Dynamic power distribution method for charging pile with integration of demand and modular control

Abstract

The invention discloses a demand and modular control integrated charging pile power dynamic distribution method, and relates to the technical field of charging scheduling, and the method comprises the steps: building a charging vehicle recognition model, and building a vehicle charging prediction model; establishing a charging distribution model; a real-time vehicle set charged at the current moment at the charging module is acquired, and a vehicle supplementary set is obtained; calculating a charging congestion index at the charging module to obtain a charging module sequence; the redundant power of the charging pile is obtained through calculation, the to-be-adjusted charging power of the vehicles in the real-time vehicle set is obtained, the to-be-distributed power of the charging module is obtained, and the charging pile carries out power distribution of the charging module according to the numerical value of the to-be-distributed power. By establishing a charging vehicle identification model, establishing a vehicle charging prediction model, establishing a charging distribution model and calculating a charging congestion index at a charging module, power inclination is preferentially performed on more important vehicles, so that the range of negative effects caused by charging waiting is limited.

Description

Technical Field

[0001] The present invention relates to the technical field of charging scheduling, and in particular to a charging stack power dynamic allocation method integrating demand and modular control. Background Art

[0002] A charging stack is a large power cluster designed specifically to meet large-scale charging needs, such as large parking lots or businesses. The charging stack can convert AC power into DC power and is equipped with multiple charging modules to serve multiple electric vehicles at the same time.

[0003] Existing charging stations do not differentiate between the attributes of vehicles. When there is a more obvious wait, they are unable to prioritize the charging needs of more important vehicles, such as buses, which can easily increase the adverse effects of charging waits. Summary of the invention

[0004] In order to solve the above technical problems, a charging stack power dynamic allocation method integrating demand and modular control is provided. This technical solution solves the problems raised in the above background technology.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is: A method for dynamically allocating charging stack power integrating demand and modular control, comprising: Obtain at least one charging module integrated in the charging stack, and obtain an upper limit of the adjustable power of the charging stack; Establish a charging vehicle identification model and a vehicle charging prediction model; Based on the charging vehicle identification model, a charging allocation model is established; Obtain the real-time vehicle set currently being charged at the charging module, and predict the subsequent charging vehicles of the charging module based on the vehicle charging prediction model to obtain a vehicle supplement set; Based on the vehicle supplement set and the real-time vehicle set, the charging congestion index at the charging module is calculated, and the charging modules are sorted from large to small according to the charging congestion index to obtain a charging module sequence; The redundant power of the charging stack is calculated, and based on the charging vehicle identification model, the charging allocation model and the charging module sequence, the charging power to be adjusted of the vehicles in the real-time vehicle set is obtained. The charging stack obtains the power to be allocated of the charging module according to the charging power to be adjusted, and the charging stack allocates the power of the charging module according to the value of the power to be allocated.

[0006] Preferably, the establishment of the charging vehicle identification model comprises the following steps: Acquire at least one sample vehicle for charging, classify the sample vehicles according to usage attributes, and obtain sample public vehicles and sample private vehicles, where the usage attributes are public attributes and private attributes; Obtain the usage purposes of the sample public vehicles, obtain the impact scope of the suspension of the sample public vehicles, and obtain the suspension costs of the businesses involved in the usage purposes of the sample public vehicles; Use the urgency comprehensive formula to calculate the urgency coefficient of the use; The value range of the urgency coefficient is taken as the urgency range; Evenly divide the urgency range into at least one identification interval, and assign grades to the identification intervals from small to large according to the midpoints of the identification intervals; The sample public vehicles corresponding to the usages with urgency coefficients in the identification interval are summarized into a feature set, and the feature set corresponds to the identification interval; Extracting features from the appearance of the sample public vehicles in the feature set to obtain at least one identification feature, summarizing the features into an identification feature set, and pairing the identification feature set with the identification interval corresponding to the feature set; Extract and summarize the features of the sample private vehicles to obtain a private feature set; Aggregating the private feature set, the identification feature set, and the levels of the identification interval into a charging vehicle identification model; The urgent comprehensive formula is as follows: , Among them, A is the urgency coefficient of the use purpose, a is the impact scope of the suspension of the sample public vehicle, and b is the suspension cost of the business involved in the use of the sample public vehicle.

[0007] Preferably, the establishment of the vehicle charging prediction model comprises the following steps: Based on historical data, the maximum distance traveled by the vehicle for charging is obtained as a characteristic distance; Obtain the position coordinates of the charging module, and based on the position coordinates, form a charging identification area, where the charging identification area is an area with the position coordinates as the center and the characteristic distance as the radius; Obtaining the charging habits of the vehicle user, the charging habits being the remaining power range of the vehicle when the vehicle is being charged and the full power of the vehicle, and obtaining the charging speed of the vehicle; Divide a day evenly into at least one time sampling point; Obtain at least one movement route of the vehicle, where the movement route is a travel path of the vehicle within a day; At the time sampling point, when the vehicle is not in the charging identification area, the charging probability of the vehicle is 0. When the vehicle is in the charging identification area, the distance the vehicle moves in the moving route is obtained, and the power consumption of the vehicle at the time sampling point is obtained according to the vehicle's benchmark power consumption. The benchmark power consumption is the power consumption of the vehicle traveling one kilometer. The full power of the vehicle minus the power consumption of the vehicle at the time sampling point is used to obtain the characteristic remaining power, and the characteristic remaining power is paired with the time sampling point; Count the number of characteristic remaining power matched with the time sampling point within the range of the vehicle's remaining power as the number of characteristics; The number of features is divided by the number of remaining power features paired with the time sampling point to obtain the charging probability of the vehicle; The time sampling points are paired and fitted with the charging probability of the vehicle to obtain a probability fitting function, which corresponds to the vehicle and the charging module.

[0008] Preferably, the establishing of the charging allocation model based on the charging vehicle identification model comprises the following steps: Classify vehicles according to usage attributes to obtain public vehicles and private vehicles, and the usage attributes are public attributes and private attributes; The number of sample private vehicles is used as the target allocation coefficient for private vehicles, and the total number of sample private vehicles and sample public vehicles is used as the preliminary allocation coefficient for public vehicles; Extracting features from the appearance of the public vehicle to obtain at least one actual feature, and assigning a level of the identification interval corresponding to the identification feature set containing the largest number of actual features to the public vehicle; The preliminary allocation coefficient of the public vehicle is multiplied by the grade of the public vehicle to obtain the target allocation coefficient of the public vehicle; When the vehicle is a public vehicle, the target allocation coefficient of the public vehicle is used as the target allocation coefficient of the vehicle; when the vehicle is a private vehicle, the target allocation coefficient of the private vehicle is used as the target allocation coefficient of the vehicle.

[0009] Preferably, the predicting of the subsequent charging vehicles of the charging module to obtain the vehicle supplement set comprises the following steps: Substituting the current moment into at least one probability fitting function corresponding to the charging module to obtain at least one suspected probability; The vehicles corresponding to the probability fitting functions corresponding to the suspected probabilities greater than 0 are summarized to obtain a vehicle supplement set.

[0010] Preferably, the calculation of the charging congestion index at the charging module based on the vehicle supplement set and the real-time vehicle set comprises the following steps: Calculating a first charging time of a vehicle in the real-time vehicle set, where the first charging time of the vehicle is equal to a difference between a full charge of the vehicle and a real-time charge of the vehicle divided by a charging speed of the vehicle; The first charging time of the vehicles in the real-time vehicle set is multiplied and superimposed by the target allocation coefficient of the vehicles to obtain a first congestion index; Calculating the second charging time of the vehicles in the vehicle supplement set using the time comprehensive formula; The second charging time of the vehicle in the vehicle supplement set is multiplied by the corresponding suspected probability and the target allocation coefficient of the vehicle in sequence and then superimposed to obtain a second congestion index; The first congestion index is added to the second congestion index to obtain a charging congestion index at the charging module; The time synthesis formula is as follows: , Wherein, B is the second charging time, c is the full charge of the vehicle, e and f are the endpoint values ​​of the remaining power range of the vehicle respectively, and g is the charging speed of the vehicle.

[0011] Preferably, the calculation of the redundant power of the charging stack includes the following steps: Adding the real-time charging power of at least one charging module in the charging stack to obtain the total charging power; The redundant power of the charging stack is obtained by subtracting the total charging power from the upper limit of the adjustable power.

[0012] Preferably, the step of obtaining the charging power to be adjusted of the vehicles in the real-time vehicle set based on the charging vehicle identification model, the charging allocation model and the charging module sequence comprises the following steps: The charging congestion index at the charging module is superimposed to obtain the overall charging congestion index; The target allocation coefficients of the vehicles in the real-time vehicle set corresponding to the charging module are superimposed to obtain the overall target allocation coefficient; When the redundant power is greater than 0, the charging congestion index at the charging module is divided by the overall charging congestion index and then multiplied by the redundant power to obtain the power to be supplemented; The power to be supplemented is divided by the overall target allocation coefficient and then multiplied by the target allocation coefficient of the vehicles in the real-time vehicle set to obtain the power to be increased; The power to be increased is added to the real-time charging power of the corresponding vehicle in the real-time vehicle set to obtain the charging power to be adjusted of the vehicle in the real-time vehicle set; When the redundant power is equal to 0, the charging congestion index at the charging module is divided by the overall charging congestion index and then multiplied by the upper limit of the adjustable power to obtain the primary power; The primary power is divided by the overall target allocation coefficient and then multiplied by the target allocation coefficient of the vehicles in the real-time vehicle set to obtain the charging power to be adjusted; According to the order of the charging module sequence, the charging power to be adjusted of the vehicles in the real-time vehicle set corresponding to the charging module is calculated.

[0013] Preferably, the charging stack obtains the power to be allocated to the charging module according to the charging power to be adjusted, comprising the following steps: The charging powers to be adjusted of the vehicles in the real-time vehicle set corresponding to the charging module are superimposed to obtain the power to be allocated to the charging module.

[0014] Compared with the prior art, the present invention has the following beneficial effects: By establishing a charging vehicle identification model, a vehicle charging prediction model, a charging allocation model, obtaining a vehicle replenishment set and calculating the charging congestion index at the charging module, vehicles are classified and identified. When making charging adjustments, the subsequent charging conditions are estimated, and based on the prediction results, power is prioritized for more important vehicles. This ensures that when the charging power is insufficient globally or locally, public vehicles are less affected, thereby limiting the scope of the negative impact caused by waiting for charging. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic flow chart of a method for dynamically allocating power of a charging stack integrated with modular control according to the requirements of the present invention; Figure 2 A schematic diagram of a process for establishing a charging vehicle identification model according to the present invention; Figure 3 A schematic diagram of a process for establishing a vehicle charging prediction model according to the present invention; Figure 4 A schematic diagram of a flow chart of establishing a charging allocation model based on a charging vehicle identification model of the present invention; Figure 5 A schematic diagram of a process of predicting the subsequent charging vehicles of the charging module and obtaining a vehicle supplement set according to the present invention; Figure 6 A schematic diagram of a flow chart of calculating a charging congestion index at a charging module based on a vehicle supplement set and a real-time vehicle set according to the present invention; Figure 7 A schematic diagram of a flow chart of calculating the redundant power of a charging stack according to the present invention; Figure 8 The present invention is a flow chart of obtaining the charging power to be adjusted of vehicles in a real-time vehicle set based on a charging vehicle identification model, a charging allocation model and a charging module sequence. DETAILED DESCRIPTION

[0016] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0017] Reference Figure 1 As shown, a method for dynamically allocating charging stack power integrating demand and modular control comprises: Obtain at least one charging module integrated in the charging stack, and obtain an upper limit of the adjustable power of the charging stack; Establish a charging vehicle identification model and a vehicle charging prediction model; Based on the charging vehicle identification model, a charging allocation model is established; Obtain the real-time vehicle set currently being charged at the charging module, and predict the subsequent charging vehicles of the charging module based on the vehicle charging prediction model to obtain a vehicle supplement set; Based on the vehicle supplement set and the real-time vehicle set, the charging congestion index at the charging module is calculated, and the charging modules are sorted from large to small according to the charging congestion index to obtain a charging module sequence; The redundant power of the charging stack is calculated, and based on the charging vehicle identification model, the charging allocation model and the charging module sequence, the charging power to be adjusted of the vehicles in the real-time vehicle set is obtained. The charging stack obtains the power to be allocated of the charging module according to the charging power to be adjusted, and the charging stack allocates the power of the charging module according to the value of the power to be allocated.

[0018] The coverage area of ​​the charging pile is large, and the distance between the charging modules of the charging pile may be far. Therefore, the vehicle cannot be easily transferred between different charging modules. Therefore, it is necessary to adjust the power of the charging pile to alleviate the waiting time for charging. However, when the power is insufficient, no matter how it is adjusted, it is difficult to completely solve the congestion. Therefore, in this case, priority is given to charging of public vehicles. Therefore, different power allocations are made according to the different properties of the vehicles, so as to avoid as much as possible the partial paralysis of public transportation caused by the failure of buses to complete charging in time and the public impact caused by other public vehicles. For private vehicles, when encountering very urgent situations, they can be replaced by taking a taxi, but it is difficult to quickly find alternative solutions for public vehicles.

[0019] Reference Figure 2 As shown, establishing a charging vehicle identification model includes the following steps: Acquire at least one sample vehicle for charging, classify the sample vehicles according to usage attributes, and obtain sample public vehicles and sample private vehicles, where the usage attributes are public attributes and private attributes; Obtain the usage purposes of the sample public vehicles, obtain the impact scope of the suspension of the sample public vehicles, and obtain the suspension costs of the businesses involved in the usage purposes of the sample public vehicles; Use the urgency comprehensive formula to calculate the urgency coefficient of the use; The value range of the urgency coefficient is taken as the urgency range; Evenly divide the urgency range into at least one identification interval, and assign grades to the identification intervals from small to large according to the midpoints of the identification intervals; The sample public vehicles corresponding to the usages with urgency coefficients in the identification interval are summarized into a feature set, and the feature set corresponds to the identification interval; Extracting features from the appearance of the sample public vehicles in the feature set to obtain at least one identification feature, summarizing the features into an identification feature set, and pairing the identification feature set with the identification interval corresponding to the feature set; Extract and summarize the features of the sample private vehicles to obtain a private feature set; Aggregating the private feature set, the identification feature set, and the levels of the identification interval into a charging vehicle identification model; The urgent comprehensive formula is as follows: , Among them, A is the urgency coefficient of the use purpose, a is the impact scope of the suspension of the sample public vehicle, and b is the suspension cost of the business involved in the use of the sample public vehicle.

[0020] The purpose of establishing a charging vehicle identification model is to identify public vehicles and private vehicles, so as to distribute charging to different degrees. At the same time, public vehicles are also classified, so that different charging schemes are used for different levels of public vehicles. In this way, when power is insufficient, more important vehicles can be charged first.

[0021] Reference Figure 3 As shown, establishing a vehicle charging prediction model includes the following steps: Based on historical data, the maximum distance traveled by the vehicle for charging is obtained as a characteristic distance; Obtain the position coordinates of the charging module, and based on the position coordinates, form a charging identification area, where the charging identification area is an area with the position coordinates as the center and the characteristic distance as the radius; Obtaining the charging habits of the vehicle user, the charging habits being the remaining power range of the vehicle when the vehicle is being charged and the full power of the vehicle, and obtaining the charging speed of the vehicle; Divide a day evenly into at least one time sampling point; Obtain at least one movement route of the vehicle, where the movement route is a travel path of the vehicle within a day; At the time sampling point, when the vehicle is not in the charging identification area, the charging probability of the vehicle is 0. When the vehicle is in the charging identification area, the distance the vehicle moves in the moving route is obtained, and the power consumption of the vehicle at the time sampling point is obtained according to the vehicle's benchmark power consumption. The benchmark power consumption is the power consumption of the vehicle traveling one kilometer. The full power of the vehicle minus the power consumption of the vehicle at the time sampling point is used to obtain the characteristic remaining power, and the characteristic remaining power is paired with the time sampling point; Count the number of characteristic remaining power matched with the time sampling point within the range of the vehicle's remaining power as the number of characteristics; The number of features is divided by the number of remaining power features paired with the time sampling point to obtain the charging probability of the vehicle; The time sampling points are paired and fitted with the charging probability of the vehicle to obtain a probability fitting function, which corresponds to the vehicle and the charging module.

[0022] Since the vehicle's route is regular but not constant, at the same time of the day, the vehicle may appear in the charging identification area today, but not in the charging identification area tomorrow. However, the overall probability of appearance can be estimated. Therefore, probability is used to describe the possibility of the vehicle charging in the charging module. Here, each combination of vehicle and charging module determines a probability fitting function; Since the operation of vehicles is regular, their positions at each moment can be predicted. The significance of the prediction is to predict the subsequent charging status of the charging module. When calculating its congestion, not only the currently charging vehicles are taken into consideration, but also the vehicles in the subsequent period of time are considered. Therefore, the allocated power is based on the combination of the two. Taking the two charging modules E and F as an example, the current number of vehicles charging at E is 5, and it is predicted that 20 vehicles will be charged in the future. The current number of vehicles charging at F is 8, and it is predicted that 2 vehicles will be charged in the future. Therefore, the power allocated to E must be greater, otherwise, serious congestion will occur in the future. Therefore, by making charging predictions, adjustments can be made in advance.

[0023] Reference Figure 4 As shown, based on the charging vehicle identification model, establishing the charging allocation model includes the following steps: Classify vehicles according to usage attributes to obtain public vehicles and private vehicles, and the usage attributes are public attributes and private attributes; The number of sample private vehicles is used as the target allocation coefficient for private vehicles, and the total number of sample private vehicles and sample public vehicles is used as the preliminary allocation coefficient for public vehicles; Extracting features from the appearance of the public vehicle to obtain at least one actual feature, and assigning a level of the identification interval corresponding to the identification feature set containing the largest number of actual features to the public vehicle; The preliminary allocation coefficient of the public vehicle is multiplied by the grade of the public vehicle to obtain the target allocation coefficient of the public vehicle; When the vehicle is a public vehicle, the target allocation coefficient of the public vehicle is used as the target allocation coefficient of the vehicle; when the vehicle is a private vehicle, the target allocation coefficient of the private vehicle is used as the target allocation coefficient of the vehicle.

[0024] The target allocation coefficient of the vehicle determines the power value obtained by the vehicle. The larger the power value, the faster the charging speed. Therefore, the target allocation coefficient of the vehicle must be proportional to the importance of the vehicle. In the above setting process, the target allocation coefficient of private vehicles is smaller than that of public vehicles, and the target allocation coefficient of low-level public vehicles is smaller than that of high-level public vehicles. Therefore, the adjustment needs are met.

[0025] Reference Figure 5 As shown, predicting the subsequent charging vehicles of the charging module to obtain a vehicle supplement set includes the following steps: Substituting the current moment into at least one probability fitting function corresponding to the charging module to obtain at least one suspected probability; The vehicles corresponding to the probability fitting functions corresponding to the suspected probabilities greater than 0 are summarized to obtain a vehicle supplement set.

[0026] The vehicle supplement set is the vehicles that may be charged in the charging module later.

[0027] Reference Figure 6 As shown, based on the vehicle supplement set and the real-time vehicle set, calculating the charging congestion index at the charging module includes the following steps: Calculating a first charging time of a vehicle in the real-time vehicle set, where the first charging time of the vehicle is equal to a difference between a full charge of the vehicle and a real-time charge of the vehicle divided by a charging speed of the vehicle; The first charging time of the vehicles in the real-time vehicle set is multiplied and superimposed by the target allocation coefficient of the vehicles to obtain a first congestion index; Calculating the second charging time of the vehicles in the vehicle supplement set using the time comprehensive formula; The second charging time of the vehicle in the vehicle supplement set is multiplied by the corresponding suspected probability and the target allocation coefficient of the vehicle in sequence and then superimposed to obtain a second congestion index; The first congestion index is added to the second congestion index to obtain a charging congestion index at the charging module; The time synthesis formula is as follows: , Wherein, B is the second charging time, c is the full charge of the vehicle, e and f are the endpoint values ​​of the remaining power range of the vehicle respectively, and g is the charging speed of the vehicle.

[0028] The calculation of the congestion coefficient should reflect the importance of the vehicle. That is, under the same charging waiting time, the congestion coefficient of more important vehicles is larger. Therefore, when calculating the charging congestion index, the charging time needs to be weighted, and the weight is the target allocation coefficient with the vehicle. The calculation of the first congestion index is different from that of the second congestion index because, when calculating the first congestion index, the real-time power of the vehicles in the real-time vehicle set is known, so their charging time can be directly calculated, but the real-time power of the vehicles in the vehicle replenishment set is unknown, so the charging time can only be estimated based on the charging habits of the vehicle users, using the mean of the calculation results of the endpoints of the vehicle's remaining power range for an approximate estimate.

[0029] Reference Figure 7 As shown, calculating the redundant power of the charging stack includes the following steps: Adding the real-time charging power of at least one charging module in the charging stack to obtain the total charging power; The redundant power of the charging stack is obtained by subtracting the total charging power from the upper limit of the adjustable power.

[0030] Reference Figure 8 As shown, based on the charging vehicle identification model, the charging allocation model and the charging module sequence, obtaining the charging power to be adjusted of the vehicles in the real-time vehicle set includes the following steps: The charging congestion index at the charging module is superimposed to obtain the overall charging congestion index; The target allocation coefficients of the vehicles in the real-time vehicle set corresponding to the charging module are superimposed to obtain the overall target allocation coefficient; When the redundant power is greater than 0, the charging congestion index at the charging module is divided by the overall charging congestion index and then multiplied by the redundant power to obtain the power to be supplemented; The power to be supplemented is divided by the overall target allocation coefficient and then multiplied by the target allocation coefficient of the vehicles in the real-time vehicle set to obtain the power to be increased; The power to be increased is added to the real-time charging power of the corresponding vehicle in the real-time vehicle set to obtain the charging power to be adjusted of the vehicle in the real-time vehicle set; When the redundant power is equal to 0, the charging congestion index at the charging module is divided by the overall charging congestion index and then multiplied by the upper limit of the adjustable power to obtain the primary power; The primary power is divided by the overall target allocation coefficient and then multiplied by the target allocation coefficient of the vehicles in the real-time vehicle set to obtain the charging power to be adjusted; According to the order of the charging module sequence, the charging power to be adjusted of the vehicles in the real-time vehicle set corresponding to the charging module is calculated.

[0031] Depending on the redundant power, adjustments are made for different situations. When the redundant power is greater than 0, the redundant power will be redistributed according to the charging congestion index at the charging module and the target allocation coefficient of the vehicle. However, when the redundant power is 0, it means that there is no spare charging power. Therefore, the charging power can only be redistributed according to the charging congestion index at the charging module and the target allocation coefficient of the vehicle. According to this allocation method, more important vehicles are allocated more charging power.

[0032] The charging stack obtains the power to be allocated to the charging module according to the charging power to be adjusted, including the following steps: The charging powers to be adjusted of the vehicles in the real-time vehicle set corresponding to the charging module are superimposed to obtain the power to be allocated to the charging module.

[0033] Furthermore, the present solution also proposes a storage medium on which a computer-readable program is stored, and when the computer-readable program is called, it executes the above-mentioned demand and modular control integrated charging stack power dynamic allocation method.

[0034] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0035] In summary, the advantages of the present invention are: by establishing a charging vehicle identification model, a vehicle charging prediction model, a charging allocation model, obtaining a vehicle replenishment set and calculating the charging congestion index at the charging module, the vehicles are classified and identified, and when making charging adjustments, the subsequent charging conditions are estimated, and based on the prediction results, power is preferentially tilted to more important vehicles, thereby ensuring that when the charging power is insufficient globally or locally, public vehicles are less affected, thereby limiting the scope of the negative impact caused by charging waiting.

[0036] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for dynamic allocation of charging stack power integrating demand and modular control, characterized in that: include: Obtain at least one charging module integrated in the charging stack, and obtain an upper limit of the adjustable power of the charging stack; Establish a charging vehicle identification model and a vehicle charging prediction model; Based on the charging vehicle identification model, a charging allocation model is established; Obtain the real-time vehicle set currently being charged at the charging module, and predict the subsequent charging vehicles of the charging module based on the vehicle charging prediction model to obtain a vehicle supplement set; Based on the vehicle supplement set and the real-time vehicle set, the charging congestion index at the charging module is calculated, and the charging modules are sorted from large to small according to the charging congestion index to obtain a charging module sequence; The redundant power of the charging stack is calculated, and based on the charging vehicle identification model, the charging allocation model and the charging module sequence, the charging power to be adjusted of the vehicles in the real-time vehicle set is obtained. The charging stack obtains the power to be allocated of the charging module according to the charging power to be adjusted, and the charging stack allocates the power of the charging module according to the value of the power to be allocated.

2. According to claim 1, a method for dynamic allocation of charging stack power integrating demand and modular control, characterized in that: The establishment of the charging vehicle identification model comprises the following steps: Acquire at least one sample vehicle for charging, classify the sample vehicles according to usage attributes, and obtain sample public vehicles and sample private vehicles, where the usage attributes are public attributes and private attributes; Obtain the usage purposes of the sample public vehicles, obtain the impact scope of the suspension of the sample public vehicles, and obtain the suspension costs of the businesses involved in the usage purposes of the sample public vehicles; Use the urgency comprehensive formula to calculate the urgency coefficient of the use; The value range of the urgency coefficient is taken as the urgency range; Evenly divide the urgency range into at least one identification interval, and assign grades to the identification intervals from small to large according to the midpoints of the identification intervals; The sample public vehicles corresponding to the usages with urgency coefficients in the identification interval are summarized into a feature set, and the feature set corresponds to the identification interval; Extracting features from the appearance of the sample public vehicles in the feature set to obtain at least one identification feature, summarizing the features into an identification feature set, and pairing the identification feature set with the identification interval corresponding to the feature set; Extract and summarize the features of the sample private vehicles to obtain a private feature set; Aggregating the private feature set, the identification feature set, and the levels of the identification interval into a charging vehicle identification model; The urgent comprehensive formula is as follows: , Among them, A is the urgency coefficient of the use purpose, a is the impact scope of the suspension of the sample public vehicle, and b is the suspension cost of the business involved in the use of the sample public vehicle.

3. The method for dynamic allocation of charging stack power integrating demand and modular control according to claim 2 is characterized in that: The establishment of the vehicle charging prediction model comprises the following steps: Based on historical data, the maximum distance traveled by the vehicle for charging is obtained as a characteristic distance; Obtain the position coordinates of the charging module, and based on the position coordinates, form a charging identification area, where the charging identification area is an area with the position coordinates as the center and the characteristic distance as the radius; Obtaining the charging habits of the vehicle user, the charging habits being the remaining power range of the vehicle when the vehicle is being charged and the full power of the vehicle, and obtaining the charging speed of the vehicle; Divide a day evenly into at least one time sampling point; Obtain at least one movement route of the vehicle, where the movement route is a travel path of the vehicle within a day; At the time sampling point, when the vehicle is not in the charging identification area, the charging probability of the vehicle is 0. When the vehicle is in the charging identification area, the distance the vehicle moves in the moving route is obtained, and the power consumption of the vehicle at the time sampling point is obtained according to the vehicle's benchmark power consumption. The benchmark power consumption is the power consumption of the vehicle traveling one kilometer. The full power of the vehicle minus the power consumption of the vehicle at the time sampling point is used to obtain the characteristic remaining power, and the characteristic remaining power is paired with the time sampling point; Count the number of characteristic remaining power matched with the time sampling point within the range of the vehicle's remaining power as the number of characteristics; The number of features is divided by the number of remaining power features paired with the time sampling point to obtain the charging probability of the vehicle; The time sampling points are paired and fitted with the charging probability of the vehicle to obtain a probability fitting function, which corresponds to the vehicle and the charging module.

4. The method for dynamic allocation of charging stack power integrating demand and modular control according to claim 3 is characterized in that: The establishment of a charging allocation model based on the charging vehicle identification model comprises the following steps: Classify vehicles according to usage attributes to obtain public vehicles and private vehicles, and the usage attributes are public attributes and private attributes; The number of sample private vehicles is used as the target allocation coefficient for private vehicles, and the total number of sample private vehicles and sample public vehicles is used as the preliminary allocation coefficient for public vehicles; Extracting features from the appearance of the public vehicle to obtain at least one actual feature, and assigning a level of the identification interval corresponding to the identification feature set containing the largest number of actual features to the public vehicle; The preliminary allocation coefficient of the public vehicle is multiplied by the grade of the public vehicle to obtain the target allocation coefficient of the public vehicle; When the vehicle is a public vehicle, the target allocation coefficient of the public vehicle is used as the target allocation coefficient of the vehicle; when the vehicle is a private vehicle, the target allocation coefficient of the private vehicle is used as the target allocation coefficient of the vehicle.

5. The method for dynamic allocation of charging stack power integrating demand and modular control according to claim 4 is characterized in that: The predicting of the subsequent charging vehicles of the charging module to obtain the vehicle supplement set includes the following steps: Substituting the current moment into at least one probability fitting function corresponding to the charging module to obtain at least one suspected probability; The vehicles corresponding to the probability fitting functions corresponding to the suspected probabilities greater than 0 are summarized to obtain a vehicle supplement set.

6. The method for dynamic allocation of charging stack power integrating demand and modular control according to claim 5, characterized in that: The calculation of the charging congestion index at the charging module based on the vehicle supplement set and the real-time vehicle set includes the following steps: Calculating a first charging time of a vehicle in the real-time vehicle set, where the first charging time of the vehicle is equal to a difference between a full charge of the vehicle and a real-time charge of the vehicle divided by a charging speed of the vehicle; The first charging time of the vehicles in the real-time vehicle set is multiplied and superimposed by the target allocation coefficient of the vehicles to obtain a first congestion index; Calculating the second charging time of the vehicles in the vehicle supplement set using the time comprehensive formula; The second charging time of the vehicle in the vehicle supplement set is multiplied by the corresponding suspected probability and the target allocation coefficient of the vehicle in sequence and then superimposed to obtain a second congestion index; The first congestion index is added to the second congestion index to obtain a charging congestion index at the charging module; The time synthesis formula is as follows: , Wherein, B is the second charging time, c is the full charge of the vehicle, e and f are the endpoint values ​​of the remaining power range of the vehicle respectively, and g is the charging speed of the vehicle.

7. The method for dynamic allocation of charging stack power integrating demand and modular control according to claim 6 is characterized in that: The calculation of the redundant power of the charging stack comprises the following steps: Adding the real-time charging power of at least one charging module in the charging stack to obtain the total charging power; The redundant power of the charging stack is obtained by subtracting the total charging power from the upper limit of the adjustable power.

8. The method for dynamic allocation of charging stack power integrating demand and modular control according to claim 7, characterized in that: The method of obtaining the charging power to be adjusted of the vehicles in the real-time vehicle set based on the charging vehicle identification model, the charging allocation model and the charging module sequence comprises the following steps: The charging congestion index at the charging module is superimposed to obtain the overall charging congestion index; The target allocation coefficients of the vehicles in the real-time vehicle set corresponding to the charging module are superimposed to obtain the overall target allocation coefficient; When the redundant power is greater than 0, the charging congestion index at the charging module is divided by the overall charging congestion index and then multiplied by the redundant power to obtain the power to be supplemented; The power to be supplemented is divided by the overall target allocation coefficient and then multiplied by the target allocation coefficient of the vehicles in the real-time vehicle set to obtain the power to be increased; The power to be increased is added to the real-time charging power of the corresponding vehicle in the real-time vehicle set to obtain the charging power to be adjusted of the vehicle in the real-time vehicle set; When the redundant power is equal to 0, the charging congestion index at the charging module is divided by the overall charging congestion index and then multiplied by the upper limit of the adjustable power to obtain the primary power; The primary power is divided by the overall target allocation coefficient and then multiplied by the target allocation coefficient of the vehicles in the real-time vehicle set to obtain the charging power to be adjusted; According to the order of the charging module sequence, the charging power to be adjusted of the vehicles in the real-time vehicle set corresponding to the charging module is calculated.

9. The method for dynamic allocation of charging stack power integrating demand and modular control according to claim 8, characterized in that: The charging stack obtains the power to be allocated to the charging module according to the charging power to be adjusted, comprising the following steps: The charging powers to be adjusted of the vehicles in the real-time vehicle set corresponding to the charging module are superimposed to obtain the power to be allocated to the charging module.

Images