Charging control method, system, device, equipment and storage medium for home charging pile

Abstract

The present invention relates to the field of intelligent electricity technology, and discloses a charging control method, system, device, equipment and storage medium for a home charging pile, the method comprising: obtaining a charging type selected by a user, the charging type comprising: orderly charging and disorderly charging; in the case of determining that the charging type is orderly charging, predicting a basic power load curve, the basic power load curve comprising the average power load corresponding to different moments in a future preset time predicted based on historical power consumption data of residents and the average power load corresponding to the current moment; determining the charging time of a vehicle to be charged; based on the basic power load curve and the charging time, determining the planned charging time of the vehicle to be charged, and sending the planned charging time to the corresponding charging pile. The present invention can avoid the problem of overload of the power grid caused by a sudden increase in the power grid load, thereby ensuring the smooth operation of the power grid, reducing the impact on the power grid load, and improving the reliability of the power grid.

Description

Technical Field

[0001] The present invention relates to the field of intelligent electricity technology, and in particular to a charging control method, system, device, equipment and storage medium for a home charging pile. Background Art

[0002] With the rapid popularization of electric vehicle charging piles and battery vehicle charging piles, charging piles are not only set up in public places and parking lots, but more and more residents are also transforming their household electricity to install charging piles to meet their personal charging needs. Most of the current charging piles use instant charging. This disorderly charging method makes the proportion of disorderly charging load in the power grid load increasingly larger. If it is not regulated, the distribution system will not be able to withstand such a large-scale disorderly charging load.

[0003] To solve this problem, although there are charging piles with orderly charging capabilities, they only meet the function of scheduled charging, that is, charging according to the time selected by the user. The electricity price for each time period is different, but this does not take into account the operating conditions of the grid load. Grid overload problems will still occur, affecting the stable operation of the grid. Summary of the invention

[0004] In view of this, the present invention provides a charging control method, system, device, equipment and storage medium for a home charging pile to solve the problem in the prior art that the operating conditions of the power grid load are not considered when designing an orderly charging solution.

[0005] In a first aspect, the present invention provides a charging control method for a home charging pile, the method comprising:

[0006] Get the charging type selected by the user, which includes: ordered charging and disordered charging;

[0007] When the charging type is determined to be orderly charging, a basic electricity load curve is predicted based on the prediction model. The basic electricity load curve includes the average electricity load corresponding to different times in the future preset time and the average electricity load corresponding to the current time predicted based on the residents' historical electricity consumption data;

[0008] Determine the charging time of the vehicle to be charged;

[0009] Based on the basic electricity load curve and charging time, the planned charging time of the vehicle to be charged is determined, and the planned charging time is sent to the corresponding charging pile.

[0010] In this embodiment, under the condition of orderly charging, the basic electricity load curve can be predicted through the residents' historical electricity consumption data, and the planned charging time can be determined based on the predicted basic electricity load curve. Finally, the charging pile charges the vehicle to be charged according to the planned charging time. This can avoid the problem of grid overload caused by the sudden increase in grid load, thereby ensuring the smooth operation of the grid, reducing the impact on the grid load, and improving the reliability of the grid.

[0011] In an optional implementation, determining a planned charging time for a vehicle to be charged based on a basic power load curve and a charging time includes:

[0012] Taking the current time as the starting point, determine in sequence whether the average power load during the charging time exceeds the preset power load;

[0013] When it is determined that the average power load within the charging time does not exceed the preset power load, the corresponding starting time is determined, and the determination is stopped, and the starting time is used as the planned charging time.

[0014] In this implementation, the time closest to the current time under the conditions is selected as the planned charging time, which can effectively shorten the waiting time for the user to charge and improve the charging efficiency.

[0015] In an optional implementation, after sending the planned charging time to the corresponding charging pile, the method further includes:

[0016] Superimpose the charging load of the vehicle to be charged to the corresponding moment on the basic power load curve;

[0017] Determine whether there is an overload point;

[0018] In the case where an overload point exists, the overload point is cut, and a cutting time period is determined, where the cutting time period is a time period that does not include the overload point;

[0019] Determine whether the cut time period satisfies the remaining charging time of the vehicle to be charged;

[0020] If the remaining charging time of the vehicle to be charged is met, the nearest cut time period is selected for charging.

[0021] If the remaining charging time of the vehicle to be charged is not satisfied, at least two maximum cutting time periods are selected for charging.

[0022] In this embodiment, according to the load conditions and charging needs, the charging time periods are reasonably divided, which can effectively avoid overload of the power grid, and ultimately achieve orderly planned charging, thereby improving the operating efficiency and stability of the power grid.

[0023] In an optional embodiment, the prediction model is established by the following steps:

[0024] Obtain residents' historical electricity consumption data, which includes user electricity consumption data and charging pile electricity consumption data;

[0025] The historical electricity consumption data of residents is divided into a sample set and a test set according to the ratio of 8:2;

[0026] Based on the sample set and the test set, the initial model is preset through the sparrow search algorithm-neural network training, where the number of input layers of the sparrow search algorithm-neural network is 7, the number of hidden layers is 15, and the number of output layers is 7; where the maximum number of training times of the hidden layer function of the hidden layer is 500 times, the learning rate is 0.1, the training error corresponding to the discoverer is 0.2, and the training error corresponding to the warning value is 0.6;

[0027] The trained preset initial model is used as the prediction model.

[0028] In this embodiment, the number of layers and the number of training times are accurately set. By reasonably setting the structure and training parameters of the Shenmiao search algorithm-neural network, the data can be better fitted and the performance and generalization ability of the model can be improved. In addition, limiting the maximum number of training times and setting a suitable learning rate can accelerate the convergence process of the model and effectively improve the training efficiency of the model.

[0029] In an optional implementation, based on the sample set and the test set, a preset initial model is trained by a sparrow search algorithm-neural network, including:

[0030] Initialize the preset parameters in the sparrow search algorithm to obtain the initial sparrow search algorithm;

[0031] Initialize the number of neural network layers, the number of nodes in each layer, and the transfer function of each layer to obtain the initial neural network;

[0032] The historical electricity consumption data of residents in the sample set and the test set are input into the initial sparrow search algorithm, and the positions of the discoverer, followers and warning values ​​are updated iteratively;

[0033] Based on the updated positions of the discoverer, follower, and alert value, the fitness value of the new position of the individual sparrow is updated;

[0034] The fitness value of the new position of the sparrow individual after the final iterative update is input into the initial neural network to obtain the preset initial model.

[0035] In this embodiment, the sparrow search algorithm combined with the neural network method can improve the optimization effect of the neural network, speed up the parameter search speed, and improve the generalization ability and robustness of the model.

[0036] In an optional implementation manner, before obtaining the historical electricity consumption data of residents, the method further includes:

[0037] Obtaining residents' electricity consumption data once every first preset time, and updating residents' historical electricity consumption data;

[0038] At every second preset time, an instruction to optimize the prediction model is triggered to optimize the prediction model based on the updated historical electricity consumption data of residents.

[0039] In this embodiment, regularly acquiring residential electricity consumption data and updating the historical residential electricity consumption data used for prediction can maintain the real-time and accuracy of the data, help improve the accuracy of the prediction model, and thus better predict the planned charging time, reduce the impact on the grid load, and improve the reliability of the grid.

[0040] In a second aspect, the present invention provides an orderly charging control system for a home charging pile, the system comprising:

[0041] Electric energy meter, used to measure the user's electricity consumption;

[0042] Charging piles, used to charge vehicles to be charged;

[0043] The concentrator is connected to the electric energy meter and the charging pile for communication, and is used to collect the user's electricity consumption data of the electric energy meter and also to monitor the charging pile electricity consumption data of the charging pile. The concentrator is applicable to the charging control method for the home charging pile in any of the above-mentioned embodiments.

[0044] In this embodiment, the user power consumption data of the energy meter collected by the concentrator and the charging pile power consumption data of the charging pile can be used as the historical power consumption data of the residents, and the basic power load curve is predicted based on the historical power consumption data of the residents, and the planned charging time is determined according to the predicted basic power load curve, and finally the charging pile charges the vehicle to be charged according to the planned charging time. In this way, the problem of grid overload caused by the sudden increase of grid load can be avoided, thereby ensuring the smooth operation of the grid, reducing the impact on the grid load, and improving the reliability of the grid.

[0045] In a third aspect, the present invention provides an orderly charging control device for a home charging pile, the device comprising:

[0046] An acquisition module is used to acquire a charging type selected by a user, where the charging types include: orderly charging and disorderly charging;

[0047] A prediction module, for predicting a basic power load curve based on a prediction model when the charging type is determined to be orderly charging, wherein the basic power load curve includes an average power load corresponding to different moments in a preset future time predicted based on historical power consumption data of residents and an average power load corresponding to the current moment;

[0048] A charging time determination module, used to determine the charging time of the vehicle to be charged;

[0049] The planned charging time determination module is used to determine the planned charging time of the vehicle to be charged based on the basic power load curve and the charging time, and send the planned charging time to the corresponding charging pile.

[0050] In a fourth aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the charging control method for a home charging pile of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0051] In a fifth aspect, the present invention provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the charging control method for a home charging pile according to the first aspect or any corresponding embodiment thereof.

[0052] It should be noted that the charging control device, electronic device and computer-readable storage medium provided by the present invention for a home charging pile correspond to the above-mentioned charging control method for a home charging pile. Therefore, for the beneficial effects of the charging control device, computer device and computer-readable storage medium for a home charging pile, please refer to the description of the corresponding beneficial effects of the charging control method for a home charging pile above, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 is a flow chart of a charging control method for a home charging pile according to an embodiment of the present invention;

[0055] Figure 2 is a schematic diagram of a process of orderly charging intelligent calculation according to an embodiment of the present invention;

[0056] Figure 3 is a schematic diagram of the overall flow of a charging control method for a home charging pile according to an embodiment of the present invention;

[0057] Figure 4 is a schematic diagram of a process for constructing a prediction model according to an embodiment of the present invention;

[0058] Figure 5 is a structural schematic diagram of a charging control system for a home charging pile according to an embodiment of the present invention;

[0059] Figure 6 is a structural block diagram of a charging control device for a home charging pile according to an embodiment of the present invention;

[0060] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0062] According to an embodiment of the present invention, a charging control method embodiment for a home charging pile is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0063] At present, the number of home charging piles is increasing, and the electricity load of residents is also getting higher and higher, which in turn leads to the problem of grid load and grid overload, affecting the stable operation of the grid.

[0064] In view of this, a charging control method for a home charging pile is provided in this embodiment, which is applicable to terminal devices such as concentrators, servers, and computers. Figure 1 is a flow chart of a charging control method for a home charging pile according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0065] Step S101, obtaining a charging type selected by a user, where the charging types include: ordered charging and disordered charging.

[0066] When users are actually charging, they can interact with information through the human-machine interface of the charging pile, that is, they can first select the charging type through the charging pile interface, such as: orderly charging and disorderly charging. Among them, orderly charging is to charge directly, while disorderly charging is to select a planned charging time after analyzing the grid load. Since the electricity fee is priced in a tiered manner, the electricity fee at night is lower than the electricity fee during the day. Generally speaking, when users charge at night, not only is the pressure on the grid load smaller, but the electricity fee is also relatively low. Therefore, users can directly choose to charge in an orderly manner at night, which can save electricity bills and reduce the grid load.

[0067] Step S102, when it is determined that the charging type is orderly charging, a basic power load curve is predicted based on a prediction model. The basic power load curve includes the average power load corresponding to different moments in a preset future time period predicted based on historical power consumption data of residents and the average power load corresponding to the current moment.

[0068] In some optional implementations, the residents' historical electricity usage data includes: user electricity usage data and charging pile electricity usage data.

[0069] The concentrator can be used to collect and record user electricity consumption data and charging pile electricity consumption data. Since the electricity load of household electricity consumption in residential areas is generally relatively stable, the historical user electricity consumption data and historical charging pile electricity consumption data can be used to build a prediction model to predict the basic electricity load curve. For example, the historical electricity consumption data of residents for the past 7 days can be collected first, and the basic electricity load curve can be calculated through the prediction model. The model calculation can be performed again every 6 hours, and the model parameters can be corrected and optimized to continuously update the basic electricity load curve.

[0070] After the user chooses orderly charging, he can first determine the current time, and then use the historical electricity consumption data before the current time to predict the latest basic electricity load curve. The predicted basic electricity load curve can be the average electricity load corresponding to each minute in the next 24 hours, of course, also including the average electricity load at the current time.

[0071] Step S103, determining the charging time of the vehicle to be charged.

[0072] The vehicle to be charged can be a vehicle that can be used for charging, such as an electric car or battery car. The charging time can be a fixed charging time selected by the user, such as two hours, or it can be a total charging time calculated based on the remaining capacity of the vehicle to be charged and the charging power of the charging pile. In this case, the charging time is actually an estimated time, which is used to assist in determining the planned charging time.

[0073] Step S104, based on the basic power load curve and the charging time, determine the planned charging time of the vehicle to be charged, and send the planned charging time to the corresponding charging pile.

[0074] Specifically, a suitable off-peak period can be selected on the basic power load curve so that the off-peak period meets the charging time of the vehicle to be charged. After the terminal device such as the collector determines the planned charging time, the planned charging time is sent to the corresponding charging pile, and the charging pile is controlled to charge according to the planned charging time.

[0075] In this embodiment, the actual charging type can be determined according to the user's choice, which can relieve the load pressure of the power grid on the one hand, and improve the charging flexibility to meet the needs of different groups of people on the other hand. In the case of orderly charging, the basic power load curve can be predicted by the historical power consumption data of residents, and the planned charging time can be determined according to the predicted basic power load curve. Finally, the charging pile charges the charging vehicle according to the planned charging time, which can avoid the problem of power grid overload caused by the sudden increase of power grid load, thereby ensuring the smooth operation of the power grid, reducing the impact on the power grid load, and improving the reliability of the power grid.

[0076] In some optional implementations, determining the planned charging time of the vehicle to be charged based on the basic power load curve and the charging time includes:

[0077] Taking the current time as the starting point, determine in sequence whether the average power load during the charging time exceeds the preset power load;

[0078] When it is determined that the average power load within the charging time does not exceed the preset power load, the corresponding starting time is determined, and the determination is stopped, and the starting time is used as the planned charging time.

[0079] The following example illustrates that, assuming that the current time is t1 and the charging time is T, it is determined in turn whether the average power load A1 at each time exceeds the preset power load A2 in the time periods [t1, t1+T], [t2, t2+T], [t3, t3+T], etc., where t3>t2>t1. Assuming that it is determined that the average power load at [t2, t2+T] does not exceed the preset power load A2, the corresponding starting time is determined to be t2, and the starting time t2 is used as the planned charging time.

[0080] In this embodiment, the time closest to the current time is selected as the planned charging time under the conditions met, which can effectively shorten the waiting time for the user to charge and improve the charging efficiency.

[0081] In some optional implementations, after sending the planned charging time to the corresponding charging pile, the method further includes:

[0082] Superimpose the charging load of the vehicle to be charged to the corresponding moment on the basic power load curve;

[0083] Determine whether there is an overload point;

[0084] In the case where an overload point exists, the overload point is cut, and a cutting time period is determined, where the cutting time period is a time period that does not include the overload point;

[0085] Determine whether the cut time period satisfies the remaining charging time of the vehicle to be charged;

[0086] If the remaining charging time of the vehicle to be charged is met, the nearest cut time period is selected for charging.

[0087] If the remaining charging time of the vehicle to be charged is not satisfied, at least two maximum cutting time periods are selected for charging.

[0088] After determining the planned charging time and sending it to the charging pile for charging, you can also perform orderly charging intelligent calculations for the charging period. Figure 2 As shown. When charging, the charging load of the charging pile corresponding to the vehicle to be charged can be superimposed on the predicted basic power load curve to find the load curve point at the corresponding time, that is, the point on the basic power load curve at the current charging time. Further, check whether there is a load overload point. If there is no overload point, determine the nearest charging time period for charging, that is, maintain the current charging state; if there is an overload point, search for the cutting time period cut out by the overload point to determine whether these cutting time periods meet the remaining charging time requirements. If they meet the requirements, select the nearest time period for direct charging; if not, select the two largest cutting time periods for charging, and use the starting time of the determined cutting time period as the planned charging time, and send it to the corresponding charging pile again, and finally realize orderly planned charging. It can be superimposed in order, and if it meets the overload requirement, it will be delayed to finally achieve orderly charging.

[0089] In this embodiment, according to the load conditions and charging needs, the charging time periods are reasonably divided, which can effectively avoid overload of the power grid, and ultimately achieve orderly planned charging, thereby improving the operating efficiency and stability of the power grid.

[0090] In some optional implementations, when the charging type is determined to be disorderly charging, the method includes:

[0091] The current time is used as the planned charging time, and the planned charging time is sent to the corresponding charging pile;

[0092] After the planned charging time is sent to the corresponding charging pile, the charging load of the vehicle to be charged is superimposed on the corresponding moment on the basic power load curve.

[0093] For details, please refer to Figure 3 As shown, after the user draws the gun to charge, he selects the charging type. If he chooses to charge in an unordered manner, the planned charging time is equal to the current time, and the load is superimposed on the basic power load curve. If he chooses to charge in an orderly manner, the charging time of the vehicle to be charged is determined, and the electric energy is calculated, that is, the grid load is calculated, so as to perform intelligent calculation for orderly charging, determine the new charging time period, and charge according to the new planned charging time; at the same time, in the case of unordered charging, intelligent calculation for orderly charging can also be performed.

[0094] In this embodiment, the actual charging type can be determined according to the user's selection, which can alleviate the load pressure on the power grid on the one hand, and improve the charging flexibility on the other hand to meet the needs of different groups of people.

[0095] Furthermore, in the case of disorderly charging, the charging load of the vehicle to be charged can be superimposed on the corresponding moment on the basic power load curve, and the above-mentioned orderly charging intelligent calculation method can be used to redetermine the charging period. This process is suitable for situations where the grid pressure is too large under disorderly charging, which is conducive to alleviating the grid overload problem and improving the grid stability.

[0096] In some optional implementations, the prediction model is established by the following steps:

[0097] Obtain residents' historical electricity consumption data, which includes user electricity consumption data and charging pile electricity consumption data;

[0098] The historical electricity consumption data of residents is divided into a sample set and a test set according to the ratio of 8:2;

[0099] Based on the sample set and the test set, the initial model is preset through the sparrow search algorithm-neural network training, where the number of input layers of the sparrow search algorithm-neural network is 7, the number of hidden layers is 15, and the number of output layers is 7; where the maximum number of training times of the hidden layer function of the hidden layer is 500 times, the learning rate is 0.1, the training error corresponding to the discoverer is 0.2, and the training error corresponding to the warning value is 0.6;

[0100] The trained preset initial model is used as the prediction model.

[0101] Specifically, the concentrator can collect user power consumption data and charging pile power consumption data through 485 and CAN channels at regular intervals, such as 5 minutes. If the data is lost or zero, the data will be re-copied.

[0102] The concentrator stores the user electricity consumption data of week K (week K of the week) at time i. The collected data is divided into a sample set and a test set according to a certain ratio, such as 8:2, and then the model is trained through the sparrow search algorithm-neural network (SSA-BP), where the number of layers is 7:15:7. The maximum number of training times for the hidden layer function is 500 times, the learning rate is 0.1, and the training error: the discoverer and warning values ​​are 0.2 and 0.6 respectively.

[0103] In this embodiment, the number of layers and the number of training times are accurately set. By reasonably setting the structure and training parameters of the Shenmiao search algorithm-neural network, the data can be better fitted and the performance and generalization ability of the model can be improved. In addition, limiting the maximum number of training times and setting a suitable learning rate can accelerate the convergence process of the model and effectively improve the training efficiency of the model.

[0104] In some optional implementations, based on the sample set and the test set, a preset initial model is trained by a sparrow search algorithm-neural network, including:

[0105] Initialize the preset parameters in the sparrow search algorithm to obtain the initial sparrow search algorithm;

[0106] Initialize the number of neural network layers, the number of nodes in each layer, and the transfer function of each layer to obtain the initial neural network;

[0107] The historical electricity consumption data of residents in the sample set and the test set are input into the initial sparrow search algorithm, and the positions of the discoverer, followers and warning values ​​are updated iteratively;

[0108] Based on the updated positions of the discoverer, follower, and alert value, the fitness value of the new position of the individual sparrow is updated;

[0109] The fitness value of the new position of the sparrow individual after the final iterative update is input into the initial neural network to obtain the preset initial model.

[0110] The sparrow search algorithm divides the population into discoverers and followers, and randomly selects individuals as sentinels in a certain proportion. Among them, the discoverer has a better fitness value and updates its position according to formula (1).

[0111]

[0112] In formula (1): t is the number of iterations; represents the position with dimension i row and j column, j = 1, 2, ..., d; Q is a random number and obeys the normal distribution; L is a matrix with all elements 1×d; α randomly takes values ​​from (0,1]; ti max is the maximum number of iterations; R2(R2∈[0,1]) is the warning value; V st (Vst ∈[0.5,1]) is a safe value.

[0113] The follower has a low fitness value, and improves its fitness value by following the discoverer, and updates its position according to formula (2).

[0114]

[0115] In formula (2): It is the optimal position of the finder when the iteration reaches t+1 times; is the worst position of the finder when the iteration reaches t+1 times; A is a 1×d matrix with random values ​​of 1 or -1, and A + =A T (AA T ) -1 .

[0116] In the sparrow search algorithm, individuals are randomly selected in a certain proportion to become vigilants, responsible for early warning and anti-predator behavior. The position update formula (3) is as follows:

[0117]

[0118] In formula (3): is the optimal position after t iterations; K is a random value in [-1,1], ε is a non-zero minimum value; β is the system step size, fi i is the fitness of position i, f g and f w are the optimal and worst fitness values ​​respectively.

[0119] Specific reference Figure 4 As shown, the initial model is preset through the sparrow search algorithm-neural network training, including:

[0120] Step 1: First, the concentrator collects the user's power load. In order to reduce the order of magnitude difference between the data, the data set is normalized and then divided into a test set and a training set. The normalization formula (4) is:

[0121]

[0122] In formula (4), X is the normalized data; x is the original data; x min and x max are the minimum and maximum values ​​in the original data.

[0123] Step 2: Initialize the parameters in the sparrow search algorithm, including the maximum number of iterations iter max , population size n, safety value ST, and warning value R2.

[0124] Step 3: Initialize the number of layers of the BP neural network, the number of nodes in each layer, and the transfer function of each layer to form a basic BP neural network model.

[0125] Step 4: Start the loop and use formula (1) to formula (3) to update the positions of the discoverer, follower, and sentinel respectively.

[0126] Step 5: Calculate the fitness value of the new position of the individual sparrow and update the historical optimal fitness.

[0127] Step 6: Execute steps 4 and 5. When the maximum number of iterations is reached, the loop ends and the optimal individual position and fitness value are output to the BP neural network.

[0128] In this embodiment, the sparrow search algorithm combined with the neural network method can improve the optimization effect of the neural network, speed up the parameter search speed, and improve the generalization ability and robustness of the model.

[0129] In some optional implementations, before obtaining the historical electricity consumption data of residents, the method further includes:

[0130] Obtaining residents' electricity consumption data once every first preset time, and updating residents' historical electricity consumption data;

[0131] At every second preset time, an instruction to optimize the prediction model is triggered to optimize the prediction model based on the updated historical electricity consumption data of residents.

[0132] Specifically, the concentrator collects user power consumption data and charging pile power consumption data through 485 and CAN channels at a first preset interval, such as 5 minutes. If the data is lost or zero, the data is copied again. After each collection, it is sent to a server or terminal device to update the historical power consumption data of residents.

[0133] Every second preset time, for example, six hours, the optimization instruction of the prediction model is triggered, and the prediction model is rebuilt to correct and optimize the model parameters, thereby continuously updating the basic power load curve.

[0134] In this embodiment, regularly acquiring residential electricity consumption data and updating the historical residential electricity consumption data used for prediction can maintain the real-time and accuracy of the data, help improve the accuracy of the prediction model, and thus better predict the planned charging time, reduce the impact on the grid load, and improve the reliability of the grid.

[0135] In this embodiment, an orderly charging control system for a home charging pile is also provided. At present, there are some charging pile monitoring systems for achieving orderly charging, but these systems have some defects and shortcomings, mainly in the following two aspects:

[0136] On the one hand, since electric charging is a rapidly developing industry in recent years, charging piles from different manufacturers use different standards and communication protocols. Therefore, there are compatibility issues between charging piles and concentrators, resulting in the inability to collect and analyze each charging pile individually, and the inability to achieve orderly charging of the charging piles.

[0137] On the other hand, most of the current charging pile monitoring systems only monitor and warn about charging, but do not control the orderly charging process, which may lead to overload and waste of power networks.

[0138] In view of this, in this embodiment, an orderly charging control system for a home charging pile is provided, which can be used to execute the above-mentioned charging control method for a home charging pile, such as Figure 5 As shown, the system includes: an electric energy meter, a charging pile, and a concentrator, as follows.

[0139] Electric energy meter, used to measure the user's electricity consumption;

[0140] Charging piles, used to charge vehicles to be charged;

[0141] The concentrator is connected to the electric energy meter and the charging pile for communication, and is used to collect the user's electricity consumption data of the electric energy meter and also to monitor the charging pile electricity consumption data of the charging pile. The concentrator is suitable for executing the charging control method for the home charging pile in any of the above embodiments.

[0142] Specifically, the concentrator can communicate with the energy meter through R485 communication, and can communicate with the charging pile through CAN channel. The CAN channel can adapt to a variety of communication protocols to avoid compatibility issues between the charging pile and the concentrator. The collector can collect and remotely monitor the electricity consumption of users and charging piles, laying a foundation for orderly charging of charging piles.

[0143] In this embodiment, the user power consumption data of the energy meter collected by the concentrator and the charging pile power consumption data of the charging pile can be used as the historical power consumption data of the residents, and the basic power load curve is predicted based on the historical power consumption data of the residents, and the planned charging time is determined according to the predicted basic power load curve, and finally the charging pile charges the vehicle to be charged according to the planned charging time. In this way, the problem of grid overload caused by the sudden increase of grid load can be avoided, thereby ensuring the smooth operation of the grid, reducing the impact on the grid load, and improving the reliability of the grid.

[0144] The further functional description of the charging control method for a home charging pile executed by the above-mentioned controller is the same as that of the above-mentioned corresponding embodiment and will not be repeated here.

[0145] In this embodiment, a charging control device for a home charging pile is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0146] This embodiment provides a charging control device for a home charging pile, such as Figure 6 As shown, including:

[0147] The acquisition module 201 is used to acquire the charging type selected by the user, and the charging type includes: orderly charging and disorderly charging;

[0148] Prediction module 202, for predicting a basic power load curve based on a prediction model when the charging type is determined to be orderly charging, the basic power load curve including average power loads corresponding to different moments in a preset future time and average power loads corresponding to the current moment predicted based on historical power consumption data of residents;

[0149] A charging time determination module 203 is used to determine the charging time of the vehicle to be charged;

[0150] The planned charging time determination module 204 is used to determine the planned charging time of the vehicle to be charged based on the basic power load curve and the charging time, and send the planned charging time to the corresponding charging pile.

[0151] In some optional implementations, the planned charging time determination module 204 includes:

[0152] The first judgment unit is used to judge whether the average power load within the charging time exceeds the preset power load in sequence, starting from the current time;

[0153] The first determination unit is used to determine the corresponding starting time when it is determined that the average power load within the charging time does not exceed the preset power load, and stop the determination, and use the starting time as the planned charging time.

[0154] In some optional embodiments, the device further comprises:

[0155] The re-determination module is used to superimpose the charging load of the vehicle to be charged to the corresponding moment on the basic power load curve; it is also used to determine whether there is an overload point; if there is an overload point, the overload point is cut and the cut time period is determined, and the cut time period is the time period that does not include the overload point; it is also used to determine whether the cut time period meets the remaining charging time of the vehicle to be charged; if it meets the remaining charging time of the vehicle to be charged, the nearest cut time period is selected for charging. If it does not meet the remaining charging time of the vehicle to be charged, at least two maximum cut time periods are selected for charging.

[0156] The unordered module is used to take the current time as the planned charging time and send the planned charging time to the corresponding charging pile; it is also used to superimpose the charging load of the vehicle to be charged to the corresponding time on the basic power load curve after sending the planned charging time to the corresponding charging pile.

[0157] In some optional implementations, the prediction module 202 further includes:

[0158] An acquisition unit is used to acquire residents' historical electricity consumption data, where the residents' historical electricity consumption data includes user electricity consumption data and charging pile electricity consumption data;

[0159] The prediction unit is used to divide the residents' historical electricity consumption data into a sample set and a test set according to a division ratio of 8:2; based on the sample set and the test set, a preset initial model is trained through a sparrow search algorithm-neural network, wherein the number of input layers of the sparrow search algorithm-neural network is 7, the number of hidden layers is 15, and the number of output layers is 7; wherein the maximum number of training times of the hidden layer function of the hidden layer is 500 times, the learning rate is 0.1, the training error corresponding to the discoverer is 0.2, and the training error corresponding to the warning value is 0.6; the trained preset initial model is used as the prediction model.

[0160] The prediction unit is also used to initialize the preset parameters in the sparrow search algorithm to obtain the initial sparrow search algorithm; initialize the number of layers of the neural network, the number of nodes in each layer and the transfer function of each layer to obtain the initial neural network; input the historical electricity consumption data of residents in the sample set and the test set into the initial sparrow search algorithm, iteratively update the positions of the discoverer, followers and warning values; based on the updated positions of the discoverer, followers and warning values, update the fitness value of the new position of the individual sparrow; input the fitness value of the new position of the individual sparrow after the final iterative update into the initial neural network to obtain the preset initial model.

[0161] In some optional embodiments, the device further comprises:

[0162] The updating unit is used to obtain the residents' electricity consumption data once every first preset time and update the residents' historical electricity consumption data; it is also used to trigger the instruction to optimize the prediction model every second preset time to optimize the prediction model based on the updated residents' historical electricity consumption data.

[0163] The charging control device for a home charging pile in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0164] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0165] The embodiment of the present invention also provides a computer device having the above Figure 7 The charging control device for a home charging pile is shown.

[0166] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0167] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0168] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0169] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0170] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0171] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0172] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0173] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A charging control method for a home charging pile, characterized in that: The method comprises: Obtaining a charging type selected by a user, where the charging type includes: ordered charging and disordered charging; When it is determined that the charging type is orderly charging, a basic power load curve is predicted based on a prediction model, wherein the basic power load curve includes average power loads corresponding to different moments in a future preset time predicted based on historical power consumption data of residents and the average power load corresponding to the current moment; Determine the charging time of the vehicle to be charged; Based on the basic power load curve and the charging duration, determine the planned charging time of the vehicle to be charged, and send the planned charging time to the corresponding charging pile; After sending the planned charging time to the corresponding charging pile, the method further includes: Superimposing the charging load of the vehicle to be charged to the corresponding moment on the basic power load curve; Determine whether there is an overload point; In the case where an overload point exists, cutting the overload point and determining a cutting time period, wherein the cutting time period is a time period that does not include the overload point; Determining whether the cut time period satisfies the remaining charging time of the vehicle to be charged; If the remaining charging time of the vehicle to be charged is satisfied, the nearest cutting time period is selected for charging; If the remaining charging time of the vehicle to be charged is not satisfied, at least two maximum cutting time periods are selected for charging.

2. The method according to claim 1, characterized in that The step of determining the planned charging time of the vehicle to be charged based on the basic power load curve and the charging time includes: Taking the current time as the starting point, determining in sequence whether the average power load within the charging time exceeds the preset power load; When it is determined that the average power load within the charging duration does not exceed the preset power load, a corresponding starting time is determined, and the determination is stopped, and the starting time is used as the planned charging time.

3. The method according to claim 1, characterized in that The prediction model is established by following the steps below: Acquire the historical electricity usage data of the residents, wherein the historical electricity usage data of the residents includes user electricity usage data and charging pile electricity usage data; Divide the residents' historical electricity consumption data into a sample set and a test set according to a division ratio of 8:2; Based on the sample set and the test set, a preset initial model is trained by a sparrow search algorithm-neural network, wherein the number of input layers of the sparrow search algorithm-neural network is 7, the number of hidden layers is 15, and the number of output layers is 7; wherein the maximum number of training times of the hidden layer function of the hidden layer is 500 times, the learning rate is 0.1, the training error corresponding to the finder is 0.2, and the training error corresponding to the warning value is 0.6; The trained preset initial model is used as the prediction model.

4. The method according to claim 3, characterized in that The method of presetting an initial model based on the sample set and the test set by using a sparrow search algorithm-neural network training includes: Initialize the preset parameters in the sparrow search algorithm to obtain the initial sparrow search algorithm; Initialize the number of neural network layers, the number of nodes in each layer, and the transfer function of each layer to obtain the initial neural network; Inputting the residents' historical electricity consumption data in the sample set and the test set into the initial sparrow search algorithm, and iteratively updating the positions of the discoverer, the follower, and the warning value; Based on the updated positions of the discoverer, follower, and alert value, the fitness value of the new position of the individual sparrow is updated; The fitness value of the new position of the individual sparrow after the final iterative update is input into the initial neural network to obtain the preset initial model.

5. The method according to claim 3, characterized in that: Before obtaining the residents' historical electricity consumption data, the method further includes: Obtaining residents' electricity consumption data once every first preset time, and updating the residents' historical electricity consumption data; At every second preset time, an instruction to optimize the prediction model is triggered to optimize the prediction model based on the updated historical electricity consumption data of the residents.

6. An orderly charging control system for a home charging pile, characterized in that: The system comprises: Electric energy meter, used to measure the user's electricity consumption; Charging piles, used to charge vehicles to be charged; A concentrator is communicatively connected with the electric energy meter and the charging pile, and is used to collect user electricity consumption data of the electric energy meter and also to monitor the charging pile electricity consumption data of the charging pile. The concentrator is suitable for executing the charging control method for a home charging pile according to any one of claims 1 to 5.

7. An orderly charging control device for a home charging pile, characterized in that: The device comprises: An acquisition module, used to acquire a charging type selected by a user, wherein the charging type includes: orderly charging and disorderly charging; A prediction module, configured to predict a basic power load curve based on a prediction model when determining that the charging type is orderly charging, wherein the basic power load curve includes average power loads corresponding to different moments in a future preset time predicted based on historical power consumption data of residents and the average power load corresponding to the current moment; A charging time determination module, used to determine the charging time of the vehicle to be charged; A planned charging time determination module, used to determine the planned charging time of the vehicle to be charged based on the basic power load curve and the charging time, and send the planned charging time to the corresponding charging pile; A redetermination module is used to superimpose the charging load of the vehicle to be charged to the corresponding moment on the basic power load curve; determine whether there is an overload point; if there is an overload point, cut the overload point and determine the cut time period, the cut time period is a time period that does not include the overload point; determine whether the cut time period meets the remaining charging time of the vehicle to be charged; if it meets the remaining charging time of the vehicle to be charged, select the nearest cut time period for charging; if it does not meet the remaining charging time of the vehicle to be charged, select at least two maximum cut time periods for charging.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the charging control method for a home charging pile according to any one of claims 1 to 5 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the charging control method for a home charging pile according to any one of claims 1 to 5.

Images