Charging pile error algorithm performance evaluation method and device, equipment and medium

Abstract

The invention provides a charging pile error algorithm performance evaluation method and device, equipment and a medium, and the method comprises the steps: inputting an electric energy data set of m charging piles of a charging station in a tm period and an electric energy data set of personal error adjustment into a to-be-evaluated charging pile error algorithm model, calculating to obtain a charging pile error set of each charging pile before and after adjustment; the error change responsivity of each charging pile is calculated; and comparing with the first threshold value and the second threshold value so as to evaluate whether the performance of the charging pile error algorithm is qualified or not. According to the method, the error positioning capability and the error change responsivity of the algorithm are evaluated by adopting a blind box test method, and a certain algorithm improvement direction is given, so that the fair and impartiality of charging pile trade settlement are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of charging pile error calculation verification, and in particular to a method, device, equipment and medium for evaluating the performance of a charging pile error algorithm. Background Art

[0002] As an important carrier of electricity trading and settlement, the demand for measurement and testing of charging piles is also growing rapidly. However, due to the large stock and rapid growth of charging piles, there are problems such as low efficiency, high cost, and difficulty in implementation in the actual calibration work. Therefore, the industry has proposed data-driven charging pile error algorithms to reduce the burden of on-site calibration of charging piles.

[0003] At present, the industry has proposed a charging pile error algorithm based on vehicle-pile data interaction, and established a vehicle-pile interaction online monitoring platform, using electric vehicle battery BMS as the transmission standard, and realizing vehicle-pile data interaction based on GB / T 27930 "Electric Vehicle Charging Standard Protocol". Once the algorithm finds that ordinary piles have a high probability of exceeding the tolerance, an on-site inspection will be carried out immediately. However, there is currently no suitable performance evaluation and improvement method for the charging pile error algorithm, and it is impossible to improve the algorithm based on the algorithm results. Therefore, it is urgent to propose a method for evaluating and improving the performance of the charging pile error algorithm to ensure the fairness and justice of charging pile trade settlement. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method, device, equipment and medium for evaluating the performance of a charging pile error algorithm, which can evaluate the error positioning capability and error change responsiveness of the algorithm and provide certain algorithm improvement directions, thereby ensuring the fairness and justice of charging pile trade settlement.

[0005] In a first aspect, the present invention provides a method for evaluating the performance of a charging pile error algorithm, comprising:

[0006] S1, t m The power data set of m charging piles in the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t m The charging pile error set of each charging pile at the charging station at all times

[0007] S2. Electric energy data collection Perform human error adjustment, adjusting the power data of at least one charging pile i each time;

[0008] S3, t m The adjusted power data set of m charging piles at the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t mThe adjusted charging pile error set of each charging pile at the charging station at any time

[0009] S4. Determine t before and after adjustment m Whether the charging pile error of each charging pile in the time period has not changed or the change direction is opposite to the adjustment direction of the manually adjusted error, if so, increase the manually adjusted error and return to S2; if not, proceed to the next step;

[0010] S5. Calculate the responsiveness of the charging pile error algorithm to be evaluated to the error change of each charging pile;

[0011] S6. Determine whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of the adjusted charging pile i is greater than a first threshold, and whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of other unadjusted charging piles is less than a second threshold. If so, it means that the algorithm's responsiveness to the error change of the charging pile is normal, and the performance evaluation of the charging pile error algorithm is qualified. If not, it means that the responsiveness of the charging pile error algorithm to be evaluated to the error change of the charging pile is abnormal, and the performance evaluation of the charging pile error algorithm is unqualified.

[0012] Furthermore, in S1, the electric energy data set It is expressed as:

[0013]

[0014] Yes m The power data of charging pile 1 during the time period;

[0015] Yes m The power data of charging pile 2 during the time period;

[0016] Yes m The power data of charging pile m during the time period;

[0017] The charging pile error set It is expressed as:

[0018]

[0019] Yes m Charging pile error of charging pile 1 in time period;

[0020] Yes m Charging pile error of charging pile 2 in time period;

[0021] Yes m Charging pile error of charging pile m in time period;

[0022] In S2, the electric energy data set after human error adjustment is expressed as:

[0023]

[0024] in, t m The adjusted power data set of m charging piles at the charging station during the period;

[0025] t m The adjusted power data of charging pile i in the time period, and

[0026] Δε is the human adjustment error;

[0027] In S3, the charging pile error set after human error adjustment It is expressed as:

[0028]

[0029] Yes m The adjusted charging pile error of charging pile 1 in time period;

[0030] Yes m The adjusted charging pile error of charging pile i in time period;

[0031] Yes m The adjusted charging pile error of charging pile m in the time period;

[0032] In S5, the calculation formula of the charging pile error algorithm to be evaluated for the error change responsiveness of each charging pile is:

[0033]

[0034] in,

[0035] r 1,1 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 1;

[0036] r 1,2 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 2;

[0037] r 1,m is the responsiveness of the charging pile error algorithm to be evaluated to the error change of the charging pile m.

[0038] Furthermore, in S4, the method of increasing the human adjustment error Δε is to increase it in a preset step increment or in a multiple increment of the current human adjustment error Δε.

[0039] Furthermore, the method of the present invention further comprises:

[0040] S7. Error compensation is performed on the charging pile with abnormal error change responsiveness, specifically including:

[0041] S71. After multiple human error adjustments, multiple error responsiveness of a charging pile with abnormal error change responsiveness are obtained, and the average value of the multiple error responsiveness is calculated to obtain the average error responsiveness.

[0042] S72, performing error compensation on the charging pile with abnormal error change responsiveness according to the average error responsiveness, wherein the specific compensation method is:

[0043]

[0044] In the formula, ε1 is t m The error of a charging pile with abnormal error change responsiveness during the time period;

[0045] ε2 is t m+1 The error of a charging pile with abnormal error change responsiveness during the time period;

[0046] ε'2 is the compensated charging pile m error, which improves the output result of the charging pile error algorithm.

[0047] In a second aspect, the present invention provides a device for evaluating the performance of a charging pile error algorithm, comprising:

[0048] Input module, used to convert t m The power data set of m charging piles in the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t m The charging pile error set of each charging pile at the charging station at all times

[0049] Error adjustment module for collecting power data Perform human error adjustment, adjusting the power data of at least one charging pile i each time;

[0050] Calling module, used to convert t m The adjusted power data set of m charging piles at the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t m The adjusted charging pile error set of each charging pile at the charging station at any time

[0051] Judgment module, used to judge the adjustment before and after t m Whether the charging pile error of each charging pile in the time period has not changed or the change direction is opposite to the adjustment direction of the manually adjusted error, if so, notify the error adjustment module to increase the manually adjusted error and make another adjustment; if not, notify the responsiveness calculation module to calculate the responsiveness of each charging pile error change;

[0052] A responsiveness calculation module, used to calculate the responsiveness of the charging pile error algorithm to be evaluated to the error change of each charging pile;

[0053] The evaluation module is used to determine whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of the adjusted charging pile i is greater than a first threshold, and whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of other unadjusted charging piles is less than a second threshold. If so, it means that the algorithm's responsiveness to the error change of the charging pile is normal, and the charging pile error algorithm performance evaluation is qualified; if not, it means that the charging pile error algorithm to be evaluated has an abnormality in its responsiveness to the error change of the charging pile, and the charging pile error algorithm performance evaluation is unqualified.

[0054] Furthermore, the electric energy data set It is expressed as:

[0055]

[0056] Yes m The power data of charging pile 1 during the time period;

[0057] Yes m The power data of charging pile 2 during the time period;

[0058] Yes m The power data of charging pile m during the time period;

[0059] The charging pile error set It is expressed as:

[0060]

[0061] Yes m Charging pile error of charging pile 1 in time period;

[0062] Yes m Charging pile error of charging pile 2 in time period;

[0063] Yes m Charging pile error of charging pile m in time period;

[0064] The formula of the electric energy data set after human error adjustment is expressed as:

[0065]

[0066] in, t m The adjusted power data set of m charging piles at the charging station during the period;

[0067] t m The adjusted power data of charging pile i in the time period, and

[0068] Δε is the human adjustment error;

[0069] The charging pile error set after human error adjustment It is expressed as:

[0070]

[0071] Yes m The adjusted charging pile error of charging pile 1 in time period;

[0072] Yes m The adjusted charging pile error of charging pile i in time period;

[0073] Yes m The adjusted charging pile error of charging pile m in the time period;

[0074] The calculation formula of the charging pile error algorithm to be evaluated for the error change responsiveness of each charging pile is:

[0075]

[0076] in,

[0077] r 1,1 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 1;

[0078] r 1,2 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 2;

[0079] r 1,m is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile m.

[0080] Furthermore, the error adjustment module increases the human adjustment error Δε by increasing it in a preset step increment or in a multiple increment of the current human adjustment error Δε.

[0081] Furthermore, the device of the present invention also includes:

[0082] The compensation module is used to compensate for the error of the charging pile with abnormal error change responsiveness, specifically including:

[0083] After multiple human error adjustments, multiple error responsiveness of a charging pile with abnormal error change responsiveness is obtained, and the average value of the multiple error responsiveness is calculated to obtain the average error responsiveness.

[0084] According to the average error responsiveness, error compensation is performed on the charging pile with abnormal error change responsiveness. The specific compensation method is:

[0085]

[0086] In the formula, ε1 is t m The error of charging pile i calculated by the time period charging pile error algorithm;

[0087] ε2 is t m+1 The error of charging pile i calculated by the time period charging pile error algorithm;

[0088] ε'2 is the compensated charging pile i error, which improves the output result of the charging pile error algorithm.

[0089] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0090] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0091] The one or more technical solutions provided by the present invention have at least the following technical effects or advantages: The present invention adopts a blind box test method to evaluate the error positioning capability and error change responsiveness of the charging pile error algorithm model. After inputting the artificial adjustment error, whether the error calculated by the charging pile error algorithm can respond to this artificial adjustment error, that is, whether the calculated error has the ability to change accordingly according to the adjustment amplitude, to achieve the accuracy evaluation of the charging pile error algorithm model, so as to determine whether there is data cheating in the charging piles in the charging station. And the present invention also proposes a corresponding error compensation scheme based on the accuracy evaluation of the algorithm model, so as to promote the improvement of the accuracy of the charging pile error algorithm model and improve the feasibility and reliability of the charging pile error algorithm model.

[0092] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] The present invention will be further described below in conjunction with embodiments with reference to the accompanying drawings.

[0094] Figure 1 Schematic diagram of the principle of the blind box testing method according to an embodiment of the present invention;

[0095] Figure 2 is a flow chart of the method in Embodiment 1 of the present invention;

[0096] Figure 3 A schematic diagram of the principle of human error adjustment according to an embodiment of the present invention;

[0097] Figure 4 It is a structural schematic diagram of the device in the second embodiment of the present invention;

[0098] Figure 5 This is a schematic diagram of the structure of an electronic device in Embodiment 3 of the present invention;

[0099] Figure 6 Schematic diagram of the structure of the medium in the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0100] The embodiments of the present application provide a method, device, equipment and medium for evaluating the performance of a charging pile error algorithm, which can evaluate the error positioning capability and error change responsiveness of the algorithm and provide certain algorithm improvement directions, thereby ensuring the fairness and justice of charging pile trade settlement.

[0101] The technical solution in the embodiment of the present application has the following overall idea: it is mainly aimed at the scenario where the charging station operator achieves data cheating by artificially adjusting the charging pile error, thereby affecting the fairness and justice of the charging pile trade settlement. The embodiment of the present application adopts the blind box testing method (also known as the black box testing method) to comprehensively and systematically test the functions of the charging pile error algorithm model. The tester does not need to understand the internal implementation details of the algorithm, but only needs to know the specific functions and input and output methods of the algorithm. This method is particularly suitable for verifying whether the algorithm can process different types of input data as expected and produce correct output results.

[0102] like Figure 1 As shown, during the evaluation, it is only necessary to input the artificial adjustment error, so that the charging pile error algorithm to be evaluated enters the black box calculation, and then judge whether the calculated error can respond to the artificial adjustment error, that is, whether the calculated error has the ability to change accordingly according to the adjustment amplitude, so as to achieve the accuracy evaluation of the charging pile error algorithm model, thereby judging whether there is data cheating in the charging piles in the charging station. Moreover, based on the accuracy evaluation of the algorithm model, the present invention also proposes a corresponding error compensation scheme, thereby promoting the improvement of the accuracy of the charging pile error algorithm model, and improving the feasibility and reliability of the charging pile error algorithm model.

[0103] Embodiment 1

[0104] like Figure 2 As shown, this embodiment provides a method for evaluating the performance of a charging pile error algorithm, including:

[0105] S1, t m The power data set of m charging piles in the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t m The charging pile error set of each charging pile at the charging station at all times

[0106] The electric energy data set It is expressed as:

[0107]

[0108] Yes m The power data of charging pile 1 during the time period;

[0109] Yes m The power data of charging pile 2 during the time period;

[0110] Yes m The power data of charging pile m during the time period;

[0111] The charging pile error set It is expressed as:

[0112]

[0113] Yes m Charging pile error of charging pile 1 in time period;

[0114] Yes m Charging pile error of charging pile 2 in time period;

[0115] Yes m The charging pile error of charging pile m in time period.

[0116] S2. Electric energy data collection Perform human error adjustment, and adjust the power data of at least one charging pile i each time; Figure 3 As shown in the figure, the formula of the electric energy data set after human error adjustment is expressed as:

[0117]

[0118] in, t m The adjusted power data set of m charging piles at the charging station during the period;

[0119] t m The adjusted power data of charging pile i in the time period, and

[0120] Δε is the human adjustment error.

[0121] If necessary, the errors of n charging piles (n≤m) can be adjusted simultaneously as needed, so that it can be determined whether the algorithm is applicable to the situation where the errors of multiple piles are adjusted.

[0122] S3, t m The adjusted power data set of m charging piles at the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t m The adjusted charging pile error set of each charging pile at the charging station at any time Charging pile error set after human error adjustment It is expressed as:

[0123]

[0124] Yes m The adjusted charging pile error of charging pile 1 in time period;

[0125] Yes m The adjusted charging pile error of charging pile i in time period;

[0126] Yes m The adjusted charging pile error of charging pile m in time period.

[0127] S4. Determine t before and after adjustment m Whether the charging pile error of each charging pile in the time period has not changed or the change direction is opposite to the adjustment direction of the manually adjusted error, if so, increase the manually adjusted error and return to S2; if not, proceed to the next step;

[0128] The method of increasing the human adjustment error Δε is to increase it in a preset step increment or in a multiple increment of the current human adjustment error Δε, for example, in a 1% step increment or in a manner of 2Δε, 3Δε, 4Δε, until the algorithm can respond to the human adjustment error.

[0129] S5. Calculate the error change responsiveness of the charging pile error algorithm to be evaluated to each charging pile; the calculation formula for the error change responsiveness is:

[0130]

[0131] in,

[0132] r 1,1 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 1;

[0133] r 1,2 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 2;

[0134] r 1,m is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile m.

[0135] S6. Determine whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of the adjusted charging pile i is greater than a first threshold, and whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of other unadjusted charging piles is less than a second threshold. If so, it means that the algorithm's responsiveness to the error change of the charging pile is normal, and the performance evaluation of the charging pile error algorithm is qualified. If not, it means that the responsiveness of the charging pile error algorithm to be evaluated to the error change of the charging pile is abnormal, and the performance evaluation of the charging pile error algorithm is unqualified.

[0136] For the ideal performance of the charging pile error algorithm, the first threshold must reach 100%, and the second threshold must reach 0%. But generally speaking, in practical applications, the first threshold can be set to 90% or greater, and the second threshold can be set to 10% or less. For the adjusted charging pile, when the error change responsiveness r ≥ 90%, and for the unadjusted charging pile, when the error change responsiveness r ≤ 10%, it can be shown that the charging pile error algorithm to be evaluated has good sensitivity to the errors of each charging pile, and the error change responsiveness meets the requirements.

[0137] Furthermore, the embodiment of the present invention also includes:

[0138] S7. Error compensation is performed on the charging pile with abnormal error change responsiveness, specifically including:

[0139] S71. After multiple human error adjustments, multiple error responsiveness of a charging pile with abnormal error change responsiveness are obtained, and an average value of the multiple error responsiveness is calculated to obtain an average error responsiveness;

[0140] According to the above blind box test method, the error response capability of the charging pile after each manual error adjustment can be obtained. Taking charging pile i as an example, the error response capability obtained is: r i = {r 1,i ,r 2,i ,...,r m,i}, where r i is the error change response set of charging pile i, r 1,i is the error change response of charging pile i after the error Δε is manually adjusted for the first charging pile, r 2,i is the error change response of charging pile i after the error Δε is manually adjusted for the second charging pile, r m,i is the error change responsiveness of charging pile i after the error Δε of the i-th charging pile is manually adjusted.

[0141] The set r of response to the error change of charging pile i m Taking the average of the elements in , we can get

[0142]

[0143] in, is the average error response capability of charging pile i.

[0144] S72, performing error compensation on the charging pile with abnormal error change responsiveness according to the average error responsiveness, wherein the specific compensation method is:

[0145]

[0146] In the formula, ε1 is t mThe error of a charging pile with abnormal error change responsiveness during the time period;

[0147] ε2 is t m+1 The error of a charging pile with abnormal error change responsiveness during the time period;

[0148] ε'2 is the compensated charging pile m error, which improves the output result of the charging pile error algorithm.

[0149] Embodiment 2

[0150] Based on the same inventive concept, the present application also provides a device corresponding to the method in Example 1, see Example 2 for details.

[0151] like Figure 4 As shown, in this embodiment, a preferred implementation of a charging pile error algorithm performance evaluation device is provided, which includes an input module, an error adjustment module, a calling module, a judgment module, a responsiveness calculation module, an evaluation module and a compensation module.

[0152] Input module, used to convert t m The power data set of m charging piles in the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t m The charging pile error set of each charging pile at the charging station at all times

[0153] The electric energy data set It is expressed as:

[0154]

[0155] Yes m The power data of charging pile 1 during the time period;

[0156] Yes m The power data of charging pile 2 during the time period;

[0157] Yes m The power data of charging pile m during the time period;

[0158] The charging pile error set It is expressed as:

[0159]

[0160] Yes m Charging pile error of charging pile 1 in time period;

[0161] Yesm Charging pile error of charging pile 2 in time period;

[0162] Yes m The charging pile error of charging pile m in time period.

[0163] Error adjustment module for collecting power data Perform human error adjustment, adjusting the power data of at least one charging pile i each time;

[0164] The formula of the electric energy data set after human error adjustment is expressed as:

[0165]

[0166] in, t m The adjusted power data set of m charging piles at the charging station during the period;

[0167] t m The adjusted power data of charging pile i in the time period, and

[0168] Δε is the human adjustment error.

[0169] Calling module, used to convert t m The adjusted power data set of m charging piles at the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t m The adjusted charging pile error set of each charging pile at the charging station at any time

[0170] The charging pile error set after human error adjustment It is expressed as:

[0171]

[0172] Yes m The adjusted charging pile error of charging pile 1 in time period;

[0173] Yes m The adjusted charging pile error of charging pile i in time period;

[0174] Yes m The adjusted charging pile error of charging pile m in time period.

[0175] Judgment module, used to judge the adjustment before and after t mWhether the charging pile error of each charging pile in the time period has not changed or the change direction is opposite to the adjustment direction of the manually adjusted error, if so, notify the error adjustment module to increase the manually adjusted error and make another adjustment; if not, notify the responsiveness calculation module to calculate the responsiveness of each charging pile error change;

[0176] The error adjustment module increases the human adjustment error Δε by increasing it in a preset step increment or in a multiple increment of the current human adjustment error Δε.

[0177] The responsiveness calculation module is used to calculate the responsiveness of the charging pile error algorithm to be evaluated to the error change of each charging pile; the calculation formula of the responsiveness of the charging pile error algorithm to be evaluated to the error change of each charging pile is:

[0178]

[0179] in,

[0180] r 1,1 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 1;

[0181] r 1,2 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 2;

[0182] r 1,m is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile m.

[0183] The evaluation module is used to determine whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of the adjusted charging pile i is greater than a first threshold, and whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of other unadjusted charging piles is less than a second threshold. If so, it means that the algorithm's responsiveness to the error change of the charging pile is normal, and the charging pile error algorithm performance evaluation is qualified; if not, it means that the charging pile error algorithm to be evaluated has an abnormality in its responsiveness to the error change of the charging pile, and the charging pile error algorithm performance evaluation is unqualified.

[0184] Furthermore, the device of the present invention also includes:

[0185] The compensation module is used to compensate for the error of the charging pile with abnormal error change responsiveness, specifically including:

[0186] After multiple human error adjustments, multiple error responsiveness of a charging pile with abnormal error change responsiveness is obtained, and the average value of the multiple error responsiveness is calculated to obtain the average error responsiveness;

[0187] According to the above blind box test method, the error response capability of the charging pile after each manual error adjustment can be obtained. Taking charging pile i as an example, the error response capability obtained is: r i = {r 1,i ,r 2,i ,...,r m,i}, where r i is the error change response set of charging pile i, r 1,i is the error change response of charging pile i after the error Δε is manually adjusted for the first charging pile, r 2,i is the error change response of charging pile i after the error Δε is manually adjusted for the second charging pile, r m,i is the error change responsiveness of charging pile i after the error Δε of the i-th charging pile is manually adjusted.

[0188] The set r of response to the error change of charging pile i m Taking the average of the elements in , we can get

[0189]

[0190] in, is the average error response capability of charging pile i.

[0191] According to the average error responsiveness, error compensation is performed on the charging pile with abnormal error change responsiveness. The specific compensation method is:

[0192]

[0193] In the formula, ε1 is t m The error of charging pile i calculated by the time period charging pile error algorithm;

[0194] ε2 is t m+1 The error of charging pile i calculated by the time period charging pile error algorithm;

[0195] ε'2 is the compensated charging pile i error, which improves the output result of the charging pile error algorithm.

[0196] Since the device introduced in the second embodiment of the present invention is a device used to implement the method of the first embodiment of the present invention, those skilled in the art can understand the specific structure and deformation of the device based on the method introduced in the first embodiment of the present invention, so it is not described here in detail. All devices used in the method of the first embodiment of the present invention belong to the scope of protection of the present invention.

[0197] Embodiment 3

[0198] Based on the same inventive concept, the present application provides an electronic device embodiment corresponding to the first embodiment, see the third embodiment for details. This embodiment provides an electronic device, such as Figure 5 As shown, it includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any implementation method in the first embodiment can be implemented.

[0199] Since the electronic device introduced in this embodiment is a device used to implement the method in the first embodiment of the present application, based on the method introduced in the first embodiment of the present application, a person skilled in the art can understand the specific implementation of the electronic device of the present embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is not described in detail here. As long as a person skilled in the art implements the device used by the method in the embodiment of the present application, it belongs to the scope of protection of the present application.

[0200] Embodiment 4

[0201] Based on the same inventive concept, this application provides a storage medium corresponding to Embodiment 1, see Embodiment 4 for details. This embodiment provides a computer-readable storage medium, such as Figure 6 As shown, a computer program is stored thereon, and when the computer program is executed by a processor, any implementation method in Example 1 can be implemented.

[0202] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0203] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0204] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0205] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0206] Although the specific implementation modes of the present invention are described above, those skilled in the art should understand that the specific implementation modes described are only illustrative and are not intended to limit the scope of the present invention. Equivalent modifications and changes made by those skilled in the art in accordance with the spirit of the present invention should be included in the scope of protection of the claims of the present invention.

Claims

1. A method for evaluating the performance of a charging pile error algorithm, characterized in that: include: S1, t m The power data set of m charging piles in the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t m The charging pile error set of each charging pile at the charging station at all times S2. Electric energy data collection Perform human error adjustment, adjusting the power data of at least one charging pile i each time; S3, t m The adjusted power data set of m charging piles at the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t m The adjusted charging pile error set of each charging pile at the charging station at any time S4. Determine t before and after adjustment m Whether the charging pile error of each charging pile in the time period has not changed or the change direction is opposite to the adjustment direction of the manually adjusted error, if so, increase the manually adjusted error and return to S2; if not, proceed to the next step; S5. Calculate the responsiveness of the charging pile error algorithm to be evaluated to the error change of each charging pile; S6. Determine whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of the adjusted charging pile i is greater than a first threshold, and whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of other unadjusted charging piles is less than a second threshold. If so, it means that the algorithm's responsiveness to the error change of the charging pile is normal, and the performance evaluation of the charging pile error algorithm is qualified. If not, it means that the responsiveness of the charging pile error algorithm to be evaluated to the error change of the charging pile is abnormal, and the performance evaluation of the charging pile error algorithm is unqualified.

2. The method for evaluating the performance of a charging pile error algorithm according to claim 1, characterized in that: In S1, the electric energy data set It is expressed as: Yes m The power data of charging pile 1 during the time period; Yes m The power data of charging pile 2 during the time period; Yes m The power data of charging pile m during the time period; The charging pile error set It is expressed as: Yes m Charging pile error of charging pile 1 in time period; Yes m Charging pile error of charging pile 2 in time period; Yes m Charging pile error of charging pile m in time period; In S2, the electric energy data set after human error adjustment is expressed as: in, t m The adjusted power data set of m charging piles at the charging station during the period; t m The adjusted power data of charging pile i in the time period, and Δε is the human adjustment error; In S3, the charging pile error set after human error adjustment It is expressed as: Yes m The adjusted charging pile error of charging pile 1 in time period; Yes m The adjusted charging pile error of charging pile i in time period; Yes m The adjusted charging pile error of charging pile m in the time period; In S5, the calculation formula of the charging pile error algorithm to be evaluated for the error change responsiveness of each charging pile is: in, r 1,1 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 1; r 1,2 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 2; r 1,m is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile m.

3. A charging pile error algorithm performance evaluation method according to claim 1 or 2, characterized in that: In S4, the method of increasing the human adjustment error Δε is to increase it in increments according to a preset step or in increments according to a multiple of the current human adjustment error Δε.

4. The method for evaluating the performance of a charging pile error algorithm according to claim 2, characterized in that: Also includes: S7, performing error compensation on the charging pile error algorithm, thereby improving the output result of the charging pile error algorithm, specifically including: S71. After multiple human error adjustments, multiple algorithms are obtained to determine the error change response of the charging pile i, and the average of the multiple error response is calculated to obtain the average error change response of the algorithm to the charging pile i. S72: Perform error compensation on the output result of the charging pile error algorithm according to the average error responsiveness. The specific compensation method is: In the formula, ε1 is t m The error of charging pile i calculated by the time period charging pile error algorithm; ε2 is t m+1 The error of charging pile i calculated by the time period charging pile error algorithm; ε'2 is the compensated charging pile i error, which improves the output result of the charging pile error algorithm.

5. A device for evaluating the performance of a charging pile error algorithm, characterized in that: include: Input module, used to convert t m The power data set of m charging piles in the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t m The charging pile error set of each charging pile at the charging station at all times Error adjustment module for collecting power data Perform human error adjustment, adjusting the power data of at least one charging pile i each time; Calling module, used to convert t m The adjusted power data set of m charging piles at the charging station during the period Input into the charging pile error algorithm model to be evaluated, and calculate t m The adjusted charging pile error set of each charging pile at the charging station at any time Judgment module, used to judge the adjustment before and after t m Whether the charging pile error of each charging pile in the time period has not changed or the change direction is opposite to the adjustment direction of the manually adjusted error, if so, notify the error adjustment module to increase the manually adjusted error and make another adjustment; if not, notify the responsiveness calculation module to calculate the responsiveness of each charging pile error change; A responsiveness calculation module, used to calculate the responsiveness of the charging pile error algorithm to be evaluated to the error change of each charging pile; The evaluation module is used to determine whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of the adjusted charging pile i is greater than a first threshold, and whether the responsiveness of the charging pile error algorithm to be evaluated to the error change of other unadjusted charging piles is less than a second threshold. If so, it means that the algorithm's responsiveness to the error change of the charging pile is normal, and the charging pile error algorithm performance evaluation is qualified; if not, it means that the charging pile error algorithm to be evaluated has an abnormality in its responsiveness to the error change of the charging pile, and the charging pile error algorithm performance evaluation is unqualified.

6. The device for evaluating the performance of a charging pile error algorithm according to claim 5, characterized in that: The electric energy data set It is expressed as: Yes m The power data of charging pile 1 during the time period; Yes m The power data of charging pile 2 during the time period; Yes m The power data of charging pile m during the time period; The charging pile error set It is expressed as: Yes m Charging pile error of charging pile 1 in time period; Yes m Charging pile error of charging pile 2 in time period; Yes m Charging pile error of charging pile m in time period; The formula for the electric energy data set after human error adjustment is expressed as: in, t m The adjusted power data set of m charging piles at the charging station during the period; t m The adjusted power data of charging pile i in the time period, and Δε is the human adjustment error; The charging pile error set after human error adjustment It is expressed as: Yes m The adjusted charging pile error of charging pile 1 in time period; Yes m The adjusted charging pile error of charging pile i in time period; Yes m The adjusted charging pile error of charging pile m in the time period; The calculation formula of the charging pile error algorithm to be evaluated for the error change responsiveness of each charging pile is: in, r 1,1 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 1; r 1,2 is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile 2; r 1,m is the responsiveness of the charging pile error algorithm to be evaluated to the error change of charging pile m.

7. A charging pile error algorithm performance evaluation device according to claim 5 or 6, characterized in that: The error adjustment module increases the human adjustment error Δε by increasing it in a preset step increment or in a multiple increment of the current human adjustment error Δε.

8. The device for evaluating the performance of a charging pile error algorithm according to claim 6, characterized in that: Also includes: The compensation module is used to compensate for the error of the charging pile with abnormal error change responsiveness, specifically including: After multiple human error adjustments, multiple error responsiveness of a charging pile with abnormal error change responsiveness is obtained, and the average value of the multiple error responsiveness is calculated to obtain the average error responsiveness. According to the average error responsiveness, error compensation is performed on the charging pile with abnormal error change responsiveness. The specific compensation method is: In the formula, ε1 is t m The error of charging pile i calculated by the time period charging pile error algorithm; ε2 is t m+1 The error of charging pile i calculated by the time period charging pile error algorithm; ε'2 is the compensated charging pile i error, which improves the output result of the charging pile error algorithm.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images