Charging pile power regulation and control method and system

Abstract

The invention discloses a charging pile power regulation and control method and system, and particularly relates to the technical field of charging pile management, data is collected from a multi-dimensional data source and summarized to form a preliminary information set, and a standard information set is obtained through format standardization processing; feature data of the charging pile are extracted based on the standard information set, and charging task analysis and resource occupation analysis are carried out respectively; inputting the analysis result into a pre-trained machine learning model to generate a charging priority coefficient; constructing a priority matrix, and dividing the charging piles into high priorities and low priorities according to the charging priority coefficients; and finally, dynamically adjusting a power distribution strategy according to the priority type, optimizing low-priority task power distribution while meeting high-priority task requirements, and improving the operation efficiency and the resource utilization rate of the charging station. According to the method, the real-time operation state and the charging task characteristics of the charging piles are combined, the power distribution strategy is dynamically adjusted, the priority division and power distribution proportion of the charging piles are adjusted in real time, and the self-adaptive capacity of operation of the charging station is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of charging pile management, and more specifically, to a charging pile power control method and system. Background Art

[0002] With the global emphasis on new energy technologies and the rapid growth of the electric vehicle market, the demand and frequency of use of charging stations and charging piles, as the core infrastructure of electric vehicles, are rapidly increasing. Charging stations are places that provide charging services for electric vehicles, usually consisting of multiple charging piles, energy distribution modules, monitoring systems and management platforms. Charging piles, as terminal equipment that directly charges vehicles, have multiple charging modes (such as fast charging and slow charging) to meet the needs of different users.

[0003] A charging station is an infrastructure platform for electric vehicle users, which is mainly responsible for the centralized management and distribution of electric energy. Typical charging stations include fast charging stations and integrated charging stations, equipped with high-power DC charging piles and low-power AC charging piles. Charging stations may also include energy storage equipment to balance the load on the power grid.

[0004] The charging pile is an important part of the charging station and is a device that directly connects the vehicle battery to the power grid. Its main function is to provide appropriate voltage and power according to the needs of the vehicle. However, the number of charging piles is limited, and the charging demand of electric vehicles is growing explosively. How to optimize the allocation of existing charging resources to meet user needs to the greatest extent is an urgent problem that the industry needs to solve. Users have increasingly higher requirements for charging speed, waiting time and service stability. When dealing with multi-task concurrency or emergency charging needs, the existing charging stations have low service efficiency and reduced user satisfaction. Therefore, a charging pile power control method and system are proposed here to solve the above problems. Summary of the invention

[0005] To achieve the above object, the present invention provides the following technical solutions: The charging pile power control method comprises the following steps: Collect data from preset multi-dimensional data sources, then summarize them to form a preliminary information set, and perform data format normalization on the preliminary information set to obtain a standardized information set; Based on the standard information set, feature data is extracted for charging piles in various usage states. Charging task analysis and resource occupancy analysis are performed based on the extracted feature data. The results of charging task analysis and resource occupancy analysis are then substituted into the pre-trained machine learning model, which outputs the charging priority coefficient. Constructing a priority matrix and classifying charging piles into high priority charging piles or low priority charging piles based on the constructed priority matrix; Based on the division results and the priority matrix, the power allocation of the charging piles in use in the charging station is strategically optimized and executed according to the priority type.

[0006] In a preferred embodiment, the multi-dimensional data source includes a charging vehicle dimension data source, a charging task reservation dimension data source, a charging pile operation dimension data source, and a charging station operation dimension data source.

[0007] In a preferred embodiment, the feature data extraction includes charging task feature extraction and resource occupancy feature extraction, and a charging task feature data set and a resource occupancy feature data set are obtained respectively.

[0008] In a preferred embodiment, performing charging task analysis refers to: From the charging task feature data set, obtain the target battery charge amount set by the user and define it as Qtarget, obtain the current vehicle battery remaining power and define it as Qcurrent, obtain the difference between the end charging time scheduled by the user and the current time and define it as Tremaining, obtain the time difference between the start and end time and define it as Ttotal, obtain the current charging power provided to the vehicle and define it as Pcurrent, obtain the rated maximum power of the charging pile and define it as Prated, and then substitute them into the following calculation formula: ; , These are all preset non-zero adjustment parameters, which are used to balance the impact of the target charge amount and the time window on the calculation results. is the task demand index.

[0009] In a preferred implementation, performing resource usage analysis refers to: From the resource occupancy feature dataset, the user's scheduled target charging amount and the vehicle's maximum charging rate are obtained, and the estimated charging time is calculated and defined as Testimated. The estimated charging time is obtained by calculating the ratio of the difference between the scheduled target charging amount and the current remaining battery power of the vehicle to the vehicle's maximum charging rate. The average power demand of the vehicle is obtained by calculating the ratio of the difference between the scheduled target charging amount and the current remaining battery power of the vehicle to the estimated charging time Testimated and defined as Pavg; Obtain and calculate the ratio of the real-time power output of the charging pile in each use state to its rated power, obtain the charging pile load rate and define it as Li, i represents the number of the charging pile, then calculate the average value of the load rate Li of all charging piles and define it as the average load rate Lavg in the station, then calculate the square of the deviation between the load rate Li of each charging pile and the average load rate Lavg in the station and divide it by the total number of charging piles in use, obtain the load rate variance and define it as LF; Finally, substitute it into the following calculation formula: ; Represents the total power capacity of the charging station, w1 and w2 are both preset non-zero proportional coefficients, Indicates the resource usage index.

[0010] In a preferred embodiment, the machine learning model is a polynomial regression model, and the priority matrix is ​​composed of the charging pile number, resource occupancy index, task demand index, and charging priority coefficient.

[0011] In a preferred embodiment, the logic for classifying charging piles into high priority charging piles or low priority charging piles is: Obtain the charging pile number j, and compare its corresponding charging priority coefficient with the preset charging priority threshold. If the charging priority coefficient corresponding to the charging pile number j is greater than or equal to the preset charging priority threshold, the charging pile number j is classified as a high-priority charging pile. If the charging priority coefficient corresponding to the charging pile number j is less than the preset charging priority threshold, the charging pile number j is classified as a low-priority charging pile.

[0012] In a preferred embodiment, the power allocation of charging piles in the charging station in use is strategically optimized according to the priority type, which means: The power allocation conditions for high priority charging piles are: ; Represents a collection of high-priority charging pile numbers. It represents the vehicle charging safety power threshold corresponding to the high priority charging pile number i. r1 and r2 are both preset non-zero adjustment coefficients. represents the task demand index corresponding to the high priority charging pile number i, Indicates the resource occupancy index corresponding to the high priority charging pile number i, Indicates the power allocation value corresponding to the high priority charging pile number i; The power allocation conditions for low priority charging piles are: ; Represents a collection of low-priority charging pile numbers. It represents the vehicle charging safety power threshold corresponding to the low priority charging pile number k. r3 and r4 are both preset non-zero control coefficients. represents the task demand index corresponding to the low priority charging pile number k, Indicates the resource occupancy index corresponding to the low priority charging pile number k, Indicates the power allocation value corresponding to the low priority charging pile number k; ; Indicates the available power remaining after high priority vehicles are allocated.

[0013] In a preferred embodiment, the charging pile power control system includes: The data collection module collects data from preset multi-dimensional data sources and then aggregates them to form a preliminary information set; The format processing module performs data format normalization processing on the preliminary information set to obtain a standardized information set; The feature analysis module extracts feature data of charging piles in various usage states based on the standard information set, and performs charging task analysis and resource occupancy analysis based on the extracted feature data; The learning model module substitutes the results of charging task analysis and resource usage analysis into the pre-trained machine learning model, and the machine learning model outputs the charging priority coefficient; A charging pile classification module constructs a priority matrix and classifies the charging piles into high priority charging piles or low priority charging piles based on the constructed priority matrix; The power allocation module optimizes and executes the strategy for power allocation of charging piles in use in the charging station according to the priority type based on the division results and the priority matrix.

[0014] Technical effects and advantages of the present invention: By dynamically collecting multi-dimensional data of vehicles and charging piles in the charging station, and using priority division and intelligent allocation strategies, the power output distribution of the charging piles is made more reasonable, reducing the inefficiency and waste caused by uneven resource allocation. It solves the resource imbalance problem of some charging piles being overloaded and some charging piles being idle in the traditional static allocation mode, and realizes load balancing of the entire station.

[0015] Based on the task demand index (CI) and resource occupancy index (RI), the priority of urgent tasks is dynamically evaluated and divided, so that high-priority tasks can quickly obtain charging power allocation and shorten the completion time of urgent tasks. At the same time, the basic needs of low-priority tasks are guaranteed, reducing user dissatisfaction caused by long waiting times for low-priority tasks.

[0016] The present invention uses a pre-trained polynomial regression model, combined with the real-time operating status of the charging pile and the characteristics of the charging task, to dynamically adjust the power allocation strategy to adapt to the complex and changeable operating environment, and improve the adaptive ability of the charging station operation by adjusting the charging pile priority division and power allocation ratio in real time.

[0017] Introducing a vehicle charging safety power threshold in the power allocation process ensures that the actual power allocation of each vehicle does not exceed the safety limit of the vehicle and equipment, avoiding battery overcharging or equipment overload. Combined with the load balancing factor (LF) in the resource occupancy index, it effectively alleviates the overall overload risk of the charging station and improves system stability.

[0018] Users can set charging requirements according to urgency. The present invention ensures that urgent tasks are completed first through a priority division strategy, reducing user waiting time. Non-urgent tasks are completed through intelligent regulation to ensure fairness and rationality, so that all users can enjoy efficient and stable charging services. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings; Figure 1 It is a schematic diagram of the charging pile power control method in the present invention.

[0020] Figure 2 It is a schematic diagram of the charging pile power control system in the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Reference Figure 1 - Figure 2 The following embodiments are obtained: Embodiment 1: A charging pile power control method comprises the following steps: Data is collected from preset multi-dimensional data sources and then summarized to form a preliminary information set to obtain the full amount of data required for the operation of the charging station and provide a data basis for subsequent analysis. The multi-dimensional data source includes vehicle battery status, user reservation information, real-time operation status of charging piles, total power status of charging stations, etc. The summarized preliminary information set contains all the original data for subsequent feature extraction and analysis.

[0023] The preliminary information set is processed by data format normalization to obtain a standardized information set, clean and unify the data format, eliminate redundancy, fill in missing values, and ensure data integrity and consistency. The standardized information set is the direct basis for feature data extraction and avoids analysis errors caused by data format problems.

[0024] Based on the specification information set, feature data is extracted for charging piles in various usage states. Core feature data related to charging task analysis and resource occupancy analysis are extracted from the specification information set. The extracted content includes task requirements (target charging amount, current battery power, etc.) and resource occupancy (load rate, average power demand, etc.). The extracted feature data is the direct source of subsequent analysis and model input.

[0025] Based on the extracted feature data, charging task analysis and resource occupancy analysis are performed respectively. Charging task analysis refers to analyzing the urgency of the task, such as the difference between the target charging amount and the current remaining power, the appointment time window, etc., to obtain the task demand index (CI), which is used to evaluate the task priority of each vehicle. Resource occupancy analysis refers to calculating the charging pile load rate, the estimated resource occupancy time, etc., to obtain the resource occupancy index (RI), which is used to evaluate the degree of system resource occupancy of each charging pile, and provide key indicators for subsequent priority matrix construction and power allocation.

[0026] The results of charging task analysis and resource occupancy analysis are substituted into the pre-trained machine learning model, and the machine learning model outputs the charging priority coefficient. A polynomial regression model is used to comprehensively consider the task demand index (CI) and the resource occupancy index (RI) to output the charging priority coefficient of each charging pile. The priority coefficient quantifies the task urgency and resource usage of the charging pile, providing a basis for the subsequent priority matrix construction and charging pile classification.

[0027] A priority matrix is ​​constructed and based on the constructed priority matrix, the charging piles are divided into high priority charging piles or low priority charging piles; the priority matrix includes the charging pile number, task requirement index (CI), resource occupancy index (RI) and charging priority coefficient. By comparing the charging priority coefficient with the charging priority threshold, the charging piles are divided into high priority or low priority. The division result provides a clear allocation basis for the power allocation optimization strategy.

[0028] Based on the division results and the priority matrix, the power allocation of the charging piles in use in the charging station is optimized and executed according to the priority type. The purpose is to achieve differentiated power allocation for high-priority and low-priority charging piles: high-priority charging piles give priority to meeting task requirements and allocate higher power; low-priority charging piles allocate the remaining power to ensure system load balancing, improve the overall resource utilization efficiency of the charging station, give priority to the completion of emergency tasks, and reduce the overall operating pressure.

[0029] The multi-dimensional data source includes the charging vehicle dimension data source, the charging task reservation dimension data source, the charging pile operation dimension data source, and the charging station operation dimension data source. The charging vehicle dimension data source determines the charging demand and safety power limit of a single vehicle. The charging task reservation dimension data source provides the time urgency and priority basis of the task. The charging pile operation dimension data source provides the resource occupancy of the current charging pile, which is used to allocate power and load balancing. The charging station operation dimension data source determines the total power allocation strategy and overall resource regulation of the entire station. The multi-dimensional data source provides comprehensive operation information at four levels: vehicles, tasks, charging piles, and charging stations, laying a solid data foundation for charging task analysis, resource occupancy analysis, priority division, and power allocation optimization. This layered design not only ensures the accuracy of regulation, but also can dynamically adapt to complex operating environments.

[0030] Feature data extraction includes charging task feature extraction and resource occupancy feature extraction, and obtains a charging task feature data set and a resource occupancy feature data set respectively.

[0031] Charging task analysis means: from the charging task feature data set, obtain the target battery charge set by the user and define it as Qtarget, which reflects the battery capacity that the vehicle needs to replenish; obtain the current remaining battery power of the vehicle and define it as Qcurrent, which is used to calculate the difference in charging demand; obtain the difference between the end charging time scheduled by the user and the current time and define it as Tremaining, which indicates the time urgency of the task; obtain the time difference between the start and end time and define it as Ttotal, which is used to measure the time margin for completing the charging task; obtain the current charging power provided to the vehicle and define it as Pcurrent, which indicates the progress of task execution; obtain the rated maximum power of the charging pile and define it as Prated, which is the maximum safe charging power negotiated by the vehicle and the charging pile, and determines the maximum executable power of the task; and then substitute it into the following calculation formula: ; , These are all preset non-zero adjustment parameters, which are used to balance the impact of the target charge amount and the time window on the calculation results. is the task demand index, CI indicates the urgency of the charging task. The larger the CI value, the higher the urgency of the task. Calculate the ratio of the target charge capacity to the current remaining capacity to indicate the urgency of the charging task. The larger the ratio, the more urgent the vehicle's charging needs. Calculate the ratio of remaining time to total appointment time to measure the time urgency of the charging task. The larger the value, the more time sufficiency the task has and the lower the urgency. By making a logarithmic correction to the current charging power, the impact of the task urgency is adjusted. The higher the current charging power, the more significant the effect of alleviating the time urgency. , The value can be adjusted according to different application situations to meet the needs of high-priority tasks or long-term scheduled tasks and adapt to the needs of different charging tasks.

[0032] Resource usage analysis refers to: From the resource occupancy feature data set, the user's scheduled target charging amount and the vehicle's maximum charging rate are obtained, and the estimated charging time is calculated and defined as Testimated. The estimated charging time is obtained by calculating the ratio of the difference between the scheduled target charging amount and the current remaining battery power of the vehicle to the vehicle's maximum charging rate, which represents the time occupied by the vehicle for charging resources. The longer the time, the higher the resource occupancy, which directly reflects the continuous impact of the charging task on the system.

[0033] By calculating the ratio of the difference between the scheduled target charging amount and the current remaining battery power of the vehicle to the estimated charging time Testimated, the average power demand of the vehicle is obtained and defined as Pavg; it represents the intensity of the task's demand for power resources. The larger Pavg is, the more significant the impact of the task on the power allocation of the charging station.

[0034] Obtain and calculate the ratio of the real-time power output of the charging pile in each usage state to its rated power, obtain the charging pile load rate and define it as Li, i represents the number of the charging pile, then calculate the average value of the load rate Li of all charging piles and define it as the average load rate Lavg in the station, then calculate the square of the deviation between the load rate Li of each charging pile and the average load rate Lavg in the station and divide it by the total number of charging piles in use, obtain the load rate variance and define it as LF; the higher the load rate variance, the more unbalanced the load distribution between the charging piles, which may cause some piles to be overloaded, provide information on system resource balance, and assist in optimizing the power allocation strategy.

[0035] Finally, substitute it into the following calculation formula: ; Represents the total power capacity of the charging station, w1 and w2 are both preset non-zero proportional coefficients, Indicates the resource usage index. Reflects the comprehensive resource usage of a single charging task in terms of power and time. The larger the ratio, the more significant the usage of a single task on the entire station resources. Reflects the overall load balance of the charging station. The higher the LF, the more unbalanced the resource allocation, and the power allocation needs to be optimized. Comprehensively evaluate the task requirements and global load, and quantify the occupation of charging station resources by single-vehicle tasks. The larger the RI value, the higher the resource occupation of the task, and its priority may be reduced to optimize global resources. The machine learning model is a polynomial regression model, and the priority matrix consists of the charging pile number, resource occupancy index, task demand index, and charging priority coefficient. The training and use logic of the polynomial regression model is as follows: Training data: historical charging task data is used as the training set, including actual task priority, completion time, task failure rate, etc. Model training: use gradient descent method or least squares method to optimize the regression coefficient θ. Online use: real-time input of task demand index (CI) and resource occupancy index (RI), output charging priority coefficient (PC). The polynomial regression model can identify the complex nonlinear relationship between task demand and resource occupancy, output charging priority coefficient, and use it for priority matrix construction and power allocation strategy optimization. The matrix is ​​composed as follows: Charging pile number (ID): uniquely identifies each charging pile, used to locate the task and operating status of the charging pile. Task demand index (CI): indicates the urgency of the task of the vehicle served by the charging pile. The higher the value, the more urgent the task. Resource occupancy index (RI): indicates the degree of occupation of system resources by the charging pile. The higher the value, the greater the resource occupation. Charging Priority Coefficient (PC): Calculated by a polynomial regression model, it is a comprehensive priority index that combines task requirements and resource usage. The higher the value, the higher the priority.

[0036] The logic for classifying charging piles as high priority charging piles or low priority charging piles is: Get the charging pile number j, and compare its corresponding charging priority coefficient with the preset charging priority threshold. If the charging priority coefficient corresponding to the charging pile number j is greater than or equal to the preset charging priority threshold, the charging pile number j is classified as a high-priority charging pile. If the charging priority coefficient corresponding to the charging pile number j is less than the preset charging priority threshold, the charging pile number j is classified as a low-priority charging pile. The logic of classifying charging piles as high-priority charging piles or low-priority charging piles accurately quantifies the importance and urgency of charging tasks by comparing the charging priority coefficient with the preset priority threshold. The charging tasks corresponding to high-priority charging piles have higher demand urgency or reasonable resource utilization, and are given priority in power allocation to ensure the timely completion of key tasks; while the tasks corresponding to low-priority charging piles have relatively low urgency or high resource occupancy, and the system load balancing requirements are met by adjusting the power allocation. This logic not only optimizes the overall scheduling of charging station resources, but also improves the fairness and efficiency of services.

[0037] Optimizing the power distribution of charging piles in use in charging stations according to priority types means: The power allocation conditions for high priority charging piles are: ; Represents a collection of high-priority charging pile numbers. It represents the vehicle charging safety power threshold corresponding to the high priority charging pile number i. r1 and r2 are both preset non-zero adjustment coefficients. represents the task demand index corresponding to the high priority charging pile number i, Indicates the resource occupancy index corresponding to the high priority charging pile number i, Indicates the power allocation value corresponding to the high priority charging pile number i; The power allocation conditions for low priority charging piles are: ; Represents a collection of low-priority charging pile numbers. It represents the vehicle charging safety power threshold corresponding to the low priority charging pile number k. r3 and r4 are both preset non-zero control coefficients. represents the task demand index corresponding to the low priority charging pile number k, Indicates the resource occupancy index corresponding to the low priority charging pile number k, Indicates the power allocation value corresponding to the low priority charging pile number k; ; Indicates the available power remaining after high priority vehicles are allocated.

[0038] Reasons for prioritization: Limited resources: The total power output of a charging station is limited and cannot meet the needs of all charging tasks at the same time.

[0039] Differences in task urgency: Different charging tasks have different urgency (task demand index, CI) and resource occupancy (resource occupancy index, RI), and resources need to be reasonably allocated according to priority.

[0040] Improve service efficiency: By allocating more power to high-priority charging piles, emergency tasks can be completed faster and overall service efficiency can be improved.

[0041] Meeting critical needs: Prioritize more power allocation to tasks with high urgency (large CI) or reasonable resource usage (low RI) to ensure that these tasks can be completed quickly.

[0042] Optimize resource usage: Allocate remaining power to low-priority charging piles to avoid over-allocating power to high-load charging piles, thereby improving overall load balancing.

[0043] Balance between fairness and efficiency: High-priority charging piles are allocated more power to meet urgent needs, and low-priority charging piles maintain system load balance by allocating remaining power.

[0044] Improve user experience: Emergency charging tasks are prioritized to reduce waiting time while avoiding overload. ), to ensure that the allocated power does not exceed the safety range of the vehicle and equipment. The vehicle charging safety power threshold takes the minimum value of the safety thresholds corresponding to the vehicle and equipment respectively.

[0045] Embodiment 2: A charging pile power control system, comprising: The data collection module collects data from preset multi-dimensional data sources and then aggregates them to form a preliminary information set; The format processing module performs data format normalization processing on the preliminary information set to obtain a standardized information set; The feature analysis module extracts feature data of charging piles in various usage states based on the standard information set, and performs charging task analysis and resource occupancy analysis based on the extracted feature data; The learning model module substitutes the results of charging task analysis and resource usage analysis into the pre-trained machine learning model, and the machine learning model outputs the charging priority coefficient; A charging pile classification module constructs a priority matrix and classifies the charging piles into high priority charging piles or low priority charging piles based on the constructed priority matrix; The power allocation module optimizes and executes the strategy for power allocation of charging piles in use in the charging station according to the priority type based on the division results and the priority matrix.

[0046] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0047] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0048] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0049] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0050] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A charging pile power control method, characterized in that: The following steps are involved: Collect data from preset multi-dimensional data sources, then summarize them to form a preliminary information set, and perform data format normalization on the preliminary information set to obtain a standardized information set; Based on the standard information set, feature data is extracted for charging piles in various usage states. Charging task analysis and resource occupancy analysis are performed based on the extracted feature data. The results of charging task analysis and resource occupancy analysis are then substituted into the pre-trained machine learning model, which outputs the charging priority coefficient. Constructing a priority matrix and classifying charging piles into high priority charging piles or low priority charging piles based on the constructed priority matrix; Based on the division results and the priority matrix, the power allocation of the charging piles in use in the charging station is strategically optimized and executed according to the priority type.

2. The charging pile power control method according to claim 1, characterized in that: The multi-dimensional data source includes a charging vehicle dimension data source, a charging task reservation dimension data source, a charging pile operation dimension data source, and a charging station operation dimension data source.

3. The charging pile power control method according to claim 2, characterized in that: Feature data extraction includes charging task feature extraction and resource occupancy feature extraction, and obtains a charging task feature data set and a resource occupancy feature data set respectively.

4. The charging pile power control method according to claim 3, characterized in that: Charging task analysis refers to: From the charging task feature data set, obtain the target battery charge amount set by the user and define it as Qtarget, obtain the current vehicle battery remaining power and define it as Qcurrent, obtain the difference between the end charging time scheduled by the user and the current time and define it as Tremaining, obtain the time difference between the start and end time and define it as Ttotal, obtain the current charging power provided to the vehicle and define it as Pcurrent, obtain the rated maximum power of the charging pile and define it as Prated, and then substitute them into the following calculation formula: ; , These are all preset non-zero adjustment parameters, which are used to balance the impact of the target charge amount and the time window on the calculation results. is the task demand index.

5. The charging pile power control method according to claim 4, characterized in that: Resource usage analysis refers to: From the resource occupancy feature dataset, the user's scheduled target charging amount and the vehicle's maximum charging rate are obtained, and the estimated charging time is calculated and defined as Testimated. The estimated charging time is obtained by calculating the ratio of the difference between the scheduled target charging amount and the current remaining battery power of the vehicle to the vehicle's maximum charging rate. The average power demand of the vehicle is obtained by calculating the ratio of the difference between the scheduled target charging amount and the current remaining battery power of the vehicle to the estimated charging time Testimated and defined as Pavg; Obtain and calculate the ratio of the real-time power output of the charging pile in each use state to its rated power, obtain the charging pile load rate and define it as Li, i represents the number of the charging pile, then calculate the average value of the load rate Li of all charging piles and define it as the average load rate Lavg in the station, then calculate the square of the deviation between the load rate Li of each charging pile and the average load rate Lavg in the station and divide it by the total number of charging piles in use, obtain the load rate variance and define it as LF; Finally, substitute it into the following calculation formula: ; Represents the total power capacity of the charging station, w1 and w2 are both preset non-zero proportional coefficients, Indicates the resource usage index.

6. The charging pile power control method according to claim 5, characterized in that: The machine learning model is a polynomial regression model, and the priority matrix consists of the charging pile number, resource occupancy index, task demand index, and charging priority coefficient.

7. The charging pile power control method according to claim 6, characterized in that: The logic for classifying charging piles as high priority charging piles or low priority charging piles is: Obtain the charging pile number j, and compare its corresponding charging priority coefficient with the preset charging priority threshold. If the charging priority coefficient corresponding to the charging pile number j is greater than or equal to the preset charging priority threshold, the charging pile number j is classified as a high-priority charging pile. If the charging priority coefficient corresponding to the charging pile number j is less than the preset charging priority threshold, the charging pile number j is classified as a low-priority charging pile.

8. The charging pile power control method according to claim 7, characterized in that: Optimizing the power distribution of charging piles in use in charging stations according to priority types means: The power allocation conditions for high priority charging piles are: ; Represents a collection of high-priority charging pile numbers. It represents the vehicle charging safety power threshold corresponding to the high priority charging pile number i. r1 and r2 are both preset non-zero adjustment coefficients. represents the task demand index corresponding to the high priority charging pile number i, Indicates the resource occupancy index corresponding to the high priority charging pile number i, Indicates the power allocation value corresponding to the high priority charging pile number i; The power allocation conditions for low priority charging piles are: ; Represents a collection of low-priority charging pile numbers. It represents the vehicle charging safety power threshold corresponding to the low priority charging pile number k. r3 and r4 are both preset non-zero control coefficients. represents the task demand index corresponding to the low priority charging pile number k, Indicates the resource occupancy index corresponding to the low priority charging pile number k, Indicates the power allocation value corresponding to the low priority charging pile number k; ; Indicates the available power remaining after high priority vehicles are allocated.

9. A charging pile power control system, implemented based on the charging pile power control method according to any one of claims 1 to 8, characterized in that: include: The data collection module collects data from preset multi-dimensional data sources and then aggregates them to form a preliminary information set; The format processing module performs data format normalization processing on the preliminary information set to obtain a standardized information set; The feature analysis module extracts feature data of charging piles in various usage states based on the standard information set, and performs charging task analysis and resource occupancy analysis based on the extracted feature data; The learning model module substitutes the results of charging task analysis and resource usage analysis into the pre-trained machine learning model, and the machine learning model outputs the charging priority coefficient; A charging pile classification module constructs a priority matrix and classifies the charging piles into high priority charging piles or low priority charging piles based on the constructed priority matrix; The power allocation module optimizes and executes the strategy for power allocation of charging piles in use in the charging station according to the priority type based on the division results and the priority matrix.

Images