Oversized parking lot variable pile position scheduling method capable of actively responding to time-varying charging stop demand

Abstract

The invention discloses an oversized parking lot variable pile position scheduling method capable of actively responding to a time-varying charging stop demand, and the method comprises the steps: (1) building a user expectation confidence model according to the commuting charging stop demand of a new energy vehicle and the parking lot entering and exiting behavior data of a user in a rolling time period; (2) collecting charging stopping demand information of a target new energy automobile user, and establishing a time-sensitive inference model; (3) according to the user expectation confidence model, the current user charging-stopping instant demand, the time-varying expectation feature and the current charging-stopping position state of the new energy vehicle, calculating a charging-stopping expectation time cost coefficient of each user; and (4) calculating a comprehensive charging stopping expected time cost coefficient of all demand users in the period time window, comprehensively scheduling the parking position and the charging power of the new energy automobile, and achieving optimal charging power distribution under the condition of meeting the parking charging requirements of the new energy automobile users. According to the invention, the oversized parking lot can be helped to assist new energy automobile owners to realize optimal parking and charging comprehensive arrangement.

Description

Technical Field

[0001] The present invention belongs to the technical field of parking and charging scheduling for new energy vehicles, and in particular relates to a method for scheduling variable pile positions in a super-large parking lot that actively responds to time-varying parking and charging demands. Background Art

[0002] In recent years, new energy vehicles have become increasingly popular, and parking lots have also added certain charging facilities to serve owners of new energy vehicles who come to park.

[0003] Some existing parking lots, especially the extra-large parking lots near large commercial facilities, have parking and charging areas separated from the user storage and retrieval areas. Car-moving robots are needed to move new energy vehicles, and most of them do not have parking and charging scheduling strategies for new energy vehicle owners. This can easily cause some new energy vehicle owners to have problems such as long charging times during parking and charging, affecting the user's car experience and user satisfaction with the parking lot.

[0004] The Chinese patent document with publication number CN115311781A discloses a parking charging management method for public parking lots, including: determining whether the number of free charging parking spaces is less than a preset number or zero; if the number of free charging parking spaces is less than a preset number or zero, selecting a vehicle to be notified according to the charging status of the vehicles in each charging parking space; sending a notification message to the owner terminal corresponding to the selected vehicle to be notified, the notification message including whether to agree to move the vehicle to a non-charging parking space; sending a moving instruction to a moving robot according to the message of agreeing to move the vehicle replied by the owner terminal, the moving instruction including vehicle information and information to transfer the vehicle to a designated non-charging parking space; receiving the moving success message sent by the moving robot; sending the information of the parking space where the vehicle is located after moving the vehicle to the corresponding owner terminal. However, this method only considers the transfer of new energy vehicles from charging parking spaces to non-charging parking spaces, and does not consider the method of mutual scheduling of new energy vehicles between fast charging parking spaces and slow charging parking spaces, because the existing super-large parking lot is equipped with both fast charging parking spaces and slow charging parking spaces.

[0005] The Chinese patent document with publication number CN111402621A discloses an intelligent vehicle dispatching method for a large parking and charging station for electric vehicles, including: judging whether there are electric vehicles parked in each parking space; obtaining the equipment information, charging status and charging amount of the charging pile corresponding to the occupied parking space; displaying the information of the vacant parking space and the equipment information of the charging pile on the intelligent guide screen to provide at least one vacant parking space for the electric vehicle; synchronously displaying the vehicle information of the electric vehicle parked in the occupied parking space and the equipment information, charging status and charging amount of the charging pile on the first charging display screen and the second charging display screen, so that the operation and maintenance personnel of the operation and maintenance platform can draw the gun of the electric vehicle when the electric vehicle is fully charged, and the driver can dispatch the vehicle to move the vehicle. However, this method does not take into account that since the parking area of ​​new energy vehicles in the super-large parking lot is isolated from the user's car pick-up area, a car moving robot is required to complete the behavior of transferring the new energy vehicle from the parking area to the user-specified car pick-up area.

[0006] Therefore, a super-large parking lot variable charging position scheduling method that actively responds to time-varying charging and stopping demands is needed to help super-large parking lots assist new energy vehicle owners to complete parking and charging. Summary of the invention

[0007] The present invention provides a super-large parking lot variable charging position scheduling method that actively responds to time-varying charging and stopping demands. The method can comprehensively optimize the comprehensive charging and stopping expected time cost coefficient and timeliness of all emerging users to be served within the sliding window time interval while taking into account the charging and stopping demands of new energy vehicles and the individual charging and stopping preferences of users, so as to achieve the optimal comprehensive charging and stopping arrangement.

[0008] A method for scheduling a large parking lot with variable parking positions that actively responds to time-varying charging and stopping demands comprises the following steps: (1) Establish a user expectation confidence model based on the commuting stop and charging needs of new energy vehicles and the user's parking lot entry and exit behavior data within a rolling time period; (2) Collect the charging stop demand information of target new energy vehicle users and establish a time-sensitive inference model; (3) Calculate the expected time cost coefficient of each user’s charging stop based on the user’s expected confidence model, time-sensitive inference model, and the current charging and stopping status of the new energy vehicle; (4) Calculate the comprehensive expected time cost coefficient of parking and charging for all demand users within the cycle time window, comprehensively dispatch the parking locations and charging powers of new energy vehicles, and achieve the optimal charging power allocation while meeting the parking and charging requirements of new energy vehicle users.

[0009] Furthermore, in step (1), the user expectation confidence model established is: ; In the formula, For the number Individual new energy vehicle users, For the number The parking lot pick-up location, is the total number of available pick-up locations in the parking lot, For the numbered The probability distribution of individual new energy vehicle users picking up their cars from different pick-up locations in the parking lot, For the numbered Individual new energy vehicle users from No. The probability of picking up and leaving the parking lot pick-up location.

[0010] Furthermore, in the user expectation confidence model, The value of needs to meet the following conditions: ; In the formula, The total number of available pickup locations in the parking lot.

[0011] Furthermore, in step (1), a user expectation confidence model is established based on the long short-term memory network.

[0012] Furthermore, in step (2), the time-sensitive inference model established is: ; In the formula, For the number of new energy vehicle users, is the current time, The expected departure time for new energy vehicle users. is the energy state of new energy vehicles at the current time, The energy status of the new energy vehicle when the user expects to leave the venue. Extract the vehicle position number when the user is expected to leave.

[0013] Furthermore, in the time-sensitive inference model, , , , , The values ​​must meet the following conditions: ; ; ; In the formula, The total number of available pickup locations in the parking lot.

[0014] Furthermore, in step (3), the calculation formula of the expected time cost coefficient of each user's charging stop is as follows: ; ; ; ; In the formula, For the number The expected cost coefficient of individual new energy vehicle users based on the time of charging new energy vehicles, is the energy state of new energy vehicles at the current time, The energy status of the new energy vehicle when the user expects to leave the venue. For the number The rated energy limit of new energy vehicles for individual new energy vehicle users, For the number The preset charging power of new energy vehicles for individual new energy vehicle users, is the current time, The expected departure time for new energy vehicle users; For the number The expected cost coefficient of the time for individual new energy vehicle users to transfer new energy vehicles to replace charging piles based on the car moving robot, For the car moving robot to move new energy vehicles from Move location to The difficulty coefficient of the position, For the car moving robot to move new energy vehicles from Move location to The required driving distance to the location, For the numbered Individual new energy vehicle users from No. The probability of picking up the car and leaving the parking lot pick-up location, is the total number of available pick-up locations in the parking lot, For the car moving robot to move new energy vehicles from The location is transferred to The difficulty coefficient of the parking lot pick-up location, For the car moving robot to move new energy vehicles from The location is transferred to The required driving distance to the parking lot pickup location of Because The position may be occupied, resulting in the waiting time required for the car moving robot to move the new energy vehicle; For the number The expected cost coefficient of the time for individual new energy vehicle users to transfer new energy vehicles to the designated pick-up location based on the car moving robot, For the car moving robot to move new energy vehicles from The location is transferred to The difficulty coefficient of the parking lot pick-up location, For the car moving robot to move new energy vehicles from The location is transferred to The required driving distance to the parking lot pickup location; For the number The expected time cost coefficient of individual new energy vehicle users stopping charging, .

[0015] Furthermore, in step (4), the comprehensive expected time cost coefficient of charging stop for all demand users within the cycle time window is calculated, and the formula is: ; In the formula, A combination of parking and charging locations for all new energy vehicles. The total number of new energy vehicle users who currently need to park and charge. For The expected time cost coefficient of charging stop for all users under the combination of .

[0016] Furthermore, in step (4), the comprehensive scheduling of the parking location and charging power of new energy vehicles needs to meet the following conditions: ; In the formula, The best parking and charging location combination for all new energy vehicles. For The expected time cost coefficient of charging stop for all users under the combination of For The minimum expected time cost coefficient of charging stop for all users under the combination of .

[0017] Furthermore, the optimal charging power distribution formula is: ; In the formula, For the number The charging power allocated to individual new energy vehicles, For The combination of The parking and charging locations to which individual new energy vehicles are dispatched. for Charging power of the charging pile at the parking charging position.

[0018] Compared with the prior art, the present invention has the following beneficial effects: In order to provide new energy vehicle owners with a time-sensitive scheduling strategy and method for parking and charging and charging piles in large parking lots with multiple power charging piles, the present invention introduces a time-sensitive inference model on the basis of parking and charging, and comprehensively performs time-sensitive scheduling of parking and charging and charging piles for all new energy vehicles by calculating the total expected time cost coefficient of each user and the comprehensive expected time cost coefficient of all users. While meeting the parking and charging needs of new energy vehicle owners, the present invention takes into account the comprehensive expected time cost coefficient of all users, and can achieve the optimal comprehensive arrangement of parking and charging. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only preferred embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 The present invention is a flowchart of a method for scheduling a super-large parking lot with variable parking positions that actively responds to time-varying charging and stopping demands according to an embodiment of the present invention.

[0021] Figure 2 This is a distribution diagram of parking spaces and charging piles in a super-large parking lot in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be pointed out that the embodiments described below are intended to facilitate the understanding of the present invention and do not have any limiting effect on the present invention.

[0023] like Figure 1 As shown, a method for scheduling a large parking lot with variable parking positions that actively responds to time-varying charging and stopping demands includes the following steps: S1. Based on the commuting and charging needs of new energy vehicles and the parking lot entry and exit behavior data of users within a rolling time period, a user expectation confidence model (UECM) is established.

[0024] The user expectation confidence model adopted is: ; In the formula, For the number Individual new energy vehicle users, For the number The parking lot pick-up location, is the total number of available pick-up locations in the parking lot, For the numbered The probability distribution of individual new energy vehicle users picking up their cars from different pick-up locations in the parking lot, For the numbered Individual new energy vehicle users from No. The probability of picking up and leaving the parking lot pick-up location.

[0025] In this embodiment, the method for establishing the user expectation confidence model is a long short-term memory network.

[0026] like Figure 2 As shown, the distribution of parking spaces and charging piles in the super-large parking lot used in the embodiment of the present invention is shown. Taking the individual new energy vehicle user numbered 1 as an example, the parking lot selected in this embodiment has a total of 3 available pick-up locations. According to the commuting parking and charging needs of new energy vehicles and the user's in-and-out parking lot behavior data within the rolling time period, the probability that the individual new energy vehicle user numbered 1 picks up the car from the parking lot pick-up locations numbered 1, 2, and 3 within the rolling time period is calculated through the long short-term memory network. 20%, 30%, and 50% respectively, the user expectation confidence model of the individual new energy vehicle user numbered 1 is obtained: ; In the user expectation confidence model adopted, The values ​​must meet the following conditions: ; In the formula, For the numbered Individual new energy vehicle users from No. The probability of picking up the car and leaving the parking lot pick-up location, The total number of available pickup locations in the parking lot.

[0027] S2. Collect the charging stop demand information of target new energy vehicle users and establish a time-sensitive inference model (TSIM).

[0028] The time-sensitive inference model used is: ; In the formula, For the number of new energy vehicle users, is the current time, The expected departure time for new energy vehicle users. is the energy status of new energy vehicles at the current time (unit: %), The energy status of the new energy vehicle when the user expects to leave the venue (unit: %), Extract the vehicle position number when the user is expected to leave.

[0029] By number For example, the current time is , the expected departure time of new energy vehicle users is , the current number is The energy state of new energy vehicles is , the user expects the energy state of the new energy vehicle to be , the vehicle position number extracted when the user expects to leave is , then the time-sensitive inference model is: .

[0030] In the time-sensitive inference model adopted, , , , , The values ​​meet the conditions: ; ; ; In the formula, is the current time, The expected departure time for new energy vehicle users. is the energy status of new energy vehicles at the current time (unit: %), The energy status of the new energy vehicle when the user expects to leave the venue (unit: %), Extract the vehicle position number when the user is expected to leave.

[0031] S3. Calculate the expected time cost coefficient of each user's charging stop based on the user's expected confidence model, the time-sensitive inference model, and the current charging and stopping status of the new energy vehicle.

[0032] Among them, the number is The current stop and charge status of individual new energy vehicle users is that the current charging pile is a fast charging pile, and the current charging power for .

[0033] Calculate the expected time cost coefficient of each user's charging stop, the formula is as follows: ; ; ; ; In the formula, For the number The expected cost coefficient of individual new energy vehicle users based on the time of charging new energy vehicles, is the energy status of new energy vehicles at the current time (unit: %), The energy status of the new energy vehicle when the user expects to leave the venue (unit: %), For the number The rated energy limit of new energy vehicles for individual new energy vehicle users, For the number The preset charging power of the new energy vehicle of the individual new energy vehicle user (i.e. the current stop and charge state of the new energy vehicle), is the current time, The expected departure time for new energy vehicle users; For the number The expected cost coefficient of the time for individual new energy vehicle users to transfer new energy vehicles to replace charging piles based on the car moving robot, For the car moving robot to move new energy vehicles from Move location to The difficulty coefficient of the position, For the car moving robot to move new energy vehicles from Move location to The required driving distance to the location, For the numbered Individual new energy vehicle users from No. The probability of picking up the car and leaving the parking lot pick-up location, is the total number of available pick-up locations in the parking lot, For the car moving robot to move new energy vehicles from The location is transferred to The difficulty coefficient of the parking lot pick-up location, For the car moving robot to move new energy vehicles from The location is transferred to The required driving distance to the parking lot pickup location of Because The position may be occupied, resulting in the waiting time required for the car moving robot to move the new energy vehicle; For the number The expected cost coefficient of the time for individual new energy vehicle users to transfer new energy vehicles to the designated pick-up location based on the car moving robot, For the car moving robot to move new energy vehicles from The location is transferred to The difficulty coefficient of the parking lot pick-up location, For the car moving robot to move new energy vehicles from The location is transferred to The required driving distance to the parking lot pickup location; For the number The expected cost coefficient of the total parking and charging time for individual new energy vehicle users.

[0034] Number The rated energy limit of new energy vehicles for individual new energy vehicle users for , preset charging pile is fast charging pile, preset charging power for , the car moving robot will move new energy vehicles from Move location to Difficulty coefficient of position for , the car moving robot will move new energy vehicles from Move location to Required driving distance to location for , the car moving robot will move new energy vehicles from The location is transferred to The difficulty coefficient of the parking lot pick-up location They are , the car moving robot will move new energy vehicles from The location is transferred to Required driving distance to the parking lot pickup location They are ,because The position may be occupied, resulting in the waiting time required for the robot to move the new energy vehicle for , the car moving robot will move new energy vehicles from The location is transferred to The difficulty coefficient of the parking lot pick-up location for , the car moving robot will move new energy vehicles from The location is transferred to Required driving distance to the parking lot pickup location for , then the number is The expected cost coefficient of individual new energy vehicle users based on the time of charging new energy vehicles for , based on the expected time cost coefficient of transferring new energy vehicles to replace charging piles by car moving robots for , based on the expected time cost coefficient of transferring new energy vehicles to the designated pick-up location by the car moving robot for , total time expected cost coefficient for .

[0035] The user's expected time cost coefficient for stopping charging is: The values ​​meet the conditions:

[0036] In the formula, For the number The expected cost coefficient of the total parking and charging time for individual new energy vehicle users.

[0037] S4. Calculate the comprehensive expected time cost coefficient of parking and charging for all demand users within the cycle time window, comprehensively dispatch the parking positions and charging powers of new energy vehicles, and achieve the optimal charging power allocation while meeting the parking and charging requirements of new energy vehicle users.

[0038] Calculate the comprehensive expected time cost coefficient of charging stop for all demand users within the cycle time window. The formula is: ; In the formula, A combination of parking and charging locations for all new energy vehicles. The total number of new energy vehicle users who currently need to park and charge. For The expected time cost coefficient of charging stop for all users under the combination of For the number The total time expected cost coefficient of new energy vehicle users.

[0039] Comprehensive dispatch of parking locations and charging power for new energy vehicles requires the following conditions to be met: ; In the formula, The best parking and charging location combination for all new energy vehicles. For The expected time cost coefficient of charging stop for all users under the combination of For The smallest expected time cost coefficient of charging stop for all users under the combination of .

[0040] The optimal charging power distribution is: ; In the formula, For the number The charging power allocated to individual new energy vehicles, For The corresponding optimal parking and charging position combinations for all new energy vehicles are numbered as follows: The parking and charging locations to which individual new energy vehicles are dispatched. for Charging power of the charging pile at the parking charging position.

[0041] The embodiments described above provide a detailed description of the technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, supplements and equivalent substitutions made within the scope of the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for scheduling large parking lot positions with active response to time-varying charging and stopping demands, characterized in that: The following steps are involved: (1) Establish a user expectation confidence model based on the commuting stop and charging needs of new energy vehicles and the user's parking lot entry and exit behavior data within a rolling time period; (2) Collect the charging stop demand information of target new energy vehicle users and establish a time-sensitive inference model; (3) Calculate the expected time cost coefficient of each user’s charging stop based on the user’s expected confidence model, time-sensitive inference model, and the current charging and stopping status of the new energy vehicle; (4) Calculate the comprehensive expected time cost coefficient of parking and charging for all demand users within the cycle time window, comprehensively dispatch the parking locations and charging powers of new energy vehicles, and achieve the optimal charging power allocation while meeting the parking and charging requirements of new energy vehicle users.

2. The method for changing the pile position of a large parking lot in active response to time-varying stop and charge demand according to claim 1 is characterized in that: In step (1), the user expectation confidence model established is: ； In the formula, For the number Individual new energy vehicle users, For the number The parking lot pick-up location, is the total number of available pick-up locations in the parking lot, For the numbered The probability distribution of individual new energy vehicle users picking up their cars from different pick-up locations in the parking lot, For the numbered Individual new energy vehicle users from No. The probability of picking up and leaving the parking lot pick-up location.

3. The method for changing the pile position of a large parking lot in active response to time-varying stop and charge demand according to claim 2 is characterized in that: In the user expectation confidence model, The value of needs to meet the following conditions: ； In the formula, The total number of available pickup locations in the parking lot.

4. The method for changing the pile position of a large parking lot in active response to time-varying stop and charge demands according to claim 1 is characterized in that: In step (1), a user expectation confidence model is established based on the long short-term memory network.

5. The method for changing the parking lot position in a large parking lot in active response to time-varying charging and stopping demand according to claim 1 is characterized in that: In step (2), the time-sensitive inference model established is: ； In the formula, For the number of new energy vehicle users, is the current time, The expected departure time for new energy vehicle users. is the energy state of new energy vehicles at the current time, The energy status of the new energy vehicle when the user expects to leave the venue. Extract the vehicle position number when the user is expected to leave.

6. The method for changing the pile position of a large parking lot in active response to time-varying charging and stopping demand according to claim 5 is characterized in that: In the time-sensitive inference model, , , , , The values ​​must meet the following conditions: ； ； ； In the formula, The total number of available pickup locations in the parking lot.

7. The method for changing the pile position of a large parking lot in active response to time-varying stop and charge demand according to claim 1 is characterized in that: In step (3), the calculation formula of the expected time cost coefficient of each user's charging suspension is as follows: ； ； ； ； In the formula, For the number The expected cost coefficient of individual new energy vehicle users based on the time of charging new energy vehicles, is the energy state of new energy vehicles at the current time, The energy status of the new energy vehicle when the user expects to leave the venue. For the number The rated energy limit of new energy vehicles for individual new energy vehicle users, For the number The preset charging power of new energy vehicles for individual new energy vehicle users, is the current time, The expected departure time for new energy vehicle users; For the number The expected cost coefficient of the time for individual new energy vehicle users to transfer new energy vehicles to replace charging piles based on the car moving robot, For the car moving robot to move new energy vehicles from Move location to The difficulty coefficient of the position, For the car moving robot to move new energy vehicles from Move location to The required driving distance to the location, For the numbered Individual new energy vehicle users from No. The probability of picking up the car and leaving the parking lot pick-up location, is the total number of available pick-up locations in the parking lot, For the car moving robot to move new energy vehicles from The location is transferred to The difficulty coefficient of the parking lot pick-up location, For the car moving robot to move new energy vehicles from The location is transferred to The required driving distance to the parking lot pickup location of Because The position may be occupied, resulting in the waiting time required for the car moving robot to move the new energy vehicle; For the number The expected cost coefficient of the time for individual new energy vehicle users to transfer new energy vehicles to the designated pick-up location based on the car moving robot, For the car moving robot to move new energy vehicles from The location is transferred to The difficulty coefficient of the parking lot pick-up location, For the car moving robot to move new energy vehicles from The location is transferred to The required driving distance to the parking lot pickup location; For the number The expected time cost coefficient of individual new energy vehicle users stopping charging, .

8. The method for changing the pile position of a large parking lot in active response to time-varying stop and charge demands according to claim 7 is characterized in that: In step (4), the comprehensive expected time cost coefficient of charging stop for all demand users within the cycle time window is calculated, and the formula is: ； In the formula, A combination of parking and charging locations for all new energy vehicles. The total number of new energy vehicle users who currently need to park and charge. For The comprehensive expected time cost coefficient of charging stop for all users under the combination of .

9. The method for changing the pile position of a large parking lot in active response to time-varying stop and charge demands according to claim 8 is characterized in that: In step (4), the comprehensive scheduling of parking locations and charging power of new energy vehicles needs to meet the following conditions: ； In the formula, The best parking and charging location combination for all new energy vehicles. For The expected time cost coefficient of charging stop for all users under the combination of For The minimum expected time cost coefficient of charging stop for all users under the combination of .

10. The method for changing the pile position of a large parking lot in active response to time-varying stop and charge demands according to claim 9 is characterized in that: The optimal charging power distribution formula is: ； In the formula, For the number The charging power allocated to individual new energy vehicles, For The combination of The parking and charging locations to which individual new energy vehicles are dispatched. for Charging power of the charging pile at the parking charging position.

Images