A method, device, equipment and medium for identifying characteristic parameters of electric vehicle charging load using complex coupling network multi-agent technology

Abstract

The present invention provides a method, device, equipment and medium for identifying characteristic parameters of electric vehicle charging load based on complex coupling network multi-agent technology, the method comprising the following steps: S1, designing a consistency control method, introducing complex coupling network restraint consistency control into data clustering analysis, and quickly obtaining the initial cluster center; S2, using a binary k-means method to quickly identify the expected value of the starting charging time of electric vehicles in typical scenarios, and extracting the probability distribution function of the charging probability of electric vehicles and the charging start time. Compared with the prior art, the present invention solves the technical difficulties of the existing data-driven electric vehicle charging load modeling method, which is complex in calculation and difficult to realize engineering application, automatically completes the selection of the initial cluster center without human intervention, and improves the clustering accuracy; quickly and accurately obtains the probability distribution function of the charging probability of electric vehicles and the charging period, and verifies that the proposed method has the characteristics of simple calculation and fast clustering.

Description

Technical Field

[0001] The present invention belongs to the field of new energy technology, and in particular relates to a method, device, equipment and medium for identifying characteristic parameters of electric vehicle charging load using a complex coupling network multi-agent technology. Background Art

[0002] New energy electric vehicles have received increasing attention and applications due to their superior handling performance, low pollution emissions, and high energy security. However, with the large-scale access of electric vehicles to the power grid, the randomness of charging loads has formed impact loads, which has an adverse impact on the safe and stable operation of the power grid. In particular, for the peak-to-valley difference in electricity consumption that has already formed in urban production and living power loads, the charging load of electric vehicles often causes a negative impact of "peaks on peaks", further increasing the demand for traditional fossil energy, but reducing the environmental advantages of electric vehicles.

[0003] Shifting the concentrated charging load from peak hours to off-peak hours can not only reduce the peak impact on the safe operation of the power system, but also facilitate the integrated utilization of renewable energy such as wind power. Therefore, it is necessary to establish an accurate electric vehicle charging load model to provide a decision-making basis for the optimal planning and design of large-scale concentrated electric vehicle charging behavior. Summary of the invention

[0004] The first purpose of the present invention is to provide an electric vehicle charging load characteristic parameter identification method using a complex coupling network multi-agent technology to address the technical difficulties of existing data-driven electric vehicle charging load modeling methods, which are complex in calculation and difficult to implement in engineering applications.

[0005] To this end, the above-mentioned purpose of the present invention is achieved through the following technical solutions:

[0006] A method for identifying characteristic parameters of electric vehicle charging load using a complex coupling network multi-agent technology, characterized in that the method for identifying characteristic parameters of electric vehicle charging load using a complex coupling network multi-agent technology comprises the following steps:

[0007] S1. Design a consistency control method, introduce complex coupling network constraint consistency control into data cluster analysis, and quickly obtain the initial cluster center;

[0008] Each data updates its clustering status according to the dissimilarity measure with the adjacent data. When all data complete the update process, the initial selection of cluster centers is completed. Only a small amount of local feedback controllers need to be injected into the data network to achieve the reasonable setting of the data network clustering boundaries.

[0009] S2. Using the binary k-means cluster analysis method, based on the binary k-means cluster analysis results, the probability distribution function of electric vehicle charging probability and charging start time is extracted.

[0010] While adopting the above technical solutions, the present invention may also adopt or combine the following technical solutions:

[0011] As a preferred technical solution of the present invention: the consistency control method in step S1 is established by the following formula:

[0012]

[0013] in:

[0014] d i is the dissimilarity measure between data point i and data point j in the charging load data network;

[0015] Function f[V i (t i )] is a self-feedback function;

[0016] ε is the consistency control parameter, which indicates the data network coupling strength, ε>0;

[0017] V(t) represents the electric vehicle charging load at time t;

[0018] Function h(·) is the internal coupling function of the interaction between adjacent data points;

[0019] u i (t i ) is a local feedback controller.

[0020] As the preferred technical solution of the present invention: i (t i ) can be expressed as:

[0021] u i (t i ) = g i {h[s(t i )-V i (t i )]}

[0022] in:

[0023] s(t i ) is the expected clustering boundary;

[0024] g i is the local feedback controller parameter, which is used to be the local feedback control gain of data point i.

[0025] As a preferred technical solution of the present invention: the probability of electric vehicle charging in step S2 is obtained by the following formula:

[0026]

[0027] in:

[0028] f i The probability of charging an electric vehicle, which is also the CP parameter of the electric vehicle;

[0029] y is the number of electric vehicle charging load data;

[0030] Z is the number of non-zero data;

[0031] i is the i-th period in a day, and w is the number of periods a day is divided into.

[0032] As a preferred technical solution of the present invention: the probability distribution function of the electric vehicle charging period in step S2 is obtained by the following formula:

[0033]

[0034] in:

[0035] h(t) is the probability distribution function of the electric vehicle charging period, which is also the CDPDF parameter;

[0036] σ c is the variance of the charging start time of the charging pile;

[0037] μ c is the expected time for the charging pile to start charging.

[0038] The second purpose of the present invention is to provide an electric vehicle charging load characteristic parameter identification device based on complex coupling network multi-agent technology in order to address the deficiencies in the prior art.

[0039] To this end, the above-mentioned purpose of the present invention is achieved through the following technical solutions:

[0040] An electric vehicle charging load characteristic parameter identification device using a complex coupling network multi-agent technology, characterized in that: the electric vehicle charging load characteristic parameter identification device using a complex coupling network multi-agent technology comprises:

[0041] An initial cluster center obtaining unit, wherein the initial cluster center obtaining unit is used to design a consistency control method, introduce complex coupling network pinning consistency control into data cluster analysis, and quickly obtain an initial cluster center;

[0042] An electric vehicle charging load characteristic parameter identification unit is used to extract the electric vehicle charging probability and charging start time probability distribution function based on the binary k-means cluster analysis result.

[0043] The third object of the present invention is to provide an electronic device to address the deficiencies in the prior art.

[0044] To this end, the above-mentioned purpose of the present invention is achieved through the following technical solutions:

[0045] An electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus, and wherein:

[0046] a memory for storing a computer program,

[0047] A processor is used to execute a computer program stored in a memory to implement the steps of the electric vehicle charging load characteristic parameter identification method using a complex coupled network multi-agent technology as described above.

[0048] Another object of the present invention is to provide a computer-readable storage medium to address the deficiencies in the prior art.

[0049] To this end, the above-mentioned purpose of the present invention is achieved through the following technical solutions:

[0050] A computer-readable storage medium, characterized in that: a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the electric vehicle charging load characteristic parameter identification method using the complex coupling network multi-agent technology described above are implemented.

[0051] The present invention provides a method, device, equipment and medium for identifying characteristic parameters of electric vehicle charging load using a complex coupling network multi-agent technology, which has the following beneficial effects:

[0052] (1) The present invention provides a consistency control method, in which each data updates its own clustering state according to the dissimilarity measure with the adjacent data. When all data complete the update process, that is, the initial selection of the cluster center is completed, only a small amount of local feedback controllers need to be injected into the data network to achieve the reasonable setting of the data network clustering boundary;

[0053] (2) The computational complexity of the binary k-means clustering method designed by the present invention is linearly related to the size of the data set, and the calculation is fast. The consistency control method completes the calculation of the number of initial cluster centers, ensuring the accuracy of the clustering results of the binary k-means algorithm, and solving the problem that one or more points in the initial cluster center disappear during the iteration process due to their extreme positions;

[0054] (3) The present invention designs a complex coupled data network consistency control method to introduce electric vehicle charging characteristic parameter analysis. It only needs to calculate the dissimilarity measure between adjacent data points to quickly identify the initial cluster center for binary k-means clustering. The binary k-means clustering method is used to accurately obtain the electric vehicle charging characteristic parameters, and quickly and accurately obtain the electric vehicle charging probability and charging period probability distribution function;

[0055] (4) The consistency-based k-means clustering method provided by the present invention has no constraints on the size and shape of the electric vehicle charging load data set, and has the characteristics of small computational complexity, fast clustering, and accurate identification of characteristic parameters. It establishes the distribution of electric vehicle charging time under typical scenarios and improves the accuracy of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a control block diagram of the electric vehicle charging load characteristic parameter identification method based on the complex coupling network multi-agent technology provided by the present invention.

[0057] Figure 2a This is the binary k-means clustering result based on restrained consistency control for one week of charging load data of an electric vehicle charging station in a financial center in the winter of 2020.

[0058] Figure 2b This is the binary k-means clustering result based on restrained consistency control for one week's charging load data of an electric vehicle charging station in a financial center in the spring of 2020.

[0059] Figure 2c This is the binary k-means clustering result based on restrained consistency control for one week's charging load data of an electric vehicle charging station in a financial center in the summer of 2020.

[0060] Figure 2d This is the binary k-means clustering result based on restrained consistency control for one week's charging load data of an electric vehicle charging station in a financial center in the fall of 2020. DETAILED DESCRIPTION

[0061] The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.

[0062] This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and a specific operation process, but the protection scope of the present invention is not limited to the following embodiments, and includes the following steps:

[0063] S1. Design a consistency control method to quickly obtain the initial cluster center;

[0064] S2. Use the binary k-means method to extract the probability distribution function of electric vehicle charging probability and charging start time.

[0065] The consistency control method is:

[0066]

[0067] in:

[0068] d i is the dissimilarity measure between data point i and data point j in the charging load data network;

[0069] Function f[V i (t i )] is a self-feedback function;

[0070] ε is the consistency control parameter, which indicates the data network coupling strength, ε>0;

[0071] V(t) represents the electric vehicle charging load at time t;

[0072] Function h(·) is the internal coupling function of the interaction between adjacent data points;

[0073] u i (t i ) is a local feedback controller;

[0074] in:

[0075] u i (t i ) = g i {h[s(t i )-V i (t i )]} (2)

[0076] in:

[0077] s(t i ) is the expected clustering boundary;

[0078] g i is the local feedback controller parameter, which is used to be the local feedback control gain of data point i.

[0079] The initial number of cluster centers k obtained by formula (1) is used to take the charging load data set V of electric vehicle charging stations in a typical scenario as a cluster. A group is taken out from the cluster in a loop, and k-means clustering is performed on it with a group number of 2. The two groups with the smallest sum of distances to the cluster center are selected and put back into the cluster until the total number of groups in the cluster reaches k.

[0080] The distance between each data point and the cluster center is calculated in each group:

[0081]

[0082] in:

[0083] x i 、x j are the data points in the i-th group and the j-th group respectively;

[0084] p is the number of data points in the group.

[0085] Based on the binary k-means clustering results, the probability distribution function of electric vehicle charging and charging period is obtained. The probability of electric vehicle charging is:

[0086]

[0087] in:

[0088] f i The probability of charging an electric vehicle, which is also the CP parameter of the electric vehicle;

[0089] y is the number of electric vehicle charging load data;

[0090] Z is the number of non-zero data;

[0091] i is the i-th period in a day, and w is the number of periods a day is divided into.

[0092] The probability distribution function of the electric vehicle charging period is obtained as follows:

[0093]

[0094] in:

[0095] h(t) is the probability distribution function of the electric vehicle charging period, which is also the CDPDF parameter;

[0096] μ c is the expected value of the charging start time of the charging pile;

[0097] σ c is the variance of the charging start time of the charging pile.

[0098] The determination of CP and CDPDF parameters of electric vehicle charging behavior prepares the conditions for electric vehicle charging load modeling. Based on this, users can be guided to choose the non-peak period of the electric vehicle starting charging time or the non-peak period of the power grid to complete charging without affecting their own needs, thereby reducing the charging load pressure of electric vehicle charging stations and the power grid.

[0099] Based on the charging load data of an electric vehicle charging station in a financial center in Hangzhou in 2020, a cluster analysis was performed on the charging load data of the electric vehicle charging station in each season. The charging load data of the electric vehicle charging station in the financial center for one week were extracted in the spring, summer, autumn and winter of 2020: January 6-January 12, April 13-April 19, August 10-August 16, and November 9-November 15, to verify the feasibility of the proposed consistent k-means clustering method.

[0100] Figure 2a-2d This is the clustering analysis result of charging load data in the four natural weeks of spring, summer, autumn and winter in 2020. The horizontal axis in the figure is the charging start time, and the vertical axis is the electric vehicle charging load.

[0101] against Figure 2a-2d It can be seen from the analysis that the consistency control method is used to quickly and accurately complete the initial clustering of charging load data in the three periods of 0-6, 6-13, and 13-24 by measuring the dissimilarity between adjacent data points of the charging load data set. The binary k-means clustering method is used to achieve clear distinction between the charging characteristics of electric vehicles in different groups. The demand for electric vehicle charging in the financial center is relatively high from 6 to 13, and the load peak occurs at around 9, with a peak load of nearly 24kW, which coincides with the rush hour. The demand for electric vehicle charging enters a stable stage from 0 to 6 and 13 to 24, and enters a sub-peak stage at 21:00. The sub-peak peak load in spring, autumn, and winter is about 13kW, and the sub-peak peak load in summer reaches 22kW, which is close to the peak peak. The proposed method uses the dissimilarity measurement between adjacent data points to quickly determine the initial cluster center of the electric vehicle load data, and uses the binary k-means clustering method to accurately capture the mathematical expectation value of the cluster center. It converges quickly and accurately obtains the cluster center, which prepares the conditions for the identification of electric vehicle charging characteristic parameters.

[0102] The present invention also provides an electric vehicle charging load characteristic parameter identification device using a complex coupling network multi-agent technology, comprising:

[0103] An initial cluster center obtaining unit, wherein the initial cluster center obtaining unit is used to design a consistency control method, introduce complex coupling network pinning consistency control into data cluster analysis, and quickly obtain an initial cluster center;

[0104] An electric vehicle charging load characteristic parameter identification unit is used to extract the electric vehicle charging probability and charging start time probability distribution function based on the binary k-means cluster analysis result.

[0105] The present invention also provides an electronic device, the electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus.

[0106] a memory for storing a computer program,

[0107] A processor is used to execute a computer program stored in a memory to implement the steps of the electric vehicle charging load characteristic parameter identification method using a complex coupled network multi-agent technology as described above.

[0108] The present invention also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the method for identifying characteristic parameters of electric vehicle charging load using the complex coupled network multi-agent technology described above are implemented.

[0109] The above-mentioned computer-readable storage medium can be any available medium or data storage device that can be accessed by the processor in the electronic device, including but not limited to magnetic storage such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc., optical storage such as CD, DVD, BD, HVD, etc., and semiconductor storage such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD), etc.

[0110] 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.

[0111] 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.

[0112] 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 The steps for the functions specified in one or more boxes.

[0113] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0114] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for identifying characteristic parameters of electric vehicle charging load based on complex coupling network multi-agent technology, characterized by: The electric vehicle charging load characteristic parameter identification method using complex coupling network multi-agent technology comprises the following steps: S1. Design a consistency control method, introduce complex coupling network constraint consistency control into data cluster analysis, and quickly obtain the initial cluster center; Each data updates its clustering status according to the dissimilarity measure with the adjacent data. When all data complete the update process, the initial selection of cluster centers is completed. Only a small amount of local feedback controllers need to be injected into the data network to achieve the reasonable setting of the data network clustering boundaries. S2. Using the binary k-means cluster analysis method, based on the binary k-means cluster analysis results, extract the probability distribution function of electric vehicle charging probability and charging start time; The consistency control method in step S1 is established by the following formula: in: d i is the dissimilarity measure between data point i and data point j in the charging load data network; Function f[V i (t i )] is a self-feedback function; ε is the consistency control parameter, which indicates the data network coupling strength, ε>0; V(t) represents the electric vehicle charging load at time t; Function h(·) is the internal coupling function of the interaction between adjacent data points; u i (t i ) is a local feedback controller; The u i (t i ) can be expressed as: u i (t i )=g i {h[s(t i )-V i (t i )]} in: s(t i ) is the expected clustering boundary; g i is the local feedback controller parameter, which is used to be the local feedback control gain of data point i.

2. The electric vehicle charging load characteristic parameter identification method based on complex coupling network multi-agent technology according to claim 1 is characterized by: In step S2, the probability of electric vehicle charging is obtained by the following formula: in: f i Probability of charging electric vehicles; y is the number of electric vehicle charging load data; Z is the number of non-zero data; i is the i-th period in a day, and w is the number of periods a day is divided into.

3. The electric vehicle charging load characteristic parameter identification method based on complex coupling network multi-agent technology according to claim 1 is characterized by: The probability distribution function of the electric vehicle charging period in step S2 is obtained by the following formula: in: h(t) is the probability distribution function of the electric vehicle charging period; σ c is the variance of the charging start time of the charging pile; μ c is the expected time for the charging pile to start charging.

4. A device for identifying characteristic parameters of electric vehicle charging load using complex coupling network multi-agent technology, characterized in that: The electric vehicle charging load characteristic parameter identification device using complex coupling network multi-agent technology includes: An initial cluster center obtaining unit, wherein the initial cluster center obtaining unit is used to design a consistency control method, introduce complex coupling network pinning consistency control into data cluster analysis, and quickly obtain an initial cluster center; An electric vehicle charging load characteristic parameter identification unit, wherein the electric vehicle charging load characteristic parameter identification unit is used to extract the electric vehicle charging probability and the charging start time probability distribution function based on the binary k-means cluster analysis result; The working process of the initial cluster center obtaining unit is as follows: The consistency control method is established by the following formula: in: d i is the dissimilarity measure between data point i and data point j in the charging load data network; Function f[V i (t i )] is a self-feedback function; ε is the consistency control parameter, which indicates the data network coupling strength, ε>0; V(t) represents the electric vehicle charging load at time t; Function h(·) is the internal coupling function of the interaction between adjacent data points; u i (t i ) is a local feedback controller; The u i (t i ) can be expressed as: u i (t i )=g i {h[s(t i )-V i (t i )]} in: s(t i ) is the expected clustering boundary; g i is the local feedback controller parameter, which is used to be the local feedback control gain of data point i.

5. An electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus, characterized in that: a memory for storing a computer program, A processor, wherein the processor is used to execute a computer program stored in a memory to implement the steps of the electric vehicle charging load characteristic parameter identification method using a complex coupled network multi-agent technology as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for identifying characteristic parameters of charging load of an electric vehicle using a complex coupled network multi-agent technology as claimed in any one of claims 1 to 3.

Images