Energy management method and system suitable for electric vehicle charging station

Abstract

The invention relates to an energy management method and system suitable for an electric vehicle charging station. The method comprises the steps that related electrical parameters of the charging station and energy management data of the charging station are acquired; establishing an energy management learning network of the charging station; training the energy management learning network to obtain a well trained energy management learning network; and the energy of the charging station is managed through the well-trained energy management learning network. According to the invention, multi-parameter collaborative accurate scheduling is realized, the operation cost of the charging station can be reduced, the voltage fluctuation of the DC bus is controlled, the SOC value of the super energy storage system is maintained in the optimal interval, the energy utilization efficiency and the stability of the power distribution network are improved, and the large-scale and intelligent operation requirements of the charging station are met.

Description

Technical Field

[0001] This invention relates to the field of energy management technology for electric vehicle charging stations, and more specifically, to an energy management method and system suitable for electric vehicle charging stations. Background Technology

[0002] With the rapid growth in the number of electric vehicles, the construction scale and usage frequency of charging stations continue to increase, and the scientific and efficient nature of their energy management has become a core issue of concern for the industry.

[0003] Currently, traditional charging station energy management relies heavily on fixed control strategies or simple logical judgments, which have significant limitations. On the one hand, it cannot dynamically adapt to multi-dimensional electrical parameters such as DC bus voltage fluctuations, changes in the SOC value of the super energy storage system, and differences in electric vehicle charging load power, resulting in a lack of flexibility in energy allocation. On the other hand, it does not fully incorporate peak-valley electricity price differences to optimize energy dispatch, which increases the operating costs of charging stations and may also bring instability to the distribution network. In addition, existing technologies lack energy management models capable of adaptively learning multi-parameter relationships, making it difficult to dynamically adjust the matching relationship between the distribution network output power, the charging and discharging power of the super energy storage system, and the charging power of electric vehicles based on real-time operating conditions. This leads to problems such as low utilization of energy storage resources and insufficient charging efficiency, failing to meet the needs of large-scale and intelligent operation of charging stations.

[0004] Therefore, there is an urgent need for a charging station energy management solution that can accurately integrate multi-source parameters and adaptively optimize energy distribution. Summary of the Invention

[0005] To address the aforementioned shortcomings or improvement needs of existing technologies, this paper provides an energy management method and system suitable for electric vehicle charging stations. This enables precise energy scheduling under multi-parameter coordination, improves charging station operating efficiency, reduces costs, and ensures stable operation of the power distribution network.

[0006] To achieve the above objectives, this application provides the following technical solution:

[0007] In a first aspect, embodiments of this application provide an energy management method suitable for electric vehicle charging stations, including:

[0008] Obtain relevant electrical parameters and energy management data of the charging station;

[0009] Establish a learning network for energy management of charging stations;

[0010] Train the energy management learning network to obtain a well-trained energy management learning network;

[0011] Energy management at charging stations is achieved through a well-trained energy management learning network.

[0012] The obtained electrical parameters related to the charging station, including the DC bus voltage of the charging station. SOC value of super energy storage system Electric vehicle side charging load power Electricity price and sampling time nodes , ;in, This represents the total number of sampling times.

[0013] Energy management instructions for charging stations include the output power of the distribution network. Output power of super energy storage system Electric vehicle charging power , ;in, This represents the total number of sampling times.

[0014] The energy management instructions for charging stations are determined by the relevant electrical parameters of the charging station based on the charging demand during peak and off-peak hours.

[0015] The calculation process for building the energy management learning network for charging stations is as follows:

[0016] The input matrix of the energy management learning network is constructed using the following formula. :

[0017] (1)

[0018] in, This represents the matrix transpose operation. This represents the number of neurons in the input layer.

[0019] The target output matrix of the energy management learning network is constructed using the following formula. :

[0020] (2)

[0021] in, The number of neurons in the hidden layer;

[0022] Initialize the parameters of the learning network, including the envelope input weight matrix. ;

[0023] The output matrix of the hidden layer is calculated using the following formula. :

[0024] (3)

[0025] By solving the following equation Estimate the output weight matrix :

[0026] (4)

[0027] in, Describing the l2 norm, Indicates the adaptive weighting coefficient. Indicates the adaptive control coefficient; The calculation can be performed using the following formula:

[0028] (5)

[0029] in, It is about The process coefficient, namely:

[0030] (6)

[0031] Output weight matrix After estimation, a well-trained energy management learning network is obtained.

[0032] The optimal output weight matrix is ​​obtained by solving formula (5) using an adaptive optimization algorithm. The process is as follows:

[0033] Initialize relevant parameters, including optimizing the population size. Maximum number of iterations ;

[0034] Define iteration label ,set up =1;

[0035] Initialize each optimization individual in Spatial vector position at the next iteration , ;

[0036] The optimization of each individual is calculated using formula (5). fitness value at time , ;

[0037] Calculate the optimization of each individual in Information concentration at the next iteration ,Right now:

[0038] (7)

[0039] in, and The first The maximum and minimum fitness values ​​in the next iteration. This is the deviation coefficient;

[0040] The attractiveness of other optimized individuals to the nth individual is calculated using the following formula. :

[0041] (8)

[0042] in, Initial attraction level, =1; Let be the spatial vector distance between the nth individual and the pth individual, i.e.:

[0043] (9)

[0044] Determine the current iteration number Is it greater than the maximum number of iterations? If not, then If so, then proceed to step 9.

[0045] Update each individual using the following formula: The spatial vector at this time, i.e.:

[0046] (10)

[0047] Jump to step 4;

[0048] Output the optimal output weight matrix .

[0049] The process of managing the energy of a charging station through a well-trained energy management learning network is as follows:

[0050] Obtain relevant electrical parameters of the charging station, including the DC bus voltage of the charging station. SOC value of super energy storage system Electric vehicle side charging load power Electricity price and sampling time nodes Construct the input matrix ;

[0051] The output matrix of the hidden layer is calculated using the following formula. :

[0052] (11)

[0053] The output matrix of the output layer is calculated using the following formula. :

[0054] (12)

[0055] pass Obtain the current energy management data of the charging station, i.e., the output power of the distribution network. Output power of super energy storage system and electric vehicle charging power .

[0056] Secondly, embodiments of this application provide an energy management system suitable for electric vehicle charging stations, comprising:

[0057] The charging station parameter acquisition module is used to obtain relevant electrical parameters and energy management data of the charging station.

[0058] The energy management learning network module is used to build an energy management learning network for charging stations.

[0059] The network training module is used to train the energy management learning network to obtain a well-trained energy management learning network.

[0060] The energy management control module is used to manage the energy of the charging station through a well-trained energy management learning network.

[0061] Compared with the prior art, the present invention has significant beneficial effects.

[0062] This method and system construct an intelligent energy dispatching system, achieving a dual improvement in economic benefits and system stability. Specific advantages are as follows:

[0063] In terms of peak-valley electricity price adaptation, it breaks through the limitations of traditional charging stations' passive electricity purchase and forms an optimal energy storage charging and discharging strategy for all time periods: During off-peak hours when electricity prices are low, the system automatically detects the status of the super energy storage system. If the optimal storage level is not reached, the system starts charging to maximize the storage of low-priced electricity. When peak hours arrive and electricity prices rise, the system prioritizes using the low-priced electricity stored in the energy storage system to power electric vehicles. Only when the stored energy is insufficient and the charging load continues to increase will the system moderately supplement the power supply from the distribution network. This strategy not only significantly reduces electricity purchase costs but also effectively diverts peak-hour grid load, alleviates the pressure on the distribution network from concentrated charging, reduces potential risks such as overload and voltage fluctuations, and lowers the difficulty of grid dispatching. In terms of multi-parameter collaborative control, it overcomes the drawbacks of traditional single-parameter control by integrating core parameters such as the charging station's DC bus voltage, the super energy storage system's SOC value, the real-time charging load power of electric vehicles, and electricity prices to construct a dynamic adaptation model. The system collects data from each parameter in real time and optimizes it through real-time calculations via an energy management learning network, achieving efficient real-time management of the energy of electric vehicle charging piles. Attached Figure Description

[0064] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a flowchart illustrating the steps of an energy management method for electric vehicle charging stations provided in an embodiment of the present invention;

[0066] Figure 2 This is a module connection diagram of an energy management system suitable for electric vehicle charging stations provided in an embodiment of the present invention;

[0067] Figure 3 This is a flowchart of the calculation process of a charging station energy management learning network provided in an embodiment of the present invention;

[0068] Figure 4 This is a flowchart of the calculation of the optimal output weight moments using an adaptive optimization algorithm provided in an embodiment of the present invention.

[0069] Figure 5 This is a schematic diagram illustrating how a well-trained energy management learning network can manage the energy of a charging station, as provided in an embodiment of the present invention. Detailed Implementation

[0070] The technical solutions of the embodiments of this application will now be described with reference to the accompanying drawings. It should be noted that similar reference numerals and letters in the following drawings indicate similar items; therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0071] The terms “comprising,” “including,” or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0072] The terms “first,” “second,” etc., are used only to distinguish one entity or operation from another, and should not be construed as indicating or implying relative importance, nor as requiring or implying any such actual relationship or order between these entities or operations.

[0073] like Figure 1 The diagram shows a step-by-step illustration of an energy management method for electric vehicle charging stations provided by an embodiment of the present invention, including the following steps:

[0074] Step 1: Obtain the relevant electrical parameters and energy management data of the charging station;

[0075] Step 2: Establish an energy management learning network for charging stations;

[0076] Step 3: Train the energy management learning network to obtain a well-trained energy management learning network;

[0077] Step 4: Manage the energy of the charging station through a well-trained energy management learning network.

[0078] like Figure 2 The diagram shown is a module connection diagram of an energy management system suitable for electric vehicle charging stations provided by an embodiment of the present invention, including:

[0079] The charging station parameter acquisition module is used to obtain relevant electrical parameters and energy management data of the charging station.

[0080] The energy management learning network module is used to build an energy management learning network for charging stations.

[0081] The network training module is used to train the energy management learning network to obtain a well-trained energy management learning network.

[0082] The energy management control module is used to manage the energy of the charging station through a well-trained energy management learning network.

[0083] like Figure 3 The diagram shown is a calculation flowchart of a charging station energy management learning network provided in an embodiment of the present invention. The specific calculation process is as follows:

[0084] Step A1: Construct the input matrix of the energy management learning network using the following formula. :

[0085] (1)

[0086] in, This represents the matrix transpose operation. This represents the number of neurons in the input layer.

[0087] Step A2: Construct the target output matrix of the energy management learning network using the following formula. :

[0088] (2)

[0089] in, The number of neurons in the hidden layer;

[0090] Step A3: Initialize the relevant parameters of the learning network, and input the envelope weight matrix. ;

[0091] Step A4: Calculate the output matrix of the hidden layer using the following formula. :

[0092] (3)

[0093] Step A5: Solve the following equation Estimate the output weight matrix :

[0094] (4)

[0095] in, Describing the l2 norm, Indicates the adaptive weighting coefficient. Indicates the adaptive control coefficient; The calculation can be performed using the following formula:

[0096] (5)

[0097] in, It is about The process coefficient, namely:

[0098] (6)

[0099] Step A6: Output the weight matrix After estimation, a well-trained energy management learning network is obtained.

[0100] like Figure 4 As shown in the figure, the calculation flowchart of an adaptive optimization algorithm for obtaining the optimal output weight moments provided in this embodiment of the invention is as follows:

[0101] Step B1: Initialize relevant parameters, including optimizing the population size. Maximum number of iterations ;

[0102] Step B2: Define iteration labels ,set up =1;

[0103] Step B3: Initialize each optimized individual in Spatial vector position at the next iteration , ;

[0104] Step B4: Calculate the performance of each optimized individual using formula (5). fitness value at time , ;

[0105] Step B5: Calculate the performance of each optimized individual. Information concentration at the next iteration ,Right now:

[0106] (7)

[0107] in, and The first The maximum and minimum fitness values ​​in the next iteration. This is the deviation coefficient;

[0108] Step B6: Calculate the attraction of other optimized individuals to the nth individual using the following formula. :

[0109] (8)

[0110] in, Initial attraction level, =1; Let be the spatial vector distance between the nth individual and the pth individual, i.e.:

[0111] (9)

[0112] Step B7: Determine the current iteration number Is it greater than the maximum number of iterations? If not, then If so, then proceed to step B9;

[0113] Step B8: Update each individual's... The spatial vector at this time, i.e.:

[0114] (10)

[0115] Jump to step B4;

[0116] Step B9: Output the optimal output weight matrix .

[0117] like Figure 5 As shown in the figure, an embodiment of the present invention provides a schematic diagram of managing the energy of a charging station through a well-trained energy management learning network, as detailed below:

[0118] Step C1: Obtain relevant electrical parameters of the charging station, including the DC bus voltage of the charging station. SOC value of super energy storage system Electric vehicle side charging load power Electricity price and sampling time nodes Construct the input matrix ;

[0119] Step C2: Calculate the output matrix of the hidden layer using the following formula. :

[0120] (11)

[0121] The output matrix of the output layer is calculated using the following formula. :

[0122] (12)

[0123] Step C3: Through Obtain the current energy management data of the charging station, i.e., the output power of the distribution network. Output power of super energy storage system and electric vehicle charging power .

[0124] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. An energy management method suitable for electric vehicle charging stations, characterized in that, include: Obtain relevant electrical parameters and energy management data of the charging station; Establish a learning network for energy management of charging stations; Train the energy management learning network to obtain a well-trained energy management learning network; Energy management at charging stations is achieved through a well-trained energy management learning network.

2. The energy management method for electric vehicle charging stations according to claim 1, characterized in that, The obtained electrical parameters related to the charging station, including the DC bus voltage of the charging station. SOC value of super energy storage system Electric vehicle side charging load power Electricity price and sampling time nodes , ;in, This represents the total number of sampling times. Energy management instructions for charging stations include the output power of the distribution network. Output power of super energy storage system Electric vehicle charging power , ;in, This represents the total number of sampling times.

3. The energy management method for electric vehicle charging stations according to claim 2, characterized in that, The energy management instructions for charging stations are determined by the relevant electrical parameters of the charging station based on the charging demand during peak and off-peak hours.

4. The energy management method for electric vehicle charging stations according to claim 1, characterized in that, The calculation process for building the energy management learning network for charging stations is as follows: The input matrix of the energy management learning network is constructed using the following formula. : （1） in, This represents the matrix transpose operation. This represents the number of neurons in the input layer. The target output matrix of the energy management learning network is constructed using the following formula. : （2） in, The number of neurons in the hidden layer; Initialize the parameters of the learning network, including the envelope input weight matrix. ; The output matrix of the hidden layer is calculated using the following formula. : （3） By solving the following equation Estimate the output weight matrix : （4） in, Describing the l2 norm, Indicates the adaptive weighting coefficient. Indicates the adaptive control coefficient; The calculation can be performed using the following formula: （5） in, It is about The process coefficient, namely: （6） Output weight matrix After estimation, a well-trained energy management learning network is obtained.

5. The energy management method for electric vehicle charging stations according to claim 4, characterized in that, The optimal output weight matrix is ​​obtained by solving formula (5) using an adaptive optimization algorithm. The process is as follows: Initialize relevant parameters, including optimizing the population size. Maximum number of iterations ; Define iteration label ,set up =1; Initialize each optimization individual in Spatial vector position at the next iteration , ; The optimization of each individual is calculated using formula (5). fitness value at time , ; Calculate the optimization of each individual in Information concentration at the next iteration ,Right now: （7） in, and The first The maximum and minimum fitness values ​​in the next iteration. This is the deviation coefficient; The attractiveness of other optimized individuals to the nth individual is calculated using the following formula. : （8） in, Initial attraction level, =1; Let be the spatial vector distance between the nth individual and the pth individual, i.e.: （9） Determine the current iteration number Is it greater than the maximum number of iterations? If not, then If so, then proceed to step 9. Update each individual using the following formula: The spatial vector at this time, i.e.: （10） Jump to step 4; Output the optimal output weight matrix .

6. The energy management method for electric vehicle charging stations according to claim 1, characterized in that, The process of managing the energy of a charging station through a well-trained energy management learning network is as follows: Obtain relevant electrical parameters of the charging station, including the DC bus voltage of the charging station. SOC value of super energy storage system Electric vehicle side charging load power Electricity price and sampling time nodes Construct the input matrix ; The output matrix of the hidden layer is calculated using the following formula. : （11） The output matrix of the output layer is calculated using the following formula. : （12） pass Obtain the current energy management data of the charging station, i.e., the output power of the distribution network. Output power of super energy storage system and electric vehicle charging power .

7. An energy management system suitable for electric vehicle charging stations, characterized in that, include: The charging station parameter acquisition module is used to obtain relevant electrical parameters and energy management data of the charging station. The energy management learning network module is used to build an energy management learning network for charging stations. The network training module is used to train the energy management learning network to obtain a well-trained energy management learning network. The energy management control module is used to manage the energy of the charging station through a well-trained energy management learning network.

Images