Mass charging pile remote verification method, system and device based on LSTM-GAN and medium

Abstract

The invention relates to the technical field of charging billing supervision, and particularly discloses an LSTM-GAN-based mass charging pile remote verification method, system and device and a medium, and the method comprises the steps: selecting a part of charging piles, and adding new electric energy meters; the charging pile electrical data detected by the original electric energy meter and the new electric energy meter are uploaded to the database of the cloud platform through the data acquisition card; calculating and obtaining the metering result deviation of the new electric energy meter and the original electric energy meter, marking the charging pile with the metering result deviation within an allowable error range as qualified, and otherwise, marking the charging pile as unqualified; the marked data are input into an LSTM-GAN model for training, and a verification model is obtained; and inputting the electrical data of the charging pile to be calibrated into the trained calibration model, and judging whether the metering accuracy of the charging pile is qualified or not by comparing the deviation. According to the LSTM-GAN-based mass charging pile remote verification method, system and equipment and the medium provided by the invention, the verification efficiency can be improved, the cost can be reduced, and remote verification of mass charging piles can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of charging billing supervision, and in particular to a method, system, device and medium for remote verification of massive charging piles based on LSTM-GAN. Background Art

[0003] The transaction settlement amount of public charging piles is calculated by the charging pile operator cloud platform based on the order data uploaded by the charging pile (mainly the power consumption of this charging measured by the built-in power meter) and the time-of-use electricity price of the current period. This requires that the measurement accuracy of the power meter inside the charging pile must meet the verification standards. If the measurement result deviates too much, it will cause economic losses to users or power grid companies. However, public charging piles belong to the assets of operators, who build and operate them. Although relevant laws and standards require that the power meter inside the charging pile be verified for measurement accuracy before leaving the factory to ensure accurate measurement, due to the problems of charging piles belonging to operators, large number of construction, wide distribution of workspaces, and complex operating environment, it is difficult for the government and power grid companies to verify each charging pile to achieve closed-loop supervision.

[0004] There are two main methods for current charging pile calibration: one is based on a physical standard calibration device, and the other is based on a cloud-based remote calibration model.

[0005] The former is designed according to the standards of standard calibration devices such as JJG 1193-2023 "Verification Procedure for Electric Vehicle AC Charging Pile Calibrators", and uses the standard calibration device with a measurement accuracy higher than the measurement accuracy specified for the charging pile as the measurement standard value transfer medium. The data collected by the device is used as the value reproduced by the measurement standard as the actual value, and is divided into two equipment solutions: built-in and mobile. The built-in standard calibration device is deployed inside the charging pile to collect the power, current, voltage and other measurement data of the charging pile in real time during the charging process. When charging, the charging data of the qualified pile is virtualized based on the monitoring data of the electric vehicle BMS system and the error estimation AI model of the qualified charging pile, and compared with the measurement data of the uncalibrated charging pile, so as to realize the value transfer and remote calibration. However, this method requires the electric vehicle to be used as the value transfer medium. The measurement data collected by the original electric energy meter of the charging pile is compared to realize the calibration of the measurement accuracy of the original electric energy meter of the charging pile. Mobile standard calibration devices are usually carried by electric vehicles to monitor the power, current, voltage and other metering data during the charging process of electric vehicles, and compare them with the metering data of the electric energy meter inside the charging pile to verify the metering accuracy of the original electric energy meter of the charging pile. The on-site calibration method based on physical standard calibration devices has high accuracy, but due to the massive number of charging piles and their discrete distribution, the calibration efficiency is low and the cost is high, so it is only suitable for the calibration of a small number of charging piles.

[0006] The latter usually uses electric vehicles as a medium for transferring measurement values. The electric vehicles are first charged on qualified charging piles, and the battery SOC data, charging voltage, current, time, temperature and other data monitored by the electric vehicle's BMS system are collected. The AI ​​model is trained based on the error between the data and the above data collected by qualified charging piles. Although the calibration efficiency of electric vehicles on uncalibrated charging piles is improved, the manpower and material costs are still high, making it difficult to achieve remote calibration of massive charging piles.

[0007] In summary, the existing charging pile calibration methods have certain limitations in terms of calibration efficiency, cost and coverage, and cannot meet the needs of remote calibration of massive charging piles. Therefore, it is necessary to study a new charging pile remote calibration method to improve calibration efficiency, reduce costs, and realize remote calibration of massive charging piles. This invention is aimed at this problem and proposes a remote calibration method for massive charging piles based on LSTM-GAN.

[0008] The above information is presented as background information only to assist with understanding the present disclosure and no determination or admission is made as to whether any of the above may be used as prior art with respect to the present disclosure. Summary of the invention

[0009] The present invention provides a method, system, device and medium for remote calibration of massive charging piles based on LSTM-GAN, which can improve calibration efficiency, reduce costs, and realize remote calibration of massive charging piles.

[0010] To achieve the above objectives, in a first aspect, the present invention provides a remote verification method for a large number of charging piles based on LSTM-GAN, comprising:

[0011] Data collection: select some charging piles for transformation, install new energy meters inside the selected charging piles, and upload the electrical data of the charging piles detected by the original energy meters and the new energy meters to the database of the cloud platform through the data acquisition card;

[0012] Data labeling: Calculate the power consumed during the charging process based on the electrical data, and calculate the measurement result deviation between the new energy meter and the original energy meter. Label the charging piles whose measurement result deviation is within the allowable error range as qualified, otherwise label them as unqualified.

[0013] Model construction and training: input the labeled data into the LSTM-GAN model for training to obtain the verification model;

[0014] Remote calibration: input the electrical data of the charging pile to be calibrated into the trained calibration model, and judge whether the measurement accuracy of the charging pile is qualified by comparing the deviation.

[0015] Optionally, the data labeling includes calculating the power consumed during the charging process according to the electrical data, calculating and obtaining the measurement result deviation between the new electric energy meter and the original electric energy meter, and labeling the charging piles whose measurement result deviation is within the allowable error range as qualified, and labeling the charging piles as unqualified.

[0016] Data cleaning: unify the format and align the time scale of the electrical data collected by the new and existing electricity meters.

[0017] Optionally, the data cleaning, after unifying the formats and aligning the time scales of the electrical data collected by the new electric energy meter and the original electric energy meter, further includes:

[0018] Data augmentation,noise injection and time scaling of electrical data.

[0019] Optionally, the electrical data includes a power curve W of the charging pile during each charging process, and the instantaneous power wi at each time mark ti is obtained from the power curve W;

[0020] The method of calculating the power consumed during the charging process according to the electrical data, and obtaining the measurement result deviation between the new electric energy meter and the original electric energy meter, and marking the charging piles whose measurement result deviation is within the allowable error range as qualified, and marking the charging piles whose measurement result deviation is within the allowable error range as unqualified, includes:

[0021] According to the power curve W, the power consumed in the charging process is calculated as Δw=w1-wT, where w1 is the power at the start of charging and wT is the power at the end of charging;

[0022] According to the power consumed in the charging process measured by the new power meter and the original power meter, the measurement result deviation δ= 00%, of which, The power consumed during the charging process measured by the new energy meter. The electricity consumed during the charging process measured by the original electricity meter.

[0023] Optionally, the method of calculating the power consumed in the charging process according to the electrical data, and calculating and obtaining the measurement result deviation between the new electric energy meter and the original electric energy meter, marking the charging piles whose measurement result deviation is within the allowable error range as qualified, and marking otherwise as unqualified, further includes:

[0024] The charging piles with δ within the allowable error range are marked as qualified, and the power curve of the original electric energy meter of the qualified charging pile is used as a positive sample;

[0025] The charging piles whose δ is outside the allowable error range are marked as unqualified, and the power curve corresponding to the original power meter of the unqualified charging pile is used as a negative sample.

[0026] Optionally, the remote verification inputs the electrical data of the charging pile to be verified into a trained verification model, and determines whether the measurement accuracy of the charging pile is qualified by comparing the deviation, including:

[0027] Input the electrical data of the charging pile to be tested into the trained test model;

[0028] The verification model compares the received charge curve with the simulated data.

[0029] Optionally, the remote verification includes inputting the electrical data of the charging pile to be verified into a trained verification model, and judging whether the measurement accuracy of the charging pile is qualified by comparing the deviation, and further includes:

[0030] If the deviation between the two is within the preset error range, the measurement accuracy of the charging pile is considered qualified;

[0031] If the deviation between the two is outside the preset error range, the metering accuracy of the charging pile is considered unqualified, and an alarm is issued or maintenance personnel are notified.

[0032] In a second aspect, a remote verification system is provided, which is used to execute any of the LSTM-GAN-based remote verification methods for massive charging piles, including:

[0033] The data acquisition module is used to select some charging piles for transformation, install new electric energy meters inside the selected charging piles, and send the electrical data of the charging piles detected by the original electric energy meters and the new electric energy meters to the database of the cloud platform through the data acquisition card;

[0034] The data labeling module is used to calculate the power consumed during the charging process based on the electrical data, and calculate the measurement result deviation between the new electric energy meter and the original electric energy meter. The charging piles with measurement result deviation within the allowable error range are marked as qualified, otherwise they are marked as unqualified;

[0035] The model building and training module is used to input the labeled data into the LSTM-GAN model for training to obtain the verification model;

[0036] The remote calibration module is used to input the electrical data of the charging pile to be calibrated into the trained calibration model, and judge whether the metering accuracy of the charging pile is qualified by comparing the deviation.

[0037] In a third aspect, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any of the LSTM-GAN-based remote calibration methods for massive charging piles is implemented.

[0038] In a fourth aspect, a storage medium comprising computer executable instructions is provided, and the computer executable instructions are executed by a computer processor to implement any of the LSTM-GAN-based remote calibration methods for massive charging piles.

[0039] Compared with the prior art, the present invention has the following beneficial effects: providing a method, system, device and medium for remote verification of massive charging piles based on LSTM-GAN, which has the following advantages:

[0040] ① Massive calibration capability: The method provided by the present invention can remotely calibrate a large number of charging piles at the same time, greatly improving the efficiency and coverage of the calibration work.

[0041] ② Improved accuracy: By using a high-precision new electricity meter as a reference, this method can accurately evaluate the accuracy of the charging pile's power statistics and ensure the reliability of the calibration results.

[0042] ③ High degree of automation: This method uses the LSTM-GAN model to automatically perform data processing and model training, reducing manual intervention and improving the automation level of the verification process.

[0043] ④Data processing efficiency: Through steps such as data cleaning and data enhancement, this method can effectively process and optimize data, thereby improving the quality of data and the training effect of the model.

[0044] ⑤ Real-time monitoring and response: This method supports real-time monitoring of charging piles. Once a measurement accuracy problem is found, it can respond quickly and take measures to ensure the normal operation of the charging piles.

[0045] ⑥ Cost-effectiveness: Compared with the traditional on-site calibration method, the method of the present invention greatly reduces the calibration cost, including manpower, material and time costs.

[0046] ⑦Easy to expand and upgrade: The remote calibration system is based on software and hardware, which is easy to maintain and upgrade through software updates to adapt to the continuous development of charging pile technology and changes in calibration standards.

[0047] ⑧ Potential for large-scale application: This method is particularly suitable for the calibration of massive charging piles. It has good potential for large-scale application and helps to improve the operational management efficiency of the charging pile network.

[0048] The present invention has other features and advantages, which will be apparent from or will be described in detail in the accompanying drawings and the following detailed description incorporated herein, which together serve to explain the specific principles of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 It is a flow chart of a remote verification method for massive charging piles based on LSTM-GAN provided in Example 1 of the present invention;

[0051] Figure 2 is a structural block diagram of a remote verification system provided by Embodiment 2 of the present invention;

[0052] Figure 3 It is a structural diagram of a computer device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0053] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects that can be achieved, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0054] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.

[0055] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.

[0056] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.

[0057] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.

[0058] Without further limitations, in this application, the words "include", "comprises", "has" or other similar expressions used in the sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.

[0059] Similar to the understanding in the Examination Guidelines, in this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.

[0060] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0061] Unless otherwise expressly specified or limited, in the description of the embodiments of the present application, the terms such as "install", "connect", "connect", "fix", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For technicians in the technical field to which the present application belongs, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0062] Example 1

[0063] Please refer to the attached Figure 1 , is a flow chart of a method for remote verification of a large number of charging piles based on LSTM-GAN provided by an embodiment of the present invention. The method is applicable to the scenario of verifying the accuracy of the electricity statistics of the charging piles. The method is executed by a remote verification system, and the remote verification system can be implemented by software and / or hardware. The method specifically includes the following steps:

[0064] S10: Data Collection

[0065] S101: Select some charging piles for transformation, and install new electric energy meters inside the selected charging piles; wherein the measurement accuracy level of the new electric energy meters is higher than the measurement accuracy level of the original electric energy meters;

[0066] S102: sending the electrical data of the charging pile detected by the original electric energy meter and the new electric energy meter to the database of the cloud platform through the data acquisition card;

[0067] S20: Data cleaning

[0068] The electrical data collected by the new electricity meter and the original electricity meter are unified in format and time-stamp aligned.

[0069] The subsequent two sets of data need to be subtracted, so the time scales must be aligned.

[0070] In addition, operations such as outlier processing and missing value completion can also be performed.

[0071] S30: Data Enhancement

[0072] Perform noise injection and time scaling on electrical data.

[0073] Noise injection usually refers to adding random perturbations or errors to a dataset to simulate real-world uncertainty or increase data diversity. This can increase the sample size.

[0074] That is, by adding noise to the original data, more "virtual" samples can be created, thereby expanding the size of the dataset. This is particularly useful for machine learning model training, because a larger sample size can improve the generalization ability of the model.

[0075] In the context of electric vehicle charging, suppose there is a set of data recording the charging time and remaining power of different electric vehicles. By adding noise to this data (for example, adding or subtracting some random decimal values ​​from the charging time), more charging records can be generated.

[0076] The purpose of doing this is to enable the training model to better adapt to various situations in the actual environment, because the charging data in reality may be affected by many factors, such as ambient temperature, charging pile status, etc., which can be regarded as noise.

[0077] Time scaling refers to adjusting the time series in a dataset so that they are stretched or compressed on the time axis. The purpose here is to simulate the variation of charging time. Specifically, due to the different remaining power of electric vehicles, the required charging time will also vary. Time scaling can be used to simulate this variation.

[0078] In the context of electric vehicle charging, if a vehicle has a lower remaining charge, it may take longer to charge. With time scaling, the charging time data can be adjusted to reflect the charging time under different remaining charge conditions.

[0079] For example, if an electric car's charging record shows that it took 2 hours to charge and its remaining power is 20%, time scaling can be used to simulate the charging time if the remaining power is 10%, and the charging time may be adjusted to 4 hours.

[0080] In general, noise injection and time scaling are data processing techniques used to enhance the representativeness of a dataset and make it closer to the complexity of the real world, thereby helping to train more accurate and robust models to predict or analyze EV charging behavior.

[0081] S40: Data Annotation

[0082] According to the value transfer process, the electrical data of the charging pile collected by the new electric energy meter with higher measurement accuracy is used as the actual value, and the electrical data of the charging pile collected by the original electric energy meter with lower measurement accuracy is used as the measured value for verification;

[0083] Specifically, the electrical data includes a power curve W of the charging pile during each charging process, from which the instantaneous power wi at each time mark ti can be obtained.

[0084] According to the power curve W, the power consumed in the charging process is calculated as Δw=w1-wT, where w1 is the power at the start of charging and wT is the power at the end of charging;

[0085] According to the power consumed in the charging process measured by the new power meter and the original power meter, the measurement result deviation δ= 00%, of which, The power consumed during the charging process measured by the new energy meter. The amount of electricity consumed during the charging process measured by the original electric energy meter;

[0086] The charging piles with δ within the allowable error range (for example, within ±1%) are marked as qualified, and the power curve of the original electric energy meter of the qualified charging pile is used as a positive sample; the charging piles with δ outside the allowable error range are marked as unqualified, and the power curve corresponding to the original electric energy meter of the unqualified charging pile is used as a negative sample;

[0087] S50: Model construction and training

[0088] The above positive samples and negative samples are input into the LSTM-GAN model for training, and a verification model is obtained for judging whether the charging pile is a qualified charging pile according to the power curve corresponding to the original electric energy meter of the charging pile;

[0089] It should be noted that LSTM-GAN (Long Short-Term Memory Generative Adversarial Network) is a deep learning model that combines long short-term memory network (LSTM) and generative adversarial network (GAN).

[0090] S60: Remote Verification

[0091] Input the electrical data of the charging pile to be tested (provided by the original electric energy meter) into the trained verification model;

[0092] The verification model compares the received charge curve with the simulated data:

[0093] If the deviation between the two is within the preset error range, the measurement accuracy of the charging pile is considered qualified;

[0094] If the deviation between the two is outside the preset error range, the metering accuracy of the charging pile is considered to be unqualified, and an alarm can be issued or maintenance personnel can be notified.

[0095] In summary, the LSTM-GAN-based remote verification method for massive charging piles provided in this embodiment has the following advantages:

[0096] ① Massive calibration capability: The method provided by the present invention can remotely calibrate a large number of charging piles at the same time, greatly improving the efficiency and coverage of the calibration work.

[0097] ② Improved accuracy: By using a high-precision new electricity meter as a reference, this method can accurately evaluate the accuracy of the charging pile's power statistics and ensure the reliability of the calibration results.

[0098] ③ High degree of automation: This method uses the LSTM-GAN model to automatically perform data processing and model training, reducing manual intervention and improving the automation level of the verification process.

[0099] ④Data processing efficiency: Through steps such as data cleaning and data enhancement, this method can effectively process and optimize data, thereby improving the quality of data and the training effect of the model.

[0100] ⑤ Real-time monitoring and response: This method supports real-time monitoring of charging piles. Once a measurement accuracy problem is found, it can respond quickly and take measures to ensure the normal operation of the charging piles.

[0101] ⑥ Cost-effectiveness: Compared with the traditional on-site calibration method, the method of the present invention greatly reduces the calibration cost, including manpower, material and time costs.

[0102] ⑦Easy to expand and upgrade: The remote calibration system is based on software and hardware, which is easy to maintain and upgrade through software updates to adapt to the continuous development of charging pile technology and changes in calibration standards.

[0103] ⑧ Potential for large-scale application: This method is particularly suitable for the calibration of massive charging piles, has good potential for large-scale application, and helps to improve the operational management efficiency of the charging pile network.

[0104] Example 2

[0105] This embodiment provides a remote verification system, which can execute the method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0106] On the basis of the above-mentioned embodiments, the features not explained in this embodiment are explained in other embodiments and will not be described again in detail.

[0107] See also Figure 2 The remote verification system provided in this embodiment includes:

[0108] Data acquisition module 1 is used to select some charging piles for transformation, install new electric energy meters inside the selected charging piles, and send the electrical data of the charging piles detected by the original electric energy meters and the new electric energy meters to the database of the cloud platform through the data acquisition card;

[0109] The data labeling module 4 is used to calculate the power consumed during the charging process based on the electrical data, and calculate the measurement result deviation between the new electric energy meter and the original electric energy meter, and label the charging piles whose measurement result deviation is within the allowable error range as qualified, otherwise, they are marked as unqualified;

[0110] Model building and training module 5, used to input the labeled data into the LSTM-GAN model for training to obtain a verification model;

[0111] The remote verification module 6 is used to input the electrical data of the charging pile to be verified into the trained verification model, and judge whether the measurement accuracy of the charging pile is qualified by comparing the deviation.

[0112] Optionally, the remote verification system also includes:

[0113] Data cleaning module 2, used for format unification and time-stamp alignment of electrical data collected by the new electric energy meter and the original electric energy meter;

[0114] The data enhancement module 3 is used to perform noise injection and time scaling processing on the electrical data.

[0115] Example 3

[0116] Figure 3 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Figure 3 A block diagram of an exemplary computer device 100 suitable for use in implementing embodiments of the present invention is shown. Figure 3 The computer device 100 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0117] like Figure 3 As shown, the computer device 100 is in the form of a general computing device. The components of the computer device 100 may include but are not limited to: one or more processors or processing units 100a, a system memory 100b, and a bus 100c connecting different system components (including the system memory 100b and the processing unit 100a).

[0118] Bus 100c represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0119] The computer device 100 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 100, including volatile and non-volatile media, removable and non-removable media.

[0120] The system memory 100b may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 100d and / or cache memory 100e. The computer device 100 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 100f may be used to read and write non-removable, non-volatile magnetic media ( Figure 3not shown, usually called a "hard drive"). Although Figure 3 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 100c via one or more data medium interfaces. The system memory 100b may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0121] A program / utility 100h having a set (at least one) of program modules 100g may be stored in, for example, a memory 100b, such program modules 100g including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment. The program modules 100g generally perform the functions and / or methods of the embodiments described herein.

[0122] The computer device 100 may also communicate with one or more external devices 200 (e.g., keyboard, pointing device, display 200a, etc.), one or more devices that enable a user to interact with the computer device 100, and / or any device that enables the computer device 100 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via input / output (I / O) interface 100i. Furthermore, the computer device 100 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) via network adapter 100j. As shown, the network adapter 100j communicates with other modules of the computer device 100 via bus 100c. It should be understood that although Figure 3 Not shown, other hardware and / or software modules may be used in conjunction with computer device 100, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0123] The processing unit 100a executes various functional applications and data processing by running the programs stored in the system memory 100b, for example, implementing the remote verification system control method provided in the embodiment of the present invention.

[0124] That is, when the processing unit 100a executes the program, the following is achieved:

[0125] Data collection: select some charging piles for transformation, install new energy meters inside the selected charging piles, and upload the electrical data of the charging piles detected by the original energy meters and the new energy meters to the database of the cloud platform through the data acquisition card;

[0126] Data labeling: Calculate the power consumed during the charging process based on the electrical data, and calculate the measurement result deviation between the new energy meter and the original energy meter. Label the charging piles whose measurement result deviation is within the allowable error range as qualified, otherwise label them as unqualified.

[0127] Model construction and training: input the labeled data into the LSTM-GAN model for training to obtain the verification model;

[0128] Remote calibration: input the electrical data of the charging pile to be calibrated into the trained calibration model, and judge whether the measurement accuracy of the charging pile is qualified by comparing the deviation.

[0129] Example 4

[0130] An embodiment of the present invention provides a computer-readable storage medium having computer-executable instructions stored thereon, which, when executed by a processor, implements a remote calibration method for a large number of charging piles based on LSTM-GAN as provided in all the embodiments of the present invention:

[0131] That is, when the processor executes the computer executable instructions:

[0132] Data collection: select some charging piles for transformation, install new energy meters inside the selected charging piles, and upload the electrical data of the charging piles detected by the original energy meters and the new energy meters to the database of the cloud platform through the data acquisition card;

[0133] Data labeling: Calculate the power consumed during the charging process based on the electrical data, and calculate the measurement result deviation between the new energy meter and the original energy meter. Label the charging piles whose measurement result deviation is within the allowable error range as qualified, otherwise label them as unqualified.

[0134] Model construction and training: input the labeled data into the LSTM-GAN model for training to obtain the verification model;

[0135] Remote calibration: input the electrical data of the charging pile to be calibrated into the trained calibration model, and judge whether the measurement accuracy of the charging pile is qualified by comparing the deviation.

[0136] Any combination of one or more computer-readable media can be used. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0137] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. 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. Computer-readable signal media 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 conjunction with an instruction execution system, apparatus, or device.

[0138] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0139] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through 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., through the Internet using an Internet service provider).

[0140] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. A remote verification method for massive charging piles based on LSTM-GAN, characterized in that: include: Data collection: select some charging piles for transformation, install new energy meters inside the selected charging piles, and upload the electrical data of the charging piles detected by the original energy meters and the new energy meters to the database of the cloud platform through the data acquisition card; Data labeling: Calculate the power consumed during the charging process based on the electrical data, and calculate the measurement result deviation between the new energy meter and the original energy meter. Label the charging piles whose measurement result deviation is within the allowable error range as qualified, otherwise label them as unqualified. Model construction and training: input the labeled data into the LSTM-GAN model for training to obtain the verification model; Remote calibration: input the electrical data of the charging pile to be calibrated into the trained calibration model, and judge whether the measurement accuracy of the charging pile is qualified by comparing the deviation.

2. According to the LSTM-GAN-based remote verification method for massive charging piles according to claim 1, it is characterized in that: The data marking includes calculating the power consumed in the charging process according to the electrical data, and calculating the measurement result deviation between the new electric energy meter and the original electric energy meter, marking the charging piles whose measurement result deviation is within the allowable error range as qualified, and marking the charging piles as unqualified. Data cleaning: unify the format and align the time scale of the electrical data collected by the new and existing electricity meters.

3. The remote verification method for massive charging piles based on LSTM-GAN according to claim 2 is characterized in that: The data cleaning, after unifying the format and aligning the time scales of the electrical data collected by the new electric energy meter and the original electric energy meter, also includes: Data augmentation,noise injection and time scaling of electrical data.

4. The method for remote verification of massive charging piles based on LSTM-GAN according to claim 1 is characterized in that: The electrical data includes a power curve W of the charging pile during each charging process, and the instantaneous power wi at each time mark ti is obtained from the power curve W; The method of calculating the power consumed during the charging process according to the electrical data, and obtaining the measurement result deviation between the new electric energy meter and the original electric energy meter, and marking the charging piles whose measurement result deviation is within the allowable error range as qualified, and marking the charging piles whose measurement result deviation is within the allowable error range as unqualified, includes: According to the power curve W, the power consumed in the charging process is calculated as Δw=w1-wT, where w1 is the power at the start of charging and wT is the power at the end of charging; According to the power consumed in the charging process measured by the new power meter and the original power meter, the measurement result deviation δ= 00%, of which, The power consumed during the charging process measured by the new energy meter. The electricity consumed during the charging process measured by the original electricity meter.

5. The method for remote verification of massive charging piles based on LSTM-GAN according to claim 4 is characterized in that: The method further includes calculating the power consumed in the charging process according to the electrical data, calculating the measurement result deviation between the new electric energy meter and the original electric energy meter, marking the charging piles whose measurement result deviation is within the allowable error range as qualified, and marking the charging piles whose measurement result deviation is within the allowable error range as unqualified, and further includes: The charging piles with δ within the allowable error range are marked as qualified, and the power curve of the original electric energy meter of the qualified charging pile is used as a positive sample; The charging piles whose δ is outside the allowable error range are marked as unqualified, and the power curve corresponding to the original power meter of the unqualified charging pile is used as a negative sample.

6. The method for remote verification of massive charging piles based on LSTM-GAN according to claim 5 is characterized in that: The remote verification inputs the electrical data of the charging pile to be verified into the trained verification model, and determines whether the measurement accuracy of the charging pile is qualified by comparing the deviation, including: Input the electrical data of the charging pile to be tested into the trained test model; The verification model compares the received charge curve with the simulated data.

7. The method for remote verification of massive charging piles based on LSTM-GAN according to claim 6 is characterized in that: The remote verification includes inputting the electrical data of the charging pile to be verified into the trained verification model, and judging whether the measurement accuracy of the charging pile is qualified by comparing the deviation, and further includes: If the deviation between the two is within the preset error range, the measurement accuracy of the charging pile is considered qualified; If the deviation between the two is outside the preset error range, the metering accuracy of the charging pile is considered unqualified, and an alarm is issued or maintenance personnel are notified.

8. A remote verification system for executing the remote verification method for massive charging piles based on LSTM-GAN according to any one of claims 1 to 7, characterized in that: include: The data acquisition module is used to select some charging piles for transformation, install new electric energy meters inside the selected charging piles, and send the electrical data of the charging piles detected by the original electric energy meters and the new electric energy meters to the database of the cloud platform through the data acquisition card; The data labeling module is used to calculate the power consumed during the charging process based on the electrical data, and calculate the measurement result deviation between the new electric energy meter and the original electric energy meter. The charging piles with measurement result deviation within the allowable error range are marked as qualified, otherwise they are marked as unqualified; The model building and training module is used to input the labeled data into the LSTM-GAN model for training to obtain the verification model; The remote calibration module is used to input the electrical data of the charging pile to be calibrated into the trained calibration model, and judge whether the metering accuracy of the charging pile is qualified by comparing the deviation.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the remote verification method for massive charging piles based on LSTM-GAN is implemented as described in any one of claims 1 to 7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are executed by a computer processor to implement the remote verification method for massive charging piles based on LSTM-GAN as described in any one of claims 1 to 7.

Images