Optimization control method for load distribution of charging pile clusters for smart charging stations

Abstract

This invention relates to the technical field of intelligent scheduling, specifically to a method for optimizing and controlling the load allocation of charging pile clusters in intelligent charging stations. The method includes: analyzing load usage data and temperature data of multiple charging piles over a historical time period to determine the thermal effect interference information of each charging pile, wherein the thermal effect interference information characterizes the heat dissipation interference of the corresponding charging pile on other charging piles; predicting load demand based on the historical load usage information of the multiple charging piles to obtain load demand prediction information; and performing particle swarm optimization on the load allocation of the multiple charging piles based on the load demand prediction information and the thermal effect interference information of each charging pile to obtain a target load allocation scheme. This invention can impose corresponding constraints on the particle swarm optimization process from the thermal effect dimension, making the final output target load allocation scheme more accurate and reliable.

Description

Technical Field

[0001] This invention relates to the technical field of intelligent scheduling, and more specifically to a method for optimizing load distribution control of charging pile clusters for intelligent charging stations. Background Technology

[0002] Charging stations' charging piles are devices that provide electrical energy to electric vehicles, responsible for transmitting power to the vehicle's battery. They typically include charging interfaces, a charging control system, and monitoring equipment. When multiple charging piles operate simultaneously, uneven power load may occur, leading to overload risks. Therefore, optimizing load allocation is crucial. It ensures the rational distribution of power resources, avoids equipment overload, and reduces the risk of failure. Furthermore, optimizing load allocation improves power utilization efficiency, reduces energy waste, extends equipment lifespan, and enhances the stability and reliability of charging services by dynamically adjusting the charging pile load to cope with changes in power demand at different times.

[0003] Generally, a Long Short-Term Memory (LSTM) prediction algorithm is used to predict the load demand of each charging station in the future by analyzing its past load usage. Based on the prediction results, a Particle Swarm Optimization (PSO) algorithm is used to adjust the load distribution of each charging station, ensuring reasonable scheduling of the charging station load, avoiding overload and energy waste, achieving load balance and efficient utilization of power resources, thereby improving overall operating efficiency, reducing power system risks, and enhancing the user charging experience.

[0004] However, in application, it was found that each charging pile generates heat during operation. Uneven load distribution may cause the temperature of some charging piles to rise, which in turn affects the heat dissipation of adjacent charging piles, generating thermal interference and affecting the stability and safety of the entire charging system. However, when using particle swarm optimization (PSO) for charging pile cluster load allocation, the fitness of each determined scheme only considers the rational scheduling problem. While this method can maximize scheduling efficiency, it fails to fully consider the impact of thermal effects. In other words, the accuracy of charging pile cluster load allocation schemes obtained based on existing technology is relatively low. Summary of the Invention

[0005] To address the technical problem of low accuracy in charging pile cluster load allocation schemes obtained based on existing technologies, the present invention aims to provide an optimized control method for charging pile cluster load allocation in smart charging stations. The specific technical solution adopted is as follows:

[0006] In a first aspect, one embodiment of the present invention provides a method for optimizing load distribution control of charging pile clusters in smart charging stations, the method comprising:

[0007] Analyze the load usage data and temperature data of multiple charging piles over a historical period to determine the thermal effect interference information of each charging pile, wherein the thermal effect interference information is used to characterize the heat dissipation interference of the corresponding charging pile on other charging piles.

[0008] Load demand forecasting information is obtained by performing load demand forecasting based on the historical load usage information of the multiple charging piles.

[0009] Based on the load demand forecast information and the thermal effect interference information of each charging pile, particle swarm optimization is performed on the load allocation of the multiple charging piles to obtain the target load allocation scheme.

[0010] In one embodiment, analyzing load usage data and temperature data of multiple charging piles over a historical time period to determine the thermal effect interference information of each charging pile includes:

[0011] In the multiple historical time segments included in the historical time period, the temperature rise characteristics of each charging pile in each historical time segment are analyzed to distinguish them from the temperature rise characteristics of other charging piles in the same historical time segment, so as to obtain the independent temperature rise index corresponding to each charging pile in each historical time segment.

[0012] The differences between different independent temperature rise indices for different charging piles in each historical time segment were analyzed to obtain multiple heat dissipation interference indices for each charging pile in each historical time segment.

[0013] Based on multiple heat dissipation interference indices corresponding to each charging pile in each historical time segment, correlation analysis is performed on different temperature data sequences corresponding to different charging piles in the historical time segment to obtain multiple heat dissipation impact indices corresponding to each charging pile. The thermal effect interference information of each charging pile includes multiple heat dissipation impact indices corresponding to that charging pile.

[0014] In one embodiment, the step of analyzing the temperature rise characteristics of each charging pile in each historical time segment within the multiple historical time segments included in the historical time period, and comparing them with the temperature rise characteristics of other charging piles in the same historical time segment to obtain an independent temperature rise index for each charging pile in each historical time segment, includes:

[0015] In the multiple historical time segments included in the historical time period, the ratio of load usage data to temperature data for each charging pile in each historical time segment is calculated to obtain the temperature rise characteristics of each charging pile in each historical time segment.

[0016] Calculate the temperature rise characteristics of each charging pile in each historical time segment and the difference between the temperature rise characteristics of other charging piles in the same historical time segment to obtain multiple characteristic differences for each charging pile in each historical time segment.

[0017] Calculate the sum of multiple feature differences for each charging pile in each historical time segment to obtain the feature difference sum for each charging pile in each historical time segment;

[0018] The characteristic differences and values ​​of each charging pile in each historical time segment are normalized to obtain the independent temperature rise index of each charging pile in each historical time segment.

[0019] In one embodiment, the analysis of the differences between different independent temperature rise indices for different charging piles in each historical time segment, to obtain multiple heat dissipation interference indices for each charging pile in each historical time segment, includes:

[0020] Calculate the ratio of the independent temperature rise index of each charging pile in each historical time segment to the independent temperature rise index of other charging piles in the same historical time segment, so as to obtain multiple independent deviation indices for each charging pile in each historical time segment.

[0021] The distance between each charging pile and other charging piles, multiple independent deviation indices and multiple temperature difference coefficients corresponding to each charging pile in each historical time segment are analyzed to obtain multiple heat dissipation interference indices corresponding to each charging pile in each historical time segment. The temperature difference coefficient represents the numerical relationship between the temperature data of the corresponding charging pile in the corresponding historical time segment and the temperature data of other charging piles in the corresponding historical time segment.

[0022] In one embodiment, the analysis of the distance between each charging pile and other charging piles, multiple independent deviation indices and multiple temperature difference coefficients corresponding to each charging pile in each historical time segment, to obtain multiple heat dissipation interference indices corresponding to each charging pile in each historical time segment, includes:

[0023] The ratios of multiple independent target deviation indices to target distances are calculated to obtain multiple target interference indices. The multiple independent target deviation indices are the multiple independent deviation indices of the first charging pile to the second charging pile in multiple historical time segments. The target distance is the distance between the first charging pile and the second charging pile. The first charging pile and the second charging pile are any two different charging piles among the multiple charging piles.

[0024] In the plurality of target interference indices, the product of each target interference index and the corresponding target temperature difference coefficient is calculated to obtain the heat dissipation interference index of the first charging pile on the second charging pile in each historical time segment, wherein the plurality of target temperature difference coefficients correspond one-to-one with the plurality of historical time segments.

[0025] When the temperature data of the first charging pile in the corresponding historical time segment is greater than the temperature data of the second charging pile in the corresponding historical time segment, the value of the corresponding target temperature difference coefficient is 1;

[0026] When the temperature data of the first charging pile in the corresponding historical time segment is less than or equal to the temperature data of the second charging pile in the corresponding historical time segment, the value of the corresponding target temperature difference coefficient is 0.

[0027] In one embodiment, the correlation analysis is performed on different temperature data sequences corresponding to different charging piles within the historical time period based on multiple heat dissipation interference indices corresponding to each charging pile in each historical time segment, to obtain multiple heat dissipation impact indices corresponding to each charging pile, including:

[0028] A first temperature sequence and a second temperature sequence are obtained, wherein the first temperature sequence is a sequence composed of multiple temperature data of the first charging pile in multiple historical time segments, and the second temperature sequence is a sequence composed of multiple temperature data of the second charging pile in multiple historical time segments, and the first charging pile and the second charging pile are any two different charging piles among the multiple charging piles.

[0029] Based on the multiple heat dissipation interference indices of the first charging pile to the second charging pile, the second temperature sequence is corrected to obtain the corrected temperature sequence.

[0030] Correlation analysis is performed on the first temperature sequence and the corrected temperature sequence to obtain the heat dissipation impact index of the first charging pile on the second charging pile.

[0031] In one embodiment, in the particle swarm optimization process, the individual optimality and the global optimality are determined based on the target fitness of each particle. The steps for obtaining the target fitness of each particle in the particle swarm optimization process include:

[0032] Based on the thermal effect interference information of each charging pile and the load allocation scheme indicated by each particle, determine the fitness correction coefficient corresponding to each particle.

[0033] The initial fitness of each particle is corrected based on the fitness correction coefficient corresponding to that particle, so as to obtain the target fitness of each particle.

[0034] In one embodiment, determining the fitness correction coefficient for each particle based on the thermal effect interference information of each charging pile and the load allocation scheme indicated by each particle includes:

[0035] Based on the load allocation scheme indicated by each particle, determine the load configuration corresponding to each charging pile in each particle;

[0036] The load configuration differences of multiple charging piles in each particle are analyzed to determine the interfering charging piles corresponding to each charging pile in each particle, wherein the load configuration of the interfering charging piles in the corresponding particle is greater than the load configuration of the corresponding charging piles in the corresponding particle.

[0037] Based on the thermal effect interference information of each charging pile, and the load configuration difference between each charging pile and the corresponding interfering charging pile in each particle, the pile coefficient of each charging pile in each particle is determined.

[0038] The pile coefficient and load configuration of each charging pile in each particle are analyzed to determine the fitness correction coefficient for each particle.

[0039] In one embodiment, the thermal effect interference information of each charging pile includes multiple heat dissipation impact indices corresponding to that charging pile.

[0040] The determination of the pile coefficient for each charging pile in each particle, based on the thermal effect interference information of each charging pile and the load configuration difference between each charging pile and the corresponding interfering charging pile in each particle, includes:

[0041] Calculate the difference in load configuration between each charging pile in each particle and the corresponding interfering charging pile to obtain multiple load configuration differences for each charging pile in each particle.

[0042] Calculate the product of multiple load configuration differences for each charging pile in each particle and the corresponding multiple heat dissipation influence coefficients to obtain multiple initial coefficients for each charging pile in each particle.

[0043] Calculate the sum of multiple initial coefficients corresponding to each charging pile in each particle to obtain the pile coefficient corresponding to each charging pile in each particle.

[0044] In one embodiment, the analysis of the pile coefficient and load configuration corresponding to each charging pile in each particle to determine the fitness correction coefficient corresponding to each particle includes:

[0045] Calculate the product of the pile coefficient and the load configuration for each charging pile in each particle to obtain the sub-correction coefficient for each charging pile in each particle.

[0046] Calculate the sum of the sub-correction coefficients corresponding to the multiple charging piles in each particle to determine the fitness correction coefficient for each particle.

[0047] Secondly, another embodiment of the present invention provides a charging pile cluster load distribution optimization control device for smart charging stations, the device comprising:

[0048] The data analysis module is used to analyze the load usage data and temperature data of multiple charging piles in a historical time period to determine the thermal effect interference information of each charging pile. The thermal effect interference information is used to characterize the heat dissipation interference of the corresponding charging pile to other charging piles.

[0049] The prediction module is used to predict load demand based on the historical load usage information of the multiple charging piles, and obtain load demand prediction information.

[0050] The particle swarm processing module is used to perform particle swarm optimization processing on the load allocation of the multiple charging piles based on the load demand prediction information and the thermal effect interference information of each charging pile, so as to obtain the target load allocation scheme.

[0051] Thirdly, in another embodiment of the present invention, an electronic device is provided, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method described in the first aspect.

[0052] Fourthly, in another embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0053] The present invention has the following beneficial effects:

[0054] This invention first analyzes the load usage and temperature data of multiple charging piles over a historical period to determine the heat dissipation interference of each charging pile on other charging piles. Then, it predicts the load demand based on the historical load usage information of multiple charging piles to determine the predicted load demand information of multiple charging piles in the future period. Combined with the aforementioned heat dissipation interference, it performs particle swarm optimization to impose corresponding constraints on the particle swarm optimization process from the perspective of thermal effects. This makes the load allocation of multiple charging piles in the future period more in line with the actual usage of multiple charging piles, and makes the final output target load allocation scheme more accurate and reliable. Attached Figure Description

[0055] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a schematic flowchart illustrating a method for optimizing load distribution in a charging pile cluster for smart charging stations, provided in one embodiment of the present invention.

[0057] Figure 2 This is a schematic diagram of the structure of a charging pile cluster load distribution optimization control device for smart charging stations, provided in one embodiment of the present invention.

[0058] Figure 3 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0059] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the charging pile cluster load distribution optimization control method for smart charging stations proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0061] The specific scheme of the charging pile cluster load distribution optimization control method for smart charging stations provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0062] This invention proposes an optimized control method for load distribution in charging pile clusters for smart charging stations. Please refer to [link / reference]. Figure 1 The diagram illustrates a schematic flowchart of a charging pile cluster load allocation optimization control method for smart charging stations, provided by an embodiment of the present invention. The method includes the following steps:

[0063] Step S1: Analyze the load usage data and temperature data of multiple charging piles over a historical period to determine the thermal effect interference information of each charging pile.

[0064] The thermal effect interference information is used to characterize the heat dissipation interference of the corresponding charging pile on other charging piles.

[0065] The aforementioned multiple charging piles can be understood as multiple charging piles set up within a smart charging station for use by electric vehicles. The aforementioned historical time period can be understood as any time period before the current moment or the current date. For example, the historical time period can be defined as the time period 10 hours prior to the current moment, or the historical time period can be defined as the 24 hours indicated by the day before the current date.

[0066] The load of a charging pile can be understood as the total charging power of the charging pile within a corresponding time period or time segment. The temperature of a charging pile can be understood as the maximum or average temperature measured within a corresponding time period or time segment.

[0067] Specifically, the analysis of load usage data and temperature data of multiple charging piles over a historical time period to determine the thermal effect interference information of each charging pile includes:

[0068] In the multiple historical time segments included in the historical time period, the temperature rise characteristics of each charging pile in each historical time segment are analyzed to distinguish them from the temperature rise characteristics of other charging piles in the same historical time segment, so as to obtain the independent temperature rise index corresponding to each charging pile in each historical time segment.

[0069] The differences between different independent temperature rise indices for different charging piles in each historical time segment were analyzed to obtain multiple heat dissipation interference indices for each charging pile in each historical time segment.

[0070] Based on multiple heat dissipation interference indices corresponding to each charging pile in each historical time segment, correlation analysis is performed on different temperature data sequences corresponding to different charging piles in the historical time segment to obtain multiple heat dissipation impact indices corresponding to each charging pile. The thermal effect interference information of each charging pile includes multiple heat dissipation impact indices corresponding to that charging pile.

[0071] In the above process, by dividing the historical time period into multiple historical time segments, fine-grained analysis of the load usage data and temperature data of multiple charging piles within the historical time period can be achieved, which can improve the accuracy of thermal effect interference information.

[0072] In the application, historical time periods can be divided by hours. For example, if a historical time period corresponds to 24 hours, it can be divided into 24 historical time segments by hours.

[0073] The temperature rise independence index is used to represent the independence of a charging pile during the temperature rise process. The higher the temperature rise independence index, the stronger the independence of the corresponding charging pile during the temperature rise process, which means that the corresponding charging pile is less affected by the thermal effects of other charging piles during the temperature rise process, and vice versa.

[0074] The heat dissipation interference index is used to represent the influence coefficient of the corresponding charging pile on the thermal effect interference of other charging piles. The larger the heat dissipation interference index, the higher the influence coefficient of the corresponding charging pile on the thermal effect interference of other charging piles, and vice versa.

[0075] The heat dissipation impact index is used to indicate the degree of thermal interference that a corresponding charging pile causes to other charging piles. The higher the heat dissipation interference index, the more serious the thermal interference that the corresponding charging pile causes to other charging piles, and vice versa.

[0076] Furthermore, within the multiple historical time segments included in the historical time period, the difference between the temperature rise characteristics of each charging pile in each historical time segment and the temperature rise characteristics of other charging piles in that historical time segment is analyzed to obtain the independent temperature rise index corresponding to each charging pile in each historical time segment, including:

[0077] In the multiple historical time segments included in the historical time period, the ratio of load usage data to temperature data for each charging pile in each historical time segment is calculated to obtain the temperature rise characteristics of each charging pile in each historical time segment.

[0078] Calculate the temperature rise characteristics of each charging pile in each historical time segment and the difference between the temperature rise characteristics of other charging piles in the same historical time segment to obtain multiple characteristic differences for each charging pile in each historical time segment.

[0079] Calculate the sum of multiple feature differences for each charging pile in each historical time segment to obtain the feature difference sum for each charging pile in each historical time segment;

[0080] The characteristic differences and values ​​of each charging pile in each historical time segment are normalized to obtain the independent temperature rise index of each charging pile in each historical time segment.

[0081] It's important to note that charging stations consume electrical energy during use, and this energy conversion generates heat. The higher the current, the more vigorous the movement of charges and the more intense the chemical reactions within the battery, resulting in increased resistance heat. Therefore, the higher the total power during charging, the more charge is consumed, requiring a larger current. This also strengthens the resistance and thermal effect of the conductors within the battery, leading to more heat generation. In other words, the use of charge and the generation of heat are directly proportional.

[0082] For each charging station, the consumption of charge directly affects the heat it generates. Therefore, ideally, the ratio of load usage data to temperature data for different charging stations should be consistent. However, in real-world scenarios, the ratio of load usage data to temperature data can change due to heat dissipation interference from other charging stations. If a charging station is more severely affected by the heat dissipation interference from other charging stations, the difference between the ratio of that charging station and the ratio of other charging stations will be greater, and vice versa. Based on this, by comparing the differences in the ratios of different charging stations, the independence of the temperature rise of each charging station can be accurately quantified.

[0083] For example, the independent temperature rise index of the i-th charging pile among multiple charging piles in the t-th historical time segment (t is a positive integer, and the maximum value of t is the total number of historical time segments M). It can be represented as:

[0084]

[0085] Where f(.) represents the maximum-minimum normalization function, and N represents the total number of charging piles. This represents the load usage data of the i-th charging pile in the t-th historical time segment. This represents the temperature data of the i-th charging pile within the t-th historical time segment. This represents the load usage data of the j-th charging pile in the t-th historical time segment. This represents the temperature data of the j-th charging pile within the t-th historical time segment. This can be viewed as the temperature rise characteristic of the i-th charging pile within the t-th historical time segment. This can be viewed as the temperature rise characteristic of the j-th charging pile within the t-th historical time segment.

[0086] Furthermore, the analysis examines the differences between different independent temperature rise indices for different charging piles in each historical time segment to obtain multiple heat dissipation interference indices for each charging pile in each historical time segment, including:

[0087] Calculate the ratio of the independent temperature rise index of each charging pile in each historical time segment to the independent temperature rise index of other charging piles in the same historical time segment, so as to obtain multiple independent deviation indices for each charging pile in each historical time segment.

[0088] The distance between each charging pile and other charging piles, multiple independent deviation indices and multiple temperature difference coefficients corresponding to each charging pile in each historical time segment are analyzed to obtain multiple heat dissipation interference indices corresponding to each charging pile in each historical time segment. The temperature difference coefficient represents the numerical relationship between the temperature data of the corresponding charging pile in the corresponding historical time segment and the temperature data of other charging piles in the corresponding historical time segment.

[0089] Furthermore, the analysis examines the distance between each charging pile and other charging piles, multiple independent deviation indices for each charging pile in each historical time segment, and multiple temperature difference coefficients to obtain multiple heat dissipation interference indices for each charging pile in each historical time segment, including:

[0090] The ratios of multiple independent target deviation indices to target distances are calculated to obtain multiple target interference indices. The multiple independent target deviation indices are the multiple independent deviation indices of the first charging pile to the second charging pile in multiple historical time segments. The target distance is the distance between the first charging pile and the second charging pile. The first charging pile and the second charging pile are any two different charging piles among the multiple charging piles.

[0091] In the plurality of target interference indices, the product of each target interference index and the corresponding target temperature difference coefficient is calculated to obtain the heat dissipation interference index of the first charging pile on the second charging pile in each historical time segment, wherein the plurality of target temperature difference coefficients correspond one-to-one with the plurality of historical time segments.

[0092] When the temperature data of the first charging pile in the corresponding historical time segment is greater than the temperature data of the second charging pile in the corresponding historical time segment, the value of the corresponding target temperature difference coefficient is 1;

[0093] When the temperature data of the first charging pile in the corresponding historical time segment is less than or equal to the temperature data of the second charging pile in the corresponding historical time segment, the value of the corresponding target temperature difference coefficient is 0.

[0094] In the above settings, in addition to analyzing the differences in the independent temperature rise index of different charging piles in the same historical time segment, the distance between different charging piles and the temperature data differences between different charging piles are further analyzed to better adapt to the location distribution and historical usage of multiple charging piles, making the calculated heat dissipation interference index more accurate and reliable.

[0095] The closer the two charging piles are, the more severe the heat dissipation interference from the other charging pile will be to one of the charging piles. The target temperature difference coefficient is set to avoid the situation where the charging pile with the lower temperature data is regarded as the charging pile that causes heat dissipation interference to a certain charging pile, so as to make the heat dissipation interference index more accurately calculated by combining the actual temperature data of the two charging piles.

[0096] For example, within the t-th historical time segment, the heat dissipation interference index of the i-th charging pile on the j-th charging pile. It can be represented as:

[0097]

[0098]

[0099] in, This represents the distance between the i-th charging pile and the j-th charging pile. This represents the independent temperature rise index of the i-th charging pile within the t-th historical time segment. This represents the independent temperature rise index of the j-th charging pile within the t-th historical time segment. This can be understood as the independent deviation index of the i-th charging pile relative to the j-th charging pile within the t-th historical time segment. This represents the target temperature difference coefficient between the i-th charging pile and the j-th charging pile within the t-th historical time segment. This represents the temperature data of the i-th charging pile within the t-th historical time segment. This represents the temperature data of the j-th charging pile within the t-th historical time segment.

[0100] Furthermore, based on multiple heat dissipation interference indices corresponding to each charging pile in each historical time segment, correlation analysis is performed on different temperature data sequences corresponding to different charging piles within the historical time segment to obtain multiple heat dissipation impact indices corresponding to each charging pile, including:

[0101] A first temperature sequence and a second temperature sequence are obtained, wherein the first temperature sequence is a sequence composed of multiple temperature data of the first charging pile in multiple historical time segments, and the second temperature sequence is a sequence composed of multiple temperature data of the second charging pile in multiple historical time segments, and the first charging pile and the second charging pile are any two different charging piles among the multiple charging piles.

[0102] Based on the multiple heat dissipation interference indices of the first charging pile to the second charging pile, the second temperature sequence is corrected to obtain the corrected temperature sequence.

[0103] Correlation analysis is performed on the first temperature sequence and the corrected temperature sequence to obtain the heat dissipation impact index of the first charging pile on the second charging pile.

[0104] Specifically, correlation analysis can be performed on the first temperature sequence and the corrected temperature sequence based on the Pearson correlation coefficient to obtain the heat dissipation impact index of the first charging pile on the second charging pile.

[0105] For example, if the temperature sequence of the i-th charging pile among multiple charging piles is set... (This can be understood as the aforementioned first temperature sequence) is as follows:

[0106]

[0107] The corrected temperature sequence of the j-th charging station among multiple charging stations (This can be understood as the aforementioned corrected temperature sequence) is as follows:

[0108]

[0109] in, This represents the heat dissipation interference index of the i-th charging pile to the j-th charging pile in the first historical time segment, and so on for subsequent charging piles. This represents the heat dissipation interference index of the i-th charging pile to the j-th charging pile in the M-th historical time segment, where M is the total number of historical time segments. This represents the temperature data of the j-th charging pile in the first historical time segment. This represents the temperature data of the j-th charging pile in the second historical time segment, and so on for subsequent charging piles. This represents the temperature data of the j-th charging pile in the M-th historical time segment.

[0110] Then the heat dissipation impact index of the i-th charging pile on the j-th charging pile It can be represented as:

[0111]

[0112] in, [] represents the function used to calculate the Pearson correlation coefficient.

[0113] Step S2: Based on the historical load usage information of the multiple charging piles, perform load demand prediction to obtain load demand prediction information.

[0114] The historical load usage information includes load usage data for each charging station across multiple historical time segments.

[0115] For example, multiple load usage data of each charging pile can be fitted (e.g., using linear regression, multinomial fitting, probability distribution fitting, etc.) to obtain a fitting function corresponding to each charging pile. Based on the fitting function corresponding to each charging pile, the load forecast usage data of the charging pile in the future time period can be predicted. Then, the multiple load forecast usage data of multiple charging piles can be summarized to form the load demand forecast information.

[0116] Step S3: Based on the load demand prediction information and the thermal effect interference information of each charging pile, perform particle swarm optimization on the load allocation of the multiple charging piles to obtain the target load allocation scheme.

[0117] Furthermore, in the particle swarm optimization process, the individual optimality and the global optimality are determined based on the target fitness of each particle. The steps for obtaining the target fitness of each particle in the particle swarm optimization process include:

[0118] Based on the thermal effect interference information of each charging pile and the load allocation scheme indicated by each particle, determine the fitness correction coefficient corresponding to each particle.

[0119] The initial fitness of each particle is corrected based on the fitness correction coefficient corresponding to that particle, so as to obtain the target fitness of each particle.

[0120] The initial fitness of a particle can be understood as the particle fitness calculated based on a conventional fitness calculation function.

[0121] In applications, the fitness calculation function can be used to comprehensively evaluate from multiple aspects, such as load balance, system stability, and charging efficiency. For example, when the difference between the predicted load and the actual load is large (i.e., the load balance is poor), the fitness of the particles is low.

[0122] Specifically, the execution process of step S3 can be as follows:

[0123] The maximum load configuration of each charging pile is pre-set, and the minimum load configuration of each charging pile (i.e., the load prediction usage data of each charging pile) is determined based on the load demand forecast information, thereby obtaining the load configuration range of each charging pile.

[0124] Using multiple load configuration ranges of multiple charging piles as the search space, K load allocation schemes are randomly generated, that is, K initial particles are generated. The load allocation scheme includes the load configuration of each charging pile.

[0125] The initial fitness of each initial particle is calculated, and the initial fitness of each initial particle is corrected based on the multiple thermal effect interference information of multiple charging piles to obtain the target fitness of each initial particle.

[0126] Then, the target fitness of different initial particles is compared to determine the individual optimal (particle) and the global optimal (particle) in the initial stage.

[0127] The position and velocity of each particle are iteratively updated based on the individual optimal and global optimal values ​​in the initial stage, and the target fitness of the updated particles is calculated based on the thermal effect interference information of multiple charging piles.

[0128] Once the preset iteration stopping condition is met, the load allocation scheme corresponding to the global optimum of the last iteration is determined as the target load allocation scheme.

[0129] This invention first analyzes the load usage and temperature data of multiple charging piles over a historical period to determine the heat dissipation interference of each charging pile on other charging piles. Then, it predicts the load demand based on the historical load usage information of multiple charging piles to determine the predicted load demand information of multiple charging piles in the future period. Combined with the aforementioned heat dissipation interference, it performs particle swarm optimization to impose corresponding constraints on the particle swarm optimization process from the perspective of thermal effects. This makes the load allocation of multiple charging piles in the future period more in line with the actual usage of multiple charging piles, and makes the final output target load allocation scheme more accurate and reliable.

[0130] In one embodiment, determining the fitness correction coefficient for each particle based on the thermal effect interference information of each charging pile and the load allocation scheme indicated by each particle includes:

[0131] Based on the load allocation scheme indicated by each particle, determine the load configuration corresponding to each charging pile in each particle;

[0132] The load configuration differences of multiple charging piles in each particle are analyzed to determine the interfering charging piles corresponding to each charging pile in each particle, wherein the load configuration of the interfering charging piles in the corresponding particle is greater than the load configuration of the corresponding charging piles in the corresponding particle.

[0133] Based on the thermal effect interference information of each charging pile, and the load configuration difference between each charging pile and the corresponding interfering charging pile in each particle, the pile coefficient of each charging pile in each particle is determined.

[0134] The pile coefficient and load configuration of each charging pile in each particle are analyzed to determine the fitness correction coefficient for each particle.

[0135] In this embodiment, by identifying interfering charging piles, other charging piles that may cause heat dissipation interference to a certain charging pile are identified, and the load configuration differences between the interfering charging pile and the corresponding charging pile are analyzed, as well as the thermal effect interference information of the interfering charging pile on the corresponding charging pile are analyzed, so as to accurately calculate the pile coefficient of the corresponding charging pile, thereby achieving accurate quantification of the degree of heat dissipation interference of the corresponding charging pile by the interfering charging pile.

[0136] The thermal effect interference information for each charging pile includes multiple heat dissipation impact indices corresponding to that charging pile.

[0137] The determination of the pile coefficient for each charging pile in each particle, based on the thermal effect interference information of each charging pile and the load configuration difference between each charging pile and the corresponding interfering charging pile in each particle, includes:

[0138] Calculate the difference in load configuration between each charging pile in each particle and the corresponding interfering charging pile to obtain multiple load configuration differences for each charging pile in each particle.

[0139] Calculate the product of multiple load configuration differences for each charging pile in each particle and the corresponding multiple heat dissipation influence coefficients to obtain multiple initial coefficients for each charging pile in each particle.

[0140] Calculate the sum of multiple initial coefficients corresponding to each charging pile in each particle to obtain the pile coefficient corresponding to each charging pile in each particle.

[0141] The pile coefficient represents the cumulative impact of heat dissipation interference from other charging piles on the corresponding charging station within the corresponding particle. The higher the pile coefficient, the more severe the cumulative impact of heat dissipation interference on the corresponding charging pile.

[0142] For example, the pile coefficient corresponding to the i-th charging pile in a certain particle among multiple charging piles. It can be represented as:

[0143]

[0144] in, This represents the load configuration of the s-th interfering charging pile among the multiple interfering charging piles in the corresponding particle, where the i-th charging pile is located. This represents the load configuration of the i-th charging pile in the corresponding particle. Let represent the heat dissipation impact index of the s-th interfering charging pile on the i-th charging pile, and W represent the total number of interfering charging piles in the corresponding particle for the i-th charging pile.

[0145] In one embodiment, the analysis of the pile coefficient and load configuration corresponding to each charging pile in each particle to determine the fitness correction coefficient corresponding to each particle includes:

[0146] Calculate the product of the pile coefficient and the load configuration for each charging pile in each particle to obtain the sub-correction coefficient for each charging pile in each particle.

[0147] Calculate the sum of the sub-correction coefficients corresponding to the multiple charging piles in each particle to determine the fitness correction coefficient for each particle.

[0148] For example, the fitness correction coefficient corresponding to a certain particle It can be represented as:

[0149]

[0150] in, This represents the load configuration of the i-th charging pile among multiple charging piles in the corresponding particle. This represents the pile coefficient of the i-th charging pile in the corresponding particle, where N is the total number of charging piles.

[0151] In this embodiment, the pile coefficients of different charging piles are summarized to achieve accurate quantification of the fitness correction coefficient corresponding to each particle. The load configuration of each charging pile in the corresponding particle is introduced into the calculation to adapt to the situation where the load configuration of the charging pile is positively correlated with the fitness of the charging pile in the corresponding particle, so that the determined fitness correction coefficient is more accurate.

[0152] For example, the target fitness of a certain particle It can be represented as:

[0153]

[0154] Where exp represents an exponential function with base e (.), This represents the fitness correction factor for the particle. This indicates the initial fitness of the particle.

[0155] This invention proposes a charging pile cluster load distribution optimization control device for smart charging stations. Please refer to [link / reference]. Figure 2 The diagram illustrates a structural schematic of a charging pile cluster load distribution optimization control device 200 for smart charging stations according to an embodiment of the present invention. The device includes:

[0156] The data analysis module 201 is used to analyze the load usage data and temperature data of multiple charging piles in a historical time period to determine the thermal effect interference information of each charging pile, wherein the thermal effect interference information is used to characterize the heat dissipation interference of the corresponding charging pile to other charging piles.

[0157] The prediction module 202 is used to predict load demand based on the historical load usage information of the multiple charging piles, and obtain load demand prediction information.

[0158] The particle swarm processing module 203 is used to perform particle swarm optimization processing on the load allocation of the multiple charging piles based on the load demand prediction information and the thermal effect interference information of each charging pile, so as to obtain the target load allocation scheme.

[0159] It should be noted that the apparatus provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, the charging pile cluster load distribution optimization control device for smart charging stations and the charging pile cluster load distribution optimization control method for smart charging stations provided in the above embodiments belong to the same concept. The specific implementation process is detailed in the method embodiments and will not be repeated here.

[0160] This invention also provides an electronic device. Please refer to [link to relevant documentation]. Figure 3 The electronic device may include a processor 301, a memory 302, and a program 3021 stored in the memory 302 and capable of running on the processor 301.

[0161] When program 3021 is executed by processor 301, it can achieve the following: Figure 1 Any steps in the corresponding method embodiments and the achievement of the same beneficial effects will not be repeated here.

[0162] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by hardware related to program instructions, and the program can be stored in a readable medium.

[0163] This invention also provides a readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described functions. Figure 1 Any step in the corresponding method embodiment can achieve the same technical effect, and will not be repeated here to avoid repetition.

[0164] The computer-readable storage medium of this invention can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0165] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0166] The program code contained on the storage medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0167] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0168] This invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement the charging pile cluster load allocation optimization control method for smart charging stations provided in the above embodiments.

[0169] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0170] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for optimizing load distribution control of charging pile clusters in smart charging stations, characterized in that, The method includes: Analyze the load usage data and temperature data of multiple charging piles over a historical period to determine the thermal effect interference information of each charging pile, wherein the thermal effect interference information is used to characterize the heat dissipation interference of the corresponding charging pile on other charging piles. Load demand forecasting information is obtained by performing load demand forecasting based on the historical load usage information of the multiple charging piles. Based on the load demand forecast information and the thermal effect interference information of each charging pile, particle swarm optimization is performed on the load allocation of the multiple charging piles to obtain the target load allocation scheme. The analysis of load usage and temperature data of multiple charging piles over a historical period to determine the thermal interference information of each charging pile includes: In the multiple historical time segments included in the historical time period, the temperature rise characteristics of each charging pile in each historical time segment are analyzed to distinguish them from the temperature rise characteristics of other charging piles in the same historical time segment, so as to obtain the independent temperature rise index corresponding to each charging pile in each historical time segment. The differences between different independent temperature rise indices for different charging piles in each historical time segment were analyzed to obtain multiple heat dissipation interference indices for each charging pile in each historical time segment. Based on multiple heat dissipation interference indices corresponding to each charging pile in each historical time segment, correlation analysis is performed on different temperature data sequences corresponding to different charging piles in the historical time segment to obtain multiple heat dissipation impact indices corresponding to each charging pile. The thermal effect interference information of each charging pile includes multiple heat dissipation impact indices corresponding to that charging pile.

2. The method for optimizing load distribution of charging pile clusters for smart charging stations according to claim 1, characterized in that, The method involves analyzing the temperature rise characteristics of each charging pile in each historical time segment within the historical time period, comparing them with the temperature rise characteristics of other charging piles in the same historical time segment, to obtain an independent temperature rise index for each charging pile in each historical time segment, including: In the multiple historical time segments included in the historical time period, the ratio of load usage data to temperature data for each charging pile in each historical time segment is calculated to obtain the temperature rise characteristics of each charging pile in each historical time segment. Calculate the temperature rise characteristics of each charging pile in each historical time segment and the difference between the temperature rise characteristics of other charging piles in the same historical time segment to obtain multiple characteristic differences for each charging pile in each historical time segment. Calculate the sum of multiple feature differences for each charging pile in each historical time segment to obtain the feature difference sum for each charging pile in each historical time segment; The characteristic differences and values ​​of each charging pile in each historical time segment are normalized to obtain the independent temperature rise index of each charging pile in each historical time segment.

3. The method for optimizing load distribution of charging pile clusters for smart charging stations according to claim 1, characterized in that, The analysis examines the differences between different independent temperature rise indices for different charging piles in each historical time segment, in order to obtain multiple heat dissipation interference indices for each charging pile in each historical time segment, including: Calculate the ratio of the independent temperature rise index of each charging pile in each historical time segment to the independent temperature rise index of other charging piles in the same historical time segment, so as to obtain multiple independent deviation indices for each charging pile in each historical time segment. The distance between each charging pile and other charging piles, multiple independent deviation indices and multiple temperature difference coefficients corresponding to each charging pile in each historical time segment are analyzed to obtain multiple heat dissipation interference indices corresponding to each charging pile in each historical time segment. The temperature difference coefficient represents the numerical relationship between the temperature data of the corresponding charging pile in the corresponding historical time segment and the temperature data of other charging piles in the corresponding historical time segment.

4. The method for optimizing load distribution of charging pile clusters for smart charging stations according to claim 3, characterized in that, The analysis examines the distance between each charging pile and other charging piles, multiple independent deviation indices for each charging pile in each historical time segment, and multiple temperature difference coefficients to obtain multiple heat dissipation interference indices for each charging pile in each historical time segment, including: The ratios of multiple independent target deviation indices to target distances are calculated to obtain multiple target interference indices. The multiple independent target deviation indices are the multiple independent deviation indices of the first charging pile to the second charging pile in multiple historical time segments. The target distance is the distance between the first charging pile and the second charging pile. The first charging pile and the second charging pile are any two different charging piles among the multiple charging piles. In the plurality of target interference indices, the product of each target interference index and the corresponding target temperature difference coefficient is calculated to obtain the heat dissipation interference index of the first charging pile on the second charging pile in each historical time segment, wherein the plurality of target temperature difference coefficients correspond one-to-one with the plurality of historical time segments. When the temperature data of the first charging pile in the corresponding historical time segment is greater than the temperature data of the second charging pile in the corresponding historical time segment, the value of the corresponding target temperature difference coefficient is 1; When the temperature data of the first charging pile in the corresponding historical time segment is less than or equal to the temperature data of the second charging pile in the corresponding historical time segment, the value of the corresponding target temperature difference coefficient is 0.

5. The method for optimizing load distribution of charging pile clusters for smart charging stations according to claim 1, characterized in that, The method involves performing correlation analysis on different temperature data sequences of different charging piles within the historical time period, based on multiple heat dissipation interference indices corresponding to each charging pile in each historical time segment, to obtain multiple heat dissipation impact indices corresponding to each charging pile, including: A first temperature sequence and a second temperature sequence are obtained, wherein the first temperature sequence is a sequence composed of multiple temperature data of the first charging pile in multiple historical time segments, and the second temperature sequence is a sequence composed of multiple temperature data of the second charging pile in multiple historical time segments, and the first charging pile and the second charging pile are any two different charging piles among the multiple charging piles. Based on the multiple heat dissipation interference indices of the first charging pile to the second charging pile, the second temperature sequence is corrected to obtain the corrected temperature sequence. Correlation analysis is performed on the first temperature sequence and the corrected temperature sequence to obtain the heat dissipation impact index of the first charging pile on the second charging pile.

6. The method for optimizing load distribution of charging pile clusters for smart charging stations according to claim 1, characterized in that, In the particle swarm optimization process, the individual optimality and the global optimality are determined based on the target fitness of each particle. The steps for obtaining the target fitness of each particle in the particle swarm optimization process include: Based on the thermal effect interference information of each charging pile and the load allocation scheme indicated by each particle, determine the fitness correction coefficient corresponding to each particle. The initial fitness of each particle is corrected based on the fitness correction coefficient corresponding to that particle, so as to obtain the target fitness of each particle.

7. The method for optimizing load distribution of charging pile clusters for smart charging stations according to claim 6, characterized in that, The process of determining the fitness correction coefficient for each particle based on the thermal effect interference information of each charging pile and the load allocation scheme indicated by each particle includes: Based on the load allocation scheme indicated by each particle, determine the load configuration corresponding to each charging pile in each particle; The load configuration differences of multiple charging piles in each particle are analyzed to determine the interfering charging piles corresponding to each charging pile in each particle, wherein the load configuration of the interfering charging piles in the corresponding particle is greater than the load configuration of the corresponding charging piles in the corresponding particle. Based on the thermal effect interference information of each charging pile, and the load configuration difference between each charging pile and the corresponding interfering charging pile in each particle, the pile coefficient of each charging pile in each particle is determined. The pile coefficient and load configuration of each charging pile in each particle are analyzed to determine the fitness correction coefficient for each particle.

8. The method for optimizing load distribution of charging pile clusters for smart charging stations according to claim 7, characterized in that, The thermal effect interference information for each charging pile includes multiple heat dissipation impact indices corresponding to that charging pile. The determination of the pile coefficient for each charging pile in each particle, based on the thermal effect interference information of each charging pile and the load configuration difference between each charging pile and the corresponding interfering charging pile in each particle, includes: Calculate the difference in load configuration between each charging pile in each particle and the corresponding interfering charging pile to obtain multiple load configuration differences for each charging pile in each particle. Calculate the product of multiple load configuration differences for each charging pile in each particle and the corresponding multiple heat dissipation influence coefficients to obtain multiple initial coefficients for each charging pile in each particle. Calculate the sum of multiple initial coefficients corresponding to each charging pile in each particle to obtain the pile coefficient corresponding to each charging pile in each particle.

9. The method for optimizing load distribution of charging pile clusters for smart charging stations according to claim 7, characterized in that, The analysis of the pile coefficient and load configuration of each charging pile in each particle is used to determine the fitness correction coefficient for each particle, including: Calculate the product of the pile coefficient and the load configuration for each charging pile in each particle to obtain the sub-correction coefficient for each charging pile in each particle. Calculate the sum of the sub-correction coefficients corresponding to the multiple charging piles in each particle to determine the fitness correction coefficient for each particle.

Images