicle and the charging station;
alternatively, referring to fig. 4, step S100 includes:
step S100A: determining the charging station performance based on the number of charging piles within a charging station and the charging efficiency of the charging station;
step S100B: determining electric vehicle performance based on a state of charge of the electric vehicle;
step S100C: and determining the comprehensive distance between the electric vehicle and the charging station based on the distance of each path between the electric vehicle and the charging station, the average speed of the electric vehicle to the charging station when the electric vehicle runs at the distance of each path, and the weight of each path between the electric vehicle and the charging station, and taking the comprehensive distance as the interactive information.
Step S101, comprising:
constructing the raw selection model based on the charging station performance, the electric vehicle performance, the interaction information, and initial model coefficients of the raw selection model and with reference to the gravity model.
M j For the charging station j performance, the number of charging piles in the charging station j is multiplied by the efficiency to obtain a value, namely M j ＝δ j v j Wherein, delta j Number of charging piles, v, representing charging station j j Representing the charging efficiency of each charging pile of charging station j.
m i As a function of the state of charge of the ith electric vehicle, i.e.
Wherein, in the step (A),
is the state of charge of the ith electric vehicle, S SOC Is the state of charge threshold.
R ij For the interactive information between the ith electric vehicle and the charging station j, the comprehensive distance between the ith electric vehicle and the charging station j is mainly considered, namely
Wherein, ω is ijk Is the path weight of the path k between the ith electric vehicle and the charging station j, d ijk Path distance, v, of path k between ith electric vehicle and charging station j ijk Is the average speed of the path k between the ith electric vehicle and the charging station j.
k ij The model coefficient is obtained by fitting the actual preference of each electric vehicle to each charging station according to a prediction function based on a gravitation model, an investigation questionnaire and actual measurement by a least square fitting method mainly considering the queuing condition of each electric vehicle in the charging station. The simulation coefficients vary with different electric vehicles and different charging stations, and also vary with different time periods.
Step S102: and solving the initial model coefficient of the original selection model to obtain the initial selection model.
Optionally, step S102 includes:
step S102A: substituting attribute information of the electric automobile and the charging station and interaction information between the electric automobile and the charging station into the original selection model;
step S102B: and fitting to obtain the initial model coefficient based on the original selection model and the actual selection result of the electric vehicle for selecting the charging station for charging.
The method comprises the steps of obtaining the number of charging piles and charging efficiency of space-time surplus in each charging station, the real-time charge state of each electric vehicle, the real-time distance between each electric vehicle and each charging station and the average speed of each electric vehicle to each charging station, namely obtaining attribute information of the electric vehicles and the charging stations. And correspondingly substituting the attribute information of the electric vehicle and the charging station in the selection model and the numerical values of all parameters of the interactive information between the electric vehicle and the charging station into the original selection model to obtain a temporary selection result through calculation, and performing fitting based on a least square curve fitting method on the actual selection result of the electric vehicle for selecting the charging station for charging to obtain an initial numerical value of a model coefficient, namely solving to obtain the initial model coefficient. The actual selection result is the result obtained by quantitatively sequencing the selection preference of each electric vehicle to each charging station during charging based on the actual measurement and research method.
Step S20: and iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result of the initial selection model and the acquired actual selection result to obtain a target selection model.
Through the initial selection model constructed in the step S10, the initial model coefficient is obtained only by once calculation and fitting according to data in a certain period, and the charging scene of the electric vehicle can be accurately predicted only by performing iterative loop optimization on the initial model coefficient for a plurality of periods.
Further, referring to fig. 5, step S20 includes:
step S200: inputting attribute information, interaction information and initial model coefficients of the electric vehicle and the charging station in the current period into the initial selection model to obtain a theoretical selection result;
step S201: acquiring an actual selection result of the electric vehicle in the current period for selecting a charging station to charge;
step S202: and iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result to obtain the target selection model.
Optionally, the step of obtaining an actual selection result that the electric vehicle selects the charging station to perform charging in the current cycle includes:
collecting actual selection preference when each electric vehicle selects a charging station for charging in the current period;
and carrying out quantitative sorting based on the actual selection preference to obtain the actual selection result.
Inputting the attribute information of the electric vehicles and the charging stations in the current period into the initial selection model, and calculating to obtain a theoretical selection result of the electric vehicles in the current period for selecting the charging stations to charge; actual selection results obtained by quantitatively sequencing selection preferences of all electric vehicles in the current period during charging of all charging stations based on actual measurement and research methods; and optimizing the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result, and taking the optimized model coefficient as the model coefficient of the target selection model, thereby obtaining the target selection model capable of accurately predicting the charging selection of the electric vehicle.
Optionally, the step of iteratively optimizing the model coefficients of the initial selection model based on the theoretical selection result and the actual selection result includes:
and dynamically correcting the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result, wherein the theoretical selection result obtained according to the model after dynamic correction is predicted to be close to or equal to the actual selection result.
When the model coefficient of the initial selection model is optimized based on the theoretical selection result and the actual selection result, the predicted value curve of the theoretical selection result is compared with the true value curve of the actual selection result, and the model coefficient of the initial selection model is dynamically corrected according to the comparison result, so that the new theoretical selection result obtained based on the prediction of the corrected selection model is close to the actual selection result. Further, when the difference value between the new theoretical selection result and the actual theoretical selection result is smaller than a preset deviation value, the correction of the initial model coefficient is determined to be completed.
Optionally, the step of iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result to obtain the target selection model includes:
if the difference between the model coefficients before and after modification is smaller than a preset threshold value, determining the modified selection model as a target selection model, and taking the modified model coefficient as the model coefficient of the target selection model;
and if the difference of the model coefficients before and after the correction is not less than a preset threshold value, circularly and dynamically correcting the model coefficient of the initially selected model until the difference of the model coefficients before and after the correction is less than a preset difference value.
In the process of dynamically modifying the model coefficients according to the theoretical selection result and the actual selection result, a dynamic modification ending condition is required. Further, whether the dynamic correction of the model coefficient is stopped or not is determined according to the size judgment result of the difference between the model coefficients before and after the correction and the preset threshold. When the difference between the model coefficients before and after modification is smaller than a preset threshold value, determining the modified selection model as a target selection model, and taking the modified model coefficient as a final target model coefficient of the target selection model; otherwise, if the difference between the model coefficients before and after the modification is not smaller than the preset threshold, the model coefficients of the initial selection model are cyclically and dynamically modified until the difference between the model coefficients before and after the modification is smaller than the preset difference, and then the model coefficient whose difference between the model coefficients before and after the modification is smaller than the corresponding preset difference is used as the final target model coefficient of the target selection model.
Further, model coefficients defining adjacent periods are fitted to a phase difference matrix of
k 11 -k′ 11 ...k 1j -k′ 1j
.........
k i1 -k′ i1 ...k ij -k′ ij
Wherein k is 11 、k 1j 、k i1 、k ij Etc. are model coefficients, k ', in the previous cycle selection model' 11 、k′ 1j 、 k′ i1 、k′ ij Etc. are the model coefficients in the selected model for the next cycle. If the second norm of the fitting phase difference matrix is smaller than a preset threshold value, the optimal fitting of the model coefficient can be considered to be no longer carried out on the basis of the actual selection result obtained by actual measurement investigation, and the constructed electric vehicle charging prediction model, namely the target selection model is adoptedThe model can accurately reflect the charging intention of the electric automobile.
Step S30: and predicting the selected charging station when the electric vehicle is charged based on the target selection model.
And predicting the selected charging station when the electric vehicle is charged through the target selection model suitable for different periods. Therefore, the spatial-temporal distribution of the charging demand of the electric automobile is accurately predicted by combining the trip desire of a user, the adverse effects of load increase, electric energy quality reduction, grid operation optimization control difficulty increase and the like caused by the disordered access of a large-scale electric automobile in the practical application scene of the electric automobile are solved by a more accurate ordered charging control method, and the planning requirement of a charging station is further met.
Further, the electric vehicle charging prediction method further includes:
constructing a first initial selection model for charging by selecting a charging station for the electric vehicle on a working day and a second initial selection model for charging by selecting the charging station for the electric vehicle on a non-working day;
optimizing the model coefficient of the first initial selection model to obtain a first target selection model, and optimizing the model coefficient of the second initial selection model to obtain a second target selection model;
and predicting the selected charging station when the electric vehicle is charged on a working day based on the first target selection model, and predicting the selected charging station when the electric vehicle is charged on a non-working day based on the second target selection model.
In two time periods of working days and non-working days, the performance M of each charging station j j Performance m of the ith electric vehicle i And interactive information R between the ith electric vehicle and the charging station j ij Model coefficient k ij Although the definitions of the users are the same, the values are different because the trip intentions of the users in the two different time periods are obviously different. Therefore, on the premise of decomposing factors influencing the charging of the electric vehicle, the influence of working days and non-working days is considered, a first initial selection model for selecting the charging station for charging the electric vehicle on the working days and a first initial selection model for selecting the charging station for charging the electric vehicle on the non-working days are constructedA second initial selection model of charging is performed. And predicting the charging station selected when the electric vehicle is charged on a working day based on a first target selection model obtained by optimizing the model coefficient of the first initial selection model, and similarly predicting the charging station selected when the electric vehicle is charged on a non-working day based on a second target selection model obtained by optimizing the model coefficient of the second initial selection model, so that the charging selection of the user when the user drives the electric vehicle is more accurately predicted.
In the embodiment, an initial selection model for selecting a charging station for charging the electric vehicle is constructed; iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result of the initial selection model and the acquired actual selection result to obtain a target selection model; and predicting the selected charging station when the electric vehicle is charged based on the target selection model.
In the method, an initial selection model for selecting a charging station for charging when a user drives an electric vehicle is constructed, and the trip will of the user is fully considered in the initial selection model; continuously optimizing the model coefficient of the initial selection model according to a theoretical charging selection result obtained by predicting the selection model and an actual charging selection result obtained based on actual measurement or research to obtain a target selection model; the charging station selected when the electric vehicle is charged is predicted based on the target selection model, so that the user's trip will be fully considered and the charging station to be selected for charging when the user drives the electric vehicle is accurately predicted when the electric vehicle is charged.
In addition, an embodiment of the present invention further provides an electric vehicle charging prediction apparatus, where the electric vehicle charging prediction apparatus includes:
the system comprises a construction module, a charging module and a charging module, wherein the construction module is used for constructing an initial selection model for selecting a charging station for charging the electric vehicle;
the optimization module is used for iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result of the initial selection model and the acquired actual selection result to obtain a target selection model;
and the prediction module is used for predicting the selected charging station when the electric automobile is charged based on the target selection model.
Optionally, the building module is further configured to:
constructing an original selection model for selecting a charging station for charging of the electric vehicle based on the gravity model;
and solving the initial model coefficient of the original selection model to obtain the initial selection model.
Optionally, the building module is further configured to:
determining the performance of a charging station, the performance of an electric vehicle and the interaction information between the electric vehicle and the charging station;
the step of constructing an original selection model for selecting the electric vehicle to charge the charging station based on the gravitation model comprises the following steps:
constructing the raw selection model based on the charging station performance, the electric vehicle performance, the interaction information, and initial model coefficients of the raw selection model and with reference to the gravity model.
Optionally, the building module is further configured to:
determining the charging station performance based on the number of charging piles within a charging station and the charging efficiency of the charging station;
determining electric vehicle performance based on a state of charge of an electric vehicle;
and determining a comprehensive distance between the electric vehicle and the charging station based on the distance of each path between the electric vehicle and the charging station, the average speed of each path between the electric vehicle and the charging station, and the weight of each path between the electric vehicle and the charging station, and taking the comprehensive distance as the interactive information.
Optionally, the building module is further configured to:
substituting attribute information of the electric automobile and the charging station and interactive information between the electric automobile and the charging station into the original selection model;
and fitting to obtain the initial model coefficient based on the original selection model and the actual selection result of the electric vehicle for selecting the charging station for charging.
Optionally, the optimization module is further configured to:
inputting attribute information, interaction information and initial model coefficients of the electric vehicle and the charging station in the current period into the initial selection model to obtain a theoretical selection result;
acquiring an actual selection result of the electric vehicle in the current period for selecting a charging station to charge;
and iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result to obtain the target selection model.
Optionally, the optimization module is further configured to:
collecting actual selection preference of each electric vehicle when the electric vehicle selects a charging station for charging in the current period;
and carrying out quantitative sorting based on the actual selection preference to obtain the actual selection result.
Optionally, the optimization module is further configured to:
and dynamically correcting the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result, wherein the theoretical selection result predicted according to the dynamically corrected model is close to or equal to the actual selection result.
Optionally, the optimization module is further configured to:
if the difference between the model coefficients before and after modification is smaller than a preset threshold value, determining the modified selection model as a target selection model, and taking the modified model coefficient as the model coefficient of the target selection model;
and if the difference between the model coefficients before and after correction is not less than a preset threshold value, circularly and dynamically correcting the model coefficients of the initially selected model until the difference between the model coefficients before and after correction is less than a preset difference value.
Optionally, the electric vehicle charging prediction apparatus further includes an advance prediction module, configured to:
constructing a first initial selection model for charging by selecting a charging station for the electric vehicle on a working day and a second initial selection model for charging by selecting the charging station for the electric vehicle on a non-working day;
optimizing the model coefficient of the first initial selection model to obtain a first target selection model, and optimizing the model coefficient of the second initial selection model to obtain a second target selection model;
and predicting the selected charging station when the electric vehicle is charged in a working day based on the first target selection model, and predicting the selected charging station when the electric vehicle is charged in a non-working day based on the second target selection model.
The electric vehicle charging prediction device provided by the invention adopts the electric vehicle charging prediction method in the embodiment, and solves the technical problem that the charging prediction of an electric vehicle is not accurate enough due to the difficulty in fully considering the travel will of a user when the electric vehicle charging prediction is carried out in the prior art. Compared with the prior art, the beneficial effects of the electric vehicle charging prediction device provided by the embodiment of the invention are the same as the beneficial effects of the electric vehicle charging prediction method provided by the embodiment, and other technical features of the electric vehicle charging prediction device are the same as those disclosed by the embodiment method, which are not repeated herein.
In addition, an embodiment of the present invention further provides an electric vehicle charging prediction device, where the electric vehicle charging prediction device includes: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the electric vehicle charging prediction method as described above.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are also included in the scope of the present invention.
Claims (12)
1. The electric vehicle charging prediction method is characterized by comprising the following steps:
constructing an initial selection model for selecting a charging station for charging the electric vehicle;
iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result of the initial selection model and the acquired actual selection result to obtain a target selection model;
and predicting the selected charging station when the electric vehicle is charged based on the target selection model.
2. The method for predicting electric vehicle charging according to claim 1, wherein the step of constructing an initial selection model for selecting a charging station for charging by an electric vehicle comprises:
constructing an original selection model for selecting a charging station for charging the electric vehicle based on the gravitation model;
and solving the initial model coefficient of the original selection model to obtain the initial selection model.
3. The electric vehicle charging prediction method of claim 2, wherein before the step of constructing a raw selection model for selecting a charging station for charging the electric vehicle based on the gravity model, the method further comprises:
determining the performance of a charging station, the performance of an electric vehicle and the interaction information between the electric vehicle and the charging station;
the step of constructing an original selection model for selecting the charging station for charging the electric vehicle based on the gravitation model comprises the following steps:
and constructing the original selection model based on the charging station performance, the electric vehicle performance, the interaction information and the initial model coefficient of the original selection model and by referring to the gravity model.
4. The electric vehicle charging prediction method of claim 3, wherein the step of determining the charging station performance, the electric vehicle performance, and the interaction information between the electric vehicle and the charging station comprises:
determining the charging station performance based on the number of charging piles within a charging station and the charging efficiency of the charging station;
determining electric vehicle performance based on a state of charge of the electric vehicle;
and determining a comprehensive distance between the electric vehicle and the charging station based on the distance of each path between the electric vehicle and the charging station, the average speed of each path between the electric vehicle and the charging station, and the weight of each path between the electric vehicle and the charging station, and taking the comprehensive distance as the interactive information.
5. The method of predicting electric vehicle charging of claim 2, wherein said step of solving initial model coefficients of said originally selected model comprises:
substituting attribute information of the electric automobile and the charging station and interaction information between the electric automobile and the charging station into the original selection model;
and fitting to obtain the initial model coefficient based on the original selection model and the actual selection result of the electric vehicle for selecting the charging station for charging.
6. The method for predicting electric vehicle charging according to claim 1, wherein the step of iteratively optimizing model coefficients of the initially selected model to obtain a target selection model comprises:
inputting attribute information, interaction information and initial model coefficients of the electric vehicle and the charging station in the current period into the initial selection model to obtain a theoretical selection result;
acquiring an actual selection result of the electric vehicle in the current period for selecting a charging station to charge;
and iteratively optimizing the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result to obtain the target selection model.
7. The method for predicting the charging of the electric vehicle according to claim 6, wherein the step of obtaining the actual selection result of the electric vehicle selecting the charging station for charging in the current cycle comprises:
collecting actual selection preference of each electric vehicle when the electric vehicle selects a charging station for charging in the current period;
and carrying out quantitative sorting based on the actual selection preference to obtain the actual selection result.
8. The electric vehicle charging prediction method of claim 6, wherein the step of iteratively optimizing model coefficients of the initial selection model based on the theoretical selection result and the actual selection result comprises:
and dynamically correcting the model coefficient of the initial selection model based on the theoretical selection result and the actual selection result, wherein the theoretical selection result predicted according to the dynamically corrected model is close to or equal to the actual selection result.
9. The electric vehicle charging prediction method of claim 6, wherein the step of iteratively optimizing model coefficients of the initial selection model based on the theoretical selection result and the actual selection result to obtain the target selection model comprises:
if the difference between the model coefficients before and after modification is smaller than a preset threshold value, determining the modified selection model as a target selection model, and taking the modified model coefficient as the model coefficient of the target selection model;
and if the difference between the model coefficients before and after correction is not less than a preset threshold value, circularly and dynamically correcting the model coefficients of the initially selected model until the difference between the model coefficients before and after correction is less than a preset difference value.
10. The electric vehicle charging prediction method of claim 1, further comprising:
constructing a first initial selection model for charging by selecting a charging station for the electric vehicle on a working day and a second initial selection model for charging by selecting the charging station for the electric vehicle on a non-working day;
optimizing the model coefficient of the first initial selection model to obtain a first target selection model, and optimizing the model coefficient of the second initial selection model to obtain a second target selection model;
and predicting the selected charging station when the electric vehicle is charged on a working day based on the first target selection model, and predicting the selected charging station when the electric vehicle is charged on a non-working day based on the second target selection model.
11. An electric vehicle charging prediction device, characterized in that the electric vehicle charging prediction device comprises:
the system comprises a construction module, a charging module and a charging module, wherein the construction module is used for constructing an initial selection model for selecting a charging station for charging the electric vehicle;
the optimization module is used for iteratively optimizing the model coefficient of the initial selection model to obtain a target selection model based on the theoretical selection result of the initial selection model and the acquired actual selection result;
and the prediction module is used for predicting the selected charging station when the electric automobile is charged based on the target selection model.
12. An electric vehicle charging prediction apparatus, characterized in that the electric vehicle charging prediction apparatus comprises: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the electric vehicle charging prediction method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211379306.3A CN115689028A (en) | 2022-11-04 | 2022-11-04 | Electric vehicle charging prediction method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211379306.3A CN115689028A (en) | 2022-11-04 | 2022-11-04 | Electric vehicle charging prediction method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115689028A true CN115689028A (en) | 2023-02-03 |
Family
ID=85049252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211379306.3A Pending CN115689028A (en) | 2022-11-04 | 2022-11-04 | Electric vehicle charging prediction method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115689028A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116691413A (en) * | 2023-07-31 | 2023-09-05 | 国网浙江省电力有限公司 | Advanced vehicle-mounted dynamic load pre-configuration method and ordered charging system |
-
2022
- 2022-11-04 CN CN202211379306.3A patent/CN115689028A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116691413A (en) * | 2023-07-31 | 2023-09-05 | 国网浙江省电力有限公司 | Advanced vehicle-mounted dynamic load pre-configuration method and ordered charging system |
| CN116691413B (en) * | 2023-07-31 | 2023-10-20 | 国网浙江省电力有限公司 | Advanced vehicle-mounted dynamic load pre-configuration method and ordered charging system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lu et al. | Multi-agent deep reinforcement learning based demand response for discrete manufacturing systems energy management | |
| Tang et al. | Waiting time minimized charging and discharging strategy based on mobile edge computing supported by software-defined network | |
| EP3938963A1 (en) | Scheduling computation graphs using neural networks | |
| CN113326126B (en) | Task processing method, task scheduling method, device and computer equipment | |
| CN109597965B (en) | Data processing method, system, terminal and medium based on deep neural network | |
| CN111585783B (en) | Flow dynamic scheduling method based on space-time flow matrix prediction | |
| US20220261833A1 (en) | Reinforcement Learning Method For Driver Incentives: Generative Adversarial Network For Driver-System Interactions | |
| CN108988325B (en) | Power distribution network planning method considering distributed power supply and electric vehicle access | |
| CN115689028A (en) | Electric vehicle charging prediction method, device and equipment | |
| CN111832869A (en) | Vehicle scheduling method and device, electronic equipment and storage medium | |
| CN107103036A (en) | Using acquisition methods, equipment and the programmable device for downloading probability | |
| CN106651464A (en) | Agricultural product price prediction method and apparatus | |
| Yang et al. | Dynamic pricing for integrated energy-traffic systems from a cyber-physical-human perspective | |
| Xu et al. | Designing van-based mobile battery swapping and rebalancing services for dockless ebike-sharing systems based on the dueling double deep Q-network | |
| CN115081743A (en) | Charging station system configuration method, device, equipment and computer readable storage medium | |
| Liang et al. | A pricing strategy for electric vehicle charging in residential areas considering the uncertainty of charging time and demand | |
| CN114725971A (en) | Operation decision method and system based on hybrid energy storage system | |
| CN111401627B (en) | Electric vehicle charging scheduling method and device | |
| CN112417748A (en) | Method, system, equipment and medium for scheduling automatic driving simulation task | |
| CN115860593A (en) | Energy storage scheduling method, device, equipment and storage medium | |
| CN114048886A (en) | Effective berthage combination prediction method based on neural network, terminal and storage medium | |
| CN113052402A (en) | Time-period joint pricing method and system for electric vehicle photovoltaic charging station network | |
| CN113014654A (en) | Data storage method, charging pile and computer readable storage medium | |
| CN113822455A (en) | Time prediction method, device, server and storage medium | |
| CN116542498B (en) | Battery scheduling method, system, device and medium based on deep reinforcement learning |
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 |