An Active Response Method for Variable Pile Position Scheduling in an Extra-large Parking Lot for Time-varying Stopping and Charging Demands

Abstract

The present invention discloses a method for active response to time-varying parking and charging demands and variable pile position scheduling in an extra-large parking lot, which includes: (1) establishing a user expectation confidence model based on the commuting parking and charging demands of new energy vehicles and the behavior data of users entering and leaving the parking lot within the rolling time period of users; (2) collecting the parking and charging demand information of target new energy vehicle users and establishing a time-sensitive inference model; (3) calculating the time cost coefficient of each user's parking and charging expectation according to the user expectation confidence model, the current immediate parking and charging demand of the user, the time-varying expectation characteristics, and the current parking and charging state of the new energy vehicle; (4) calculating the comprehensive time cost coefficient of all demand users within the cycle time window, comprehensively scheduling the parking positions and charging powers of new energy vehicles, and achieving the optimal charging power distribution while meeting the parking and charging requirements of new energy vehicle users. The present invention can help the owners of new energy vehicles in an extra-large parking lot to achieve the optimal comprehensive arrangement of parking and charging.

Description

Technical Field

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

[0002] In recent years, new energy vehicles have gradually become popular, and parking lots are required to be equipped with certain charging facilities to serve the owners of new energy vehicles who come to park.

[0003] In some existing parking lots, especially extra-large parking lots near large commercial facilities, etc., the parking and charging areas are separated from the user's vehicle access and storage areas. It is necessary to use a vehicle moving robot to move new energy vehicles, and most of them do not have a parking and charging scheduling strategy for new energy vehicle owners, which easily causes problems such as too long charging time for some new energy vehicle owners during the parking and charging process, affecting the user's vehicle use experience and the user's satisfaction with the parking lot.

[0004] Chinese patent document with publication number CN115311781A discloses a parking and charging management method for parking spaces in a public parking lot, including: determining whether the number of idle charging parking spaces is less than a preset number or zero; if the number of idle charging parking spaces is less than the preset number or zero, then select the vehicle to be notified according to the charging status of the vehicles on each charging parking space; send a notification message to the owner terminal corresponding to the selected vehicle to be notified, and the notification message includes whether to agree to move the vehicle to a non-charging parking space; send a vehicle moving instruction to the vehicle moving robot according to the information of agreeing to move the vehicle replied by the owner terminal, and the vehicle moving instruction includes vehicle information and information on transferring the vehicle to a specified non-charging parking space; receive the vehicle moving success information sent by the vehicle moving robot; send the information of the parking space where the vehicle is located after moving to the corresponding owner terminal. However, this method only considers moving new energy vehicles from charging parking spaces to non-charging parking spaces, and does not consider a method that allows new energy vehicles to be mutually scheduled between fast charging parking spaces and slow charging parking spaces in existing extra-large parking lots.

[0005] The Chinese patent document with the publication number CN111402621A discloses an intelligent vehicle scheduling method for large-scale parking charging stations of electric vehicles, including: determining whether there are electric vehicles parked in each parking space; obtaining the device information, charging status, and charging amount of the charging piles corresponding to the occupied parking spaces; displaying the information of the idle parking spaces and the device information of the charging piles on the intelligent guidance screen to provide at least one idle parking space for the electric vehicle; synchronously displaying the vehicle information of the electric vehicle parked in the occupied parking space, the device information of the charging pile, the charging status, and the charging amount 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 unplug the electric vehicle when it is fully charged and enable the driver to carry out vehicle relocation scheduling. However, this method does not take into account that due to the mutual isolation of the parking area and the user pick-up area of new energy vehicles in the super-large parking lot, a vehicle relocation robot is needed to complete the behavior of transferring the new energy vehicle from the parking area to the user-specified pick-up area.

[0006] Therefore, a variable charging pile position scheduling method for super-large parking lots that actively responds to time-varying parking and charging demands is needed to help the owners of new energy vehicles in super-large parking lots complete the parking and charging behavior. Summary of the Invention

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

[0008] A variable charging pile position scheduling method for super-large parking lots that actively responds to time-varying parking and charging demands includes the following steps:

[0009] (1) Establish a user expectation confidence model according to the commuting parking and charging demands of new energy vehicles and the in-out parking lot behavior data of users within the rolling time period;

[0010] (2) Collect the parking and charging demand information of target new energy vehicle users and establish a time-sensitive inference model;

[0011] (3) Calculate the parking and charging expected time cost coefficient of each user according to the user expectation confidence model, the time-sensitive inference model, and the current parking and charging state of the new energy vehicle;

[0012] (4) Calculate the comprehensive parking and charging expected time cost coefficient of all demand users within the cycle time window, comprehensively schedule the parking positions and charging powers of new energy vehicles, and achieve the optimal charging power distribution under the condition of meeting the parking and charging requirements of new energy vehicle users.

[0013] Further, in step (1), the established user expectation confidence model is:

[0014] ;

[0015] Wherein, is an individual new energy vehicle user numbered . is the vehicle pick-up location of the parking lot numbered . is the total number of available vehicle pick-up locations in the parking lot. is the probability distribution of an individual new energy vehicle user numbered leaving the parking lot from different vehicle pick-up locations within the rolling time period. is the probability that an individual new energy vehicle user numbered leaves the parking lot from the vehicle pick-up location numbered within the rolling time period.

[0016] Furthermore, in the user expectation confidence model, needs to satisfy the following conditions:

[0017] ;

[0018] Wherein, is the total number of available vehicle pick-up locations in the parking lot.

[0019] Furthermore, in step (1), a user expectation confidence model is established based on a long short-term memory network.

[0020] Furthermore, in step (2), the established time-sensitive inference model is:

[0021] ;

[0022] Wherein, is a new energy vehicle user numbered . is the current time. is the expected departure time of the new energy vehicle user. is the energy state of the new energy vehicle at the current time. is the energy state of the new energy vehicle when the user expects to leave. is the vehicle position number to be retrieved when the user expects to leave.

[0023] Furthermore, in the time-sensitive inference model, , , , , need to satisfy the conditions:

[0024] ;

[0025] ;

[0026] ;

[0027] Wherein, is the total number of available vehicle pick-up positions in the parking lot.

[0028] Furthermore, in step (3), the calculation formula for the time expected cost coefficient of each user's charging and parking is as follows:

[0029] ;

[0030] ;

[0031] ;

[0032] ;

[0033] Wherein, is the time expected cost coefficient of the individual new energy vehicle user numbered based on the new energy vehicle charging, is the energy state of the new energy vehicle at the current time, is the energy state of the new energy vehicle when the user expects to leave the parking lot, is the upper limit of the rated energy of the new energy vehicle of the individual new energy vehicle user numbered ; is the preset charging power of the new energy vehicle of the individual new energy vehicle user numbered ; is the current time, is the time when the new energy vehicle user expects to leave the parking lot; is the time expected cost coefficient of the individual new energy vehicle user numbered based on the vehicle moving robot transferring the new energy vehicle to replace the charging pile, is the difficulty coefficient for the vehicle moving robot to transfer the new energy vehicle from the position to the position, is the required driving distance for the vehicle moving robot to transfer the new energy vehicle from the position to the position, is the probability that the individual new energy vehicle user numbered picks up the vehicle and leaves from the vehicle pick-up position numbered in the rolling time period range, is the total number of available vehicle pick-up positions in the parking lot, For the difficulty coefficient of the parking robot to transfer a new energy vehicle from the position to the pick-up position in the parking lot numbered ; For the required driving distance of the parking robot to transfer a new energy vehicle from the position to the pick-up position in the parking lot numbered ; For the waiting time required for the parking robot to transfer a new energy vehicle due to the possible occupation of the position; For the time expectation cost coefficient of the individual new energy vehicle user numbered on the parking robot to transfer the new energy vehicle to the designated pick-up position; For the difficulty coefficient of the parking robot to transfer a new energy vehicle from the position to the pick-up position in the parking lot numbered ; For the required driving distance of the parking robot to transfer a new energy vehicle from the position to the pick-up position in the parking lot numbered ; For the stop-charging expectation time cost coefficient of the individual new energy vehicle user numbered ; .

[0034] Furthermore, in step (4), calculate the comprehensive stop-charging expectation time cost coefficient of all demand users within the cycle time window. The formula is:

[0035] ;

[0036] In the formula, is the combination mode of the parking and charging positions of all new energy vehicles, is the total number of new energy vehicle users currently requiring parking and charging, is within the stop-charging expectation time cost coefficient of all users under the combination mode.

[0037] Furthermore, in step (4), when comprehensively scheduling the parking positions and charging powers of new energy vehicles, the following conditions need to be met:

[0038] ;

[0039] In the formula, is the optimal combination mode of the parking and charging positions of all new energy vehicles, is within the stop-charging expectation time cost coefficient of all users under the combination mode, is within The minimum expected time cost coefficient of all user charging stops under the combination method.

[0040] Furthermore, the optimal charging power distribution formula is:

[0041] ;

[0042] In the formula, is the charging power allocated to the new energy vehicle of the individual numbered , is the parking charging location where the new energy vehicle numbered is scheduled to stop and charge under the combination method of , is the charging power of the charging pile at the parking charging location.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] In order to provide a time-sensitive scheduling strategy and method for new energy vehicle owners to stop and charge and change charging piles in a super-large parking lot with multiple power charging piles, the present invention introduces a time-sensitive inference model on the basis of parking charging. By calculating the total expected time cost coefficient of each user and the comprehensive expected time cost coefficient of all users, the present invention comprehensively conducts time-sensitive scheduling of stopping and charging and changing charging piles for all new energy vehicles. 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 an optimal comprehensive arrangement of parking and charging. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following described drawings are only the preferred embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0046] Figure 1 It is a flowchart of a method for scheduling charging pile positions in a super-large parking lot with active response to time-varying stopping and charging demands according to an embodiment of the present invention.

[0047] Figure 2 It is a distribution diagram of parking spaces and charging piles in a super-large parking lot according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] The following will further describe the present invention in detail with reference to the drawings and embodiments. It should be noted that the following described embodiments are intended to facilitate the understanding of the present invention and do not limit it in any way.

[0049] AsFigure 1 As shown in Figure 1 , an active response method for time-varying charging stop demand in a super-large parking lot for pile position scheduling includes the following steps:

[0050] S1. Establish a user expectation confidence model (UECM) based on the commuting charging stop demand of new energy vehicles and the in-out parking lot behavior data of users within the rolling time period.

[0051] The adopted user expectation confidence model is:

[0052] ;

[0053] In the formula, is the individual new energy vehicle user numbered , is the vehicle pick-up position in the parking lot numbered , is the total number of available vehicle pick-up positions in the parking lot, is the probability distribution of the individual new energy vehicle user numbered leaving the parking lot from different vehicle pick-up positions within the rolling time period, is the probability that the individual new energy vehicle user numbered leaves the parking lot from the vehicle pick-up position numbered within the rolling time period.

[0054] In this embodiment, the method for establishing the user expectation confidence model is a long short-term memory network.

[0055] As Figure 2 shown, it shows the distribution of parking spaces and charging piles in the super-large parking lot adopted in the embodiment of the present invention. Taking the individual new energy vehicle user numbered 1 as an example, there are a total of 3 available vehicle pick-up positions in the selected parking lot. According to the commuting charging stop demand of new energy vehicles and the in-out parking lot behavior data of users within the rolling time period, through the long short-term memory network calculation, the probabilities that the individual new energy vehicle user numbered 1 leaves the parking lot from the vehicle pick-up positions numbered 1, 2, and 3 within the rolling time period are 20%, 30%, and 50% respectively. The user expectation confidence model of the individual new energy vehicle user numbered 1 is obtained as:

[0056] ;

[0057] In the adopted user expectation confidence model, the numerical value needs to meet the condition:

[0058] ;

[0059] Wherein, is the probability that the individual new energy vehicle user numbered takes a vehicle and leaves from the vehicle pick-up location of the parking lot numbered within the rolling time period, is the total number of available vehicle pick-up locations in the parking lot.

[0060] S2. Collect the parking and charging demand information of the target new energy vehicle user and establish a time-sensitive inference model (TSIM).

[0061] The adopted time-sensitive inference model is:

[0062] ;

[0063] Wherein, is the new energy vehicle user numbered , is the current time, is the expected departure time of the new energy vehicle user, is the energy state of the new energy vehicle at the current time (unit: %), is the energy state of the new energy vehicle when the user is expected to leave (unit: %), is the vehicle pick-up location number when the user is expected to leave.

[0064] Taking the new energy vehicle user numbered as an example, the current time is , the expected departure time of the new energy vehicle user is , the energy state of the new energy vehicle numbered at present is , the energy state of the new energy vehicle when the user is expected to leave is , and the vehicle pick-up location number when the user is expected to leave is , then the time-sensitive inference model is:

[0065] .

[0066] In the adopted time-sensitive inference model, , , , , the numerical values satisfy the conditions:

[0067] ;

[0068] ;

[0069] ;

[0070] In the formula, is the current time, is the expected departure time of the new energy vehicle user, is the energy state of the new energy vehicle at the current time (unit: %), is the energy state of the new energy vehicle when the user expects to leave (unit: %), is the vehicle position number extracted when the user expects to leave.

[0071] S3. Calculate the expected time cost coefficient for each user's charging and parking based on factors such as the user expectation confidence model, time-sensitive inference model, and the current charging and parking state of the new energy vehicle.

[0072] Among them, for the individual new energy vehicle user numbered the current charging and parking state of the individual new energy vehicle is that the current charging pile is a fast charging pile, and the current charging power is .

[0073] Calculate the expected time cost coefficient for each user's charging and parking. The formula is as follows:

[0074] ;

[0075] ;

[0076] ;

[0077] ;

[0078] In the formula, is the time expectation cost coefficient of the individual new energy vehicle user numbered based on the charging of the new energy vehicle, is the energy state of the new energy vehicle at the current time (unit: %), is the energy state of the new energy vehicle when the user expects to leave (unit: %), is the rated energy upper limit of the new energy vehicle of the individual new energy vehicle user numbered , is the preset charging power of the new energy vehicle of the individual new energy vehicle user numbered (i.e., the current charging and parking state of the new energy vehicle), is the current time, is the expected departure time of the new energy vehicle user; is the time expectation cost coefficient of the individual new energy vehicle user numbered based on the transfer of the new energy vehicle by the vehicle relocation robot to replace the charging pile, is the difficulty coefficient for the parking robot to transfer a new energy vehicle from position to position; is the required driving distance for the parking robot to transfer a new energy vehicle from position to position; is the probability that the individual new energy vehicle user numbered picks up the vehicle and leaves from the vehicle pick-up position in the parking lot numbered within the rolling time period; is the total number of available vehicle pick-up positions in the parking lot; is the difficulty coefficient for the parking robot to transfer a new energy vehicle from position to the vehicle pick-up position numbered in the parking lot; is the required driving distance for the parking robot to transfer a new energy vehicle from position to the vehicle pick-up position numbered in the parking lot; is the waiting time required for the parking robot to transfer the new energy vehicle due to the possible occupation of position; is the time expectation cost coefficient of the individual new energy vehicle user numbered based on the parking robot transferring the new energy vehicle to the designated vehicle pick-up position; is the difficulty coefficient for the parking robot to transfer a new energy vehicle from position to the vehicle pick-up position numbered in the parking lot; is the required driving distance for the parking robot to transfer a new energy vehicle from position to the vehicle pick-up position numbered in the parking lot; is the total time expectation cost coefficient of the individual new energy vehicle user numbered for parking and charging.

[0079] The upper limit of the rated energy of the new energy vehicle of the individual new energy vehicle user numbered is ; the preset charging pile is a fast charging pile, and the preset charging power is ; the difficulty coefficient for the parking robot to transfer the new energy vehicle from position to position is ; the required driving distance for the parking robot to transfer the new energy vehicle from position to position is For , the difficulty coefficients for the parking robot to transfer a new energy vehicle from the position to the pick-up position in the parking lot numbered are respectively ; the required driving distances for the parking robot to transfer a new energy vehicle from the position to the pick-up position in the parking lot numbered are respectively ; due to the possible occupation of the position, the waiting time required for the parking robot to transfer the new energy vehicle is ; the difficulty coefficients for the parking robot to transfer a new energy vehicle from the position to the pick-up position in the parking lot numbered are respectively ; the required driving distances for the parking robot to transfer a new energy vehicle from the position to the pick-up position in the parking lot numbered are respectively ; then, for the individual new energy vehicle user numbered , the time expectation cost coefficient based on the charging time of the new energy vehicle is ; the time expectation cost coefficient based on the parking robot transferring the new energy vehicle to change the charging pile is ; the time expectation cost coefficient based on the parking robot transferring the new energy vehicle to the designated pick-up position is ; the total time expectation cost coefficient is . Among the user's stop-charging expectation time cost coefficients adopted, the numerical values satisfy the condition:

[0080]

[0081]

[0082] In the formula, is the total time expectation cost coefficient of the individual new energy vehicle user numbered for parking and charging.

[0083] S4. Calculate the comprehensive stop-charging expectation time cost coefficients of all demand users within the cycle time window, comprehensively schedule the parking positions and charging powers of new energy vehicles, and achieve the optimal charging power distribution while meeting the parking and charging requirements of new energy vehicle users.

[0084] ​​​​​​​​Calculate the comprehensive expected time cost coefficient of all demand users within the calculation cycle time window. The formula is as follows:

[0085] ;

[0086] In the formula, is the combination mode of the parking and charging positions of all new energy vehicles, is the total number of new energy vehicle users who need to park and charge currently, is at Under the combination mode, the expected time cost coefficient of all users' parking and charging, is numbered The total time expected cost coefficient of the new energy vehicle user.

[0087] The comprehensive scheduling of the parking positions and charging powers of new energy vehicles needs to meet the conditions:

[0088] ;

[0089] In the formula, is the optimal combination mode of the parking and charging positions of all new energy vehicles, is at Under the combination mode, the expected time cost coefficient of all users' parking and charging, is at Under the combination mode, the minimum expected time cost coefficient of all users' parking and charging.

[0090] The optimal charging power distribution is:

[0091] ;

[0092] In the formula, is the charging power allocated to the individual new energy vehicle numbered , is at Under the optimal combination mode of the parking and charging positions of all new energy vehicles corresponding to The parking and charging position to which the individual new energy vehicle numbered is The charging power of the charging pile at the parking and charging position.

[0093] The above embodiments have described the technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the present invention. Any modifications, supplements, and equivalent replacements made within the scope of the principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An active response method for variable pile position scheduling in a super-large parking lot to time-varying charging stop demands, characterized in that, Including the following steps: (1) Establish a user expectation confidence model based on the commuting charging and discharging requirements of new energy vehicles and the in-and-out parking lot behavior data of users within the rolling time period; (2) Collect the charging and discharging requirement information of target new energy vehicle users and establish a time-sensitive inference model; (3) Calculate the charging and discharging expected time cost coefficient of each user according to the user expectation confidence model, the time-sensitive inference model and the current charging and discharging state of the new energy vehicle. The calculation formula is as follows: ； ； ； ； In the formula, is the expected time cost coefficient of the individual new energy vehicle user numbered based on the new energy vehicle charging, is the energy state of the new energy vehicle at the current time, is the expected energy state of the new energy vehicle when the user expects to leave, is the upper limit of the rated energy of the new energy vehicle of the individual new energy vehicle user numbered ; is the preset charging power of the new energy vehicle of the individual new energy vehicle user numbered ; is the current time, is the expected departure time of the new energy vehicle user; is the expected time cost coefficient of the individual new energy vehicle user numbered based on the time for the parking robot to transfer the new energy vehicle to replace the charging pile, is the difficulty coefficient for the parking robot to transfer the new energy vehicle from the position to the position, is the required driving distance for the parking robot to transfer the new energy vehicle from the position to the position, is the probability that the individual new energy vehicle user numbered takes the vehicle and leaves from the pick-up location of the parking lot numbered within the rolling time period, is the total number of available pick-up locations in the parking lot, is the difficulty coefficient for the parking robot to transfer the new energy vehicle from the position to the pick-up location of the parking lot numbered , is the required driving distance for the parking robot to transfer the new energy vehicle from the position to the pick-up location of the parking lot numbered , is the waiting time required for the parking robot to transfer the new energy vehicle due to the possible occupation of the position; is the expected time cost coefficient of the individual new energy vehicle user numbered based on the time for the parking robot to transfer the new energy vehicle to the designated pick-up location, is the difficulty coefficient for the parking robot to transfer the new energy vehicle from the position to the pick-up location of the parking lot numbered , is the required driving distance for the parking robot to transfer the new energy vehicle from the position to the pick-up location of the parking lot numbered The required driving distance to the car pick-up location in the parking lot; For the individual new energy vehicle user numbered the expected time cost coefficient for charging and parking, ; (4) Calculate the comprehensive charging and discharging expected time cost coefficient of all users with demands within the cycle time window, comprehensively schedule the parking positions and charging powers of new energy vehicles, and achieve the optimal charging power distribution while meeting the parking and charging requirements of new energy vehicle users.

2. The method for scheduling variable pile positions in an extra-large parking lot with active response to time-varying charging stop requirements according to claim 1, wherein In step (1), the established user expectation confidence model is: ； In the formula, is the individual new energy vehicle user numbered , is the vehicle pick-up location in the parking lot numbered , is the total number of available vehicle pick-up locations in the parking lot, is the probability distribution of the individual new energy vehicle user numbered leaving the parking lot from different vehicle pick-up locations within the rolling time period, is the probability that the individual new energy vehicle user numbered leaves the parking lot from the vehicle pick-up location numbered within the rolling time period.

3. The method for actively responding to time-varying stop-and-charge demand and scheduling variable pile positions in an extra-large parking lot according to claim 2, wherein, In the user expectation confidence model, The values need to meet the following conditions: ； In the formula, is the total number of available pick-up locations in the parking lot.

4. The method for scheduling variable pile positions in an extra-large parking lot that actively responds to time-varying stop-and-charge demands according to claim 1, characterized in that In step (1), establish a user expectation confidence model based on the long short-term memory network.

5. The method for scheduling variable pile positions in an extra-large parking lot that actively responds to time-varying charging stop demands according to claim 1, wherein, In step (2), the established time-sensitive inference model is: ； Wherein, is a new energy vehicle user numbered , is the current time, is the expected departure time of the new energy vehicle user, is the energy state of the new energy vehicle at the current time, is the energy state of the new energy vehicle when the user expects to leave, is the vehicle position number extracted when the user expects to leave.

6. The method for actively responding to time-varying charging stop requirements and scheduling variable pile positions in an extra-large parking lot according to claim 5, characterized in that In the time-sensitive inference model, , , , , The numerical values need to meet the conditions: ； ； ； Wherein, is the total number of available vehicle pick-up positions in the parking lot.

7. The method for active response to time-varying stop-and-charge demand and variable pile position scheduling in an extra-large parking lot according to claim 1, characterized in that In step (4), calculate the comprehensive charging and discharging expected time cost coefficient of all users with demands within the cycle time window. The formula is: ； In the formula, represents the parking and charging location combination modes of all new energy vehicles, represents the total number of new energy vehicle users who currently need to park and charge, is the comprehensive parking and charging expected time cost coefficient of all users under the combination mode of 8. The method for active response to time-varying charging stop demand and variable pile position scheduling in an extra-large parking lot according to claim 7, wherein In step (4), comprehensively scheduling the parking positions and charging powers of new energy vehicles needs to meet the following conditions: ； In the formula, is the optimal combination mode of parking and charging positions for all new energy vehicles, is the expected time cost coefficient of parking and charging for all users under the combination mode of , is the minimum expected time cost coefficient of parking and charging for all users under the combination mode of .

9. The method for active response to time-varying charging stop and demand for variable pile position scheduling in an extra-large parking lot according to claim 8, wherein The optimal charging power distribution, the formula is: ； Wherein, is the charging power allocated to the individual new energy vehicle numbered , is the parking charging location to which the individual new energy vehicle numbered is scheduled under the combination mode of , is the charging power of the charging pile at the parking charging location.

Images