Distribution network charging pile recommendation method, device, electronic device and storage medium

Abstract

The present invention discloses a method, device, electronic device and storage medium for recommending charging piles in a distribution network, including: receiving a charging request from a car owner, determining a candidate charging pile based on a first position and a drivable distance of a vehicle to be charged, obtaining the charging habit characteristics of the car owner and determining a direct transformer of the candidate charging pile, obtaining the total load and user type of the direct transformer of users other than the charging pile at a target charging time, calculating the load rate using the total load and rated power, and judging whether the load rate is greater than a load rate threshold; if so, calculating the score of the candidate charging pile according to the charging habit characteristics, the charging amount, the first position, the target charging time, the load rate, and the user type, determining the target charging pile according to the score and recommending it to the car owner, so that the recommended charging pile not only meets the charging habit of the car owner, improves the car owner's satisfaction with the charging service, but also reduces the impact of the charging pile on the power supply of the distribution network when it is connected to the distribution network, so that the charging pile recommendation is more complete.

Description

Technical Field

[0001] The present invention relates to the technical field of charging pile operation in a distribution network, and in particular to a method, device, electronic device and storage medium for recommending charging piles in a distribution network. Background Art

[0002] With the increase in the number of new energy vehicles, a large number of charging stations have been added to the distribution network to meet the charging needs of vehicles to be charged through the charging piles in the charging stations.

[0003] In the prior art, car owners can issue charging requests or make charging reservations on an APP. The APP will recommend the nearest charging pile or the one with the lowest charging cost to the car owner based on the vehicle's current power level, location or scheduled charging time. However, the above charging pile recommendations do not take into account the impact of the charging pile on the power supply of the distribution network when it is connected to the distribution network, which will cause insufficient power supply for civil and commercial purposes other than the charging piles, affecting the power supply quality of the distribution network and causing a surge in complaints. Summary of the invention

[0004] The present invention provides a method, device, electronic device and storage medium for recommending charging piles in a distribution network, so as to solve the problem that the existing charging pile recommendation is not perfect, resulting in a decline in the power supply quality of the distribution network and a surge in complaints.

[0005] In a first aspect, the present invention provides a method for recommending charging piles in a distribution network, comprising:

[0006] receiving a charging request from a vehicle owner, the charging request including a first location of the vehicle to be charged, a target charging time, a charging amount, and a drivable distance;

[0007] Determine a plurality of candidate charging piles based on the first position and the drivable distance of the vehicle to be charged;

[0008] Obtaining the charging habit characteristics of the vehicle owner, and determining the direct transformer of each candidate charging pile;

[0009] For each directly affiliated transformer, obtaining a first total load of non-charging pile users of the directly affiliated transformer at the target charging time, and obtaining a user type of the directly affiliated transformer;

[0010] Calculating a load rate using the first total load and the rated power of the directly-affiliated transformer, and determining whether the load rate is greater than a preset load rate threshold;

[0011] If so, calculating the score of the candidate charging pile according to the charging habit characteristics, the charging amount, the first location, the target charging time, the load rate, and the user type;

[0012] A target charging pile is determined from the candidate charging piles according to the scores, and the target charging pile is recommended to the car owner.

[0013] In a second aspect, the present invention provides a charging pile recommendation device for a distribution network, comprising:

[0014] A charging request receiving module, used to receive a charging request from a vehicle owner, wherein the charging request includes a first position of the vehicle to be charged, a target charging time, a charging amount, and a drivable distance;

[0015] A candidate charging pile determination module, configured to determine a plurality of candidate charging piles based on the first position and the drivable distance of the vehicle to be charged;

[0016] A charging habit feature and direct transformer determination module, used to obtain the charging habit feature of the vehicle owner and determine the direct transformer of each candidate charging pile;

[0017] A directly-affiliated transformer data acquisition module, configured to acquire, for each directly-affiliated transformer, a first total load of non-charging pile users of the directly-affiliated transformer at the target charging time, and acquire a user type of the directly-affiliated transformer;

[0018] A load rate determination module, configured to calculate the load rate using the first total load and the rated power of the directly-affiliated transformer, and determine whether the load rate is greater than a preset load rate threshold, and if so, execute a charging pile score calculation module;

[0019] A charging pile score calculation module, used to calculate the score of the candidate charging pile according to the charging habit characteristics, the charging amount, the first location, the target charging time, the load rate and the user type;

[0020] The charging pile recommendation module is used to determine a target charging pile from the candidate charging piles according to the scores, and recommend the target charging pile to the car owner.

[0021] In a third aspect, the present invention provides an electronic device, the electronic device comprising:

[0022] at least one processor; and

[0023] a memory communicatively connected to the at least one processor; wherein,

[0024] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution network charging pile recommendation method described in the first aspect of the present invention.

[0025] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the distribution network charging pile recommendation method described in the first aspect of the present invention when executed.

[0026] After receiving the charging request from the car owner, the embodiment of the present invention determines multiple candidate charging piles according to the position and drivable distance of the vehicle to be charged, predicts the total load of non-charging pile users of the direct transformer of each candidate charging pile, and determines the user type of the user supplied by the direct transformer, and calculates the load rate according to the total load and the rated power. When the load rate is greater than the threshold, the score of each candidate charging pile is calculated according to the charging habit characteristics of the car owner, the charging amount, position, target charging time, load rate and user type of the vehicle to be charged, and the target charging pile is determined according to the score and recommended to the car owner. The charging habit of the car owner, the position, target charging time and charging amount of the vehicle to be charged, and the load rate of the direct transformer of the charging pile and the user type of the power supply are considered, so that the recommended charging pile can meet the charging habit of the car owner, improve the satisfaction of the car owner with the charging service, and reduce the impact of the recommended charging pile on the distribution network when it is connected to the distribution network to perform the charging service, so that the charging pile recommendation is more complete, and it is ensured that the power supply of users other than the charging pile in the distribution network has sufficient power, the power supply quality of the distribution network is improved, and the complaints caused by insufficient power supply are reduced.

[0027] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 This is a flow chart of a method for recommending charging piles in a distribution network provided in Embodiment 1 of the present invention;

[0030] Figure 2 This is a flow chart of a method for recommending charging piles in a distribution network provided in Embodiment 2 of the present invention;

[0031] Figure 3 It is a structural schematic diagram of a charging pile recommendation device for a distribution network provided by the third embodiment of the present invention;

[0032] Figure 4 It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0033] 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.

[0034] Embodiment 1

[0035] Figure 1 This is a flow chart of a method for recommending charging piles in a distribution network provided in the first embodiment of the present invention. This embodiment can be applied to the case of recommending charging piles in response to a charging request of a car owner in a distribution network. The method can be executed by a charging pile recommendation device for a distribution network. The charging pile recommendation device for a distribution network can be implemented in the form of hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the recommended method for charging piles in the distribution network includes:

[0036] S101. Receive a charging request from a vehicle owner, where the charging request includes a first location of the vehicle to be charged, a target charging time, a charging amount, and a drivable distance.

[0037] In this embodiment, when the owner of the vehicle to be charged needs to charge, he can input the expected charging amount, charging time and drivable distance on the APP (APPlication). The APP will then generate a charging request including the first position of the vehicle to be charged, the target charging time, the charging amount and the drivable distance, and send the charging request to the server, which can receive the charging request.

[0038] Among them, the first position of the vehicle to be charged may be the position of the vehicle to be charged when the charging request is sent. Exemplarily, while the vehicle to be charged is traveling, the first position may be obtained by positioning through a positioning system on the vehicle to be charged or a mobile phone of the owner on the vehicle to be charged. When the vehicle to be charged and the owner are not in the same position, the owner may manually input the position of the vehicle to be charged. The target charging time may be the charging time expected by the owner, which may be a specific moment or a time period. The charging amount may be the amount of electricity required to be charged for the vehicle to be charged, which may be input by the owner, or may be the remaining power of the battery of the vehicle to be charged obtained after the APP interacts with the vehicle to be charged, and the charging amount is obtained by calculating the difference between the total capacity of the battery and the remaining power. The drivable distance may be the maximum distance that the remaining power can support the vehicle to be charged.

[0039] S102: Determine a plurality of candidate charging piles based on a first position and a drivable distance of the vehicle to be charged.

[0040] Specifically, a circular area may be determined with the first position of the vehicle to be charged as the center and the drivable distance as the radius, and the charging piles within the circular area may be determined as candidate charging piles.

[0041] In another embodiment, the first position may be used as a starting point, and a plurality of driving paths that can be reached by the drivable distance may be used as a reference to generate charging piles that can be reached by the plurality of driving paths as candidate charging piles.

[0042] S103: Obtain the charging habit characteristics of the vehicle owner, and determine the direct transformer of each candidate charging pile.

[0043] A directly affiliated transformer may refer to a transformer in the distribution network that directly supplies power to a candidate charging pile. In one example, the transformer that directly supplies power to each candidate charging pile may be determined as a directly affiliated transformer through the distribution network line topology diagram. In another example, the number of the candidate charging pile may be entered in the distribution network system to search for the directly affiliated transformer.

[0044] The charging habit feature of the vehicle owner may be data reflecting the charging preference of the vehicle owner. In one embodiment, the charging habit feature may be the probability that the vehicle owner belongs to various charging types, where the charging types may include the following types:

[0045] Distance priority type: Car owners prefer to charge at the nearest charging station;

[0046] Cost priority type: Car owners prefer to charge at charging stations with more economical electricity prices;

[0047] Time priority type: Car owners prefer to charge at charging stations with short waiting times;

[0048] Fixed charging station preference type: Car owners prefer to charge at the same charging station.

[0049] This embodiment can pre-train a charging classification model, and use the charging classification model to identify the probability that the owner belongs to each charging type. In an example, the charging data of each owner within a period of time (such as one year or half a year) can be obtained as sample data during training. The sample data includes the time and location of the charging request issued by the owner each time, the location of the charging pile used for charging, the electricity price and other data, and the probability that the owner belongs to each charging type is calculated for each sample data. For example, assuming that the owner charges 10 times in a month, 4 times he chooses the nearest charging pile, 2 times he chooses the charging pile with the lowest electricity price, 1 time he chooses the charging pile with the shortest waiting time, and 3 times he chooses to charge at the same charging pile, then the owner can be marked as belonging to the distance priority type The probability of belonging to the cost priority type is 0.4, the probability of belonging to the time priority type is 0.2, the probability of belonging to the fixed charging pile priority type is 0.1, and the probability of belonging to the fixed charging pile priority type is 0.3. During training, the sample data is input into the charging classification model to predict the probability of the owner belonging to various charging types, and the loss rate is calculated by the predicted probability and the marked probability. The parameters of the charging classification model are adjusted according to the loss rate until the loss rate is less than the threshold or the number of training times reaches the preset number of times, and the trained charging classification model can be obtained. Among them, the loss rate can adopt the mean square error loss function, the cross entropy loss function, etc., and the stochastic gradient descent algorithm and the small batch gradient descent algorithm can be used when adjusting the model parameters. This embodiment does not limit the algorithm for calculating the loss rate and adjusting the model parameters.

[0050] After the charging classification model is trained, the owner's historical charging data can be obtained, such as the owner's historical charging data within one year before the current time, and the historical charging data can be input into the charging classification model to obtain the probability of the owner belonging to various charging types as the owner's charging habit characteristics, that is, the probability of the owner belonging to the distance priority type, cost priority type, time priority type and fixed charging pile priority type is used as the charging habit feature.

[0051] Of course, the charging habit feature may also include the probability that the car owner prefers to charge in a certain charging time period (such as the off-peak period), etc. The embodiment of the present invention does not limit the charging habit feature.

[0052] S104: For each directly affiliated transformer, obtain a first total load of non-charging pile users of the directly affiliated transformer at a target charging time, and obtain a user type of the directly affiliated transformer.

[0053] In the distribution network, power is supplied to users in a region through a transformer. Power users in the power supply area of ​​the transformer may include charging pile users and non-charging pile users such as residents, hospitals, and water plants. The user type of the directly affiliated transformer can be determined and the first total load of the non-charging pile users at the target charging time can be predicted. Specifically, the historical total load of the non-charging pile users of the directly affiliated transformer can be obtained, and the first total load of the non-charging pile users of the directly affiliated transformer at the target charging time can be predicted based on the historical total load.

[0054] In one embodiment, a statistical analysis can be performed on the total load of non-charging pile users at various times on different dates of the directly affiliated transformer, and the total load of non-charging pile users at various times of the statistical analysis can be used as the predicted total load. For example, the total load of non-charging pile users of the directly affiliated transformer at 10:30 every day is counted. When it is necessary to predict the total load of non-charging pile users at 10:30 on the nearest day in the future, the average total load of non-charging pile users of the directly affiliated transformer in the past 5 days is calculated as the total load of non-charging pile users at 10:30 on the nearest day in the future.

[0055] In another embodiment, the load forecasting model can also be pre-trained, and the total historical load can be input into the load forecasting model to obtain the first total load of the non-charging pile users directly under the transformer at the target charging time. Exemplarily, when training the load forecasting model, a load sequence can be constructed first, which includes time and load, and then N load sequences before the target time node are extracted from the load sequence and input into the load forecasting model to predict the load at m time nodes after the target time node. The loss rate is calculated by the predicted load and the load at m time nodes in the load sequence, and the load forecasting model is adjusted by the loss rate until the training conditions are met to obtain a trained load forecasting model. For example, a total load sequence of non-charging pile users directly under the transformer is as follows:

[0056] (2023-01-01-08:00, 23KW; 2023-01-02-08:00, 33KW; 2023-01-03-08:00, 30KW; 2023-01-04-08:00, 29KW; 2023-01-05-08:00, 27KW; 2023-01-06-08:00, 31KW; 2023-01-07-08:00, 30KW; 2023-01-08-08:00, 35KW; 2023-01-09-08:00, 33KW; 2023-01-10-08:00, 33KW).

[0057] In the training load forecasting model, 2023-01-05-08:00 is taken as the target time node, and the load sequence (including time and load) from 2023-01-01-08:00 to 2023-01-04-08:00 between 2023-01-05-08:00 is input into the load forecasting model to predict the load from 2023-01-06-08:00 to 2023-01-10-08:00. The loss rate of the load from 1-06-08:00 to 2023-01-10-08:00 and the load from 2023-01-06-08-08:00 to 2023-01-10-08:00 in the total load sequence is calculated, such as calculating the mean square error loss, the cross entropy loss, etc., and the parameters of the load forecasting model are adjusted by gradient descent according to the calculated loss rate until the loss rate is less than a threshold or the number of training times reaches a preset number, and the trained load forecasting model is obtained.

[0058] When it is necessary to predict the first total load of non-charging pile users directly under the transformer at the target charging time, the historical total load of non-charging pile users can be input into the load prediction model to obtain the first total load of non-charging pile users directly under the transformer at the target charging time.

[0059] S105: Calculate the load rate using the first total load and the rated power of the directly-affiliated transformer, and determine whether the load rate is greater than a preset load rate threshold.

[0060] In this embodiment, the rated power of the direct transformer may be the maximum power allowed to be output when the direct transformer is working normally. The ratio of the first total load to the rated power of the direct transformer may be calculated as the load rate, and it may be determined whether the load rate is greater than the load rate threshold. Among them, those skilled in the art may determine based on the rated power of the direct transformer and the total power load of non-charging pile users. If the load rate is greater than the load rate threshold, it indicates that the power consumption of non-charging pile users of the direct transformer is large, and the power supply power of non-charging pile users should be met first. In order to avoid too many charging piles being connected to the distribution network to distribute the output power of the direct transformer, it is necessary to optimize the charging piles. For the method of accessing the power grid, S106 can be executed to optimize the charging pile recommendation to recommend charging piles other than the direct transformer. If the load rate is less than the load rate threshold, it indicates that the power consumption of non-charging pile users of the direct transformer is small, and the direct transformer has sufficient output power to supply the charging pile. The charging pile under the direct transformer can be recommended to the car owner based on the charging habit characteristics of the car owner. For example, when the car owner is accustomed to charging at the nearest charging pile, the nearest charging pile under the direct transformer can be recommended to the car owner. When the car owner is accustomed to charging at a fixed charging pile (the charging pile with which the car owner charges most times), the charging pile under the direct transformer can be recommended to the car owner.

[0061] S106. Calculate the score of the candidate charging pile according to the charging habit characteristics, the charging amount, the first location, the target charging time, the load rate, and the user type.

[0062] Specifically, the second position, target idle time and electricity price at the target charging time of each candidate charging pile can be obtained first, wherein the target idle time is the time after the target charging time and with the shortest time interval with the target charging time, and then the initial score of each candidate charging pile is calculated through the charging habit characteristics, the first position, the second position, the target idle time, the target charging time, the charging amount and the electricity price. Exemplarily, the distance can be calculated through the first position and the second position, the queuing time required for charging can be calculated through the target idle time and the target charging time, the charging cost can be calculated through the charging amount and the electricity price, and the initial score of each candidate charging pile can be calculated based on the probability that the owner belongs to the distance priority type, time priority type, cost priority type in the charging habit characteristics, the distance, the queuing time and the charging cost.

[0063] Furthermore, the reward and punishment factor of the candidate charging pile is determined based on the load rate of the directly affiliated transformer and the user type, and the initial score is adjusted by the reward and punishment factor to obtain the final score of the candidate charging pile, wherein the greater the load rate, the smaller the reward and punishment factor; the more designated user types are included in the user type, the smaller the reward and punishment factor; the smaller the reward and punishment factor, the greater the penalty for the initial score, so that the final score of the candidate charging pile is smaller.

[0064] S107: Determine a target charging pile from the candidate charging piles according to the scores, and recommend the target charging pile to the car owner.

[0065] Specifically, the candidate charging piles can be sorted from large to small according to the scores, the top N candidate charging piles can be determined as target charging piles, and the target charging piles can be recommended to the car owner. For example, the location, queue time, electricity price and other information of the target charging pile can be recommended to the car owner so that the car owner can select a charging pile for appointment charging.

[0066] After receiving the charging request from the car owner, the embodiment of the present invention determines multiple candidate charging piles according to the position and drivable distance of the vehicle to be charged, predicts the total load of non-charging pile users of the direct transformer of each candidate charging pile, and determines the user type of the user supplied by the direct transformer, and calculates the load rate according to the total load and the rated power. When the load rate is greater than the threshold, the score of each candidate charging pile is calculated according to the charging habit characteristics of the car owner, the charging amount, position, target charging time, load rate and user type of the vehicle to be charged, and the target charging pile is determined according to the score and recommended to the car owner. The charging habit of the car owner, the position, target charging time and charging amount of the vehicle to be charged, and the load rate of the direct transformer of the charging pile and the user type of the power supply are considered, so that the recommended charging pile can meet the charging habit of the car owner, improve the satisfaction of the car owner with the charging service, and reduce the impact of the recommended charging pile on the distribution network when it is connected to the distribution network to perform the charging service, so that the charging pile recommendation is more complete, and it is ensured that the power supply of users other than the charging pile in the distribution network has sufficient power, the power supply quality of the distribution network is improved, and the complaints caused by insufficient power supply are reduced.

[0067] Embodiment 2

[0068] Figure 2 This is a flow chart of a method for recommending charging piles in a distribution network provided in the second embodiment of the present invention. The embodiment of the present invention is optimized on the basis of the above-mentioned first embodiment. Figure 2 As shown, the recommended method for charging piles in the distribution network includes:

[0069] S201. Receive a charging request from a vehicle owner, where the charging request includes a first location of the vehicle to be charged, a target charging time, a charging amount, and a drivable distance.

[0070] S202: Determine a plurality of candidate charging piles based on a first position and a drivable distance of the vehicle to be charged.

[0071] S203: Obtain the charging habit characteristics of the vehicle owner, and determine the direct transformer of each candidate charging pile.

[0072] S204: For each directly-affiliated transformer, obtain a first total load of non-charging pile users of the directly-affiliated transformer at a target charging time, and obtain a user type of the directly-affiliated transformer.

[0073] S205: Calculate the load rate using the first total load and the rated power of the directly-affiliated transformer, and determine whether the load rate is greater than a preset load rate threshold.

[0074] S201-S205 in this embodiment are substantially similar to S101-S105 in the first embodiment, and specific reference may be made to S101-S105 in the first embodiment, which will not be described in detail here.

[0075] S206: Obtain the second position, target idle time, and electricity price at the target charging time of each candidate charging pile, where the target idle time is the time after the target charging time and with the shortest time interval with the target charging time.

[0076] If the load rate of the directly affiliated transformer is greater than the load rate threshold, the second position, target idle time and electricity price at the target charging time of each candidate charging pile can be obtained, wherein the target idle time is the time after the target charging time and with the shortest time interval with the target charging time. Specifically, each charging pile in the distribution network can upload idle time information and real-time electricity price to the server, and the location of the charging pile can be pre-stored in the server.

[0077] S207: Calculate an initial score for each candidate charging post according to the charging habit characteristics, the first location, the second location, the target idle time, the target charging time, the charging amount, and the electricity price.

[0078] In this embodiment, the charging habit feature includes the probability that the owner's charging belongs to the distance priority type, the cost priority type, the time priority type and the fixed charging pile priority type. For each candidate charging pile, the first position and the second position can be used to calculate the distance from the vehicle to be charged to the candidate charging pile, the target idle time and the target charging time can be used to calculate the queue time, and the product of the electricity price and the charging amount of each candidate charging pile is calculated to obtain the charging cost of the vehicle to be charged at each candidate charging pile. The distance, queue time and charging cost of each candidate charging pile are normalized to obtain the distance d, queue time t and charging cost c with normalized values ​​between 0 and 1, and the initial score of each candidate charging pile is further calculated by the following formula:

[0079] ;

[0080] ;

[0081] Where i represents the i-th candidate charging pile, p_d is the probability that the owner belongs to the distance priority type, p_t is the probability that the owner belongs to the time priority type, p_c is the probability that the owner belongs to the cost priority type, p_a is the probability that the owner belongs to the fixed charging pile priority type, d i represents the distance from the vehicle to be charged to the i-th candidate charging pile, t i represents the queuing time required for the vehicle to be charged at the i-th candidate charging pile, c i represents the cost required for the vehicle to be charged at the i-th candidate charging pile, ε 1i It represents the second reward and penalty factor when the vehicle to be charged is charged at the i-th candidate charging pile. γ is a value greater than 0, for example, it can be a constant between 0 and 1. i_target represents the charging pile with the most charging times by the owner when the priority type of the fixed charging pile is set.

[0082] Through the above initial score Score i Calculation formula: If the probability p_d of the car owner belonging to the distance priority type is the largest, for each candidate charging pile, the queue time t i and charging cost c i In the same case, the distance d i The smaller the value, the probability p_d that the owner belongs to the distance priority type is in the initial score Score i The larger the proportion of the candidate charging pile with a short distance, the larger the initial score is, the more likely it is to recommend the candidate charging pile with a short distance to the car owner with distance priority. Similarly, the initial score Score i The calculation formula can recommend candidate charging piles with short waiting time for car owners who prioritize time, and recommend candidate charging piles with low electricity price for car owners who prioritize cost. 1i The initial score of the candidate charging pile i_target with the most charging times by the owner is increased by γ, so as to recommend the charging pile with the most charging times to the owner of the fixed charging pile priority type, so that the initial score of the candidate charging pile takes into account the various charging habits of the owner.

[0083] S208: Calculate a first reward or penalty factor of the candidate charging pile by using the load rate of the transformer directly under the candidate charging pile and the user type.

[0084] Specifically, the second total load of the preset type of users directly under the transformer can be obtained, and the ratio of the second total load to the first total load can be calculated to obtain the load proportion Ra of the preset type of users, and the first reward and punishment factor can be calculated by the following formula:

[0085] ;

[0086] Among them, Load_rate i Represents the load rate of the transformer directly under the i-th candidate charging pile, Ra i Indicates the load proportion of the preset type of users of the direct transformer of the i-th candidate charging pile.

[0087] Exemplarily, preset type users may refer to users who cannot have power outages, that is, users who are indispensable in daily life. For example, power outages in hospitals will affect the treatment of important patients, power outages in water plants will affect domestic water use, power outages in gas plants will affect gas supply, and power outages in municipal transportation will affect traffic operations. The preset type users may be hospital users, water plant users, gas plant users, municipal transportation users and other users. The historical loads of preset type users at the target charging time can be counted, and the sum of the historical loads of preset type users at the target charging time can be calculated as the second total load of preset type users, and the ratio of the second total load to the first total load can be calculated to obtain the load proportion Ra of preset type users. The larger the load proportion Ra, the higher the priority of the directly affiliated transformer in ensuring the power consumption of non-charging pile users.

[0088] S209: Calculate the product of the initial score and the first reward and punishment factor to obtain the score of the candidate charging pile.

[0089] That is, the final score of candidate charging pile i = Score i ×ε 2i , through the first reward and punishment factor ε 2i From the calculation formula, it can be seen that if the load rate of the direct transformer of the candidate charging pile i is larger and the load proportion Ra of the preset type of users is larger, the first reward and punishment factor ε 2i The smaller the value, the higher the initial score of candidate charging pile i. i The greater the penalty, the smaller the final score of the candidate charging pile, and the less likely it is to recommend the candidate charging pile i to the car owner, thereby preventing the car owner from sharing the output power of the direct transformer after charging at the candidate charging pile, resulting in insufficient power consumption for non-charging pile users of the direct transformer (especially preset types of users such as hospitals and water plants).

[0090] On the contrary, if the load rate of the direct transformer of the candidate charging pile i is smaller and the load proportion Ra of the preset type of users is smaller, the first reward and punishment factor ε 2i The larger the value, the higher the initial score of candidate charging pile i. i The smaller the penalty, the larger the final score of the candidate charging pile, and the more likely it is to recommend the candidate charging pile i to the car owner, thereby recommending the charging pile under the direct transformer with sufficient power and few users of the preset type to the car owner.

[0091] S210: Determine a target charging pile from the candidate charging piles according to the scores, and recommend the target charging pile to the car owner.

[0092] Specifically, the candidate charging piles can be sorted from large to small according to the scores, the top N candidate charging piles can be determined as target charging piles, and the target charging piles can be recommended to the car owner. For example, the location, queue time, electricity price and other information of the target charging pile can be recommended to the car owner so that the car owner can select a charging pile for appointment charging.

[0093] After receiving the charging request from the vehicle owner, the embodiment of the present invention determines multiple candidate charging piles according to the position and drivable distance of the vehicle to be charged, predicts the total load of non-charging pile users of the direct transformer of each candidate charging pile, and determines the user type of the user supplied by the direct transformer, and calculates the load rate according to the total load and the rated power. When the load rate is greater than the threshold, the initial score of each candidate charging pile is calculated according to the charging habit characteristics, the first position, the second position, the target idle time, the target charging time, the charging amount and the electricity price, and the first reward and punishment factor of the candidate charging pile is calculated by using the load rate of the direct transformer of the candidate charging pile and the user type, and the product of the initial score and the first reward and punishment factor is calculated to obtain The scores of the candidate charging piles are used to determine the target charging pile from the candidate charging piles and recommend the target charging pile to the car owner. This takes into account the car owner's charging habits, the location of the vehicle to be charged, the target charging time, the charging amount, the load rate of the direct transformer of the charging pile, and the type of user supplied with power. This ensures that the recommended charging piles can both meet the car owner's charging habits and improve the car owner's satisfaction with the charging service, and reduce the impact of the recommended charging piles on the distribution network when they are connected to the distribution network to perform charging services. This makes the recommendation of charging piles more complete, ensures that the power supply to users other than the charging piles in the distribution network has sufficient power, improves the power supply quality of the distribution network, and reduces complaints caused by insufficient power supply.

[0094] Furthermore, when calculating the initial scores of candidate charging piles, the probabilities of the car owner's charging belonging to the distance priority type, cost priority type, time priority type and fixed charging pile priority type are taken into account, and the distance, queuing time and charging cost of the candidate charging piles are combined. The second reward and punishment factor is determined by whether the candidate charging pile is the largest charging pile for on-board charging to set the penalty item, so that the initial scores of the candidate charging piles can reflect the car owner's charging habits.

[0095] Furthermore, the first reward and punishment factor is determined by the load rate of the candidate charging pile's direct transformer and the user type to penalize the initial score of the candidate charging pile, thereby avoiding recommending charging piles under direct transformers with high load rates and high load proportions of preset user types to car owners, thereby ensuring the power supply quality of the distribution network.

[0096] Embodiment 3

[0097] Figure 3 This is a schematic diagram of the structure of a charging pile recommendation device for a distribution network provided by the third embodiment of the present invention. Figure 3 As shown, the recommended device for the distribution network charging pile includes:

[0098] A charging request receiving module 301 is used to receive a charging request from a vehicle owner, wherein the charging request includes a first position of the vehicle to be charged, a target charging time, a charging amount, and a drivable distance;

[0099] A candidate charging pile determination module 302 is used to determine a plurality of candidate charging piles based on the first position and the drivable distance of the vehicle to be charged;

[0100] The charging habit characteristics and directly-affiliated transformer determination module 303 is used to obtain the charging habit characteristics of the vehicle owner and determine the directly-affiliated transformer of each candidate charging pile;

[0101] A directly-affiliated transformer data acquisition module 304 is used to acquire, for each directly-affiliated transformer, a first total load of non-charging pile users of the directly-affiliated transformer at the target charging time, and to acquire a user type of the directly-affiliated transformer;

[0102] A load rate determination module 305 is used to calculate the load rate using the first total load and the rated power of the directly-affiliated transformer, and determine whether the load rate is greater than a preset load rate threshold. If so, a charging pile score calculation module 306 is executed;

[0103] A charging pile score calculation module 306, configured to calculate the score of the candidate charging pile according to the charging habit characteristics, the charging amount, the first location, the target charging time, the load rate and the user type;

[0104] The charging pile recommendation module 307 is used to determine a target charging pile from the candidate charging piles according to the scores, and recommend the target charging pile to the car owner.

[0105] Optionally, the charging habit characteristics and directly-affiliated transformer determination module 303 includes:

[0106] A historical charging data acquisition unit, used to acquire the historical charging data of the vehicle owner;

[0107] The vehicle owner classification unit is used to input the historical charging data into a pre-trained charging classification model to obtain the probability that the vehicle owner belongs to various charging types as the charging habit characteristics of the vehicle owner, wherein the charging types include distance priority type, cost priority type, time priority type and fixed charging pile priority type.

[0108] Optionally, the directly-affiliated transformer data acquisition module 304 includes:

[0109] A historical total load acquisition unit, used to acquire the historical total load of non-charging pile users directly under the transformer;

[0110] The load prediction unit is used to predict the first total load of the non-charging pile users of the directly-affiliated transformer at the target charging time according to the historical total load.

[0111] Optionally, the charging pile score calculation module 306 includes:

[0112] A candidate charging pile data acquisition unit, configured to acquire a second position, a target idle time, and an electricity price at the target charging time of each candidate charging pile, wherein the target idle time is a time after the target charging time and with the shortest time interval from the target charging time;

[0113] an initial score calculation unit, configured to calculate an initial score for each candidate charging pile according to the charging habit characteristics, the first location, the second location, the target idle time, the target charging time, the charging amount, and the electricity price;

[0114] A first reward and punishment factor calculation unit, configured to calculate a first reward and punishment factor of the candidate charging pile by using a load rate of a transformer directly under the candidate charging pile and a user type;

[0115] The score calculation unit is used to calculate the product of the initial score and the first reward and punishment factor to obtain the score of the candidate charging pile.

[0116] Optionally, the charging habit feature includes the probability that the owner's charging belongs to the distance priority type, the cost priority type, the time priority type, and the fixed charging pile priority type. The initial score calculation unit includes:

[0117] A distance calculation subunit, used to calculate the distance between the vehicle to be charged and the candidate charging pile using the first position and the second position;

[0118] A queuing time calculation subunit, used to calculate the queuing time using the target idle time and the target charging time;

[0119] The charging cost calculation subunit is used to calculate the product of the electricity price and the charging amount of each candidate charging pile to obtain the charging cost of the vehicle to be charged at each candidate charging pile;

[0120] A normalization processing subunit, used to normalize the distance, queuing time and charging cost of each candidate charging pile to obtain the normalized distance d, queuing time t and charging cost c;

[0121] The initial score calculation subunit is used to calculate the initial score of each candidate charging pile using the following formula:

[0122] ;

[0123] ;

[0124] Where i represents the i-th candidate charging pile, p_d is the probability that the owner belongs to the distance priority type, p_t is the probability that the owner belongs to the time priority type, p_c is the probability that the owner belongs to the cost priority type, p_a is the probability that the owner belongs to the fixed charging pile priority type, d i represents the distance from the vehicle to be charged to the i-th candidate charging pile, t i represents the queuing time required for the vehicle to be charged at the i-th candidate charging pile, c i represents the cost required for the vehicle to be charged at the i-th candidate charging pile, ε 1i It represents the second reward and penalty factor when the vehicle to be charged is charging at the i-th candidate charging pile, γ is a value greater than 0, and i_target represents the charging pile with the most charging times by the owner when the priority type of the fixed charging pile is set.

[0125] Optionally, the first reward and punishment factor calculation unit includes:

[0126] A load proportion calculation sub-sheet, used to obtain a second total load of a preset type of users directly under the transformer, and calculate a ratio of the second total load to the first total load to obtain a load proportion Ra of the preset type of users;

[0127] The reward and punishment factor calculation subunit is used to calculate the first reward and punishment factor using the following formula:

[0128] ;

[0129] Among them, Load_rate i Represents the load rate of the transformer directly under the i-th candidate charging pile, Ra i Indicates the load proportion of the preset type of users of the direct transformer of the i-th candidate charging pile.

[0130] Optionally, the charging pile recommendation module 307 includes:

[0131] A sorting unit, used to sort the candidate charging piles according to the scores from large to small;

[0132] The target charging pile determination unit is used to determine the top N candidate charging piles as target charging piles.

[0133] The distribution network charging pile recommendation device provided in the embodiment of the present invention can execute the distribution network charging pile recommendation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0134] Embodiment 4

[0135] Figure 4A schematic diagram of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0136] like Figure 4 As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0137] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0138] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as the distribution network charging pile recommendation method.

[0139] In some embodiments, the distribution network charging pile recommendation method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the distribution network charging pile recommendation method described above can be performed. Alternatively, in other embodiments, the processor 41 can be configured to execute the distribution network charging pile recommendation method in any other appropriate manner (for example, by means of firmware).

[0140] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0142] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0143] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0144] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0145] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0146] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0147] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for recommending charging piles in a distribution network, characterized in that: include: receiving a charging request from a vehicle owner, the charging request including a first location of the vehicle to be charged, a target charging time, a charging amount, and a drivable distance; Determine a plurality of candidate charging piles based on the first position and the drivable distance of the vehicle to be charged; Obtaining the charging habit characteristics of the vehicle owner, and determining the direct transformer of each candidate charging pile; For each directly affiliated transformer, obtaining a first total load of non-charging pile users of the directly affiliated transformer at the target charging time, and obtaining a user type of the directly affiliated transformer; Calculating a load rate using the first total load and the rated power of the directly-affiliated transformer, and determining whether the load rate is greater than a preset load rate threshold; If so, calculating the score of the candidate charging pile according to the charging habit characteristics, the charging amount, the first location, the target charging time, the load rate, and the user type; Determine a target charging pile from the candidate charging piles according to the scores, and recommend the target charging pile to the car owner; Determining a plurality of candidate charging piles based on the first position and the drivable distance of the vehicle to be charged includes: Taking the first position as a starting point and the drivable distance as a reference, generating a plurality of driving paths reaching the drivable distance, and determining the charging piles reached by the plurality of driving paths as candidate charging piles; The score of the candidate charging pile is calculated according to the charging habit characteristics, the charging amount, the first location, the target charging time, the load rate, and the user type, including: Obtaining a second position, a target idle time, and an electricity price at the target charging time for each candidate charging pile, wherein the target idle time is a time after the target charging time and with the shortest time interval from the target charging time; Calculate an initial score for each candidate charging post according to the charging habit feature, the first location, the second location, the target idle time, the target charging time, the charging amount, and the electricity price; Calculate a first reward and punishment factor of the candidate charging pile by using the load rate of the transformer directly under the candidate charging pile and the user type; Calculate the product of the initial score and the first reward and punishment factor to obtain the score of the candidate charging pile; The charging habit feature includes the probability that the owner's charging belongs to the distance priority type, the cost priority type, the time priority type, and the fixed charging pile priority type. The initial score of each candidate charging pile is calculated according to the charging habit feature, the first position, the second position, the target idle time, the target charging time, the charging amount, and the electricity price, including: Calculate the distance between the vehicle to be charged and the candidate charging pile using the first position and the second position; The target idle time and target charging time are used to calculate the queue duration; Calculate the product of the electricity price and the charging amount of each candidate charging pile to obtain the charging cost of the vehicle to be charged at each candidate charging pile; Normalizing the distance, queuing time, and charging cost of each candidate charging pile to obtain a normalized distance d, queuing time t, and charging cost c; The initial score of each candidate charging station is calculated using the following formula: ； ； Where i represents the i-th candidate charging pile, p_d is the probability that the owner belongs to the distance priority type, p_t is the probability that the owner belongs to the time priority type, p_c is the probability that the owner belongs to the cost priority type, p_a is the probability that the owner belongs to the fixed charging pile priority type, d i represents the distance from the vehicle to be charged to the i-th candidate charging pile, t i represents the queuing time required for the vehicle to be charged at the i-th candidate charging pile, c i represents the cost required for the vehicle to be charged at the i-th candidate charging pile, ε 1i represents the second reward and penalty factor when the vehicle to be charged is charged at the i-th candidate charging pile, γ is a value greater than 0, and i_target represents the charging pile with the most charging times by the owner when the priority type of the fixed charging pile is fixed; The first reward and punishment factor of the candidate charging pile is calculated by using the load rate of the transformer directly under the candidate charging pile and the user type, including: Obtaining a second total load of a preset type of users directly under the transformer, and calculating a ratio of the second total load to the first total load to obtain a load proportion Ra of the preset type of users; The first reward and penalty factor is calculated by the following formula: ； Among them, Load_rate i Represents the load rate of the transformer directly under the i-th candidate charging pile, Ra i Indicates the load proportion of preset type users of the direct transformer of the i-th candidate charging pile, where the preset type users are users who cannot have power outages.

2. The method for recommending charging piles in a distribution network according to claim 1, characterized in that: Obtain the charging habit characteristics of the vehicle owner, including: Obtaining historical charging data of the vehicle owner; The historical charging data is input into a pre-trained charging classification model to obtain the probability that the car owner belongs to various charging types as the charging habit characteristics of the car owner, wherein the charging types include distance priority type, cost priority type, time priority type and fixed charging pile priority type.

3. The method for recommending charging piles in a distribution network according to claim 1, characterized in that: Obtaining a first total load of non-charging pile users of the directly affiliated transformer at the target charging time includes: Obtain the historical total load of non-charging pile users of the directly affiliated transformer; Predict the first total load of the non-charging pile users of the directly-affiliated transformer at the target charging time according to the historical total load.

4. The method for recommending charging piles for a distribution network according to any one of claims 1 to 3, characterized in that: Determining a target charging pile from the candidate charging piles according to the scores includes: Sort the candidate charging piles according to the scores from large to small; The top N candidate charging piles are determined as target charging piles.

5. A charging pile recommendation device for a distribution network, characterized in that: include: A charging request receiving module, used to receive a charging request from a vehicle owner, wherein the charging request includes a first position of the vehicle to be charged, a target charging time, a charging amount, and a drivable distance; A candidate charging pile determination module, configured to determine a plurality of candidate charging piles based on the first position and the drivable distance of the vehicle to be charged; A charging habit feature and direct transformer determination module, used to obtain the charging habit feature of the vehicle owner and determine the direct transformer of each candidate charging pile; A directly-affiliated transformer data acquisition module, configured to acquire, for each directly-affiliated transformer, a first total load of non-charging pile users of the directly-affiliated transformer at the target charging time, and acquire a user type of the directly-affiliated transformer; A load rate determination module, configured to calculate the load rate using the first total load and the rated power of the directly-affiliated transformer, and determine whether the load rate is greater than a preset load rate threshold, and if so, execute a charging pile score calculation module; A charging pile score calculation module, used to calculate the score of the candidate charging pile according to the charging habit characteristics, the charging amount, the first location, the target charging time, the load rate and the user type; A charging pile recommendation module, configured to determine a target charging pile from the candidate charging piles according to the scores, and recommend the target charging pile to the car owner; a candidate charging pile determination module, specifically configured to generate a plurality of driving paths reaching the drivable distance with the first position as a starting point and the drivable distance as a reference, and determine the charging piles reached by the plurality of driving paths as candidate charging piles; The charging pile score calculation module includes: A candidate charging pile data acquisition unit, configured to acquire a second position, a target idle time, and an electricity price at the target charging time of each candidate charging pile, wherein the target idle time is a time after the target charging time and with the shortest time interval from the target charging time; an initial score calculation unit, configured to calculate an initial score for each candidate charging pile according to the charging habit characteristics, the first location, the second location, the target idle time, the target charging time, the charging amount, and the electricity price; A first reward and punishment factor calculation unit, configured to calculate a first reward and punishment factor of the candidate charging pile by using a load rate of a transformer directly under the candidate charging pile and a user type; a score calculation unit, configured to calculate the product of the initial score and the first reward and punishment factor to obtain the score of the candidate charging pile; The charging habit characteristics include the probability that the owner's charging belongs to the distance priority type, cost priority type, time priority type, and fixed charging pile priority type. The initial score calculation unit includes: A distance calculation subunit, used to calculate the distance between the vehicle to be charged and the candidate charging pile using the first position and the second position; A queuing time calculation subunit, used to calculate the queuing time using the target idle time and the target charging time; The charging cost calculation subunit is used to calculate the product of the electricity price and the charging amount of each candidate charging pile to obtain the charging cost of the vehicle to be charged at each candidate charging pile; A normalization processing subunit, used to normalize the distance, queuing time and charging cost of each candidate charging pile to obtain the normalized distance d, queuing time t and charging cost c; The initial score calculation subunit is used to calculate the initial score of each candidate charging pile using the following formula: ； ； Where i represents the i-th candidate charging pile, p_d is the probability that the owner belongs to the distance priority type, p_t is the probability that the owner belongs to the time priority type, p_c is the probability that the owner belongs to the cost priority type, p_a is the probability that the owner belongs to the fixed charging pile priority type, d i represents the distance from the vehicle to be charged to the i-th candidate charging pile, t i represents the queuing time required for the vehicle to be charged at the i-th candidate charging pile, c i represents the cost required for the vehicle to be charged at the i-th candidate charging pile, ε 1i represents the second reward and penalty factor when the vehicle to be charged is charged at the i-th candidate charging pile, γ is a value greater than 0, and i_target represents the charging pile with the most charging times by the owner when the priority type of the fixed charging pile is fixed; The first reward and punishment factor calculation unit includes: A load proportion calculation sub-sheet, used to obtain a second total load of a preset type of users directly under the transformer, and calculate a ratio of the second total load to the first total load to obtain a load proportion Ra of the preset type of users; The reward and punishment factor calculation subunit is used to calculate the first reward and punishment factor using the following formula: ； Among them, Load_rate i Represents the load rate of the transformer directly under the i-th candidate charging pile, Ra i Indicates the load proportion of preset type users of the direct transformer of the i-th candidate charging pile, where the preset type users are users who cannot have power outages.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution network charging pile recommendation method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the distribution network charging pile recommendation method according to any one of claims 1 to 4 when executed.

Images