A peak-valley regulation method and system for AC charging pile of electric vehicle

Abstract

The present invention provides a peak-valley regulation method and system for an AC charging pile of an electric vehicle, and belongs to the field of data processing technology. The regulation method includes: obtaining data of electric vehicles to be charged and historical data of AC charging piles; calculating the charging urgency value of each electric vehicle to be charged; judging whether the charging urgency value of the electric vehicle is greater than the preset charging urgency value; if so, adding it to the emergency dispatch queue; otherwise, adding it to the normal dispatch queue; with the goal of minimizing the change in power demand of the AC charging pile during peak hours and maximizing the utilization rate of the AC charging pile, constructing a peak-valley regulation model for the AC charging pile, and determining the objective function and constraint conditions; under the constraints of the constraint conditions, with the goal of minimizing the function value of the objective function, optimizing the peak-valley regulation model, and outputting the optimal charging scheduling strategy; according to the optimal charging scheduling strategy, scheduling the electric vehicles to be charged to perform peak-valley regulation of the AC charging pile.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a peak-valley regulation method and system for an AC charging pile for an electric vehicle. Background Art

[0002] As the popularity of hybrid and pure electric vehicles among urban residents has increased significantly, this trend has also led to a rapid increase in the demand for charging pile installation, especially in residential areas and community parking lots. However, the concentrated growth of these demands has brought huge challenges to the community power supply network, especially in old communities, where transformer capacity is often insufficient due to the relatively backward distribution facilities, which directly affects users' charging needs and experience. How to balance the interests between power supply companies and users and optimize charging strategies has become an urgent problem to be solved.

[0003] The main solutions to deal with the growth of charging pile loads are: one is that power supply companies usually choose to replace transformers with larger capacity and upgrade the transmission lines as a whole to meet the power demand of users' charging piles. Another is that for areas that cannot bear more loads, power supply companies may reject users' charging pile installation applications on the grounds of "insufficient capacity".

[0004] However, the existing technology for replacing transformers and upgrading lines is not only costly, but also requires a long implementation period. The construction process may affect the normal electricity consumption of the community, which not only increases production costs but also seriously affects the user experience. At the same time, since users' charging needs are concentrated in time periods, the existing technical solutions fail to reasonably dispatch charging vehicles, resulting in further aggravated pressure on the power grid when the charging piles are running. Summary of the invention

[0005] The main purpose of the present invention is to provide a peak-valley regulation method and system for an AC charging pile for an electric vehicle, so as to solve the problem that the replacement of transformers and the upgrading of lines in the prior art are not only costly, but also require a long implementation period, and the normal electricity consumption of the community may be affected during the construction process, which not only increases the production cost, but also seriously affects the user experience; at the same time, since the charging demand of users is concentrated in a certain period of time, the existing technical solutions fail to reasonably dispatch the charging vehicles, resulting in the problem that the pressure on the power grid is further aggravated when the charging pile is running.

[0006] In order to achieve the above object, according to one aspect of the present invention, a peak-valley regulation method for an AC charging pile of an electric vehicle is provided, comprising:

[0007] S1: Obtaining data of electric vehicles to be charged and historical data of AC charging piles;

[0008] S2: Calculating the charging urgency value of each electric vehicle to be charged based on the data of the electric vehicles to be charged;

[0009] S3: Determine whether the charging urgency value of each of the electric vehicles to be charged is greater than a preset charging urgency value; if so, add the electric vehicle to be charged to an emergency dispatch queue; otherwise, add the electric vehicle to be charged to a normal dispatch queue;

[0010] S4: Based on the historical data of the AC charging pile, the data of the electric vehicles to be charged, the emergency dispatch queue data and the normal dispatch queue data, a peak-valley regulation model of the AC charging pile is constructed with the goal of minimizing the change in power demand of the AC charging pile during peak hours and maximizing the utilization rate of the AC charging pile;

[0011] S5: Determine the objective function and constraint conditions of the peak-valley regulation model;

[0012] S6: Under the constraints of the constraints, with the goal of minimizing the function value of the objective function, the peak-valley regulation model is optimized by the tribal intelligent evolutionary algorithm to output an optimal charging scheduling strategy;

[0013] S7: According to the optimal charging scheduling strategy, the electric vehicles to be charged are scheduled to perform peak-valley regulation of the AC charging pile.

[0014] Furthermore, the historical data of the AC charging pile specifically includes: the maximum charging power of the AC charging pile, historical voltage load data, historical peak time period data, and maximum charging capacity data;

[0015] The electric vehicle data to be charged specifically includes: the arrival time, departure time, current battery status, total battery capacity, required charging power status and minimum acceptable power status of each electric vehicle to be charged.

[0016] Furthermore, the calculation formula of the charging urgency value is specifically:

[0017] ;

[0018] Among them, L i represents the charging urgency value of the i-th electric vehicle, represents the parking time of the i-th electric vehicle, Δx i represents the required charging time of the i-th electric vehicle, SOC i represents the current power state of the i-th electric car, , SOC min Indicates the lowest acceptable state of charge, .

[0019] Furthermore, the calculation formula for the parking time of the electric vehicle is specifically:

[0020] ;

[0021] in, represents the departure time of the i-th electric car, represents the arrival time of the i-th electric car;

[0022] The calculation formula for the required charging time of the electric vehicle is:

[0023] ;

[0024] Among them, P charge Indicates the charging power of the AC charging pile, C i Represents the total capacity of the battery of the i-th electric vehicle, SOC target Indicates the charging state required by the i-th electric vehicle.

[0025] Furthermore, the objective function is specifically:

[0026] ;

[0027] ;

[0028] Among them, min means taking the minimum value, f means the objective function, α t represents the power demand weight in the tth time period, P t represents the power demand in the tth time period, P t-1 represents the power demand in the t-1th time period, Δ represents the increment operator, T 0 represents the time period of peak load, β t represents the charging demand weight of electric vehicles in the tth time period, r it represents the charging amount of the i-th electric vehicle in the t-th time period, T represents the set of related time periods, and E represents the set of electric vehicles participating in charging.

[0029] Furthermore, the calculation formula of the power demand weight is specifically as follows:

[0030] ;

[0031] Among them, P max represents the maximum load of the power grid, and γ represents the adjustment parameter that controls the impact of power demand fluctuation on the weight.

[0032] Furthermore, the calculation formula of the electric vehicle charging demand weight is specifically as follows:

[0033] ;

[0034] Among them, Q charge,t represents the charging demand in the tth time period, Q max represents the maximum charging demand, and δ represents the adjustment parameter that controls the impact of the charging demand on the weight.

[0035] Furthermore, the constraints specifically include:

[0036] Each electric vehicle’s charging capacity does not exceed its own requested charging capacity;

[0037] The charging capacity of each electric vehicle needs to be greater than or equal to its own minimum required charging capacity;

[0038] The charging amount in each time period shall not exceed the maximum charging capacity of the AC charging pile;

[0039] The sum of each EV’s charging amount during all time periods is equal to its charging request amount;

[0040] The charging rate of each electric vehicle cannot exceed the maximum power limit of the AC charging station;

[0041] In each time period, each electric vehicle in the emergency dispatch queue takes precedence over each electric vehicle in the normal dispatch queue.

[0042] Furthermore, the objective function is used as the fitness function of the tribal intelligent evolutionary algorithm.

[0043] According to one aspect of the present invention, a peak-valley regulation system for an AC charging pile of an electric vehicle is provided, comprising:

[0044] processor;

[0045] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the peak-valley regulation method for the AC charging pile of an electric vehicle is implemented.

[0046] By applying the technical solution of the present invention, it is possible to obtain historical data of electric vehicles to be charged and charging piles, combine the peak-valley regulation model with the intelligent optimization algorithm, output the optimal charging scheduling strategy, and implement peak-valley load regulation, so as to effectively balance the load demand under the existing hardware conditions, without replacing the transformer or upgrading the line, thus greatly reducing the construction cost and improving the user experience; by calculating the charging urgency value of the vehicle, reasonably dividing the emergency and normal scheduling queues, dynamically optimizing the peak load distribution, and dispersing the charging demand in a specific time period, the pressure on the power grid can be alleviated, and efficient peak-valley regulation of the AC charging piles can be achieved.

[0047] In addition to the above-described purposes, features and advantages, the present invention has other purposes, features and advantages. The present invention will be further described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0049] Figure 1 A schematic flow chart of a peak-valley regulation method for an AC charging pile for an electric vehicle provided by an embodiment of the present invention is shown;

[0050] Figure 2 A schematic structural diagram of a peak-valley regulation system for an AC charging pile for an electric vehicle provided in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0051] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0052] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0053] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so as to describe the embodiments of the present invention described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0054] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0055] Reference Manual Attached Figure 1 , showing a flow chart of a peak-valley regulation method for an AC charging pile of an electric vehicle provided in an embodiment of the present invention.

[0056] The embodiment of the present invention provides a peak-valley regulation method for an AC charging pile of an electric vehicle, comprising:

[0057] S1: Obtain the data of electric vehicles to be charged and the historical data of AC charging piles.

[0058] In a possible implementation manner, the historical data of the AC charging pile specifically includes: the maximum charging power of the AC charging pile, historical voltage load data, historical peak time period data, and maximum charging capacity data.

[0059] The data of the electric vehicles to be charged specifically include: the arrival time, departure time, current battery status, total battery capacity, required charging power status and minimum acceptable power status of each electric vehicle to be charged.

[0060] It should be noted that real-time data is collected through smart charging piles or charging station equipment. These devices usually have power sensors, communication interfaces (such as RFID, NFC), GPS modules, etc., which can automatically record and upload information such as the arrival time, charging amount, and charging time of each vehicle. Through the vehicle system or mobile application, the user automatically records the arrival time when arriving at the charging pile, and records the departure time and obtains the vehicle's SOC, target SOC, and battery capacity when leaving. The historical power demand data of the charging station, the maximum charging power, the load conditions of the charging pile, and other information are usually stored in the charging management system. The system provides real-time and historical charging status by monitoring and recording the data of each charging pile.

[0061] In the present invention, by comprehensively acquiring historical data of AC charging piles and data of electric vehicles to be charged, efficient use of resources can be achieved. Especially in the intelligent scheduling system, such data collection is the basis for precise optimization and dynamic regulation.

[0062] S2: Based on the data of the electric vehicles to be charged, the charging urgency value of each electric vehicle to be charged is calculated.

[0063] Among them, the charging urgency value is an important indicator used to measure the urgency of electric vehicle charging demand. It reflects the priority of each electric vehicle to be charged under the current charging conditions. Through the charging urgency value, vehicles can be divided into different priority queues, so as to more reasonably allocate charging resources and optimize the scheduling strategy.

[0064] In a possible implementation manner, the calculation formula of the charging urgency value is specifically:

[0065] ;

[0066] Among them, L i represents the charging urgency value of the i-th electric vehicle, represents the parking time of the i-th electric vehicle, Δx i represents the required charging time of the i-th electric vehicle, SOC i represents the current power state of the i-th electric car, , SOC min Indicates the lowest acceptable state of charge, .

[0067] In a possible implementation, the calculation formula for the parking time of the electric vehicle is specifically:

[0068] ;

[0069] in, represents the departure time of the i-th electric car, represents the arrival time of the i-th electric car.

[0070] The calculation formula for the required charging time of an electric vehicle is:

[0071] ;

[0072] Among them, P charge Indicates the charging power of the AC charging pile, C i Represents the total capacity of the battery of the i-th electric vehicle, SOC target Indicates the charging state required by the i-th electric vehicle.

[0073] Specifically, in order to calculate the charging urgency value of each electric vehicle to be charged, it is necessary to comprehensively consider the vehicle's parking time, required charging time, current state of charge (SOC) and minimum acceptable state of charge, as well as Represents the charging demand of the i-th electric vehicle. Based on the acquired data, the parking time is first calculated to reflect the available time of the electric vehicle at the charging pile. Secondly, the required charging time is calculated. Finally, the charging emergency situation of each electric vehicle can be obtained by combining the required charging time and the parking time.

[0074] In the present invention, high-priority vehicles can complete charging more quickly, avoiding user dissatisfaction due to long waiting time; at the same time, by calculating the charging urgency value based on the data of electric vehicles to be charged, the charging priority of each vehicle can be comprehensively measured to ensure reasonable allocation of resources and real-time optimization scheduling.

[0075] S3: Determine whether the charging urgency value of each electric vehicle to be charged is greater than a preset charging urgency value; if so, add the electric vehicle to be charged to an emergency dispatch queue; otherwise, add the electric vehicle to be charged to a normal dispatch queue.

[0076] The emergency dispatch queue is a queue in the charging management system used to handle emergency charging needs. It is determined based on the charging urgency value of the vehicle, and vehicles with high charging urgency values ​​are given priority to enter the queue. This queue ensures that when charging pile resources are limited, vehicles with urgent needs can be charged in time to avoid insufficient power or inability to continue driving.

[0077] It should be noted that the normal dispatch queue is another type of queue in the charging management system, which is used to arrange the charging of electric vehicles with lower urgency. Compared with the emergency dispatch queue, the charging requirements of vehicles in the normal dispatch queue are more relaxed. Usually, these vehicles have higher power or their charging tasks can be flexibly completed during non-peak hours.

[0078] In the present invention, vehicles in the emergency dispatch queue have a high charging urgency value, which may require faster charging due to a short parking time or low power. The needs of these vehicles are met first, and charging pile resources can be allocated more reasonably. At the same time, vehicles with high urgency values ​​directly enter the emergency dispatch queue, which can quickly complete charging and avoid users waiting for too long.

[0079] Furthermore, by prioritizing resource allocation during peak hours through the emergency dispatch queue, peak load pressure can be effectively alleviated.

[0080] S4: Based on the historical data of AC charging piles, data of electric vehicles to be charged, data of emergency dispatch queues, and data of normal dispatch queues, a peak-valley regulation model of AC charging piles is constructed with the goal of minimizing the change in power demand of AC charging piles during peak hours and maximizing the utilization rate of AC charging piles.

[0081] In the present invention, the peak load that may occur in the future can be predicted through historical voltage load data and peak time period data, and load optimization strategies can be formulated in advance. At the same time, combined with the data of electric vehicles to be charged, the arrival time, departure time and charging demand of the vehicles can be obtained in real time to provide accurate input data for the optimization model.

[0082] Furthermore, by constructing a peak-valley regulation model with the goal of minimizing power fluctuations and maximizing the utilization of charging piles, it is possible to achieve rational resource allocation, dynamic load optimization, improved user experience, and reduced system costs. This approach not only meets the charging needs of electric vehicle owners, but also enhances the operational stability of charging piles and power grids.

[0083] S5: Determine the objective function and constraints of the peak-valley regulation model.

[0084] In a possible implementation, the objective function is specifically:

[0085] ;

[0086] ;

[0087] Among them, min means taking the minimum value, f means the objective function, α t represents the power demand weight in the tth time period, P t represents the power demand in the tth time period, P t-1 represents the power demand in the t-1th time period, Δ represents the increment operator, T 0 represents the time period of peak load, β t represents the charging demand weight of electric vehicles in the tth time period, r it represents the charging amount of the i-th electric vehicle in the t-th time period, T represents the set of related time periods, and E represents the set of electric vehicles participating in charging.

[0088] In a possible implementation, the calculation formula of the power demand weight is specifically:

[0089] ;

[0090] Among them, P max represents the maximum load of the power grid, and γ represents the adjustment parameter that controls the impact of power demand fluctuation on the weight.

[0091] In the present invention, the weight is dynamically adjusted as the load 𝑃𝑡 changes in the current time period. When the load is high, the weight is higher, and the optimization model will pay more attention to reducing fluctuations and effectively reduce the pressure on the power grid.

[0092] In a possible implementation, the calculation formula of the electric vehicle charging demand weight is specifically:

[0093] ;

[0094] Among them, Q charge,t represents the charging demand in the tth time period, Q maxrepresents the maximum charging demand, and δ represents the adjustment parameter that controls the impact of the charging demand on the weight.

[0095] In the present invention, through the design of the objective function and the introduction of dynamic weights, this method can balance the grid load and improve the utilization rate of charging piles. At the same time, the optimization scheduling strategy has the ability of dynamic adjustment and multi-scenario adaptation, which not only meets the operational efficiency, but also improves the user experience. It is a scientific, flexible and efficient charging optimization solution.

[0096] In a possible implementation, the constraints specifically include:

[0097] Each electric vehicle’s charging capacity does not exceed its own requested charging capacity:

[0098] ;

[0099] Among them, r it represents the charging amount of the i-th electric vehicle in the t-th time period, q i represents the charging demand of the i-th electric vehicle, T represents the set of relevant time periods, and E represents the set of electric vehicles participating in charging.

[0100] In the present invention, the charging amount of each electric vehicle does not exceed the charging amount requested by itself, so as to ensure that the charging amount of each electric vehicle does not exceed its demand and prevent waste of resources. At the same time, limiting the upper limit of vehicle charging helps to reduce unnecessary power load and reduce the pressure on the power grid during peak hours.

[0101] The charging capacity of each electric vehicle needs to be greater than or equal to its own minimum required charging capacity:

[0102] ;

[0103] in, Indicates the minimum charging ratio allowed for each vehicle.

[0104] In the present invention, by limiting the charging amount of each electric vehicle to be greater than or equal to its own minimum required charging amount, it can be ensured that all users can meet their minimum charging requirements and improve user satisfaction.

[0105] The charging amount in each time period shall not exceed the maximum charging capacity of the AC charging pile:

[0106] ;

[0107] Among them, M t It means that the total charging request power in the tth time period does not exceed the total power capacity of the AC charging pile.

[0108] The sum of the charging amount of each EV in all time periods is equal to its charging request amount:

[0109] .

[0110] The charging rate of each electric vehicle cannot exceed the maximum power limit of the AC charging pile:

[0111] ;

[0112] Among them, r max Indicates the maximum charging power.

[0113] In each time period, each electric vehicle in the emergency dispatch queue takes precedence over each electric vehicle in the normal dispatch queue:

[0114] ;

[0115] Among them, E emergency represents the set of vehicles in the emergency dispatch queue, P jt represents the priority of the jth electric vehicle in the emergency dispatch queue in the tth time period, E normal represents the set of vehicles in the normal dispatch queue, P kt represents the priority of the kth electric vehicle in the normal dispatch queue in the tth time period, and T represents the set of related time periods.

[0116] In the present invention, by limiting each time period, each electric vehicle in the emergency dispatch queue takes precedence over each electric vehicle in the normal dispatch queue, it can be ensured that vehicles with short parking time or low battery power are given priority to complete charging, avoiding user dissatisfaction or driving problems caused by dispatch delays.

[0117] In summary, by strictly controlling the allocation of charging resources, load balancing and priority scheduling through constraints, the operating efficiency, stability and user experience of the charging pile system can be significantly improved. At the same time, it provides a clear constraint framework for the intelligent scheduling optimization algorithm, which is an important part of the peak and valley regulation optimization of charging piles.

[0118] S6: Under the constraints, with the goal of minimizing the function value of the objective function, the peak-valley regulation model is optimized through the tribal intelligent evolutionary algorithm to output the optimal charging scheduling strategy.

[0119] Among them, the Tribal Intelligence Evolutionary Algorithm (TIEA) is an intelligent optimization algorithm that simulates the natural evolution process and group behavior. It combines the characteristics of evolutionary algorithms and group intelligence, simulating the interaction, competition and collaboration of multiple tribes (i.e. populations) in the evolution process to find the optimal solution. The core idea of ​​the algorithm is to simulate the adaptation process of species in nature in different environments through the co-evolution of multiple tribes in order to obtain the global optimal solution.

[0120] In a possible implementation, the objective function is used as the fitness function of the tribal intelligent evolutionary algorithm.

[0121] In a possible implementation, the tribal intelligent evolution algorithm specifically includes:

[0122] S601: Using the objective function as the fitness function of the tribal intelligent evolutionary algorithm.

[0123] S602: Initialize a population and a Q table, wherein the population includes a plurality of individuals, and each individual represents a set of feasible charging scheduling strategies.

[0124] S603: Clustering each individual using a clustering algorithm to form multiple tribes.

[0125] S604: Calculate the fitness value of each individual in each tribe, and select the individual with the lowest fitness value as the leader.

[0126] In the present invention, each tribe selects the individual with the lowest fitness as the leader, and uses it to guide the local development direction of the tribe to improve development efficiency.

[0127] S605: Determine whether the minimum fitness value of each tribe is less than the average fitness value of the existing tribes; if so, the tribe is evaluated as a strong tribe; otherwise, the tribe is evaluated as a weak tribe.

[0128] S606: Use the following formula to adjust the individual parameters of each strong tribe and each weak tribe for war:

[0129] ;

[0130] ;

[0131] in, represents the parameters of the plundered individual, represents the parameter for defeating the tribal leader, and ε represents a constant.

[0132] In the present invention, the strong tribe plunders the parameters of individuals from the weak tribe, dynamically absorbs the potential excellent solutions of the weak tribe, and improves the quality of the global solution.

[0133] S607: Determine the tribe action reward value for each tribe to perform the execution action by the following formula:

[0134] ;

[0135] Among them, S i It represents the status of the i-th tribe, Strong tribe represents a strong tribe, and Weak tribe represents a weak tribe.

[0136] In the present invention, the reward values ​​of strong tribes and weak tribes are set so that strong tribes can obtain more incentives, while weak tribes retain a certain chance of survival in the competition, thereby enhancing the dynamic adaptability of the system.

[0137] S608: According to the tribe action reward value, update the Q table by the following formula:

[0138] ;

[0139] in, represents the updated Q value under the current state and action, represents the Q value before update under the current state and action, λ represents the learning rate, γ represents the discount factor, Indicates the action with the largest Q value in the state after the action is executed.

[0140] In the present invention, by using the Q-table update formula, the tribal intelligent evolutionary algorithm can achieve dynamic learning, balance exploration and development, improve decision-making accuracy and fast convergence. This method combines reinforcement learning with evolutionary optimization, providing an efficient, flexible and intelligent solution to complex charging scheduling problems.

[0141] S609: Based on the Q table, use the accumulated reward value data to guide the update of each individual in the existing tribe.

[0142] S610: Based on the updated individual information, the leaders of each tribe are re-determined, and the fitness values ​​of the leaders of each tribe are compared, and the leader with the lowest fitness value is selected as the best leader.

[0143] S611: Determine whether the number of iterations reaches the maximum number of iterations or whether the convergence accuracy reaches the preset convergence accuracy. If so, output the charging scheduling strategy represented by the best leader as the best charging scheduling strategy; otherwise, proceed to the next step.

[0144] S612: Determine whether there is only one tribe; if so, proceed to S603; otherwise, proceed to S606.

[0145] In summary, the charging scheduling optimization solution based on the tribal intelligent evolutionary algorithm achieves a balance between global optimization and local development through multi-tribe collaborative search, dynamic adjustment of reinforcement learning, and iterative update driven by fitness, and has high efficiency, stability, and flexibility. The optimal scheduling strategy outputted in the end can significantly improve the operating efficiency of charging piles, user experience, and grid load balancing capabilities.

[0146] S7: According to the optimal charging scheduling strategy, the electric vehicles to be charged are scheduled to adjust the peak and valley of the AC charging pile.

[0147] Specifically, the optimal charging scheduling strategy is obtained, which will tell you the specific arrangements of charging amount, charging sequence, charging period, etc. for each vehicle in different time periods. According to the historical power demand data of the charging piles and the real-time grid load conditions, the peak hours (such as daytime working hours) and the off-peak hours are identified, and the peak hour data is used to mark the periods with higher charging demand. The off-peak hours are usually the periods with lower power demand. According to the optimal scheduling strategy, the charging tasks are dynamically allocated in combination with the load requirements of the peak hours and off-peak hours. When allocating, the vehicles in the emergency scheduling queue must be charged as early as possible during the peak hours or other periods with lower loads due to their urgent charging needs, to ensure that the charging needs of these vehicles are not delayed, while the vehicles in the normal scheduling queue can be flexibly arranged to charge during the off-peak hours, especially when the grid load is light (such as at night or on weekends), to avoid these vehicles occupying too many resources during peak hours.

[0148] In the present invention, the charging tasks of vehicles in the emergency dispatch queue should be arranged first due to their high charging demand. By ensuring that these vehicles can be charged during peak hours or at appropriate times, the emergency needs of electric vehicles can be responded to quickly, avoiding problems caused by delayed charging. At the same time, the intelligent scheduling of charging tasks not only improves the utilization rate of charging piles, but also enables charging piles to smoothly transition between different load periods, thereby improving the overall operational efficiency of charging piles.

[0149] From the above description, it can be seen that the peak-valley regulation method for the electric vehicle AC charging pile provided by the present invention can obtain historical data of the electric vehicles to be charged and the charging piles, combine the peak-valley regulation model with the intelligent optimization algorithm, output the optimal charging scheduling strategy, and implement peak-valley load regulation, so as to effectively balance the load demand under the existing hardware conditions, without replacing the transformer or upgrading the line, greatly reducing the construction cost, and improving the user experience at the same time; by calculating the vehicle charging urgency value, reasonably dividing the emergency and normal scheduling queues, dynamically optimizing the peak load distribution, and dispersing the charging demand in a specific time period, the pressure on the power grid can be alleviated, and efficient peak-valley regulation of the AC charging pile can be achieved.

[0150] Reference Manual Attached Figure 2 , showing a structural schematic diagram of a peak-valley regulation system for an AC charging pile for an electric vehicle provided in an embodiment of the present invention.

[0151] The embodiment of the present invention provides a peak-valley regulation system 20 for an AC charging pile of an electric vehicle, comprising:

[0152] Processor 201;

[0153] The memory 202 stores computer-readable instructions, and when the computer-readable instructions are executed by the processor 201, the peak-valley regulation method of the AC charging pile of the electric vehicle is implemented.

[0154] From the above description, it can be seen that the peak-valley regulation system of the electric vehicle AC charging pile provided by the present invention can obtain historical data of the electric vehicles to be charged and the charging piles, combine the peak-valley regulation model with the intelligent optimization algorithm, output the optimal charging scheduling strategy, and implement peak-valley load regulation, so as to effectively balance the load demand under the existing hardware conditions, without replacing the transformer or upgrading the line, greatly reducing the construction cost, and improving the user experience at the same time; by calculating the vehicle charging urgency value, reasonably dividing the emergency and normal scheduling queues, dynamically optimizing the peak load distribution, and dispersing the charging demand in a specific time period, the pressure on the power grid can be alleviated, and efficient peak-valley regulation of the AC charging pile can be achieved.

[0155] Unless otherwise specifically stated, the relative arrangement of the parts and steps described in these embodiments, numerical expressions and numerical values ​​do not limit the scope of the present invention. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the accompanying drawings are not drawn according to the actual proportional relationship. The technology, method and equipment known to ordinary technicians in the relevant field may not be discussed in detail, but in appropriate cases, the technology, method and equipment should be regarded as a part of the authorization specification. In all examples shown and discussed here, any specific value should be interpreted as being merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once a certain item is defined in an accompanying drawing, it does not need to be further discussed in subsequent drawings.

[0156] For ease of description, spatially relative terms such as "above", "above", "on the upper surface of", "above", etc. may be used here to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" may include both "above" and "below". The device may also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatially relative descriptions used here are interpreted accordingly.

[0157] In the description of the present invention, it is necessary to understand that the directions or positional relationships indicated by directional words such as "front, back, up, down, left, right", "lateral, vertical, perpendicular, horizontal" and "top, bottom" are usually based on the directions or positional relationships shown in the drawings. They are only for the convenience of describing the present invention and simplifying the description. Unless otherwise specified, these directional words do not indicate or imply that the devices or elements referred to must have a specific direction or be constructed and operated in a specific direction. Therefore, they cannot be understood as limiting the scope of protection of the present invention. The directional words "inside and outside" refer to the inside and outside relative to the contours of each component itself.

[0158] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A peak-valley regulation method for an AC charging pile of an electric vehicle, characterized in that: include: S1: Obtaining data of electric vehicles to be charged and historical data of AC charging piles; S2: Calculating the charging urgency value of each electric vehicle to be charged based on the data of the electric vehicles to be charged; S3: Determine whether the charging urgency value of each of the electric vehicles to be charged is greater than a preset charging urgency value; if so, add the electric vehicle to be charged to an emergency dispatch queue; otherwise, add the electric vehicle to be charged to a normal dispatch queue; S4: Based on the historical data of the AC charging pile, the data of the electric vehicles to be charged, the emergency dispatch queue data and the normal dispatch queue data, a peak-valley regulation model of the AC charging pile is constructed with the goal of minimizing the change in power demand of the AC charging pile during peak hours and maximizing the utilization rate of the AC charging pile; S5: Determine the objective function and constraint conditions of the peak-valley regulation model; S6: Under the constraints of the constraints, with the goal of minimizing the function value of the objective function, the peak-valley regulation model is optimized by the tribal intelligent evolutionary algorithm to output an optimal charging scheduling strategy; S7: Dispatching the electric vehicles to be charged according to the optimal charging dispatching strategy to perform peak-valley regulation of the AC charging pile; Among them, the tribal intelligent evolution algorithm specifically includes: S601: Using the objective function as the fitness function of the tribal intelligent evolution algorithm; S602: Initializing a population and a Q table, wherein the population includes a plurality of individuals, each of which represents a set of feasible charging scheduling strategies; S603: clustering each individual using a clustering algorithm to form multiple tribes; S604: Calculate the fitness value of each individual in each tribe, and select the individual with the lowest fitness value as the leader; S605: Determine whether the minimum fitness value of each tribe is less than the average fitness value of the existing tribes; if so, the tribe is rated as a strong tribe; otherwise, the tribe is rated as a weak tribe; S606: Perform war adjustments on the individual parameters of each of the strong tribes and the individual parameters of each of the weak tribes using the following formula: ； ； in, represents the parameters of the plundered individual, Indicates the parameters of defeating the tribal leader, ε represents a constant; S607: Determine the tribe action reward value for each tribe to perform an action using the following formula: ； in, S i Indicates i The state of a tribe, Strong tribe It means a strong tribe. Weak tribe It means a weak tribe; S608: According to the tribe action reward value, update the Q table by the following formula: ； in, Indicates the updated state and action Q value, Indicates the current state and action before the update Q value, λ represents the learning rate, γ represents the discount factor, Indicates the state after executing the action Q The action with the largest value; S609: According to the Q table, using the accumulated reward value data, guiding the update of each individual in the existing tribe; S610: re-determine the leaders of each tribe based on the updated individual information, compare the fitness values ​​of the leaders of each tribe, and select the leader with the lowest fitness value as the best leader; S611: Determine whether the number of iterations reaches the maximum number of iterations or whether the convergence accuracy reaches the preset convergence accuracy. If so, output the charging scheduling strategy represented by the best leader as the best charging scheduling strategy; otherwise, proceed to the next step; S612: Determine whether there is only one tribe; if so, proceed to S603; otherwise, proceed to S606.

2. The peak-valley regulation method for an AC charging pile for an electric vehicle according to claim 1, characterized in that: The historical data of the AC charging pile specifically includes: the maximum charging power of the AC charging pile, historical voltage load data, historical peak time period data, and maximum charging capacity data; The electric vehicle data to be charged specifically includes: the arrival time, departure time, current battery status, total battery capacity, required charging power status and minimum acceptable power status of each electric vehicle to be charged.

3. The peak-valley regulation method for an AC charging pile for an electric vehicle according to claim 1, characterized in that: The calculation formula of the charging urgency value is specifically: ； in, L i Indicates i The charging urgency value of an electric vehicle, Indicates i The parking time of an electric vehicle, Δ x i Indicates i The time required to charge an electric car, SOC i Indicates i The current state of charge of an electric vehicle, , SOC min Indicates the lowest acceptable state of charge, .

4. The peak-valley regulation method for an AC charging pile for an electric vehicle according to claim 3, characterized in that: The calculation formula of the parking time of the electric vehicle is specifically: ； in, Indicates i The departure time of electric vehicles, Indicates i The arrival time of electric vehicles; The calculation formula for the required charging time of the electric vehicle is: ； in, P charge Indicates the charging power of the AC charging pile, C i Indicates i The total capacity of electric vehicle batteries, SOC target Indicates i The charging state required by an electric vehicle.

5. The peak-valley regulation method for an AC charging pile for an electric vehicle according to claim 1, characterized in that: The objective function is specifically: ； ； Among them, min means taking the minimum value, f represents the objective function, α t Indicates t The power demand weight in a time period is P t Indicates t The power demand in a period of time, P t-1 Indicates t -1 time period, Δ represents the increment operator, T 0 represents the time period with peak load. β t Indicates t The weight of electric vehicle charging demand in a time period, r it Indicates i Electric cars in t The amount of charge in a period of time, T represents a collection of related time periods, E Represents the collection of electric vehicles participating in charging.

6. The peak-valley regulation method for an AC charging pile for an electric vehicle according to claim 5, characterized in that: The calculation formula of the power demand weight is specifically: ； in, P max Indicates the maximum load of the power grid. γ It represents the adjustment parameter that controls the impact of power demand fluctuation on the weight.

7. The peak-valley regulation method for an AC charging pile for an electric vehicle according to claim 5, characterized in that: The calculation formula of the electric vehicle charging demand weight is specifically: ； in, Q charge,t Indicates t Charging demand in a certain period of time, Q max Indicates the maximum charging demand, δ Represents the adjustment parameter that controls the impact of charging demand on weight.

8. The peak-valley regulation method for an AC charging pile for an electric vehicle according to claim 1, characterized in that: The constraints specifically include: Each electric vehicle’s charging capacity does not exceed its own requested charging capacity; The charging capacity of each electric vehicle needs to be greater than or equal to its own minimum required charging capacity; The charging amount in each time period shall not exceed the maximum charging capacity of the AC charging pile; The sum of each EV’s charging amount during all time periods is equal to its charging request amount; The charging rate of each electric vehicle cannot exceed the maximum power limit of the AC charging station; In each time period, each electric vehicle in the emergency dispatch queue takes precedence over each electric vehicle in the normal dispatch queue.

9. The peak-valley regulation method for an AC charging pile for an electric vehicle according to claim 1, characterized in that: The objective function is used as the fitness function of the tribal intelligent evolutionary algorithm.

10. A peak-valley regulation system for an AC charging pile of an electric vehicle, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the peak-valley regulation method for an AC charging pile for an electric vehicle as claimed in any one of claims 1 to 9 is implemented.

Images