CN117465272A - Multi-gun low-power charging pile system and charging method - Google Patents
Multi-gun low-power charging pile system and charging method Download PDFInfo
- Publication number
- CN117465272A CN117465272A CN202311698363.2A CN202311698363A CN117465272A CN 117465272 A CN117465272 A CN 117465272A CN 202311698363 A CN202311698363 A CN 202311698363A CN 117465272 A CN117465272 A CN 117465272A
- Authority
- CN
- China
- Prior art keywords
- charging
- data
- state
- gun
- charging pile
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 230000009471 action Effects 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims description 16
- 238000011176 pooling Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000013527 convolutional neural network Methods 0.000 description 18
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
-
- 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
- B60L53/63—Monitoring or controlling charging stations in response to network capacity
-
- 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
- B60L53/67—Controlling two or more charging stations
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention relates to the technical field of charging piles, and provides a multi-gun low-power charging pile system and a method, wherein the system comprises the following components: the power grid load prediction module predicts power grid load prediction data of a target period; the charging pile state classification module is used for carrying out state classification on the charging piles to obtain the charging pile state of each group of charging piles; the user demand acquisition module is used for acquiring the use demand of the charging gun of a user; and the charging strategy generation module is used for generating a charging strategy for controlling the charging gun of each group of charging piles to execute a charging action according to the power grid load prediction data, the charging pile state of each group of charging piles and the charging gun use requirement of a user. According to the invention, by generating the charging strategies of the plurality of charging guns of each group of charging piles, more charging positions are provided to solve the problem of unbalanced supply and demand of the charging piles, and meanwhile, the influence of peak time on the power grid is considered, so that the charging strategies adapting to the charging demands of users are generated for each group of charging piles, and the problem of unbalanced load of the power grid is solved.
Description
Technical Field
The invention relates to the technical field of charging piles, in particular to a multi-gun low-power charging pile system and a multi-gun low-power charging pile method.
Background
Electric vehicles are gaining wide attention and popularization as an environmentally friendly and efficient vehicle. However, with the popularization of electric vehicles and the increase of the number of users, there are some practical problems and disadvantages in terms of charging infrastructure, and in the period of high demand, the situation that charging piles are used for charging often occurs. This results in the user spending more time waiting for charging, which is inconvenient, and may lengthen the charging process and waste time. Some charging stake users will continue to occupy the charging stake after charging is completed without removing the vehicle, which limits the use of other users. Even if there are charging piles in some areas, their number is still insufficient to meet the needs of the users. This results in users who may experience charging difficulties when traveling, particularly in urban and residential areas.
With the increase of the number of electric vehicles, the problem of unbalanced supply and demand of the charging piles is gradually revealed. In some areas, congestion and scarcity of charging piles become common problems, and the charging experience of users and popularization of electric automobiles are affected. Large-scale electric vehicle charging can cause huge load pressure on the power grid during peak hours, leading to unstable power grid and power supply problems. Grid load balancing remains a critical issue to be addressed. Improving charging efficiency and speed is an important goal. Currently, some electric vehicles still require a relatively long time to charge, which limits their use and popularization. And the private pile is charged with larger time waste, and the charging time is far lower than the parking time/the occupied time of the charging pile.
In summary, how to solve the unbalanced supply and demand of the charging pile and the unbalanced load of the power grid in the peak period is a problem to be solved.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a multi-gun low-power charging pile system and a multi-gun low-power charging pile method, which aim to solve the problems of unbalanced supply and demand of a charging pile, unbalanced load of a power grid in a peak period and the like in the prior art.
In a first aspect of the present invention, there is provided a multi-gun low-power charging pile system comprising:
the power grid load prediction module is configured to acquire historical power grid load data in a regional range and predict power grid load prediction data of a target period according to the historical power grid load data;
the charging pile state classification module is configured to acquire historical state data of each group of charging piles, and classify the charging piles according to the historical state data to acquire the charging pile state of each group of charging piles;
the charging gun comprises a user demand acquisition module, a charging gun storage module and a charging gun storage module, wherein the user demand acquisition module is configured to acquire the use demand of a charging gun of a user;
and the charging strategy generation module is configured to generate a charging strategy for controlling the charging gun of each group of charging piles to execute a charging action according to the power grid load prediction data, the charging pile state of each group of charging piles and the charging gun use requirement of the user.
Optionally, the power grid load prediction module specifically includes:
the prediction model building unit is configured to extract historical time window data from historical power grid load data, input the historical time window data into an initial model for training, and obtain a trained power grid load prediction model;
and the power grid load prediction unit is configured to input future time window data into the power grid load prediction model to obtain power grid load prediction data output by the power grid load prediction model.
Optionally, the prediction model building unit specifically includes:
a historical time window data extraction subunit configured to divide historical grid load data into time windows of fixed length, treat grid load values within each time window as pixel values of an image, and form historical time window data;
and the model training subunit is configured to input each data point in the historical time window data into the CNN model for training, so as to obtain a trained power grid load prediction model.
Optionally, in the model training subunit, the historical time window data includes N input data points X at a characteristic dimension d with time steps i i,d,1 The method comprises the steps of carrying out a first treatment on the surface of the The CNN model includes:
a convolution layer, the expression of the convolution layer being:
wherein F is the convolution kernel size, Z (1) Is the output of the convolution layer, W (1) Is the weight of the convolution kernel, k is the index of the convolution kernel;
a pooling layer, the pooling layer having an expression:
wherein P is the size of the pooling window,for the activation function ReLU;
the expression of the full-connection layer is as follows:
wherein Z is (2) Is the output of the full connection layer, W (2) Is the weight of the full connection layer, h is the index of the neuron;
the output layer has the expression:
wherein,representing the predicted value of the grid load at time step i.
Optionally, the charging pile state classification module specifically includes:
the historical state data processing unit is configured to acquire historical state data of each group of charging piles, extract state characteristics of the historical state data and calculate the confidence coefficient of the charging piles according to the state characteristics;
the charging pile state classification unit is configured to calculate confidence degree of the charging pile and fuzzy membership degree of a threshold value by using a fuzzy C-means method, and classify the states of each group of charging piles according to the fuzzy membership degree to obtain the charging pile state of each group of charging piles.
Optionally, the charging pile state classification unit specifically includes:
a classification definition subunit configured to define a feature vector of a data point as x= (X) 1 ,x 2 ,…,x N ) The feature vector defining the cluster center is v= (V) 1 ,v 2 ,…,v C ) The method comprises the steps of carrying out a first treatment on the surface of the N is the number of data points, C is the number of clustering centers, and each clustering center represents the state of one charging pile;
a fuzzy membership calculation subunit configured to determine a fuzzy membership matrix U = [ U ] ij ] N×C ]By Euclidean distance d ij :[d ij ＝||X i -V j || 2 ]Calculating fuzzy membership value Wherein X is i Is the eigenvector of the ith data point, V j Is the feature vector of the jth cluster center, m is an ambiguity parameter, generally takes an integer greater than 1, and t represents the iteration number;
and the charging pile state classification subunit is configured to take the clustering center with the largest fuzzy membership value as the charging pile state of the charging pile.
Optionally, the system further comprises: the charging pile state updating module specifically comprises:
the charging pile real-time state acquisition unit is configured to acquire the charging pile real-time state of each group of charging piles;
the system comprises a charging pile real-time state updating unit, a clustering center updating unit and a clustering center updating unit, wherein the clustering center updating unit is configured to update a fuzzy membership value according to the charging pile real-time state and update a clustering center according to the updated fuzzy membership value; the updating expression of the clustering center is specifically as follows:
wherein V is j Representing the new position of the jth cluster center, u ij Is the fuzzy membership value of the data point i to the clustering center j, X i Is the eigenvector of the data point i, m is the ambiguity parameter;
and the charging pile state updating unit is configured to update the charging pile state of the charging pile in the target period according to the updated clustering center.
Optionally, the charging gun use requirement includes a charging period requirement and a charging power requirement of the charging gun.
Optionally, the charging policy generation module specifically includes:
the charging power distribution unit of the charging piles is configured to distribute corresponding charging power to each group of charging piles according to the power grid load prediction data and the charging pile state of each group of charging piles so as to balance the power grid load;
and the charging strategy generation unit is configured to generate a charging strategy for executing a charging action for each charging gun of each group of charging piles according to the charging power distributed by each group of charging piles and the charging period requirement and the charging electric quantity requirement of the charging gun of the user, so that the charging gun use requirement of each user is matched with the corresponding charging gun.
In a second aspect of the present invention, there is provided a multi-gun low-power charging pile method comprising:
acquiring historical power grid load data in a regional range, and predicting power grid load prediction data of a target period according to the historical power grid load data;
acquiring historical state data of each group of charging piles, and classifying the states of the charging piles according to the historical state data to obtain the state of the charging piles of each group of charging piles;
acquiring the use requirement of a charging gun of a user;
and generating a charging strategy for controlling the charging gun of each group of charging piles to execute charging action according to the power grid load prediction data, the charging pile state of each group of charging piles and the charging gun use requirement of the user.
The invention has the beneficial effects that: according to the multi-gun low-power charging pile system and the multi-gun low-power charging pile method, charging strategies of a plurality of charging guns of each group of charging piles are generated by predicting power grid load data and utilizing the state of the charging piles and the use requirements of the charging guns of users, so that the problem of unbalanced supply and demand of the charging piles can be solved by providing more charging positions, meanwhile, the influence of peak time on the power grid caused by unbalanced load is considered, the charging strategies adapting to the charging requirements of the users are generated for each group of charging piles, and the problem of unbalanced power grid load is solved.
Drawings
Fig. 1 is a schematic structural diagram of a multi-gun low-power charging pile system provided by the invention;
fig. 2 is a schematic flow chart of a multi-gun low-power charging pile method provided by the invention.
Reference numerals:
10-a power grid load prediction module; 20-a charging pile state classification module; 30-a user demand acquisition module; 40-a charging strategy generation module.
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.
Example 1:
referring to fig. 1, fig. 1 is a schematic structural diagram of a multi-gun low-power charging pile system according to an embodiment of the present invention.
As shown in fig. 1, a multi-gun low-power charging pile system includes: a grid load prediction module 10, the grid load prediction module 10 being configured to obtain historical grid load data over a range of areas and predict grid load prediction data for a target period from the historical grid load data; the charging pile state classification module 20 is configured to acquire historical state data of each group of charging piles, and classify the charging piles according to the historical state data to acquire the charging pile state of each group of charging piles; a user demand acquisition module 30, the user demand acquisition module 30 configured to acquire a user's charging gun usage demand; the charging policy generation module 40 is configured to generate a charging policy for controlling the charging gun of each group of charging piles to execute a charging action according to the power grid load prediction data, the charging pile state of each group of charging piles and the charging gun use requirement of the user.
It should be noted that, due to the continuous increase of the number of electric vehicles, the unbalanced supply and demand problem of the charging piles appears gradually, so that in a certain area, particularly in a city and a residential area, the waiting time of the charging piles is long, the use experience of the electric vehicles of users is affected, in some cases, the charging pile users can continue to occupy the charging piles after the charging is completed, and the vehicles are not moved away, so that the use of other users is limited. Meanwhile, large-scale electric automobile charging can cause huge load pressure to a power grid in a peak period, so that the power grid is unstable and power supply is problematic. In order to solve the above-mentioned problem, the embodiment provides a multi-gun low-power charging pile system, which generates a charging strategy of a plurality of charging guns of each group of charging piles by predicting power grid load data and utilizing charging pile states and charging gun use requirements of users, and can generate a charging strategy adapting to charging requirements of users for each group of charging piles in consideration of load imbalance influence of peak time to a power grid while providing more charging positions to solve the problem of unbalanced supply and demand of the charging piles, thereby solving the problem of unbalanced power grid load. Therefore, through intelligent charging control based on data driving, the multi-gun and low-power design of one charging pile group is utilized, charging positions can be provided for as many users as possible, and a charging scheme with high efficiency and high flexibility is provided for more users by generating a charging strategy with higher adaptability, so that the overall charging efficiency in a regional range is improved, the overall charging time is reduced, the electric automobile is more easily charged, the load of a power grid is reduced, the peak load is reduced, and the stability of the power grid is improved.
In a preferred embodiment, the power grid load prediction module 10 specifically includes: the prediction model building unit is configured to extract historical time window data from historical power grid load data, input the historical time window data into an initial model for training, and obtain a trained power grid load prediction model; and the power grid load prediction unit is configured to input future time window data into the power grid load prediction model to obtain power grid load prediction data output by the power grid load prediction model.
The prediction model building unit specifically comprises: a historical time window data extraction subunit configured to divide historical grid load data into time windows of fixed length, treat grid load values within each time window as pixel values of an image, and form historical time window data; and the model training subunit is configured to input each data point in the historical time window data into the CNN model for training, so as to obtain a trained power grid load prediction model.
In this embodiment, in order to implement the prediction of the power grid load in the target period, a power grid load prediction algorithm based on a convolutional neural network is provided, and the power grid load in the future period is predicted by capturing the time sequence features in the historical time sequence data, so as to provide data support for the charging policy generation of each charging pile. Specifically, the power grid load prediction algorithm based on the convolutional neural network comprises the following implementation steps:
1. data preparation: first, historical grid load data is prepared. These data are time series including date and time stamps and corresponding grid load values. These data are divided into training and test sets.
2. Characteristic engineering: in order to use CNN for grid load prediction, it is necessary to convert the time series data into a form suitable for CNN input. The time series data is divided into time windows of a fixed length, and then the load value within each time window is regarded as the pixel value of the image. This combines the time dimension and the load value dimension together to form a two-dimensional input.
3. Constructing a CNN model: a CNN model is designed for time series data. CNNs typically include a convolutional layer, a pooling layer, and a fully-connected layer. The convolution layer is used for extracting time sequence characteristics, the pooling layer is used for reducing data dimension, and the full-connection layer is used for outputting a prediction result.
When using Convolutional Neural Networks (CNNs) for grid load prediction, the forward propagation process of the model is performed as follows:
(1) Input data represents:
there is a time series containing historical grid load data, which includes N time steps. We denote the input data by X, the dimensions of which are (N, D, 1), where N is the number of time steps and D is the characteristic dimension of each time step, here 1 (since we only consider the grid load values). X is X i,d,1 Representing data points at time step i and feature dimension d.
(2) Convolution layer operation:
feature extraction is performed using one convolution layer, which is assumed to have K convolution kernels and a convolution kernel size F. The convolution operation is expressed as:
wherein Z is (1) Is the output of the convolution layer, W (1) Is the weight of the convolution kernel and k is the index of the convolution kernel. This operation extracts features on the input data by sliding the convolution kernel.
(3) Activation function:
for the output of each convolution kernel, we apply an activation function ReLU:
(4) Pooling layer operation:
next, we downsample the feature map using the pooling layer. Assuming we use a max pooling operation, with a pooling window size of P, the pooling operation is expressed as:
the pooling layer helps reduce the dimensionality of the data, preserving important features.
(5) Full connection layer operation:
finally, we connect the output of the pooling layer to a fully connected layer with H neurons. The fully connected operation is expressed as:
wherein Z is (2) Is the output of the full connection layer, W (2) Is the weight of the full connection layer, h is the index of the neuron.
(6) Output layer:
finally, we can apply the output of the fully connected layer to an appropriate activation function, such as a linear activation function, to obtain a predicted value of the grid load:
predictive valueRepresenting the predicted value of the grid load at time step i.
4. Loss function and optimizer: an appropriate loss function is chosen to measure the gap between the predicted value and the true value. For regression problems, mean square error is typically used as a loss function. An optimizer is selected to minimize the loss function.
5. Model training: model training is performed using the training set. The time window data is input into the CNN model, and weight updating is performed according to the loss function until a stopping condition (such as a fixed training period or loss function convergence) is reached.
The following is a specific example of an algorithm formula for loss functions and weight updates:
loss function:
wherein L (θ) represents a loss function, θ represents a parameter of the CNN model, N represents the number of samples, y i Representing the value of the real grid load,representing the predicted value of the CNN model.
The weight update uses a gradient descent method to update the weight of the model according to the gradient of the loss function:
wherein,representing the gradient of the loss function with respect to the parameter θ +.>Representing the gradient of the CNN model output with respect to the parameter θ.
6. Model evaluation: the test set is used to evaluate the performance of the model. In this embodiment, the accuracy of the model is measured using a calculated Mean Square Error (MSE) or other correlation indicator.
7. Predicting future grid loads: the trained CNN model can be used to predict future grid loads. The data of the future time window is input into a model, which will output the predicted grid load value.
Therefore, the embodiment can automatically capture the complex time sequence characteristics in the time sequence data by using the convolutional neural network to predict the power grid load in the regional range, so as to realize the power grid load prediction of the future period and improve the accuracy of the power grid load prediction.
In a preferred embodiment, the charging pile state classification module 20 specifically includes: the historical state data processing unit is configured to acquire historical state data of each group of charging piles, extract state characteristics of the historical state data and calculate the confidence coefficient of the charging piles according to the state characteristics; the charging pile state classification unit is configured to calculate confidence degree of the charging pile and fuzzy membership degree of a threshold value by using a fuzzy C-means method, and classify the states of each group of charging piles according to the fuzzy membership degree to obtain the charging pile state of each group of charging piles.
In this embodiment, after the historical state data is obtained, the data is preprocessed first, including data cleaning, outlier detection and missing value filling, so as to ensure accuracy and integrity of the data, and then the collected historical state data (charging power and charging period) is extracted by the historical state data processing unit, for example: and extracting frequency domain features such as frequency spectrum, frequency components, power spectrum density and other state features by utilizing Fourier transformation or wavelet transformation, and analyzing the state features to obtain the confidence of the charging pile. After that, the state of the charging pile is classified by calculating the confidence level of the charging pile and the fuzzy membership degree of the threshold value by using a fuzzy C-means algorithm (FCM) through the state classification unit of the charging pile. The charging pile state classification unit calculates the confidence level of the charging pile and the fuzzy membership degree of the threshold value by using a fuzzy C-means algorithm (FCM), and specifically comprises the following implementation steps:
(1) Classification definition:
1. assume that there are N data points and C cluster centers, each representing the state of one charging stake.
2. Defining a feature vector of data points: x= (X 1 ,x 2 ,…,x N )
3. Feature vector v= (V) defining cluster center 1 ,v 2 ,…,v C )
(2) Calculating fuzzy membership degree:
4. fuzzy membership matrix U: [ U= [ U ] ij ] N×C ]Wherein (u) ij ) Representing the membership value of the ith data point to the jth cluster center.
5. Distance metric formulas, typically using euclidean distance: [ d ] ij ＝||X i -V j || 2 ]Wherein (X) i ) Is the eigenvector of the ith data point, (V) j ) Is the feature vector of the j-th cluster center.
6. By calculating the U matrix, membership between each charging pile state category and each data point in the charging pile history data can be determined. This means that each data point is assigned to a different state class whose membership value describes the extent to which it belongs to each state. By analyzing the U matrix, it can be determined which state class each data point is most likely to be in. Specifically, for each data point, a cluster center with the largest membership value in the U matrix can be found, and the cluster center is the most probable state category. Further, it may be helpful to identify the current state of the charging stake, such as idle state, charging state, fault state, and inactive state, etc., so as to take corresponding measures and decisions. Thus, the fuzzy membership update formula:
where (m) is the ambiguity parameter (typically taking an integer greater than 1) and (t) represents the number of iterations.
(3) Classification of charging pile states:
7. cluster centers typically represent different status categories in the charge pile management system, such as idle status, charge status, fault status, and inactive status. Each cluster center of each state class represents a charging pile state, and the membership value u ij Indicating the extent to which data point i belongs to the charging pile state j.
Therefore, the embodiment judges the most likely charging pile state of the charging pile corresponding to each data point by establishing the fuzzy membership matrix, so as to classify each charging pile, further help identify the current state of the charging pile, further provide data support for the charging strategy generation of each charging pile, realize the intelligent charging method based on data driving, optimize the power of a power grid and improve the stability of a power system.
In a preferred embodiment, the system further comprises: the charging pile state updating module specifically comprises: the charging pile real-time state acquisition unit is configured to acquire the charging pile real-time state of each group of charging piles; the system comprises a charging pile real-time state updating unit, a clustering center updating unit and a clustering center updating unit, wherein the clustering center updating unit is configured to update a fuzzy membership value according to the charging pile real-time state and update a clustering center according to the updated fuzzy membership value; and the charging pile state updating unit is configured to update the charging pile state of the charging pile in the target period according to the updated clustering center.
In this embodiment, considering that a fault, a communication interruption or other abnormal conditions of a charging pile may occur in the charging pile network, the situation that the whole charging pile network is unstable occurs, the fuzzy membership value is updated by acquiring the real-time state of the charging pile of each group of charging piles, and then the clustering center is updated, and the system can gradually adjust the boundary and the characteristic of each state by continuously and iteratively updating the position of the clustering center, so that the system better matches with the actual data distribution. Finally, the state represented by the clustering center can reflect the state of the charging pile more accurately, so that the system is helped to judge the state of the charging pile in the target period.
The cluster center position is updated according to the membership value of the data point in the iterative process of the algorithm. The clustering center updates the formula:
the cluster center update formula is to redefine the location of each cluster center by considering the membership of the data points to the cluster center to better fit the data distribution. Wherein V is j Representing the new position of the jth cluster center, u ij Is the membership value of the data point i to the cluster center j, X i Is the eigenvector of data point i and m is the ambiguity parameter. The clustering center updating formula is a key step for adjusting the position of the state class of the charging pile, and by updating the clustering center, the system can judge the state of the charging pile more accurately. Therefore, the charging pile state updating module provided by the embodiment continuously monitors the behavior of the charging pile so as to dynamically adjust, updates the charging pile state of the charging pile according to the updated clustering center, and timely performs early warning and discrimination when the charging pile breaks down, thereby achieving the effects of optimizing the power utilization of the power grid, improving the stability of the power system and reducing the cost.
In a preferred embodiment, the charging gun usage requirements include a charging period requirement and a charging power requirement of the charging gun. On this basis, the charging policy generation module 40 specifically includes: the charging power distribution unit of the charging piles is configured to distribute corresponding charging power to each group of charging piles according to the power grid load prediction data and the charging pile state of each group of charging piles so as to balance the power grid load; and the charging strategy generation unit is configured to generate a charging strategy for executing a charging action for each charging gun of each group of charging piles according to the charging power distributed by each group of charging piles and the charging period requirement and the charging electric quantity requirement of the charging gun of the user, so that the charging gun use requirement of each user is matched with the corresponding charging gun.
In this embodiment, first, the system allocates corresponding charging power to each group of charging piles according to the power grid load prediction data and the charging pile state of each group of charging piles, so that the power grid load is balanced, that is, different charging powers are allocated to different charging piles in consideration of the charging pile state of each group of charging, so that the power grid load balance in a regional range is realized.
On the basis, the charging time period requirement and the charging power requirement of the user are considered, a charging strategy for executing a charging action is generated for each charging gun of each group of charging piles, so that the charging gun use requirement of each user is matched with the corresponding charging gun, namely, by acquiring the charging requirement of each user, a corresponding charging control instruction is distributed on the charging gun of the corresponding charging pile so as to adapt to the charging requirement of the user, under the condition, charging positions can be provided for as many users as possible, meanwhile, because the charging strategy (charging time and charging power) is accurately distributed according to time and the charging gun, even if a certain user does not timely move away from the vehicle after charging is completed, the use of other charging guns is not influenced due to the low-power design of the multiple charging guns, and the overall charging efficiency is improved to a certain extent.
Therefore, the charging power distribution unit of the charging piles distributes corresponding charging power for each group of charging piles according to the power grid load prediction data and the charging pile state of each group of charging piles, the charging strategy generation unit of the charging gun generates a charging pile multi-gun low-power charging intelligent control scheme of a charging strategy for executing charging actions for each charging gun of each group of charging piles according to the charging power distributed by each group of charging piles, the charging period requirement and the charging electric quantity requirement of a charging gun of a user, so that the balance of the power grid load can be realized, the charging positions for the user can be provided as much as possible, the overall charging efficiency and other effects can be improved, and the system benefit can be improved.
Referring to fig. 2, fig. 2 is a schematic flow chart of a multi-gun low-power charging pile method according to an embodiment of the invention.
As shown in fig. 2, a multi-gun low-power charging pile method includes the steps of:
s1: acquiring historical power grid load data in a regional range, and predicting power grid load prediction data of a target period according to the historical power grid load data;
s2: acquiring historical state data of each group of charging piles, and classifying the states of the charging piles according to the historical state data to obtain the state of the charging piles of each group of charging piles;
s3: acquiring the use requirement of a charging gun of a user;
s4: and generating a charging strategy for controlling the charging gun of each group of charging piles to execute charging action according to the power grid load prediction data, the charging pile state of each group of charging piles and the charging gun use requirement of the user.
In this embodiment, by predicting the power grid load data and using the states of the charging piles and the use requirements of the charging guns of the users, the charging strategies of the charging guns of each group of charging piles are generated, so that the problem of unbalanced supply and demand of the charging piles can be solved, and meanwhile, the influence of the peak time on the power grid caused by unbalanced load is considered, the charging strategies adapting to the charging requirements of the users are generated for each group of charging piles, and the problem of unbalanced power grid load is solved.
The specific implementation manner of the multi-gun low-power charging pile method is basically the same as that of each embodiment of the multi-gun low-power charging pile system, and is not repeated here.
In describing embodiments of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "center", "top", "bottom", "inner", "outer", "inside", "outside", etc. indicate orientations or positional relationships based on the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Wherein "inside" refers to an interior or enclosed area or space. "peripheral" refers to the area surrounding a particular component or region.
In the description of embodiments of the present invention, the terms "first," "second," "third," "fourth" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", "a third" and a fourth "may explicitly or implicitly include one or more such feature. In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more.
In describing embodiments of the present invention, it should be noted that the terms "mounted," "connected," and "assembled" are to be construed broadly, as they may be fixedly connected, detachably connected, or integrally connected, unless otherwise specifically indicated and defined; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
In the description of embodiments of the invention, a particular feature, structure, material, or characteristic may be combined in any suitable manner in one or more embodiments or examples.
In the description of the embodiments of the present invention, it is to be understood that "-" and "-" denote the same ranges of the two values, and the ranges include the endpoints. For example, "A-B" means a range greater than or equal to A and less than or equal to B. "A-B" means a range of greater than or equal to A and less than or equal to B.
In the description of embodiments of the present invention, the term "and/or" is merely an association relationship describing an association object, meaning that three relationships may exist, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A multi-gun low power charging stake system, comprising:
the power grid load prediction module is configured to acquire historical power grid load data in a regional range and predict power grid load prediction data of a target period according to the historical power grid load data;
the charging pile state classification module is configured to acquire historical state data of each group of charging piles, and classify the charging piles according to the historical state data to acquire the charging pile state of each group of charging piles;
the charging gun comprises a user demand acquisition module, a charging gun storage module and a charging gun storage module, wherein the user demand acquisition module is configured to acquire the use demand of a charging gun of a user;
and the charging strategy generation module is configured to generate a charging strategy for controlling the charging gun of each group of charging piles to execute a charging action according to the power grid load prediction data, the charging pile state of each group of charging piles and the charging gun use requirement of the user.
2. The multi-gun low-power charging pile system according to claim 1, wherein the grid load prediction module specifically comprises:
the prediction model building unit is configured to extract historical time window data from historical power grid load data, input the historical time window data into an initial model for training, and obtain a trained power grid load prediction model;
and the power grid load prediction unit is configured to input future time window data into the power grid load prediction model to obtain power grid load prediction data output by the power grid load prediction model.
3. The multi-gun low-power charging pile system according to claim 2, wherein the prediction model building unit specifically comprises:
a historical time window data extraction subunit configured to divide historical grid load data into time windows of fixed length, treat grid load values within each time window as pixel values of an image, and form historical time window data;
and the model training subunit is configured to input each data point in the historical time window data into the CNN model for training, so as to obtain a trained power grid load prediction model.
4. A multi-gun low-power charging pile system according to claim 3, wherein in the model training subunit, the historical time window data comprises N input data points X at a characteristic dimension d with time steps i i,d,1 The method comprises the steps of carrying out a first treatment on the surface of the The CNN model includes:
a convolution layer, the expression of the convolution layer being:
wherein F is the convolution kernel size, Z (1) Is the output of the convolution layer, W (1) Is the weight of the convolution kernel, k is the index of the convolution kernel;
a pooling layer, the pooling layer having an expression:
wherein P is the size of the pooling window,for the activation function ReLU;
the expression of the full-connection layer is as follows:
wherein Z is (2) Is the output of the full connection layer, W (2) Is the weight of the full connection layer, h is the index of the neuron;
the output layer has the expression:
wherein,representing the predicted value of the grid load at time step i.
5. The multi-gun low-power charging pile system according to claim 1, wherein the charging pile state classification module specifically comprises:
the historical state data processing unit is configured to acquire historical state data of each group of charging piles, extract state characteristics of the historical state data and calculate the confidence coefficient of the charging piles according to the state characteristics;
the charging pile state classification unit is configured to calculate confidence degree of the charging pile and fuzzy membership degree of a threshold value by using a fuzzy C-means method, and classify the states of each group of charging piles according to the fuzzy membership degree to obtain the charging pile state of each group of charging piles.
6. The multi-gun low-power charging pile system according to claim 5, wherein the charging pile state classification unit specifically comprises:
a classification definition subunit configured to define a feature vector of a data point as x= (X) 1 ,x 2 ,…,x N ) The feature vector defining the cluster center is v= (V) 1 ,v 2 ,…,v C ) The method comprises the steps of carrying out a first treatment on the surface of the N is the number of data points, C is the number of clustering centers, and each clustering center represents the state of one charging pile;
a fuzzy membership calculation subunit configured to determine a fuzzy membership matrix U = [ U ] ij ] N×C ]By Euclidean distance d ij :[d ij ＝||X i -V j || 2 ]Calculating fuzzy membership valueWherein X is i Is the eigenvector of the ith data point, V j Is the feature vector of the jth cluster center, m is an ambiguity parameter, generally takes an integer greater than 1, and t represents the iteration number;
and the charging pile state classification subunit is configured to take the clustering center with the largest fuzzy membership value as the charging pile state of the charging pile.
7. The multi-gun low-power charging stake system of claim 6, wherein the system further includes: the charging pile state updating module specifically comprises:
the charging pile real-time state acquisition unit is configured to acquire the charging pile real-time state of each group of charging piles;
the system comprises a charging pile real-time state updating unit, a clustering center updating unit and a clustering center updating unit, wherein the clustering center updating unit is configured to update a fuzzy membership value according to the charging pile real-time state and update a clustering center according to the updated fuzzy membership value; the updating expression of the clustering center is specifically as follows:
wherein V is j Representing the new position of the jth cluster center, u ij Is the fuzzy membership value of the data point i to the clustering center j, X i Is the eigenvector of the data point i, m is the ambiguity parameter;
and the charging pile state updating unit is configured to update the charging pile state of the charging pile in the target period according to the updated clustering center.
8. The multi-gun low-power charging stake system of claim 1, wherein the charging gun usage requirements include a charging period requirement and a charging power requirement of the charging gun.
9. The multi-gun low-power charging stake system of claim 8, characterized in that the charging strategy generation module specifically includes:
the charging power distribution unit of the charging piles is configured to distribute corresponding charging power to each group of charging piles according to the power grid load prediction data and the charging pile state of each group of charging piles so as to balance the power grid load;
and the charging strategy generation unit is configured to generate a charging strategy for executing a charging action for each charging gun of each group of charging piles according to the charging power distributed by each group of charging piles and the charging period requirement and the charging electric quantity requirement of the charging gun of the user, so that the charging gun use requirement of each user is matched with the corresponding charging gun.
10. A multi-gun low-power charging pile method, comprising:
acquiring historical power grid load data in a regional range, and predicting power grid load prediction data of a target period according to the historical power grid load data;
acquiring historical state data of each group of charging piles, and classifying the states of the charging piles according to the historical state data to obtain the state of the charging piles of each group of charging piles;
acquiring the use requirement of a charging gun of a user;
and generating a charging strategy for controlling the charging gun of each group of charging piles to execute charging action according to the power grid load prediction data, the charging pile state of each group of charging piles and the charging gun use requirement of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311698363.2A CN117465272A (en) | 2023-12-12 | 2023-12-12 | Multi-gun low-power charging pile system and charging method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311698363.2A CN117465272A (en) | 2023-12-12 | 2023-12-12 | Multi-gun low-power charging pile system and charging method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117465272A true CN117465272A (en) | 2024-01-30 |
Family
ID=89636403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311698363.2A Pending CN117465272A (en) | 2023-12-12 | 2023-12-12 | Multi-gun low-power charging pile system and charging method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117465272A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117901694A (en) * | 2024-02-23 | 2024-04-19 | 宁波恒升电气有限公司 | Power supply control method and system of intelligent power distribution cabinet for charging pile |
| CN118399377A (en) * | 2024-03-28 | 2024-07-26 | 深圳市泰玖新能源科技有限公司 | Charging pile state early warning method based on load balance |
-
2023
- 2023-12-12 CN CN202311698363.2A patent/CN117465272A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117901694A (en) * | 2024-02-23 | 2024-04-19 | 宁波恒升电气有限公司 | Power supply control method and system of intelligent power distribution cabinet for charging pile |
| CN117901694B (en) * | 2024-02-23 | 2024-09-06 | 宁波恒升电气有限公司 | Power supply control method and system of intelligent power distribution cabinet for charging pile |
| CN118399377A (en) * | 2024-03-28 | 2024-07-26 | 深圳市泰玖新能源科技有限公司 | Charging pile state early warning method based on load balance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117465272A (en) | Multi-gun low-power charging pile system and charging method | |
| CN111398832A (en) | Bus battery SOC prediction method based on ANFIS model | |
| CN109215344B (en) | Method and system for urban road short-time traffic flow prediction | |
| Sun et al. | A real-time PMP energy management strategy for fuel cell hybrid buses based on driving segment feature recognition | |
| CN108596667A (en) | A kind of electric vehicle real time charging Prices Calculation based on car networking | |
| CN112670999B (en) | Low-voltage distribution network real-time voltage control method based on user-side flexible resources | |
| CN110866636A (en) | Microgrid planning method comprehensively considering electric vehicle charging station and distributed energy | |
| CN115841176A (en) | Charging pile variable frequency load security situation sensing method and system | |
| CN117060470B (en) | Power distribution network voltage optimization control method based on flexible resources | |
| CN110084426A (en) | A kind of wind power interval prediction method based on industry and mining city | |
| CN117691602A (en) | Source network load storage collaborative planning method and system considering flexibility and economy | |
| CN116914751A (en) | Intelligent power distribution control system | |
| CN115513945A (en) | Distributed power supply management method based on Internet of things | |
| Kumar et al. | Energy management of a fuel cell/ultra-capacitor hybrid electric vehicle under uncertainty based on CO-SNN method | |
| CN112668764B (en) | Offshore wind farm energy storage system optimization configuration method based on cloud model and FCM algorithm | |
| CN111027017B (en) | Comprehensive evaluation system for management state of power distribution network | |
| CN118350548B (en) | Intelligent energy consumption management system and method for AI (advanced technology attachment) computing equipment based on big data | |
| CN118097969B (en) | Congestion early warning method based on short-time prediction of traffic parameters | |
| CN117811169B (en) | Battery active equalization management system | |
| CN113177320B (en) | Simulation optimization method, system, equipment and medium for road dynamic congestion charging | |
| CN114742285B (en) | Construction method and application of resident power consumption mode prediction model | |
| Han et al. | Space load forecasting considering distributed energy and electric vehicles | |
| CN118861731A (en) | Electric vehicle load prediction method based on TCN-BiGRU deep learning | |
| CN118748449A (en) | Near space vehicle energy system management method based on deep reinforcement learning | |
| CN117521361A (en) | Low-voltage area active characteristic identification method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |