CN116872780B - Electric automobile charging supply control method, device, terminal and medium - Google Patents
Electric automobile charging supply control method, device, terminal and medium Download PDFInfo
- Publication number
- CN116872780B CN116872780B CN202311153137.6A CN202311153137A CN116872780B CN 116872780 B CN116872780 B CN 116872780B CN 202311153137 A CN202311153137 A CN 202311153137A CN 116872780 B CN116872780 B CN 116872780B
- Authority
- CN
- China
- Prior art keywords
- charging
- electric energy
- energy meters
- charging behavior
- user
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000006399 behavior Effects 0.000 claims abstract description 196
- 238000012549 training Methods 0.000 claims abstract description 48
- 238000004364 calculation method Methods 0.000 claims abstract description 26
- 238000003062 neural network model Methods 0.000 claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000003064 k means clustering Methods 0.000 claims abstract description 18
- 238000007621 cluster analysis Methods 0.000 claims abstract description 10
- 238000004590 computer program Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 abstract description 5
- 230000001276 controlling effect Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
- B60L53/60—Monitoring or controlling charging stations
- B60L53/62—Monitoring or controlling charging stations in response to charging parameters, e.g. current, voltage or electrical charge
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
- B60L53/60—Monitoring or controlling charging stations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses a charging supply control method, a device, a terminal and a medium for an electric automobile, wherein the method comprises the steps of extracting charging behavior data of all users in history records of all electric energy meters in a target area, carrying out cluster analysis and statistical calculation through an unsupervised learning K-means clustering algorithm to obtain a user charging behavior classification duty ratio; taking the classification duty ratio of the charging behaviors of the user and the collected load power data of the electric vehicle as a training set, and training through a CNN-LSTM hybrid neural network model to obtain a real-time estimation model of the load of the electric vehicle; and obtaining the electric vehicle cluster load power values of all the electric energy meters according to the electric vehicle load power data acquired at the current moment and the classification duty ratio of the charging behaviors of the users. Therefore, the embodiment of the invention can estimate the total load of the electric vehicles of all the electric energy meters in real time only by keeping the communication state between the acquisition system and part of the electric energy meters in the real-time state so as to control the charging supply of the electric vehicles in the target area.
Description
Technical Field
The invention relates to the technical field of electric automobiles, in particular to a method, a device, a terminal and a medium for controlling charging supply of an electric automobile.
Background
In recent years, with the rapid development of world economy, the consumption of fossil energy such as petroleum, coal, etc. has tended to increase significantly, and over-exploitation and use of fossil fuels have also been accompanied by serious environmental problems. Compared with the traditional fuel oil automobile, the electric automobile has the characteristics of green, energy saving, environmental protection and high efficiency, but the unordered access of the large-scale electric automobile load provides new challenges for the operation and maintenance planning of the power grid.
The current collection of the load power of the electric automobile is mainly aimed at the prediction of the load power of the electric automobile in the future period, but the collection of the load of the whole electric automobile under the condition that the collection of part of electric energy meter information fails is not involved. Although most living areas have established complete electric energy meter collection facilities at present, under the situation that communication is weak, such as communication interference, network congestion and the like, the real-time connection between the collection system and all electric energy meters cannot be guaranteed. Under the condition that only part of electric energy meters are connected with the acquisition system in the living area scene, the whole load condition of the electric automobile cluster can be predicted and estimated by utilizing the acquisition information of the part of electric energy meters, a basis is provided for orderly regulation and control of the electric automobile load, and the operation and maintenance management on the power grid side is facilitated. Therefore, it is necessary to establish a method for controlling the charging supply of the electric vehicle in the residential area under the condition of incomplete user information collection, so as to solve the above technical problems.
Disclosure of Invention
The invention provides a method, a device, a terminal and a medium for controlling charging supply of an electric vehicle, which are applied to incomplete user information acquisition conditions, fully excavate the influence of historical charging behaviors of a user on the load condition of the electric vehicle, and can estimate the whole load condition of the electric vehicle under all electric energy meters in real time by only adopting the load power information of the electric vehicle in a part of electric energy meters connected in real time and classification data of the historical charging behaviors of the user so as to control the charging supply of the electric vehicle in a region.
In order to achieve the above object, in a first aspect, an embodiment of the present invention provides a method for controlling charging supply of an electric vehicle, including:
extracting charging behavior data of all users in a history record in the time range of all electric energy meters T in a target area; the charging behavior data comprise starting time, charging duration and charging electric quantity of each charging behavior; for 30 daysTFor 90 days;
performing cluster analysis on the charging behavior data by adopting an unsupervised learning K-means clustering algorithm, and performing statistical calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user;
the electric vehicle load power data collected in the historic records of the m electric energy meters T in the target area are used as training sets; training the training set by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model;the number of the electric energy meters is greater than zero and smaller than the number of all the electric energy meters;
and taking the electric vehicle load power data acquired at the current moment in the connected electric energy meters in the target area, the proportion of the connected electric energy meters to all the electric energy meters and the classification duty ratio of the charging behaviors of the users at the current moment of the connected electric energy meters as the input of the electric vehicle load real-time estimation model to obtain electric vehicle cluster load power values of all the electric energy meters in the target area so as to control the charging supply of the electric vehicles in the target area.
Further, the extracting the charging behavior data of all users in the history record in the time range of the electric energy meter T in the target area specifically includes:
according to the power consumption data of all the electric energy meters in the target area at each moment in the history record within the time range of the electric energy meters T, recording the moment when the power consumption record in all the electric energy meters is not zero as the starting time of the current charging behavior of the user;
after the current charging behavior starts, recording the moment when the power consumption in all the electric energy meters is zero as the ending time of the current charging behavior;
obtaining the duration of the current charging behavior by making a difference between the ending time of the current charging behavior and the starting time of the current charging behavior;
and adding and summing the power consumption data of the electric energy meter in the starting time and the ending time of the current charging behavior to obtain the charging electric quantity of the current charging behavior, thereby obtaining the charging behavior data of all users.
Further, the method for performing cluster analysis on the charging behavior data by adopting an unsupervised learning K-means clustering algorithm, and performing statistical calculation on the charging behavior clustering result of each user to obtain a user charging behavior classification duty ratio specifically includes:
normalizing the starting time, the charging time length and the charging electric quantity of each charging behavior, and determining the K value classification number by adopting an unsupervised learning K-means clustering algorithm through a contour coefficient;
dividing the processed charging behavior data of all users into K classes for clustering; carrying out statistical calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user;
the calculation formula of the classification duty ratio of the charging behavior of the user is as follows:
，
wherein,the method comprises the steps that the k-th charging behavior clustering result of an i-th user accounts for the percentage of all charging behavior clustering results of the i-th user; />The charging behaviors of the ith user belong to the number of the k-th charging behavior clustering results; k is the number of the charging behavior clustering results of all the users.
Further, the step of taking the electric vehicle load power data collected in the history records of the m electric energy meters t in the target area and the user charging behavior classification duty ratio as a training set specifically includes:
randomly selecting electric vehicle load power data in m electric energy meter records at each moment in the T time range, and accumulating and summing to obtain m electric energy meter total power values at each moment; calculating the proportion of the m electric energy meters to all electric energy meters in the target area;
classifying the duty ratio according to the user charging behaviors, obtaining the proportion of the user charging behaviors of the m electric energy meters at each moment, obtaining characteristic data and constructing a training set;
the characteristic data comprise the total power values of the m electric energy meters at each moment, the proportion of the m electric energy meters accounting for all electric energy meters in the target area, and the proportion of the user charging behaviors of the m electric energy meters at each moment.
Further, the training set is trained by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model, which specifically comprises the following steps:
selecting the training set as input of a CNN-LSTM hybrid neural network model, and carrying out feature extraction on data of the training set by adopting a convolutional neural network to obtain first feature data;
inputting the first characteristic data into a long-short-term memory neural network for training, selecting a Huber loss function combined with an average absolute error and a mean square error as an objective function, and calculating an error between an electric vehicle integral load real-time estimated value and a true value;
and carrying out iterative updating on the bias and the weight of the neuron in the CNN-LSTM hybrid neural network model through back propagation to obtain the electric vehicle load real-time estimation model.
Further, the calculation formula of the proportion of the charging behaviors of the users of the m electric energy meters at each moment is as follows:
，
，
wherein,m electric energy meter sets randomly selected for the time t; />The accumulated sum of the k-th charging behavior probabilities of all users in the m electric energy at the t moment is obtained; />The k-th charging behavior of all users in the m electric energy connected at the t moment accounts for the proportion of the total charging behavior; />The k-th charging behavior clustering result for the j-th user accounts for a percentage of all charging behavior clustering results of the j-th user.
In a second aspect, an embodiment of the present invention provides an electric vehicle charging supply control device, including:
the data preprocessing module is used for extracting charging behavior data of all users in the historical records in the time range of all the electric energy meters T in the target area; the charging behavior data comprise starting time, charging duration and charging electric quantity of each charging behavior; for 30 daysT/>For 90 days;
the clustering result statistics module is used for carrying out clustering analysis on the charging behavior data by adopting an unsupervised learning K-means clustering algorithm, and carrying out statistics calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user;
the load real estimation model module is used for taking the electric vehicle load power data collected in the historic records of the m electric energy meters T in the target area and the user charging behavior classification duty ratio as a training set; training the training set by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model;the number of the electric energy meters is greater than zero and smaller than the number of all the electric energy meters;
the load real-time estimation module is used for taking electric vehicle load power data acquired at the current moment in the connected electric energy meters in the target area, the proportion of the connected electric energy meters to all the electric energy meters and the classification proportion of the user charging behaviors at the current moment of the connected electric energy meters as input of the electric vehicle load real-time estimation model, and obtaining electric vehicle cluster load power values of all the electric energy meters in the target area so as to control charging supply of electric vehicles in the target area.
Further, the clustering result statistics module is specifically configured to:
normalizing the starting time, the charging time length and the charging electric quantity of each charging behavior, and determining the K value classification number by adopting an unsupervised learning K-means clustering algorithm through a contour coefficient;
dividing the processed charging behavior data of all users into K classes for clustering; carrying out statistical calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user;
the calculation formula of the classification duty ratio of the charging behavior of the user is as follows:
，
wherein,the method comprises the steps that the k-th charging behavior clustering result of an i-th user accounts for the percentage of all charging behavior clustering results of the i-th user; />The charging behaviors of the ith user belong to the number of the k-th charging behavior clustering results; k is the number of the charging behavior clustering results of all the users.
In a third aspect, an embodiment of the present invention correspondingly provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor implements the above-mentioned electric vehicle charging supply control method when executing the computer program.
In addition, the embodiment of the invention also provides a computer readable storage medium, which comprises a stored computer program, wherein the equipment where the computer readable storage medium is located is controlled to execute the electric automobile charging supply control method when the computer program runs.
Compared with the prior art, the charging supply control method, device, terminal and medium for the electric automobile disclosed by the embodiment of the invention are characterized in that the charging behavior data of all users in the historical records of all electric energy meters T in the target area are extracted; the charging behavior data comprise starting time, charging duration and charging electric quantity of each charging behavior; for 30 daysT/>For 90 days; performing cluster analysis on the charging behavior data by adopting an unsupervised learning K-means clustering algorithm, and performing statistical calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user; the electric vehicle load power data collected in the historic records of the m electric energy meters T in the target area are used as training sets; training the training set by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model; />The number of the electric energy meters is greater than zero and smaller than the number of all the electric energy meters; and taking the electric vehicle load power data acquired at the current moment in the connected electric energy meters in the target area, the proportion of the connected electric energy meters to all the electric energy meters and the classification duty ratio of the charging behaviors of the users at the current moment of the connected electric energy meters as the input of the electric vehicle load real-time estimation model to obtain electric vehicle cluster load power values of all the electric energy meters in the target area so as to control the charging supply of the electric vehicles in the target area. Therefore, the embodiment of the invention can collect the system and the part only in a real-time state under the condition of incomplete user information collectionThe sub-electric energy meter keeps a communication state, so that the total load of the electric vehicles under all the electric energy meters can be estimated in real time, a basis is provided for orderly regulating and controlling the loads of the electric vehicles, and the operation and maintenance management of the power grid side is facilitated.
Drawings
Fig. 1 is a schematic flow chart of an electric vehicle charging supply control method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an electric vehicle charging supply control device according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a clustering result of performing cluster analysis on the charging behavior data by using an unsupervised learning K-means clustering algorithm according to an embodiment of the present invention;
fig. 4 is a schematic diagram of comparison between an electric vehicle load curve obtained by an electric vehicle load real-time estimation model and an actual electric vehicle charging load curve.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1, fig. 1 is a flowchart of an electric vehicle charging supply control method according to an embodiment of the present invention, where the electric vehicle charging supply control method includes steps S11 to S14:
s11: extracting charging behavior data of all users in a history record in the time range of all electric energy meters T in a target area; the charging behavior data comprise starting time, charging duration and charging electric quantity of each charging behavior; for 30 daysT/>For 90 days;
s12: performing cluster analysis on the charging behavior data by adopting an unsupervised learning K-means clustering algorithm, and performing statistical calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user;
s13: the electric vehicle load power data collected in the historic records of the m electric energy meters T in the target area are used as training sets; training the training set by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model;the number of the electric energy meters is greater than zero and smaller than the number of all the electric energy meters;
s14: and taking the electric vehicle load power data acquired at the current moment in the connected electric energy meters in the target area, the proportion of the connected electric energy meters to all the electric energy meters and the classification duty ratio of the charging behaviors of the users at the current moment of the connected electric energy meters as the input of the electric vehicle load real-time estimation model to obtain electric vehicle cluster load power values of all the electric energy meters in the target area so as to control the charging supply of the electric vehicles in the target area.
Specifically, in the step S11, the method specifically includes:
according to the power consumption data of all the electric energy meters in the target area at each moment in the history record within the time range of the electric energy meters T, recording the moment when the power consumption record in all the electric energy meters is not zero as the starting time of the current charging behavior of the user;
after the current charging behavior starts, recording the moment when the power consumption in all the electric energy meters is zero as the ending time of the current charging behavior;
obtaining the duration of the current charging behavior by making a difference between the ending time of the current charging behavior and the starting time of the current charging behavior;
and adding and summing the power consumption data of the electric energy meter in the starting time and the ending time of the current charging behavior to obtain the charging electric quantity of the current charging behavior, thereby obtaining the charging behavior data of all users.
In the embodiment of the invention, an electric vehicle historical charging power data set in an electric energy meter uploading record under a certain cell is selected, 24 hours a day are divided at 15-minute time intervals, the intervals of adjacent time points are 15 minutes, 96 time points are counted in total, and the starting time and the charging duration of each charging action of a user are counted in the order of 15 minutes.
And according to the power consumption data of the electric energy meter at each moment in the uploading record, when the power consumption record of the electric energy meter is not zero, recording the starting time of each charging action, and when the power consumption record of the electric energy meter is zero after each charging action starts, recording the ending time of the charging action. And obtaining the duration time of each charging action by making a difference between the recorded end time of the charging action and the starting time of the charging action, and adding and summing the power consumption data of the electric energy meter in the end time of each charging action to obtain the charging electric quantity of each charging action, thereby obtaining the start time, the charging duration and the charging electric quantity of each charging action of a user.
Specifically, in the step S12, specifically, the method includes:
normalizing the starting time, the charging time length and the charging electric quantity of each charging behavior, and determining the K value classification number by adopting an unsupervised learning K-means clustering algorithm through a contour coefficient;
dividing the processed charging behavior data of all users into K classes for clustering; carrying out statistical calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user;
the calculation formula of the classification duty ratio of the charging behavior of the user is as follows:
，
wherein,the method comprises the steps that the k-th charging behavior clustering result of an i-th user accounts for the percentage of all charging behavior clustering results of the i-th user; />The charging behaviors of the ith user belong to the number of the k-th charging behavior clustering results; k is the number of the charging behavior clustering results of all the users.
In the embodiment of the invention, K-means cluster analysis is performed by using the starting time, the charging duration and the normalized data of the charging electric quantity of all users, the classified number is determined by adopting a contour coefficient method, and the clustering result is totally divided into 4 types as shown in fig. 3.
Specifically, in the step S13, the step of taking the electric vehicle load power data collected in the history records of the m electric energy meters t in the target area and the user charging behavior classification duty ratio as the training set specifically includes:
randomly selecting electric vehicle load power data in m electric energy meter records at each moment in the T time range, and accumulating and summing to obtain m electric energy meter total power values at each moment; calculating the proportion of the m electric energy meters to all electric energy meters in the target area;
classifying the duty ratio according to the user charging behaviors, obtaining the proportion of the user charging behaviors of the m electric energy meters at each moment, obtaining characteristic data and constructing a training set;
the characteristic data comprise the total power values of the m electric energy meters at each moment, the proportion of the m electric energy meters accounting for all electric energy meters in the target area, and the proportion of the user charging behaviors of the m electric energy meters at each moment.
Specifically, the training set is trained by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model, which specifically comprises the following steps:
selecting the training set as input of a CNN-LSTM hybrid neural network model, and carrying out feature extraction on data of the training set by adopting a convolutional neural network to obtain first feature data;
inputting the first characteristic data into a long-short-term memory neural network for training, selecting a Huber loss function combined with an average absolute error and a mean square error as an objective function, and calculating an error between an electric vehicle integral load real-time estimated value and a true value;
and carrying out iterative updating on the bias and the weight of the neuron in the CNN-LSTM hybrid neural network model through back propagation to obtain the electric vehicle load real-time estimation model.
In the embodiment of the invention, 356 electric energy meters are selected in total from residential areas, in order to verify the effectiveness of the invention, the condition of failure in acquisition of information of the electric energy meters is extremely simulated, partial electric energy meters are selected as the disconnection electric energy meters according to N (0.4,0.6) at each moment, 15 minutes are taken as intervals within 31 days, the first 25 days of data are selected as training sets, and the last 6 days of data are selected as test sets. The training set input data is the total power value of the partial connection electric energy meter, the percentage of the partial connection electric energy meter to the total electric energy meter, the proportion of various charging behaviors of the partial connection electric energy meter user, and the total characteristic data is 6 types.
Further, the calculation formula of the proportion of the charging behaviors of the users of the m electric energy meters at each moment is as follows:
，
，
wherein,m electric energy meter sets randomly selected for the time t; />The accumulated sum of the k-th charging behavior probabilities of all users in the m electric energy at the t moment is obtained; />The k-th charging behavior of all users in the m electric energy connected at the t moment accounts for the proportion of the total charging behavior; />The k-th charging behavior clustering result for the j-th user accounts for a percentage of all charging behavior clustering results of the j-th user.
In the embodiment of the invention, the data of the last 6 days is used as a test set, and an electric vehicle load real-time estimation model is input to obtain a real-time estimation curve of electric vehicle cluster load power at each moment. As shown in fig. 4.
To demonstrate the superiority of this embodiment, consider the following two cases, as shown in Table 1:
and Case1, taking no consideration of historical charging behavior data of a user, and only adopting a real-time value of the electric vehicle load power in a part of the connected electric energy meters as input of an electric vehicle load real-time estimation model.
Case 2. The method for controlling the charging supply of the electric automobile in the residential area under the condition of incomplete user information acquisition provided by the embodiment of the invention.
Table 1 electric vehicle load real-time estimation model evaluation comparison table considering whether user charging behavior
Fig. 2 is a schematic structural diagram of an electric vehicle charging supply control device according to an embodiment of the present invention, where the electric vehicle charging supply control device includes:
data preprocessingThe module 21 is configured to extract charging behavior data of all users in the history record within a time range of all electric energy meters T in the target area; the charging behavior data comprise starting time, charging duration and charging electric quantity of each charging behavior; for 30 daysT/>For 90 days;
the clustering result statistics module 22 is configured to perform clustering analysis on the charging behavior data by using an unsupervised learning K-means clustering algorithm, and perform statistics calculation on the charging behavior clustering result of each user, so as to obtain a user charging behavior classification duty ratio;
the load real estimation model module 23 is configured to use the electric vehicle load power data collected in the history records in the m electric energy meters T time ranges of the target area and the user charging behavior classification duty ratio as a training set; training the training set by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model;the number of the electric energy meters is greater than zero and smaller than the number of all the electric energy meters;
the load real-time estimation module 24 is configured to use the electric vehicle load power data collected at the current time in the connected electric energy meters in the target area, the proportion of the connected electric energy meters to all electric energy meters, and the classification proportion of the charging behavior of the user at the current time of the connected electric energy meters as input of the electric vehicle load real-time estimation model, and obtain electric vehicle cluster load power values of all electric energy meters in the target area, so as to control charging supply of electric vehicles in the target area.
Specifically, the clustering result statistics module 22 is specifically configured to:
normalizing the starting time, the charging time length and the charging electric quantity of each charging behavior, and determining the K value classification number by adopting an unsupervised learning K-means clustering algorithm through a contour coefficient;
dividing the processed charging behavior data of all users into K classes for clustering; carrying out statistical calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user;
the calculation formula of the classification duty ratio of the charging behavior of the user is as follows:
，
wherein,the method comprises the steps that the k-th charging behavior clustering result of an i-th user accounts for the percentage of all charging behavior clustering results of the i-th user; />The charging behaviors of the ith user belong to the number of the k-th charging behavior clustering results; k is the number of all charging behavior clustering results of the ith user.
The electric vehicle charging supply control device provided by the embodiment of the invention can realize all the processes of the electric vehicle charging supply control method of the embodiment, and the actions and the realized technical effects of each module in the device are respectively the same as those of the electric vehicle charging supply control method of the embodiment, and are not repeated here.
The embodiment of the invention correspondingly provides a terminal device, which comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor. The steps in the embodiment of the electric vehicle charging supply control method are implemented when the processor executes the computer program. Or the processor executes the computer program to realize the functions of each module in the embodiment of the electric vehicle charging supply control device.
The terminal equipment can be computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The terminal device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of a terminal device and does not constitute a limitation of the terminal device, and may include more or less components than illustrated, or may combine certain components, or different components, e.g., the terminal device may further include an input-output device, a network access device, a bus, etc.
The processor may be a central processing unit, but also other general purpose processors, digital signal processors, application specific integrated circuits, field programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center of the terminal device, and which connects various parts of the entire terminal device using various interfaces and lines.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the terminal device by running or executing the computer program and/or module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
It should be noted that the above-described apparatus embodiments are merely illustrative, and the units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The embodiment of the invention also provides a computer readable storage medium, which comprises a stored computer program, wherein the equipment where the computer readable storage medium is located is controlled to execute the electric vehicle charging supply control method according to the embodiment when the computer program runs.
In summary, according to the method, the device, the terminal and the medium for controlling charging supply of the electric vehicle disclosed by the embodiment of the invention, charging behavior data of all users in histories in time ranges of all electric energy meters T in a target area are extracted; the charging behavior data comprise starting time, charging duration and charging electric quantity of each charging behavior; for 30 daysT/>For 90 days; performing cluster analysis on the charging behavior data by adopting an unsupervised learning K-means clustering algorithm, and performing statistical calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user; the electric vehicle load power data collected in the historic records of the m electric energy meters T in the target area are used as training sets; training the training set by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model; />The number of the electric energy meters is greater than zero and smaller than the number of all the electric energy meters; the electric vehicle load power data acquired at the current moment in the connected electric energy meter in the target area, the proportion of the connected electric energy meter to all electric energy meters and the classification duty ratio of the user charging behavior at the current moment of the connected electric energy meter are used as the input of the electric vehicle load real-time estimation model, and the target is obtainedAnd the electric automobile cluster load power values of all the electric energy meters in the region are used for controlling the charging supply of the electric automobiles in the target region. Therefore, the embodiment of the invention can estimate the total load of the electric vehicles under all electric energy meters in real time only by keeping the communication state between the acquisition system and part of the electric energy meters in a real-time state under the condition of incomplete user information acquisition, provides a basis for orderly regulation and control of the electric vehicle load, and is beneficial to ensuring the operation and maintenance management of a power grid side.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Claims (8)
1. An electric vehicle charge supply control method, characterized by comprising:
extracting charging behavior data of all users in a history record in the time range of all electric energy meters T in a target area; the charging behavior data comprise starting time, charging duration and charging electric quantity of each charging behavior; for 30 daysT/>For 90 days;
performing cluster analysis on the charging behavior data by adopting an unsupervised learning K-means clustering algorithm, and performing statistical calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user;
randomly selecting electric vehicle load power data in m electric energy meter records at each moment in the T time range, and accumulating and summing to obtain m electric energy meter total power values at each moment; calculating the proportion of the m electric energy meters to all electric energy meters in the target area; according to the classification duty ratio of the user charging behaviors, the proportion of the user charging behaviors of the m electric energy meters at each moment is obtained, and the characteristic data are obtained and constructedA training set; the characteristic data comprise the total power values of the m electric energy meters at each moment, the proportion of the m electric energy meters accounting for all electric energy meters in the target area and the proportion of the user charging behaviors of the m electric energy meters at each moment; training the training set by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model;the number of the electric energy meters is greater than zero and smaller than the number of all the electric energy meters;
the electric vehicle load power data acquired at the current moment in the connected electric energy meters in the target area, the proportion of the connected electric energy meters to all the electric energy meters and the classification duty ratio of the charging behaviors of the users at the current moment of the connected electric energy meters are used as the input of the electric vehicle load real-time estimation model, and the electric vehicle cluster load power values of all the electric energy meters in the target area are obtained so as to control the charging supply of the electric vehicles in the target area;
the training set is trained by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model, which specifically comprises the following steps:
selecting the training set as input of a CNN-LSTM hybrid neural network model, and carrying out feature extraction on data of the training set by adopting a convolutional neural network to obtain first feature data;
inputting the first characteristic data into a long-short-term memory neural network for training, selecting a Huber loss function combined with an average absolute error and a mean square error as an objective function, and calculating an error between an electric vehicle integral load real-time estimated value and a true value;
and carrying out iterative updating on the bias and the weight of the neuron in the CNN-LSTM hybrid neural network model through back propagation to obtain the electric vehicle load real-time estimation model.
2. The method for controlling charging supply of an electric vehicle according to claim 1, wherein the extracting the charging behavior data of all users in the history record in the time range of all electric energy meters T in the target area specifically includes:
according to the power consumption data of all the electric energy meters in the target area at each moment in the history record within the time range of the electric energy meters T, recording the moment when the power consumption record in all the electric energy meters is not zero as the starting time of the current charging behavior of the user;
after the current charging behavior starts, recording the moment when the power consumption in all the electric energy meters is zero as the ending time of the current charging behavior;
obtaining the duration of the current charging behavior by making a difference between the ending time of the current charging behavior and the starting time of the current charging behavior;
and adding and summing the power consumption data of the electric energy meter in the starting time and the ending time of the current charging behavior to obtain the charging electric quantity of the current charging behavior, thereby obtaining the charging behavior data of all users.
3. The method for controlling charging supply of an electric vehicle according to claim 1, wherein the performing cluster analysis on the charging behavior data by using an unsupervised learning K-means clustering algorithm, and performing statistical calculation on the charging behavior clustering result of each user, to obtain a user charging behavior classification duty ratio, comprises:
normalizing the starting time, the charging time length and the charging electric quantity of each charging behavior, and determining the K value classification number by adopting an unsupervised learning K-means clustering algorithm through a contour coefficient;
dividing the processed charging behavior data of all users into K classes for clustering; carrying out statistical calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user;
the calculation formula of the classification duty ratio of the charging behavior of the user is as follows:
，
wherein,the method comprises the steps that the k-th charging behavior clustering result of an i-th user accounts for the percentage of all charging behavior clustering results of the i-th user; />The charging behaviors of the ith user belong to the number of the k-th charging behavior clustering results; k is the number of the charging behavior clustering results of all the users.
4. The electric vehicle charging supply control method according to claim 1, wherein the calculation formula of the proportion of the user charging behaviors of the m electric energy meters at each moment is:
，
，
wherein,m electric energy meter sets randomly selected for the time t; />The accumulated sum of the k-th charging behavior probabilities of all users in the m electric energy at the t moment is obtained; />The k-th charging behavior of all users in the m electric energy connected at the t moment accounts for the proportion of the total charging behavior; />The k-th charging behavior clustering result for the j-th user accounts for a percentage of all charging behavior clustering results of the j-th userRatio of; k is the number of the charging behavior clustering results of all the users.
5. An electric vehicle charging supply control device, characterized by comprising:
the data preprocessing module is used for extracting charging behavior data of all users in the historical records in the time range of all the electric energy meters T in the target area; the charging behavior data comprise starting time, charging duration and charging electric quantity of each charging behavior; for 30 daysT/>For 90 days;
the clustering result statistics module is used for carrying out clustering analysis on the charging behavior data by adopting an unsupervised learning K-means clustering algorithm, and carrying out statistics calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user;
the load real estimation model module is used for randomly selecting the electric vehicle load power data in the records of the m electric energy meters at each moment in the T time range, and accumulating and summing to obtain the total power values of the m electric energy meters at each moment; calculating the proportion of the m electric energy meters to all electric energy meters in the target area; classifying the duty ratio according to the user charging behaviors, obtaining the proportion of the user charging behaviors of the m electric energy meters at each moment, obtaining characteristic data and constructing a training set; the characteristic data comprise the total power values of the m electric energy meters at each moment, the proportion of the m electric energy meters accounting for all electric energy meters in the target area and the proportion of the user charging behaviors of the m electric energy meters at each moment; training the training set by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model;the number of the electric energy meters is greater than zero and smaller than the number of all the electric energy meters;
the load real-time estimation module is used for taking electric vehicle load power data acquired at the current moment in the connected electric energy meters in the target area, the proportion of the connected electric energy meters to all the electric energy meters and the classification proportion of the user charging behaviors at the current moment of the connected electric energy meters as input of the electric vehicle load real-time estimation model, and obtaining electric vehicle cluster load power values of all the electric energy meters in the target area so as to control charging supply of electric vehicles in the target area;
the training set is trained by adopting a CNN-LSTM hybrid neural network model to obtain an electric vehicle load real-time estimation model, which specifically comprises the following steps:
selecting the training set as input of a CNN-LSTM hybrid neural network model, and carrying out feature extraction on data of the training set by adopting a convolutional neural network to obtain first feature data;
inputting the first characteristic data into a long-short-term memory neural network for training, selecting a Huber loss function combined with an average absolute error and a mean square error as an objective function, and calculating an error between an electric vehicle integral load real-time estimated value and a true value;
and carrying out iterative updating on the bias and the weight of the neuron in the CNN-LSTM hybrid neural network model through back propagation to obtain the electric vehicle load real-time estimation model.
6. The electric automobile charging supply control device according to claim 5, wherein the clustering result statistics module is specifically configured to:
normalizing the starting time, the charging time length and the charging electric quantity of each charging behavior, and determining the K value classification number by adopting an unsupervised learning K-means clustering algorithm through a contour coefficient;
dividing the processed charging behavior data of all users into K classes for clustering; carrying out statistical calculation on the charging behavior clustering result of each user to obtain the charging behavior classification duty ratio of the user;
the calculation formula of the classification duty ratio of the charging behavior of the user is as follows:
，
wherein,the method comprises the steps that the k-th charging behavior clustering result of an i-th user accounts for the percentage of all charging behavior clustering results of the i-th user; />The charging behaviors of the ith user belong to the number of the k-th charging behavior clustering results; k is the number of the charging behavior clustering results of all the users.
7. A terminal device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the electric vehicle charging supply control method according to any one of claims 1 to 4 when executing the computer program.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer-readable storage medium is located to execute the electric vehicle charging supply control method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311153137.6A CN116872780B (en) | 2023-09-08 | 2023-09-08 | Electric automobile charging supply control method, device, terminal and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311153137.6A CN116872780B (en) | 2023-09-08 | 2023-09-08 | Electric automobile charging supply control method, device, terminal and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116872780A CN116872780A (en) | 2023-10-13 |
| CN116872780B true CN116872780B (en) | 2023-12-15 |
Family
ID=88272231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311153137.6A Active CN116872780B (en) | 2023-09-08 | 2023-09-08 | Electric automobile charging supply control method, device, terminal and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116872780B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118117757A (en) * | 2024-04-11 | 2024-05-31 | 浙江大学 | Regional-level electric vehicle charging load virtual acquisition method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633924A (en) * | 2020-12-21 | 2021-04-09 | 国网浙江省电力有限公司嘉兴供电公司 | Cell electric energy substitution demand analysis method based on load decomposition |
| CN112653241A (en) * | 2020-12-16 | 2021-04-13 | 南方电网深圳数字电网研究院有限公司 | Power grid monitoring method and device and Internet of things metering unit |
| AU2021106177A4 (en) * | 2021-08-20 | 2021-10-28 | Changsha University Of Science & Technology | Method for predicting spatial-temporal dynamic distribution of electric vehicle charging loads |
| WO2022077693A1 (en) * | 2020-10-15 | 2022-04-21 | 中国科学院深圳先进技术研究院 | Load prediction model training method and apparatus, storage medium, and device |
| CN114418298A (en) * | 2021-12-15 | 2022-04-29 | 重庆邮电大学 | Charging load probability prediction system and method based on non-invasive detection |
| CN114648171A (en) * | 2022-04-08 | 2022-06-21 | 国网湖南省电力有限公司 | Electric vehicle charging pile load prediction method, system and storage medium |
| CN115034507A (en) * | 2022-06-30 | 2022-09-09 | 杭州凯达电力建设有限公司 | Power load prediction method of charging pile and related components |
| CN116523681A (en) * | 2023-05-04 | 2023-08-01 | 广东电网有限责任公司 | Load decomposition method and device for electric automobile, electronic equipment and storage medium |
| CN116703464A (en) * | 2023-06-09 | 2023-09-05 | 广东电网有限责任公司珠海供电局 | Electric automobile charging demand modeling method and device, electronic equipment and storage medium |
-
2023
- 2023-09-08 CN CN202311153137.6A patent/CN116872780B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022077693A1 (en) * | 2020-10-15 | 2022-04-21 | 中国科学院深圳先进技术研究院 | Load prediction model training method and apparatus, storage medium, and device |
| CN112653241A (en) * | 2020-12-16 | 2021-04-13 | 南方电网深圳数字电网研究院有限公司 | Power grid monitoring method and device and Internet of things metering unit |
| CN112633924A (en) * | 2020-12-21 | 2021-04-09 | 国网浙江省电力有限公司嘉兴供电公司 | Cell electric energy substitution demand analysis method based on load decomposition |
| AU2021106177A4 (en) * | 2021-08-20 | 2021-10-28 | Changsha University Of Science & Technology | Method for predicting spatial-temporal dynamic distribution of electric vehicle charging loads |
| CN114418298A (en) * | 2021-12-15 | 2022-04-29 | 重庆邮电大学 | Charging load probability prediction system and method based on non-invasive detection |
| WO2023109099A1 (en) * | 2021-12-15 | 2023-06-22 | 重庆邮电大学 | Charging load probability prediction system and method based on non-intrusive detection |
| CN114648171A (en) * | 2022-04-08 | 2022-06-21 | 国网湖南省电力有限公司 | Electric vehicle charging pile load prediction method, system and storage medium |
| CN115034507A (en) * | 2022-06-30 | 2022-09-09 | 杭州凯达电力建设有限公司 | Power load prediction method of charging pile and related components |
| CN116523681A (en) * | 2023-05-04 | 2023-08-01 | 广东电网有限责任公司 | Load decomposition method and device for electric automobile, electronic equipment and storage medium |
| CN116703464A (en) * | 2023-06-09 | 2023-09-05 | 广东电网有限责任公司珠海供电局 | Electric automobile charging demand modeling method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 计及电动汽车渗透率的台区负荷预测研究;刘云;吴家宏;;电网与清洁能源(第01期);第72-77页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116872780A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111144468B (en) | Method and device for labeling power consumer information, electronic equipment and storage medium | |
| CN103559655B (en) | The Forecasting Methodology of the novel feeder line load of microgrid based on data mining | |
| CN116872780B (en) | Electric automobile charging supply control method, device, terminal and medium | |
| CN111476435B (en) | Charging pile load prediction method based on density peak value | |
| CN112686464A (en) | Short-term wind power prediction method and device | |
| CN108805213B (en) | Power load curve double-layer spectral clustering method considering wavelet entropy dimensionality reduction | |
| CN114066071A (en) | Power parameter optimization method based on energy consumption, terminal equipment and storage medium | |
| CN112734135A (en) | Power load prediction method, intelligent terminal and computer readable storage medium | |
| CN113449919A (en) | Power consumption prediction method and system based on feature and trend perception | |
| CN116757465A (en) | Line risk assessment method and device based on double training weight distribution model | |
| CN116663746A (en) | Power load prediction method and device, computer equipment and storage medium | |
| CN117856238A (en) | Distributed power supply dissipatable capacity calculation method and system based on graph calculation | |
| CN117748609A (en) | Optical storage power distribution method of comprehensive energy supply station | |
| CN116632841A (en) | Power distribution area short-term electricity load prediction method and system integrating multiple time sequence characteristics | |
| CN112560325B (en) | Prediction method, system, equipment and storage medium for electricity conversion service | |
| CN115169630A (en) | Electric vehicle charging load prediction method and device | |
| Xia et al. | Pattern analysis for load forecasting | |
| CN118117757A (en) | Regional-level electric vehicle charging load virtual acquisition method and system | |
| CN113361960B (en) | Method, medium, device and equipment for quantifying large-scale demand response capacity | |
| CN116050677B (en) | Electric automobile charging load adjustable capacity prediction method | |
| CN116911461B (en) | Electric automobile charging load prediction method, system and prediction terminal | |
| CN118011220B (en) | Battery pack state of charge estimation method, system and medium | |
| CN118644012A (en) | Method, system, equipment and medium for calculating standby capacity of electric automobile cluster | |
| CN116384568B (en) | Electric automobile charging load prediction method, system, equipment and medium | |
| CN118411003B (en) | Load control method, system, device and storage medium for multi-class power device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |