Charging method and device of battery swap station and storage medium

Abstract

The invention discloses a charging method and device for a battery swap station and a storage medium, and the method comprises the steps: obtaining a data index of the battery swap station through a preset feature construction method according to a pre-obtained information data set of the battery swap station; inputting into a preset power conversion prediction model based on the power conversion station information data set and the data index to obtain a predicted power conversion demand frequency of the power conversion station; according to the predicted number of times of battery replacement demands, through data accumulation, determining an accumulated predicted number of times of battery replacement demands within a preset demand time; inputting the accumulatively predicted battery replacement demand times and the number of replaceable batteries into a preset advanced charging algorithm to obtain the number of batteries needing to be charged; determining a charging strategy of the batteries needing to be charged according to the number of the batteries needing to be charged; the method is used for solving the technical problems of high power use cost and low utilization rate of an existing battery swap station charging strategy, and the operation cost is saved on the premise of meeting the battery swap requirement of a user.

Description

[0001] This application claims priority based on the invention patent application filed with the China National Intellectual Property Administration on December 29, 2023, with the application number 202311870387.1 and the invention title "An Intelligent Low-cost Charging Method, Device and Storage Medium for Swap Station Operation". The entire content of the above-mentioned Chinese patent application is incorporated herein by reference. Technical Field

[0002] This application relates to the technical field of swap station operation management, and particularly to a charging method, device and storage medium for a swap station. Background Art

[0003] Currently, the charging strategy of swap stations is "charging immediately after replacement", that is, when the battery is removed from the customer's vehicle, the palletizer immediately sends the removed battery to an idle charging bay to start charging. The industrial electricity prices in each city vary at different times, and there are dynamic changes in electricity prices during peak and valley periods of electricity consumption. For swap stations with low to medium load rates, during non-busy swap periods, the existing charging strategies of swap stations do not fully utilize the advantage of low electricity prices during valley periods to reduce charging costs, resulting in problems of high electricity usage costs and low utilization rates. Summary of the Invention

[0004] The embodiments of this application provide a charging method, device and storage medium for a swap station, which solve the technical problem that the existing charging strategies of swap stations have problems of high electricity usage costs and low utilization rates.

[0005] In a first aspect, the embodiments of this application provide a charging method for a swap station, characterized in that the method includes: obtaining data indicators of the swap station through a preset feature construction method according to a pre-obtained swap station information data set; inputting the swap station information data set and the data indicators into a preset swap demand prediction model to obtain the predicted swap demand times of the swap station; determining the cumulative predicted swap demand times within a preset demand time through data accumulation according to the predicted swap demand times; inputting the cumulative predicted swap demand times and the number of replaceable batteries into a preset early charging algorithm to obtain the number of batteries to be charged; and determining the charging strategy for the batteries to be charged according to the number of batteries to be charged.

[0006] In an implementation manner of this application, determining the cumulative predicted swap demand times within a preset demand time through data accumulation according to the predicted swap demand times specifically includes: determining the time nodes to be accumulated according to the preset demand time to obtain the predicted swap demand times corresponding to the time nodes to be accumulated; and adding up the predicted swap demand times to obtain the cumulative predicted swap demand times.

[0007] In this application, the replacement power demand for the time period passed at a certain time point is determined by accumulating the replacement power demand times, so as to satisfy the prediction of the replacement power situation at any time.

[0008] In one implementation manner of this application, based on the replacement power station information data set and data metrics, input into a preset replacement power prediction model to obtain the predicted replacement power demand times of the replacement power station, specifically including: determining the time series length based on the replacement power station information data set and data metrics; determining the time series direction through piecewise linear regression according to the time series length; and determining the predicted replacement power demand times through predictive accumulation based on the time series direction.

[0009] In this application, the replacement power demand times are predicted for the replacement power demand at the station end, providing a data basis for subsequent operations and realizing the prediction of the future replacement power situation at the urban station end.

[0010] In one implementation manner of this application, the accumulated predicted replacement power demand times and the number of replaceable batteries are input into a preset charging algorithm to obtain the number of batteries to be charged, specifically including: within a preset time range, determining whether the number of replaceable batteries is less than the accumulated predicted replacement power demand times to obtain the predicted charging demand; in the case where the number of replaceable batteries is less than the accumulated predicted replacement power demand times, the predicted charging demand is that charging is required; determining the number of batteries to be charged based on the difference between the accumulated predicted replacement power demand times and the number of replaceable batteries; in the case where the number of replaceable batteries is not less than the accumulated predicted replacement power demand times, the predicted charging demand is that charging is not required. In this application, the charging algorithm determines whether the station end needs to charge the battery and determines the number of batteries to be charged to meet the actual replacement power demand.

[0011] In one implementation manner of this application, according to the number of batteries to be charged, a charging strategy for the batteries to be charged is determined, specifically including: querying the historical low electricity price time period according to a preset time interval, and obtaining the low electricity price prediction interval according to a preset low electricity price interval calculation method; controlling at least part of the batteries to be charged to be charged within the low electricity price prediction interval according to the number of batteries to be charged and the battery charging time. In this application, by querying the time interval of the daily low electricity price and determining the time when the battery needs to start charging accordingly, the battery can be charged within the low electricity price interval, so as to improve resource utilization rate and save funds.

[0012] In one implementation manner of this application, controlling at least part of the batteries to be charged to be charged within the low electricity price prediction interval according to the number of batteries to be charged and the battery charging time specifically includes: determining the boundary time threshold between the low electricity price and the high electricity price according to the low electricity price prediction interval; determining the charging start time of the batteries to be charged in advance according to the boundary time threshold and the battery charging time.

[0013] In this application, by using the boundary time threshold, the low electricity price interval is fully utilized to determine the charging start time for the batteries to be charged in advance, and the low electricity price interval is fully utilized to further improve the resource utilization rate.

[0014] In an implementation manner of this application, before obtaining the predicted number of battery swapping demands of the battery swapping station, the method further includes: determining the accuracy of the prediction data based on the battery swapping prediction model; when the accuracy rate of the comparison between the prediction data and the real data is higher than a preset comparison threshold, the accuracy of the prediction data is accurate; when the accuracy rate of the comparison between the prediction data and the real data is lower than the preset comparison threshold, the accuracy of the prediction data is inaccurate.

[0015] In this application, by setting a threshold for the prediction data, it is judged whether the accuracy of the data prediction meets the expectation, thereby enhancing the accuracy of the data prediction.

[0016] In an implementation manner of this application, before obtaining the dataset according to the pre-obtained data, the method further includes: obtaining the basic battery swapping information of each city, and performing preset data dimension processing on the battery swapping station information to obtain a dataset based on the data dimension; wherein, the data dimension includes: city dimension, station end dimension, date dimension, and hour dimension.

[0017] In a second aspect, an embodiment of this application further provides a charging device for a battery swapping station. The device includes: a data module, configured to obtain the data index of the battery swapping station by using a preset feature construction method according to the pre-obtained battery swapping station information dataset; a prediction module, configured to input the battery swapping station information dataset and the data index into a preset battery swapping prediction model to obtain the predicted number of battery swapping demands of the battery swapping station; an accumulation module, configured to determine the accumulated predicted number of battery swapping demands within a preset demand time through data accumulation according to the predicted number of battery swapping demands; a calculation module, configured to input the accumulated predicted number of battery swapping demands and the number of replaceable batteries into a preset charging algorithm to obtain the number of batteries to be charged; a strategy module, configured to determine the charging strategy for the batteries to be charged according to the number of batteries to be charged.

[0018] In a third aspect, an embodiment of this application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. The electronic device is characterized in that when the processor executes the computer program, it implements the charging method for the battery swapping station according to any one of claims 1-8. In a fourth aspect, an embodiment of this application further provides a computer-readable storage medium, on which a computer program is stored. The computer-readable storage medium is characterized in that when the computer program is executed by a processor, it implements the charging method for the battery swapping station according to any one of claims 1-8.

[0019] A charging method, device, and storage medium for a battery swapping station provided by an embodiment of the present application solve the technical problems of high power usage costs and low utilization rates existing in the charging strategies of existing battery swapping stations through battery swapping data prediction and data processing, and have the technical effect of saving operation costs on the premise of meeting the battery swapping needs of users. Description of the Drawings

[0020] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0021] Figure 1 It is a flowchart of a charging method for a battery swapping station provided by an embodiment of the present application;

[0022] Figure 2 It is a specific flowchart of a charging method for a battery swapping station provided by an embodiment of the present application;

[0023] Figure 3 It is a schematic internal structure diagram of a charging device for a battery swapping station provided by an embodiment of the present application. Detailed Embodiments

[0024] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments and corresponding drawings of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0025] A charging method, device, and storage medium for a battery swapping station provided by an embodiment of the present application solve the technical problems of high power usage costs and low utilization rates existing in the charging strategies of existing battery swapping stations through battery swapping data prediction and data processing, and have the technical effect of saving operation costs on the premise of meeting the battery swapping needs of users.

[0026] The technical solutions proposed by the embodiments of the present application will be described in detail below with reference to the drawings.

[0027] Figure 1 It is a flowchart of a charging method for a battery swapping station provided by an embodiment of the present application. As Figure 1 shown, a charging method for a battery swapping station provided by an embodiment of the present application specifically includes the following steps: Step 101, obtaining data indicators of the battery swapping station through a preset feature construction method according to the pre-obtained battery swapping station information dataset.

[0028] Among them, the data indicators may include: the number of rechargeable batteries, the number of replaceable batteries, the number of idle batteries, the number of battery replacement orders, the type of electricity price, the electricity price, and the number of configured batteries at the station end.

[0029] Before according to the pre-obtained data set, the method further includes: obtaining the basic battery replacement information of each city, and performing preset data dimension processing on the battery replacement station information to obtain a data set based on data dimensions; among them, the data dimensions include: city dimension, station end dimension, date dimension, and hour dimension.

[0030] Through data acquisition and feature construction, perform dimension processing on the data, and clearly present the corresponding aspects of the data according to actual needs.

[0031] In the embodiments of the present application, it is explained in detail through the following Example 1.

[0032] Example 1: The data for obtaining and processing the battery replacement station information, which is mainly used to complete the establishment of the battery replacement prediction model, includes:

[0033] Battery replacement record form, recording information such as the time, status, station, power, vehicle, etc. of each battery replacement.

[0034] Station end information form, recording the basic information of the station end, such as the station name, code, business hours, etc.

[0035] Electricity price, that is, the peak-valley electricity price information of the city station, recording the peak-valley electricity price type and electricity price information in the city dimension.

[0036] City power peak-valley period information form, recording information such as the distribution time period of peak-valley in the city dimension.

[0037] Station battery charge and replacement information form, recording information such as the charge and replacement time and power change of each battery in the station dimension.

[0038] The data dimensions include: city, station end, date, hour;

[0039] The data indicators include: the number of charging batteries, the number of replaceable batteries, the number of idle batteries, the number of battery replacement orders, the peak-valley electricity price type, the peak-valley electricity price, and the number of configured batteries at the station end.

[0040] The specific situation of the data indicators after feature construction is as follows:

[0041] Number of charging batteries: The number of charging batteries per hour at the station end, de-duplicated by battery code.

[0042] Number of replaceable batteries: The number of batteries with an SOC of 90% or more per hour at the station end.

[0043] Number of idle batteries: The number of batteries that can be replaced but have not been replaced out per hour at the station end.

[0044] Number of battery swapping orders: The de-duplicated statistics of the hourly battery swapping orders at the station end.

[0045] Peak-valley electricity price type: The peak-valley electricity price type per hour at the station end.

[0046] Peak-valley electricity price: The peak-valley electricity price per hour at the station end.

[0047] Number of batteries configured at the station end: The total number of batteries configured at the station end for battery swapping.

[0048] Step 102: Based on the battery swapping station information dataset and data metrics, input them into a preset battery swapping prediction model to obtain the predicted number of battery swapping demands at the battery swapping station.

[0049] Specifically, it includes: determining the time series length based on the battery swapping station information dataset and data metrics; determining the time series direction through piecewise linear regression according to the time series length; and determining the predicted number of battery swapping demands through cumulative prediction based on the time series direction.

[0050] Before obtaining the predicted number of battery swapping demands at the battery swapping station, the method further includes: determining the accuracy of the predicted data based on the battery swapping prediction model; when the accuracy rate of the comparison between the predicted data and the real data is higher than a preset comparison threshold, the accuracy of the predicted data is accurate; when the accuracy rate of the comparison between the predicted data and the real data is lower than the preset comparison threshold, the accuracy of the predicted data is inaccurate.

[0051] By modeling the obtained data, predicting the future battery swapping demands at the station end, and realizing data prediction, so as to make adjustments in advance. In this application, the number of battery swapping demands is predicted for the battery swapping demands at the station end, providing a data basis for subsequent operations and realizing the prediction of the future battery swapping situation at the urban station end.

[0052] In the embodiments of this application, it is explained in detail through Example 2 below.

[0053] Example 2: The battery swapping prediction model takes FBProphet as an example, and the model is suitable for data prediction of commercial behaviors with obvious internal laws.

[0054] The prediction logic of FBProphet is based on time series decomposition and machine learning fitting. It models the time series data as a combination of trend, seasonality, and noise components to generate accurate predictions and capture the potential patterns in the data.

[0055] Specifically, the prediction logic of FBProphet includes the following steps:

[0056] Trend modeling: Use a piecewise linear regression model to capture the overall direction of the time series, whether it increases or decreases over time;

[0057] Seasonal Modeling: Use Fourier series to capture periodic patterns in the data, such as weekly or monthly trends;

[0058] Noise Modeling: Use a Bayesian framework to model the random fluctuations in the data that cannot be explained by trend or seasonal components;

[0059] Fitting the Model: Use the open-source tool pyStan to fit the model and obtain parameter estimates for each component;

[0060] Forecast Generation: Accumulate the trend, seasonal, and noise components to obtain the predicted values of the time series.

[0061] Input the corresponding data of the existing time series into FBProphet and determine the corresponding length of the time series; FBProphet outputs the predicted future trend of the time series, specifically including: the fitted curve, upper bound, lower bound, etc.

[0062] After outputting the time series trend, evaluate the model. In practical applications, a prediction accuracy of over 80% can meet the prediction requirements. When the evaluation result is determined to be qualified, obtain the battery swapping data at the corresponding time at the station end, as well as the upper and lower prediction limits (fluctuation range) corresponding to the predicted number of battery swapping demands.

[0063] Step 103: According to the predicted number of battery swapping demands, determine the cumulative predicted number of battery swapping demands within the preset demand time through data accumulation.

[0064] Among them, data accumulation is the accumulation of the predicted number of battery swapping demands.

[0065] Specifically include: According to the preset demand time, determine the time nodes to be accumulated, and obtain the predicted number of battery swapping demands corresponding to the time nodes to be accumulated; accumulate the predicted number of battery swapping demands to obtain the cumulative predicted number of battery swapping demands.

[0066] In this application, the battery swapping demands for the time period passed at a certain time point are determined by accumulating the number of battery swapping demands, which meets the prediction of the battery swapping situation at any time.

[0067] In the embodiments of this application, it is explained in detail through Example 3 below.

[0068] Example 3: For the predicted number of battery swapping demands, the time corresponding to the predicted value is the prediction until x o'clock. If it is necessary to know the prediction for a period of time, the predicted values need to be accumulated.

[0069] According to the actual operation of the battery swapping station, since most of the time before 8 am belongs to the area with lower electricity prices in a day, and because there are fewer battery swapping orders during this period, the strategy of "charging immediately after swapping" can be implemented (that is, after removing the vehicle battery, directly send the discharged battery for charging).

[0070] The actual points that need to be compared and analyzed are from 9 to 23. Through the output result of the battery replacement prediction model in the front, the predicted number of battery replacement demands is in hourly granularity, and the predicted number of battery replacement demands is determined through data accumulation.

[0071] Taking the cumulative number of battery replacement demands when the prediction station works until 10 o'clock as an example, the predicted cumulative number of battery replacement demands at 10 o'clock = the predicted number of battery replacement demands at 8 o'clock + the predicted number of battery replacement demands at 9 o'clock + the predicted number of battery replacement demands at 10 o'clock. In this way, the data required for any time period can be obtained through accumulation.

[0072] Step 104: Input the cumulative predicted number of battery replacement demands and the number of replaceable batteries into a preset charging algorithm to obtain the number of batteries that need to be charged.

[0073] Specifically, it includes: inputting the cumulative predicted number of battery replacement demands and the number of replaceable batteries into a preset charging algorithm to obtain the number of batteries that need to be charged. Specifically, within a preset time range, it is judged whether the number of replaceable batteries is less than the cumulative predicted number of battery replacement demands to obtain the predicted charging demand; when the number of replaceable batteries is less than the cumulative predicted number of battery replacement demands, the predicted charging demand is that charging is required; based on the difference between the cumulative predicted number of battery replacement demands and the number of replaceable batteries, the number of batteries that need to be charged is determined; when the number of replaceable batteries is not less than the cumulative predicted number of battery replacement demands, the predicted charging demand is that charging is not required. In this application, the charging algorithm judges whether the station end needs to charge the battery and determines the number of batteries that need to be charged to meet the actual battery replacement demand. In the embodiment of this application, it is explained in detail through the following Example 4.

[0074] Example 4: It should be noted that the need for charging not only represents the number of charging batteries in the case where the battery needs to be charged, but also the number of batteries that need to be charged will still be determined according to the actual situation during the idle stage or the busy stage.

[0075] As Figure 2 shown, especially during the busy stage, the early charging strategy is beneficial to improving the overall charging efficiency; during the idle stage, other cost-saving and efficiency-enhancing methods can be used for charging. The number of charging batteries is determined according to the charging demand. When the predicted number of battery replacement demands cannot be met, early charging is required.

[0076] For the number of replaceable batteries, it is judged through the following method.

[0077] Similar to Example 3, before 8 o'clock every morning, due to fewer battery replacement orders and lower electricity prices, the station end implements the "replace and charge immediately" strategy.

[0078] Therefore, when the time reaches 9 o'clock, since most of the batteries before this are fully charged and replaceable (SOC > 90%), if the "replace without charging" strategy is implemented starting from 9 o'clock, then due to the limited number of batteries at the station end, with each battery replacement, the number of replaceable batteries decreases by 1.

[0079] Then, within the time period from 9 to 23 o'clock, if the cumulative predicted number of battery replacement demands ≤ the number of replaceable batteries, and the available battery replacement resources actually owned by the station end meet the predicted demands, then the number of batteries that need to be pre-charged is 0; if the total cumulative predicted number of battery replacement demands from 9 to 23 o'clock > the original available number of batteries at the station end, it is considered that under the "replace without charging" strategy, there will be a moment when there are no batteries available for replacement later, and the number of batteries that need to be pre-charged = the cumulative predicted number of battery replacement demands - the number of replaceable batteries.

[0080] Step 105: Determine the charging strategy for the batteries that need to be charged according to the number of batteries that need to be charged. Specifically, it includes: query the historical low electricity price time period according to the preset time interval, and obtain the low electricity price prediction interval according to the preset low electricity price interval calculation method; determine the charging strategy for the batteries that need to be charged according to the number of batteries that need to be charged and the battery charging time. As Figure 2 shown, to determine the charging strategy for the batteries that need to be charged according to the number of batteries that need to be charged and the battery charging time, it specifically includes: determine the boundary time threshold between the low electricity price and the high electricity price according to the low electricity price prediction interval; determine the starting time for pre-charging the batteries that need to be charged through the battery charging time according to the boundary time threshold.

[0081] By querying the time interval of the daily low electricity price and thus determining the time when the battery needs to start charging, the battery can be pre-charged within the low electricity price interval, so as to improve resource utilization rate and save costs; through the boundary time threshold, make full use of the low electricity price interval, determine the starting time for arranging the pre-charging of the batteries, and make full use of the low electricity price interval to further improve the resource utilization rate.

[0082] In the embodiments of the present application, it is explained in detail through the following Example 5.

[0083] Example 5: It should be noted that for the charging strategy, the core is the starting time and the ending time of charging. The process time from the start to the end of charging is the charging duration of the battery, and this charging duration is derived from the relevant parameters of the battery.

[0084] That is to say, the charging strategy is the complete process of satisfying the charging of the batteries that need to be charged.

[0085] After determining the number of batteries that need to be charged in advance, according to the low daytime electricity price intervals in City X: 10:00 - 10:30, 11:20 - 11:40, 15:00 - 16:00; determine the start charging time of the actually to-be-charged batteries according to the charging duration of the batteries.

[0086] It should be noted that the time arrangement will flexibly consider the situation of extremely large battery replacement volume on that day. However, when there are relatively abundant replaceable batteries, all the batteries that need to be charged in advance should be arranged to be charged in the low electricity price interval as much as possible. Among them, the advance charging time is generally 1.5 hours. It can be known from the basic working logic of the battery swapping station that being able to charge in advance in the low electricity price interval can reduce the charging cost. However, since there is not always a suitable low electricity price interval for selection. Based on the basic capabilities of the battery swapping station, the battery swapping strategy will also be determined according to the actual demand during other time periods to meet the actual battery swapping needs; even when it is in the high electricity price interval, the battery swapping station will also charge the batteries.

[0087] The above is the method embodiment proposed in this application. Based on the same inventive concept, the embodiment of this application also provides a charging device for a battery swapping station, and the device includes:

[0088] A data module, configured to obtain the data indicators of the battery swapping station by means of a preset feature construction method according to the pre-acquired battery swapping station information data set; a prediction module, configured to input the battery swapping station information data set and the data indicators into a preset battery swapping prediction model to obtain the predicted battery swapping demand times of the battery swapping station; an accumulation module, configured to determine the cumulative predicted battery swapping demand times within a preset demand time through data accumulation according to the predicted battery swapping demand times; a calculation module, configured to input the cumulative predicted battery swapping demand times and the number of replaceable batteries into a preset charging algorithm to obtain the number of batteries that need to be charged; a strategy module, configured to determine the charging strategy of the batteries that need to be charged according to the number of batteries that need to be charged. The embodiment of this application also provides a charging device for a battery swapping station, and its structure is as Figure 3 shown.

[0089] Figure 3 This is a schematic diagram of the internal structure of a charging device for a battery swapping station provided by the embodiment of this application. As Figure 3 shown, the device includes:

[0090] At least one processor 301;

[0091] And a memory 302 communicatively connected to at least one processor;

[0092] Among them, the memory 302 stores instructions that can be executed by at least one processor. The instructions are executed by at least one processor 301 so that at least one processor 301 can: obtain data metrics of the swapping station according to a pre-acquired dataset of swapping station information through a preset feature construction method; input the dataset of swapping station information and the data metrics into a preset swapping demand prediction model to obtain the predicted number of swapping demands of the swapping station; determine the cumulative predicted number of swapping demands within a preset demand time through data accumulation based on the predicted number of swapping demands; input the cumulative predicted number of swapping demands and the number of swappable batteries into a preset early charging algorithm to obtain the number of batteries to be charged; and determine the charging strategy for the batteries to be charged according to the number of batteries to be charged.

[0093] Some embodiments of the present application provide an electronic device corresponding to Figure 1 including a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that when the processor executes the computer program, it implements the charging method of the swapping station according to any one of claims 1-8. Some embodiments of the present application provide an electronic device corresponding to Figure 1 A computer-readable storage medium, on which a computer program is stored, characterized in that when the computer program is executed by a processor, it implements the charging method of the swapping station according to any one of claims 1-8.

[0094] Each embodiment in the present application is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the embodiments of the Internet of Things devices and media, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0095] The systems and media provided by the embodiments of the present application correspond one-to-one with the methods. Therefore, the systems and media also have beneficial technical effects similar to those of the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media are not repeated here.

[0096] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0097] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0098] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0100] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0101] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0102] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0103] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0104] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A charging method for a battery swapping station, characterized in that, The method includes: According to a pre-acquired dataset of battery swapping station information, data indicators of the battery swapping station are obtained through a preset feature construction method; Based on the battery swapping station information dataset and the data indicators, they are input into a preset battery swapping prediction model to obtain the predicted number of battery swapping demands of the battery swapping station; According to the predicted number of battery swapping demands, through data accumulation, the cumulative predicted number of battery swapping demands within a preset demand time is determined; The cumulative predicted number of battery swapping demands and the number of replaceable batteries are input into a preset charging algorithm to obtain the number of batteries to be charged; According to the number of batteries to be charged, a charging strategy for the batteries to be charged is determined.

2. The charging method of a power exchange station according to claim 1, wherein According to the predicted number of battery swapping demands, through data accumulation, determining the cumulative predicted number of battery swapping demands within a preset demand time specifically includes: According to the preset demand time, a time node to be accumulated is determined, and the predicted number of battery swapping demands corresponding to the time node to be accumulated is obtained; The predicted number of battery swapping demands is accumulated to obtain the cumulative predicted number of battery swapping demands.

3. The charging method of a battery swapping station according to claim 1, characterized in that, Based on the battery swapping station information dataset and the data indicators, inputting them into a preset battery swapping prediction model to obtain the predicted number of battery swapping demands of the battery swapping station specifically includes: Based on the battery swapping station information dataset and the data indicators, the time series length is determined; According to the time series length, the time series direction is determined through piecewise linear regression; Based on the time series direction, through prediction accumulation, the predicted number of battery swapping demands is determined.

4. The charging method for a battery swapping station according to claim 1, wherein The cumulative predicted number of battery swapping demands and the number of replaceable batteries are input into a preset charging algorithm to obtain the number of batteries to be charged, specifically including: Within a preset time range, it is judged whether the number of replaceable batteries is less than the cumulative predicted number of battery swapping demands to obtain a predicted charging demand; When the number of replaceable batteries is less than the cumulative predicted number of battery swapping demands, the predicted charging demand is that charging is required; Based on the difference between the cumulative predicted number of battery swapping demands and the number of replaceable batteries, the number of batteries to be charged is determined; When the number of replaceable batteries is not less than the cumulative predicted number of battery swapping demands, the predicted charging demand is that charging is not required.

5. A charging method for a battery swapping station according to claim 1, characterized in that According to the number of batteries to be charged, determining the charging strategy for the batteries to be charged specifically includes: According to a preset time interval, a historical low electricity price time period is queried, and a low electricity price prediction interval is obtained according to a preset low electricity price interval calculation method; According to the number of batteries to be charged and the battery charging time, at least part of the batteries to be charged are controlled to be charged within the low electricity price prediction interval.

6. The charging method of a battery swapping station according to claim 5, wherein, According to the number of batteries to be charged and the battery charging time, controlling at least part of the batteries to be charged within the low electricity price prediction interval specifically includes: According to the low electricity price prediction interval, a boundary time threshold between the low electricity price and the high electricity price is determined; According to the boundary time threshold and through the battery charging time, the charging start time of the batteries to be charged is determined.

7. A charging method for a battery swapping station according to claim 1, wherein, Before obtaining the predicted number of battery swapping demands of the battery swapping station, the method further includes: Based on the battery swapping prediction model, determine the accuracy of the prediction data; When the accuracy rate of the comparison between the prediction data and the real data is higher than a preset comparison threshold, the accuracy of the prediction data is accurate; When the accuracy rate of the comparison between the prediction data and the real data is lower than a preset comparison threshold, the accuracy of the prediction data is inaccurate.

8. A charging method for a battery swapping station according to claim 1, characterized in that, Before the data set is obtained in advance, the method further includes: Obtain the basic information of battery swapping in each city, and perform preset data dimension processing on the battery swapping station information to obtain a data set based on data dimensions; wherein, the data dimensions include: city dimension, station end dimension, date dimension, hour dimension.

9. A charging device for a battery swapping station, characterized in that, The device includes: A data module, configured to obtain the data indicators of the battery swapping station by a preset feature construction method according to the pre-obtained data set of battery swapping station information; A prediction module, configured to input the pre-obtained data set of battery swapping station information and the data indicators into a preset battery swapping prediction model to obtain the predicted number of battery swapping demands of the battery swapping station; An accumulation module, configured to determine the cumulative predicted number of battery swapping demands within a preset demand time through data accumulation according to the predicted number of battery swapping demands; A calculation module, configured to input the cumulative predicted number of battery swapping demands and the number of replaceable batteries into a preset charging algorithm to obtain the number of batteries to be charged; A strategy module, configured to determine the charging strategy for the batteries to be charged according to the number of batteries to be charged.

10. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the charging method of the battery swapping station according to any one of claims 1-8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the charging method of the battery swapping station according to any one of claims 1-8.

Images