Charging pile metering error prediction method and device, electronic equipment and computer readable medium

Abstract

The invention relates to a charging pile metering error prediction method and device, electronic equipment and a computer readable medium, and the method comprises the steps: obtaining historical charging data of a target DC charging pile, and carrying out the preprocessing of the historical charging data; the historical charging data comprises an output voltage, an output current, a battery charge state, a ripple coefficient and an electric energy indication error; based on the preprocessed historical charging data, training an improved LSTM model based on a variable coefficient; and inputting charging data of a target direct current charging pile obtained in real time into the trained LSTM model to obtain a predicted value of an electric energy indication error. According to the invention, the multi-scale prediction model is constructed through the historical data of the charging pile in combination with the data fluctuation characteristics, and the accuracy and adaptability of the measurement error prediction of the DC charging pile are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of deep learning and charging pile metering, and specifically relates to a charging pile metering error prediction method, device, electronic device, and computer-readable medium. Background Art

[0002] With the rapid development of the electric vehicle industry, the accuracy and stability of the metering of charging stations, as key facilities for its energy supply, are becoming more and more important. One of the main tasks of charging stations is to provide AC or DC power to electric vehicles. The metering system is the core component of the charging station, which directly affects the charging fees paid by users and the energy replenishment efficiency of electric vehicles.

[0003] In actual operation, errors may occur in the metering of charging stations. These errors may be caused by a variety of factors, such as equipment aging, sensor failure, interference from environmental factors, and errors in software algorithms. These factors may cause the metering results to not match the actual charging amount, which in turn damages the interests of users and may cause disputes.

[0004] In order to ensure the accuracy of measurement, it is necessary to conduct regular calibration of charging stations. Traditional calibration methods require the charging station to be placed offline, which not only hinders its normal operation, but may also cause economic losses. Traditional offline calibration technology no longer meets modern needs. The use of artificial intelligence technology for online error prediction can accurately predict the errors that may occur in the metering process of charging stations, and realize early warning and prompts for abnormal charging stations, thereby improving the accuracy and efficiency of measurement and protecting user rights. However, since the metering error of charging piles is affected by many factors, the prediction is usually complicated by the change of error sequence caused by non-stationary fluctuations. Therefore, it has become a current technical challenge to study how to use intelligent algorithms to more accurately capture this fluctuation for error prediction, thereby improving the accuracy of prediction. Summary of the invention

[0005] In order to improve the prediction accuracy and adaptability of the metering error of the charging station, a first aspect of the present invention provides a charging pile metering error prediction method, comprising: obtaining historical charging data of a target DC charging pile, and preprocessing the historical charging data; the historical charging data includes output voltage, output current, battery state of charge, ripple factor and electric energy indication error; based on the preprocessed historical charging data, training an LSTM model improved based on the coefficient of variation; inputting the charging data of the target DC charging pile acquired in real time into the trained LSTM model to obtain a predicted value of the electric energy indication error.

[0006] In some embodiments of the present invention, the LSTM model includes: multiple LSTM networks, used to extract time series features of multiple scales from preprocessed historical charging data; a coefficient of variation calculation module, used to calculate the coefficient of variation of each LSTM network based on the preprocessed historical charging data, and dynamically adjust the output gate of each LSTM network through the coefficient of variation; a fully connected layer, used to fuse time series features of multiple scales, and predict the electric energy indication error based on the fused time series features.

[0007] Furthermore, the calculation of the coefficient of variation of each LSTM network based on the preprocessed historical charging data includes: extracting multiple electric energy indication error sequences of each LSTM network from the preprocessed historical charging data; and calculating the coefficient of variation of each LSTM network based on the multiple electric energy indication error sequences.

[0008] Furthermore, the coefficient of variation of each LSTM network is calculated based on multiple electric energy indication error sequences: the mean and standard deviation of the multiple electric energy indication error sequences are calculated; and the coefficient of variation is calculated based on the mean and standard value.

[0009] Furthermore, dynamically adjusting the output gate of each LSTM network through the coefficient of variation includes: dividing the activation value of the output gate into at least two parts; determining the gating weight matrix of each part respectively through the coefficient of variation; and calculating the activation value of the output gate based on the gating weight matrix of each part and the Logistic activation function.

[0010] Furthermore, the activation value of the output gate is calculated based on the gate weight matrix and the Logistic activation function of each part as follows:

[0011] .

[0012] in represents the activation value of the output gate, and Respectively represent the input data as The corresponding coefficient of variation the transformed dynamic gating weight matrix; Indicates the hidden state value at the previous moment; and Through and Generate the first part The weight matrix corresponding to the value and the second part are generated The weight matrix corresponding to the value; and Through and Generate the first part The bias term corresponding to the value and the second part of the generation The offset term corresponding to the value.

[0013] According to a second aspect of the present invention, a charging pile metering error prediction device is provided, comprising: an acquisition module, used to acquire historical charging data of a target DC charging pile, and preprocess the historical charging data; the historical charging data includes output voltage, output current, battery state of charge, ripple factor and electric energy indication error; a training module, used to train an LSTM model improved based on the coefficient of variation based on the preprocessed historical charging data; and a prediction module, used to input the charging data of the target DC charging pile acquired in real time into the trained LSTM model to obtain a predicted value of the electric energy indication error.

[0014] In a third aspect of the present invention, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the charging pile metering error prediction method provided in the first aspect of the present invention.

[0015] A fourth aspect of the present invention provides a computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the charging pile metering error prediction method provided in the first aspect of the present invention is implemented.

[0016] The beneficial effects of the present invention are:

[0017] The present invention relates to a charging pile metering error prediction method, device, electronic device, and computer-readable medium. The method comprises: obtaining historical charging data of a target DC charging pile, and preprocessing the historical charging data; the historical charging data comprises output voltage, output current, battery state of charge, ripple factor, and electric energy indication error; based on the preprocessed historical charging data, training an improved LSTM model based on a coefficient of variation; inputting the charging data of the target DC charging pile obtained in real time into the trained LSTM model to obtain a predicted value of the electric energy indication error.

[0018] It can be seen that the present invention constructs a multi-scale LSTM model for historical charging data, and improves the internal structure of the LSTM network by reflecting the coefficient of variation of the error sequence fluctuation degree, so that the model can utilize the non-stationary characteristics of the sequence to obtain more accurate error prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a basic flow chart of a charging pile metering error prediction method in some embodiments of the present invention;

[0020] Figure 2It is a schematic diagram of the structure of the LSTM model in some embodiments of the present invention;

[0021] Figure 3 Improved LSTM network structure diagram for coefficient of variation in some embodiments of the present invention;

[0022] Figure 4 It is a basic flow chart of a charging pile metering error prediction method in some embodiments of the present invention;

[0023] Figure 5 It is a schematic diagram of the structure of an electronic device in some embodiments of the present invention. DETAILED DESCRIPTION

[0024] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0025] refer to Figure 1 and Figure 2 In a first aspect of the present invention, a charging pile metering error prediction method is provided, comprising: S100. acquiring historical charging data of a target DC charging pile, and preprocessing the historical charging data; the historical charging data comprises output voltage, output current, battery state of charge, ripple factor and electric energy indication error; S200. training an LSTM model improved based on the coefficient of variation based on the preprocessed historical charging data; S300. inputting the charging data of the target DC charging pile acquired in real time into the trained LSTM model to obtain a predicted value of the electric energy indication error.

[0026] In step S100 of some embodiments of the present invention, historical charging data of a target DC charging pile is obtained, and the historical charging data is preprocessed; the historical charging data includes output voltage, output current, battery state of charge, ripple factor, and electric energy indication error;

[0027] Specifically, historical charging data of a sample DC charging pile is collected, wherein the historical charging data includes the output voltage U, current I, battery state of charge S, ripple factor K and electric energy indication error E of the charging pile, and the obtained data is preprocessed.

[0028] Collect secondary voltage data U, current data I, battery state of charge S, ripple factor K, and electric energy indication error E. Since the above collected data are original collected data, there may be problems such as missing data and large order of magnitude differences that affect the quality of model training. Therefore, before entering the model, all types of data obtained are cleaned of outliers and standardized.

[0029] refer to Figure 2In step S200 or S300 of some embodiments of the present invention, the LSTM model includes: multiple LSTM networks, used to extract time series features of multiple scales from the preprocessed historical charging data; a coefficient of variation calculation module, used to calculate the coefficient of variation of each LSTM network according to the preprocessed historical charging data, and dynamically adjust the output gate of each LSTM network according to the coefficient of variation; a fully connected layer, used to fuse the time series features of multiple scales, and predict the electric energy indication error according to the fused time series features.

[0030] Specifically, after the input data enters the multi-scale convolution layer, it will be subjected to multi-scale feature extraction through 1×1, 3×3 and 5×5 convolutions respectively. At this time, the 1×1 convolution result is recorded as the first-scale temporal feature, the 3×3 convolution result is recorded as the second-scale temporal feature, and the 5×5 convolution result is recorded as the third-scale temporal feature; the first-scale temporal feature obtained by the 1×1 convolution is directly sent to the LSTM as the input feature, and on the other hand, it will be upsampled and superimposed and fused with the second-scale temporal feature obtained by the 3×3 convolution, and then the fused result is sent to the LSTM as the input feature. Similarly, the second-scale temporal feature obtained by the 3×3 convolution is input to the LSTM after being fused with the first-scale temporal feature after upsampling, and on the other hand, it will be upsampled and superimposed and fused with the third-scale temporal feature obtained by the 5×5 convolution, and then the fused result is also sent to the LSTM.

[0031] It can be understood that the above describes the process of constructing an error prediction model combining the coefficient of variation and multi-scale LSTM. The model provided by the present invention designs a multi-scale LSTM network for extracting time series features of different granularities of input data, and at the same time combines the coefficient of variation that can reflect the degree of fluctuation of the error sequence to improve the internal LSTM network, so that the model can utilize the non-stationary characteristics of the sequence to obtain more accurate error prediction results.

[0032] Furthermore, the calculation of the coefficient of variation of each LSTM network based on the preprocessed historical charging data includes: extracting multiple electric energy indication error sequences of each LSTM network from the preprocessed historical charging data; and calculating the coefficient of variation of each LSTM network based on the multiple electric energy indication error sequences.

[0033] Specifically, if there is an electric energy indication error sequence in the current input data , is the error value of the electric energy indication at time t. The coefficient of variation is calculated through this data. The smaller the coefficient of variation, the lower the volatility of the data. Conversely, the larger the coefficient of variation, the higher the volatility of the data. The specific calculation process is as follows:

[0034] First calculate the mean and standard deviation of the sequence data:

[0035] Mean: .

[0036] Standard Deviation: .

[0037] In the formula, is the sequence mean, T is the length of the sequence at time t, It is the electric energy indication error value at time t. is the series standard deviation.

[0038] Calculate the corresponding coefficient of variation through the mean and standard deviation of the sequence at this time .

[0039] .

[0040] refer to Figure 3 Furthermore, the coefficient of variation of each LSTM network is calculated based on multiple electric energy indication error sequences: the mean and standard deviation of multiple electric energy indication error sequences are calculated; and the coefficient of variation is calculated based on the mean and standard value.

[0041] Furthermore, dynamically adjusting the output gate of each LSTM network through the coefficient of variation includes: dividing the activation value of the output gate into at least two parts; determining the gating weight matrix of each part respectively through the coefficient of variation; and calculating the activation value of the output gate based on the gating weight matrix of each part and the Logistic activation function.

[0042] Specifically, Figure 3 The improved LSTM network structure provided by the present invention is shown in FIG. The input gate, forget gate and memory unit are the same as those of the traditional LSTM network. The difference is that the coefficient of variation is introduced to set the dynamic output gate. If there is a feature sequence X extracted by multi-scale convolution at time t, the sequence value When input into the network, the forget gate, input gate, output gate and memory unit will be updated and calculated respectively. The specific process is as follows:

[0043] .

[0044] .

[0045] .

[0046] .

[0047] The calculation of forget gate, input gate and memory unit update is the same as that of traditional LSTM. and the hidden state value at the previous moment Calculated. As shown in the above formula, is the calculation result of the forget gate. The activation value calculated for the input gate, is a candidate memory unit. is the Logistic activation function, is the hyperbolic tangent activation function. , , Calculate , , The weight matrix at that time. , , Calculation , , The bias term when . is the memory unit updated at the current moment, It is the memory unit of the previous moment. is element-wise multiplication.

[0048] The calculation of the output gate is to combine the coefficient of variation with the activation value Dynamic gating adjustment is performed. Specifically, it can be explained as: the activation value of the output gate Split into two parts, and each part is a weight matrix of the coefficient of variation processed by the Logistic activation function and Dynamic regulation can be performed. The formula can be expressed as:

[0049] .

[0050] In the above formula, Calculate the activation value of the improved output gate. and The input data is The corresponding coefficient of variation The transformed dynamic gating weight matrix. The hidden state value at the last moment. and Through and Generate the first part The weight matrix corresponding to the value and the second part are generated The weight matrix corresponding to the value. and Through and Generate the first part The bias term corresponding to the value and the second part of the generation The offset term corresponding to the value.

[0051] Then the hidden state output of the improved LSTM is can be and Calculated, expressed as:

[0052] .

[0053] Since the three time series features of different scales will pass through three improved LSTMs respectively, three hidden state results will be output. These three hidden state results will then be sent to the fully connected layer, and the three results will be integrated through the softmax function to output the final error prediction result.

[0054] In step S300 of some embodiments of the present invention, the charging data of the target DC charging pile acquired in real time is input into the trained LSTM model to obtain a predicted value of the electric energy indication error.

[0055] Specifically, the charging pile electric energy indication error prediction model is trained by collecting historical data. After the training is completed, the electric energy indication error of the charging pile at future moments is accurately predicted using the trained model to obtain the prediction result of the charging electric energy indication error.

[0056] Example 2

[0057] refer to Figure 4 In a second aspect of the present invention, a charging pile metering error prediction device 1 is provided, comprising: an acquisition module 11, for acquiring historical charging data of a target DC charging pile, and preprocessing the historical charging data; the historical charging data comprises output voltage, output current, battery state of charge, ripple factor and electric energy indication error; a training module 12, for training an LSTM model improved based on the coefficient of variation based on the preprocessed historical charging data; a prediction module 13, for inputting the charging data of the target DC charging pile acquired in real time into the trained LSTM model to obtain a predicted value of the electric energy indication error.

[0058] Furthermore, the acquisition module 11 includes: a preprocessing unit, which is used to perform outlier cleaning and standardization processing on the historical charging data.

[0059] Example 3

[0060] refer to Figure 5According to a third aspect of the present invention, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the charging pile metering error prediction method according to the first aspect of the present invention.

[0061] The electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 are also stored in the random access memory 503. The processing device 501, the read-only memory 502, and the random access memory 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0062] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 5 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0063] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device 509, or installed from a storage device 508, or installed from a read-only memory 502. When the computer program is executed by the processing device 501, the above functions defined in the method of the embodiment of the present disclosure are executed. It should be noted that the computer-readable medium described in the embodiment of the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In an embodiment of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus, or a device. In an embodiment of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus, or a device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wire, optical cable, RF (radio frequency), etc., or any suitable combination of the foregoing.

[0064] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device. The computer-readable medium carries one or more computer programs. When the one or more programs are executed by the electronic device, the electronic device:

[0065] Computer program code for performing the operations of embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, Python, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0066] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0067] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A charging pile metering error prediction method, characterized in that: include: Acquire historical charging data of a target DC charging pile, and preprocess the historical charging data; The historical charging data includes output voltage, output current, battery charge state, ripple factor and electric energy indication error; Based on the preprocessed historical charging data, train the LSTM model based on the improved coefficient of variation; The charging data of the target DC charging pile acquired in real time is input into the trained LSTM model to obtain the predicted value of the electric energy indication error.

2. The charging pile measurement error prediction method according to claim 1, characterized in that: The LSTM model includes: Multiple LSTM networks are used to extract time series features of multiple scales from the preprocessed historical charging data; A coefficient of variation calculation module, used to calculate the coefficient of variation of each LSTM network based on the preprocessed historical charging data, and dynamically adjust the output gate of each LSTM network according to the coefficient of variation; The fully connected layer is used to fuse time series features of multiple scales and predict the electric energy indication error based on the fused time series features.

3. The charging pile measurement error prediction method according to claim 2, characterized in that: The calculation of the coefficient of variation of each LSTM network based on the preprocessed historical charging data includes: Extract multiple electric energy indication error sequences of each LSTM network from the preprocessed historical charging data; Based on multiple electric energy indication error sequences, the coefficient of variation of each LSTM network is calculated.

4. The charging pile metering error prediction method according to claim 3 is characterized in that: The calculation of the coefficient of variation of each LSTM network based on multiple electric energy indication error sequences includes: Calculate the mean and standard deviation of multiple electric energy indication error sequences; Based on the mean and standard values, the coefficient of variation was calculated.

5. The charging pile measurement error prediction method according to claim 2, characterized in that: Dynamically adjusting the output gate of each LSTM network by the coefficient of variation includes: Split the output gate activation into at least two parts; The gating weight matrix of each part is determined separately by the coefficient of variation; Based on the gating weight matrix and Logistic activation function of each part, the activation value of the output gate is calculated.

6. The charging pile measurement error prediction method according to claim 5, characterized in that: Based on the gated weight matrix and Logistic activation function of each part, the activation value of the output gate is calculated as: ， in represents the activation value of the output gate, and Respectively represent the input data as The corresponding coefficient of variation the transformed dynamic gating weight matrix; Indicates the hidden state value at the previous moment; and Through and Generate the first part The weight matrix corresponding to the value and the second part are generated The weight matrix corresponding to the value; and Through and Generate the first part The bias term corresponding to the value and the second part of the generation The offset term corresponding to the value.

7. A charging pile metering error prediction device, characterized in that: include: An acquisition module, used to acquire historical charging data of a target DC charging pile and pre-process the historical charging data; The historical charging data includes output voltage, output current, battery charge state, ripple factor and electric energy indication error; The training module is used to train the LSTM model based on the improved coefficient of variation based on the preprocessed historical charging data; The prediction module is used to input the charging data of the target DC charging pile acquired in real time into the trained LSTM model to obtain the predicted value of the electric energy indication error.

8. The charging pile measurement error prediction device according to claim 7, characterized in that: The acquisition module comprises: The preprocessing unit is used to perform outlier cleaning and standardization processing on the historical charging data.

9. An electronic device, comprising: one or more processors; A storage device, used to store one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the charging pile metering error prediction method according to any one of claims 1 to 6.

10. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the charging pile metering error prediction method according to any one of claims 1 to 6 is implemented.

Images