Charging station charge capacity prediction method, device, electronic equipment and medium

Abstract

The present application provides a method, device, electronic device, and medium for predicting the charge capacity of a charging station. This method obtains multiple charging time series features and the charge capacities corresponding to the corresponding charging time series features based on the charge capacity of a target charging station in a preset time period. The method then determines the charging time series feature that satisfies a preset feature selection condition among the multiple charging time series features as the target charging time series feature associated with the current prediction date. The method also obtains meteorological forecast information for the target charging station's environment on the current prediction date, as well as meteorological observation information for a target date with the same week in the previous charging week adjacent to the charging week of the current prediction date within a preset time period. The method uses the charge capacity corresponding to the target charging time series feature, the meteorological forecast information for the current prediction date, and the meteorological observation information for the target date as prediction data, and inputs the data into a trained meteorological factor impact fitting prediction model to obtain the predicted charge capacity for the current prediction date. This method improves prediction accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of electric vehicles, and in particular to a method, device, electronic device, and medium for predicting the charge amount of a charging station. Background Art

[0002] Electric vehicles (EVs) are being actively promoted worldwide amidst global warming, energy shortages, environmental protection demands, and rapid technological advancements. Governments and researchers worldwide are placing high priority on the development of EVs and related industries, and major countries have successively introduced medium- and long-term strategic plans for EV development. With the increasing number of EVs and their widespread access to the power grid, their charging and discharging behaviors have a significant impact on power system planning, operation, and market operations. Therefore, planning and coordination of EV charging and discharging behaviors are necessary to minimize their impact on low-voltage distribution networks.

[0003] Existing methods for achieving orderly EV charging may include electricity price guidance methods. In this method, when charging service providers provide corresponding operating strategies (such as price adjustments, promotional activities, etc.) based on the power grid conditions, they cannot accurately predict changes in the revenue indicators of charging stations (such as the charging volume of the charging station, the power utilization rate of the charging station, the revenue of the charging station, etc., where the power utilization rate and revenue of the charging station are both related to the charging volume). As a result, the charging operation strategy has no flexibility, resulting in a lack of attractiveness to users, which in turn affects the revenue of the charging station. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a method, device, electronic device and medium for predicting the charging capacity of a charging station, so as to solve the above-mentioned problems existing in the prior art and obtain the accurate charging capacity of the charging station.

[0005] In a first aspect, a method for predicting the charge capacity of a charging station is provided. The method may include:

[0006] Based on the charging amount of the target charging station in a preset time period, a plurality of charging time series characteristics and the charging amounts corresponding to the corresponding charging time series characteristics are obtained; at the initial moment, the start date and the end date of the preset time period are both historical dates;

[0007] Determining a charging timing feature that satisfies a preset feature selection condition among the multiple charging timing features as a target charging timing feature associated with a current prediction date; the current prediction date is the first future date that is adjacent to the preset time period in chronological order;

[0008] Obtaining weather forecast information for the target charging station's environment on the current forecast date, and weather observation information for a target date on the same week as the charging week of the current forecast date within the preset time period, the weather forecast information including the forecast temperature and the forecast weather type; and the weather observation information including the temperature and the weather type.

[0009] The charging amount corresponding to the target charging timing characteristics, the meteorological forecast information of the current forecast date and the meteorological observation information of the target date are used as prediction data, and the trained meteorological factor impact fitting prediction model is input to obtain the predicted charging amount of the current forecast date; wherein, the meteorological factor impact fitting prediction model is based on the historical charging timing characteristics within the historical time period, the meteorological forecast information of the historical forecast date and the meteorological observation information of the historical date with the same week as the historical forecast date as training samples and the historical charging amount of the historical forecast date as label data.

[0010] In an optional implementation, the weather forecast information for the current forecast date includes the maximum forecast temperature, the minimum forecast temperature, the daily average forecast temperature, and the weather type of the environment in which the target charging station is located;

[0011] The meteorological observation information of the target date of the same week in the previous charging week adjacent to the charging week in which the current predicted date is located within the preset time period includes the maximum temperature, minimum temperature, daily average temperature and weather type of the environment in which the target charging station is located on the target date.

[0012] In an optional implementation, based on the charging amount of the target charging station in a preset time period, obtaining a plurality of charging time sequence characteristics and the charging amounts corresponding to the corresponding charging time sequence characteristics includes:

[0013] The timing fitting prediction model is used to process the charging amount input for the preset time period to obtain multiple charging timing characteristics corresponding to the charging amount and the charging amount corresponding to the corresponding charging timing characteristics; the charging timing characteristics include a first charging timing characteristic that is independent of temperature and weather type and a second charging timing characteristic other than the first charging timing characteristic.

[0014] In an optional implementation, the charging capacity corresponding to the target charging time series feature, the weather forecast information of the current forecast date, and the weather observation information of the target date are used as prediction data, and a trained weather factor influence fitting prediction model is input to obtain the predicted charging capacity of the current forecast date, including:

[0015] The charging amount corresponding to the target charging timing feature, the weather forecast information of the current forecast date, the weather observation information of the target date and the second charging timing feature are used as prediction data, and the trained meteorological factor influence fitting prediction model is input to obtain the predicted charging amount of the current forecast date.

[0016] In an optional implementation, the first charging time sequence feature that is independent of temperature and weather type includes: a long-term charging trend feature, a weekly charging trend feature, and a holiday charging feature;

[0017] The second charging time series feature related to temperature and weather type includes: a charging seasonal trend feature and an error term feature, wherein the error term feature represents other charging time series features considered in addition to the above charging time series features.

[0018] In an optional implementation, the target charging timing characteristics include:

[0019] a time series feature of a date preceding the current predicted date in the long-term charging trend feature or the weekly charging trend feature;

[0020] The time series features of the charging week trend features and the date of the same week in the previous charging week adjacent to the charging week where the current predicted date is located;

[0021] The average time series characteristics of the three consecutive days preceding the current forecast date in the long-term charging trend characteristics or the weekly charging trend characteristics;

[0022] The average time series characteristics of the seven consecutive dates preceding the current forecast date in the long-term charging trend characteristics or the weekly charging trend characteristics;

[0023] The average time series characteristics of the first fifteen consecutive days adjacent to the current forecast date in the long-term charging trend characteristics or the weekly charging trend characteristics;

[0024] Charging holiday characteristics of the preset time period;

[0025] The charging weekly trend characteristics of the preset time period.

[0026] In an optional implementation, after obtaining the predicted charge amount for the current predicted date, the method further includes:

[0027] Obtain a new preset time period, where the end date of the new preset time period is the current predicted date and the start date is the date immediately following the start date in the preset time period;

[0028] Determining the date immediately following the current forecast date as a new current forecast date;

[0029] Based on the new preset time period and the new current predicted date, return to the execution step: based on the charging amount of the target charging station in the preset time period, obtain multiple charging time sequence features and the charging amounts corresponding to the corresponding charging time sequence features.

[0030] In a second aspect, a device for predicting the charge capacity of a charging station is provided, which may include:

[0031] an acquiring unit, configured to acquire, based on the charging amount of a target charging station during a preset time period, a plurality of charging time sequence characteristics and the charging amounts corresponding to the corresponding charging time sequence characteristics; wherein at an initial moment, the start date and the end date of the preset time period are both historical dates;

[0032] a determining unit, configured to determine a charging timing sequence feature that satisfies a preset feature selection condition among the plurality of charging timing sequence features as a target charging timing sequence feature associated with a current prediction date; the current prediction date being the first future date adjacent to the preset time period in chronological order;

[0033] The acquisition unit is further configured to acquire weather forecast information of the environment of the target charging station on the current forecast date, and weather observation information of a target date having the same week as the charging week of the current forecast date in a previous charging week adjacent to the charging week of the current forecast date within the preset time period; the weather forecast information includes a forecast temperature and a forecast weather type; and the weather observation information includes a temperature and a weather type.

[0034] A prediction unit is used to use the charging amount corresponding to the target charging timing characteristics, the meteorological forecast information of the current prediction date and the meteorological observation information of the target date as prediction data, input a trained meteorological factor impact fitting prediction model, and obtain the predicted charging amount of the current prediction date; wherein, the meteorological factor impact fitting prediction model is based on the historical charging timing characteristics within a historical time period, the meteorological forecast information of the historical prediction date and the meteorological observation information of the historical date with the same week as the historical prediction date as training samples and the historical charging amount of the historical prediction date as label data.

[0035] In a third aspect, an electronic device is provided, the electronic device including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0036] Memory for storing computer programs;

[0037] The processor is configured to implement any of the method steps described in the first aspect when executing a program stored in the memory.

[0038] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any of the method steps described in the first aspect is implemented.

[0039] The present application provides a charging capacity prediction method for a charging station, which obtains multiple charging time series features and the charging capacity corresponding to the corresponding charging time series features based on the charging capacity of a target charging station during a preset time period. At the initial moment, the start date and end date of the preset time period are both historical dates. A charging time series feature that satisfies a preset feature selection condition among the multiple charging time series features is determined as a target charging time series feature associated with a current prediction date. The current prediction date is the first future date adjacent to the preset time period in chronological order. Weather forecast information for the target charging station's environment on the current prediction date is obtained, as well as weather observation information for a target date with the same week in the previous charging week adjacent to the current prediction date within the preset time period. The weather forecast information includes forecast temperature and forecast weather type. The weather observation information includes temperature and weather type. The charging capacity corresponding to the target charging time series feature, the weather forecast information for the current prediction date, and the weather observation information for the target date are used as prediction data and input into a trained meteorological factor influence fitting prediction model to obtain a predicted charging capacity for the current prediction date. This method considers the impact of conventional factors such as time series, temperature, and weather on charging capacity when predicting charging capacity, thereby improving prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A system architecture diagram of a method for predicting the charge capacity of a charging station provided in an embodiment of the present application;

[0042] Figure 2 A flow chart of a method for predicting the charge capacity of a charging station provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of the structure of a charging capacity prediction device for a charging station provided in an embodiment of the present application;

[0044] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0046] The charging capacity prediction method of the charging station provided in the embodiment of the present application can be applied in the following situations: Figure 1 The system architecture consists of a server, at least one charging terminal in the target charging station, and at least one weather station in the area where the target charging station is located. The server can be a physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. The terminal can be a user equipment (UE), computing device, etc. such as a laptop computer, personal digital assistant (PDA), tablet computer (PAD) with strong computing power. The server and the charging terminal can be connected to each other by wired or wireless communication.

[0047] The weather station is used to collect meteorological observation data of the environment in the area where the target charging station is located, and the meteorological observation data includes temperature and weather type.

[0048] The charging terminal is used to upload charging information of each charging service to the server, including the charging amount and charging time of each charging service;

[0049] The server is configured to obtain weather forecast data for the next 15 days based on meteorological observation data uploaded by at least one weather station, and to execute the charging capacity prediction method for a charging station of the present application based on charging information uploaded by at least one charging terminal and the weather forecast data for the corresponding date, to accurately predict the expected charging capacity for a future time period, thereby formulating corresponding operating strategies for the future time period based on the predicted charging capacity, such as adjusting prices and implementing promotional activities. The weather forecast data includes predicted temperature and predicted weather type.

[0050] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application can be combined with each other if there is no conflict.

[0051] Figure 2This is a flow chart of a method for predicting the charge capacity of a charging station provided in an embodiment of the present application. Figure 2 As shown, the method may include:

[0052] Step S210: Based on the charging amount of the target charging station in a preset time period, a plurality of charging time sequence characteristics and the charging amounts corresponding to the corresponding charging time sequence characteristics are obtained.

[0053] In the specific implementation, at the initial moment, the start date and end date of the preset time period are historical dates. For example, today is February 28, 2022, and the current predicted date is March 1, 2022. At the initial moment, the preset time period is February 14, 2022 to February 28, 2022, a total of 15 days.

[0054] Based on the acquired charging amount of the target charging station in a preset time period, a charging amount curve can be drawn, thereby obtaining the charging timing characteristics of the charging amount in the preset time period and the charging amount corresponding to the corresponding charging timing characteristics, such as long-term charging trend characteristics, weekly charging trend characteristics, holiday charging characteristics, seasonal charging trend characteristics, etc.

[0055] Alternatively, a time series fitting prediction model (Prophet model) can be used to obtain the above-mentioned charging time series characteristics and the charging amount corresponding to the corresponding charging time series characteristics. Specifically: the time series fitting prediction model is used to process the charging amount of the input preset time period to obtain multiple charging time series characteristics corresponding to the charging amount and the charging amount corresponding to the corresponding charging time series characteristics; the charging time series characteristics include a first charging time series characteristic that is unrelated to the temperature and weather type and a second charging time series characteristic other than the first charging time series characteristic. Among them, the first charging time series characteristic that is unrelated to the temperature and weather type may include: a long-term charging trend characteristic, a weekly charging trend characteristic, and a holiday charging characteristic; the second charging time series characteristic that is related to the temperature and weather type may include: a seasonal charging trend characteristic (or "annual trend characteristic") and an error term characteristic, the error term characteristic representing other charging time series characteristics considered in addition to the above-mentioned charging time series characteristics.

[0056] The following is a graph showing the change in charging capacity at a charging station during a certain period of time due to the city's weather and holidays:

[0057] (1) Changes in charging capacity due to weather conditions:

[0058] Blizzard is similar to heavy snow. The charging capacity decreases at [-4 to 0 degrees] and increases at [-9 to -5 degrees]. The only difference is the size of the impact. Blizzard affects more than 15%, and heavy snow affects about 5%.

[0059] Moderate snow is similar to light snow, causing an increase in charge capacity (up to +10%) at higher temperatures and a decrease in charge capacity (up to -13%) at lower temperatures.

[0060] Heavy rain and torrential rain are similar, with a larger increase in charging at [6-10 degrees], 15% for heavy rain and 6% for heavy rain. Heavy rain: As the temperature drops, the charging capacity increases.

[0061] Moderate rain is similar to light rain, and the charging capacity increases by about 4% at [-4 to 0 degrees].

[0062] Heavy rain and light rain at the lowest temperatures will cause the charging capacity to drop. Heavy rain will drop by 3% at [1-5 degrees], and light rain will drop by 6% at [-9--5 degrees].

[0063] (2) Changes in charging capacity due to holidays:

[0064] During holidays, the charging capacity decreases, which affects the day after the holiday.

[0065] During long holidays such as the Spring Festival, Labor Day, and National Day, the charging volume is lowest on the 4th day: it drops by about 10% during the Spring Festival and Labor Day, and drops by 14% during the National Day.

[0066] The charging volume is lowest on the second day of Dragon Boat Festival and the third day of New Year's Day / Tomb-Sweeping Day / Mid-Autumn Festival, down about 6%.

[0067] The charging volume increased two days before the Spring Festival and began to decrease two days before National Day.

[0068] Step S220: Determine a charging timing sequence feature that meets a preset feature selection condition among the multiple charging timing sequence features as a target charging timing sequence feature associated with the current forecast date.

[0069] Among them, the current predicted date is the first future date adjacent to the preset time period in chronological order. If the preset time period is February 14, 2022 - February 28, 2022, the current predicted date is March 1, 2022.

[0070] In a specific implementation, based on the above-obtained charging long-term trend characteristics, charging weekly trend characteristics, and charging holiday characteristics, the target charging time sequence characteristics may include:

[0071] The time series feature of the date before the current forecast date in the long-term charging trend feature or the weekly charging trend feature. If the current forecast date is today, the time series feature is the charging time series feature of yesterday's charging amount.

[0072] The time series feature of the date with the same week in the previous charging week adjacent to the charging week of the current prediction date in the charging week trend feature. If the current prediction date is today, then the time series feature is the charging time series feature of the charging amount in the same week of the previous charging week;

[0073] The average time series feature of the three consecutive days preceding the current forecast date in the long-term charging trend feature or the weekly charging trend feature. If the current forecast date is today, the time series feature is the average feature of the charging amount in the past three days.

[0074] The average time series feature of the seven consecutive days preceding the current forecast date in the long-term charging trend feature or the weekly charging trend feature. If the current forecast date is today, the time series feature is the average feature of the charging capacity in the past seven days.

[0075] The average time series feature of the fifteen consecutive days preceding the current forecast date in the long-term charging trend feature or weekly charging trend feature. If the current forecast date is today, the time series feature is the average feature of the charging capacity in the past 15 days.

[0076] Charging holiday characteristics for preset time periods;

[0077] Charging weekly trend characteristics for a preset time period.

[0078] Step S230: Obtain weather forecast information for the target charging station's environment on the current forecast date, and weather observation information for the target date of the same week in the previous charging week adjacent to the charging week of the current forecast date within a preset time period.

[0079] In a specific implementation, the weather forecast information for the current forecast date is obtained from the weather station in the area where the target charging station is located, as well as the weather observation information for the target date of the same week in the previous charging week adjacent to the charging week of the current forecast date within a preset time period.

[0080] Among them, the meteorological forecast information for the current forecast date includes the maximum forecast temperature, minimum forecast temperature, daily average forecast temperature and weather type of the environment in which the target charging station is located; the meteorological observation information of the target date with the same week in the previous charging week adjacent to the charging week in which the current forecast date is located within the preset time period includes the maximum temperature, minimum temperature, daily average temperature and weather type of the environment in which the target charging station is located on the target date.

[0081] Step S240: The charging capacity corresponding to the target charging time series characteristics, the weather forecast information of the current forecast date, and the weather observation information of the target date are used as forecast data, and the trained weather factor influence fitting forecast model is input to obtain the forecast charging capacity of the current forecast date.

[0082] Among them, the meteorological factor-affected fitting prediction model (such as the LGBM model) is based on the historical charging timing characteristics within the historical time period, the meteorological forecast information of the historical forecast date, and the meteorological observation information of the historical date with the same week as the historical forecast date as training samples and the historical charging amount of the historical forecast date as label data. The specific training process can refer to the existing model training method, and this application has been implemented and will not be elaborated here.

[0083] In some embodiments, if a timing fitting prediction model is used to obtain multiple charging timing characteristics and the charging capacity corresponding to the corresponding charging timing characteristics, the specific step is: the charging capacity corresponding to the target charging timing characteristic, the meteorological forecast information of the current prediction date, the meteorological observation information of the target date and the second charging timing characteristic are used as prediction data, and the trained meteorological factor influence fitting prediction model is input to obtain the predicted charging capacity of the current prediction date.

[0084] Furthermore, after obtaining the predicted charge amount for the current prediction date, the preset time period can be updated to obtain a new preset time period, where the end date of the preset time period is the current prediction date and the start date is the date immediately following the start date in the preset time period. The date immediately following the current prediction date is also determined as the new current prediction date. For example, if the preset time period is February 14, 2022, to February 28, 2022, and the current prediction date is March 1, 2022, then the new preset time period is February 15, 2022, to March 1, 2022, and the new current prediction date is March 2, 2022.

[0085] Based on the new preset time period and the new current forecast date, the process returns to step S210 : based on the charging amount of the target charging station in the preset time period, a plurality of charging time sequence features and the charging amounts corresponding to the corresponding charging time sequence features are obtained.

[0086] Since the duration of an accurate weather forecast is 15 days, the charging capacity prediction method for a charging station provided in the embodiment of the present application can accurately predict the predicted charging capacity for each day within the corresponding 15 days.

[0087] The present application provides a charging capacity prediction method for a charging station, which obtains multiple charging time series features and the charging capacity corresponding to the corresponding charging time series features based on the charging capacity of a target charging station during a preset time period. At the initial moment, the start date and end date of the preset time period are both historical dates. A charging time series feature that satisfies a preset feature selection condition among the multiple charging time series features is determined as a target charging time series feature associated with a current prediction date. The current prediction date is the first future date adjacent to the preset time period in chronological order. Weather forecast information for the target charging station's environment on the current prediction date is obtained, as well as weather observation information for a target date with the same week in the previous charging week adjacent to the current prediction date within the preset time period. The weather forecast information includes forecast temperature and forecast weather type. The weather observation information includes temperature and weather type. The charging capacity corresponding to the target charging time series feature, the weather forecast information for the current prediction date, and the weather observation information for the target date are used as prediction data and input into a trained meteorological factor influence fitting prediction model to obtain a predicted charging capacity for the current prediction date. This method considers the impact of conventional factors such as time series, temperature, and weather on charging capacity when predicting charging capacity, thereby improving prediction accuracy.

[0088] Corresponding to the above method, the embodiment of the present application also provides a charging capacity prediction device for a charging station, such as Figure 3 As shown, the device includes:

[0089] An acquiring unit 310 is configured to acquire, based on the charge amount of a target charging station during a preset time period, a plurality of charging time series characteristics and the charge amounts corresponding to the corresponding charging time series characteristics; at an initial moment, the start date and the end date of the preset time period are both historical dates;

[0090] A determining unit 320 is configured to determine a charging timing series feature that satisfies a preset feature selection condition among the multiple charging timing series features as a target charging timing series feature associated with a current prediction date; the current prediction date is the first future date that is adjacent to the preset time period in chronological order;

[0091] The acquisition unit 310 is further configured to acquire weather forecast information for the environment of the target charging station on the current forecast date, and weather observation information for a target date of the same week in a previous charging week adjacent to the charging week of the current forecast date within the preset time period; the weather forecast information includes a forecast temperature and a forecast weather type; and the weather observation information includes a temperature and a weather type.

[0092] The prediction unit 330 is used to use the charging amount corresponding to the target charging timing characteristics, the meteorological forecast information of the current prediction date and the meteorological observation information of the target date as prediction data, input the trained meteorological factor impact fitting prediction model, and obtain the predicted charging amount of the current prediction date; wherein, the meteorological factor impact fitting prediction model is based on the historical charging timing characteristics within the historical time period, the meteorological forecast information of the historical prediction date and the meteorological observation information of the historical date with the same week as the historical prediction date as training samples and the historical charging amount of the historical prediction date as label data.

[0093] The functions of the various functional units of the charging capacity prediction device of the charging station provided in the above embodiments of the present application can be achieved through the above-mentioned method steps. Therefore, the specific working process and beneficial effects of each unit in the device provided in the embodiments of the present application will not be repeated here.

[0094] The present application also provides an electronic device, such as Figure 4 As shown, it includes a processor 410 , a communication interface 420 , a memory 430 and a communication bus 440 , wherein the processor 410 , the communication interface 420 , and the memory 430 communicate with each other via the communication bus 440 .

[0095] Memory 430, for storing computer programs;

[0096] The processor 410 is configured to execute the program stored in the memory 430 by performing the following steps:

[0097] Based on the charging amount of the target charging station in a preset time period, a plurality of charging time series characteristics and the charging amounts corresponding to the corresponding charging time series characteristics are obtained; at the initial moment, the start date and the end date of the preset time period are both historical dates;

[0098] Determining a charging timing feature that satisfies a preset feature selection condition among the multiple charging timing features as a target charging timing feature associated with a current prediction date; the current prediction date is the first future date that is adjacent to the preset time period in chronological order;

[0099] Obtaining weather forecast information for the target charging station's environment on the current forecast date, and weather observation information for a target date on the same week as the charging week of the current forecast date within the preset time period, the weather forecast information including the forecast temperature and the forecast weather type; and the weather observation information including the temperature and the weather type.

[0100] The charging amount corresponding to the target charging timing characteristics, the meteorological forecast information of the current forecast date and the meteorological observation information of the target date are used as prediction data, and the trained meteorological factor impact fitting prediction model is input to obtain the predicted charging amount of the current forecast date; wherein, the meteorological factor impact fitting prediction model is based on the historical charging timing characteristics within the historical time period, the meteorological forecast information of the historical forecast date and the meteorological observation information of the historical date with the same week as the historical forecast date as training samples and the historical charging amount of the historical forecast date as label data.

[0101] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0102] The communication interface is used for communication between the above electronic device and other devices.

[0103] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0104] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0105] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments to solve the problems can be found in Figure 2 The various steps in the embodiment shown are implemented, therefore, the specific working process and beneficial effects of the electronic device provided by the embodiment of the present application are not repeated here.

[0106] In another embodiment provided in the present application, a computer-readable storage medium is also provided, which stores instructions. When the computer-readable storage medium is executed on a computer, the computer executes the charging capacity prediction method of the charging station described in any of the above embodiments.

[0107] In another embodiment provided by the present application, a computer program product including instructions is further provided, which, when executed on a computer, enables the computer to execute the charging capacity prediction method for a charging station described in any one of the above embodiments.

[0108] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the embodiments of the present application can be implemented in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of the present application can be implemented in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0110] These computer program instructions may 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, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0112] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0113] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims and their equivalents, the embodiments of the present application are also intended to include these modifications and variations.

Claims

1. A method for predicting the charge capacity of a charging station, characterized in that: The method comprises: Based on the charging amount of the target charging station in a preset time period, a plurality of charging time series characteristics and the charging amounts corresponding to the corresponding charging time series characteristics are obtained; at the initial moment, the start date and the end date of the preset time period are both historical dates; Determining a charging timing feature that satisfies a preset feature selection condition among the multiple charging timing features as a target charging timing feature associated with a current prediction date; the current prediction date is the first future date that is adjacent to the preset time period in chronological order; Obtaining weather forecast information for the target charging station's environment on the current forecast date, and weather observation information for a target date on the same week as the charging week of the current forecast date within the preset time period, the weather forecast information including the forecast temperature and the forecast weather type; and the weather observation information including the temperature and the weather type. The charge capacity corresponding to the target charging time series characteristics, the weather forecast information for the current forecast date, and the weather observation information for the target date are used as forecast data and input into a trained weather factor impact fitting forecasting model to obtain a forecast charge capacity for the current forecast date; wherein the weather factor impact fitting forecasting model is trained based on historical charging time series characteristics within a historical time period, weather forecast information for historical forecast dates, and weather observation information for historical dates on the same week as the historical forecast dates as training samples, and historical charge capacities on historical forecast dates as label data; The method of obtaining a plurality of charging time sequence characteristics and charging amounts corresponding to the corresponding charging time sequence characteristics based on the charging amount of the target charging station in a preset time period includes: Using a time series fitting prediction model, processing the input charging amount during the preset time period to obtain a plurality of charging time series features corresponding to the charging amount and the charging amount corresponding to the corresponding charging time series features; the charging time series features include a first charging time series feature that is unrelated to temperature and weather type and a second charging time series feature other than the first charging time series feature; The first charging time series features include: long-term charging trend features, weekly charging trend features, and holiday charging features; the second charging time series features include: seasonal charging trend features and error term features, wherein the error term features represent other second charging time series features considered in addition to the seasonal charging trend features; The first charging timing characteristics include: a time series feature of a date preceding the current predicted date in the long-term charging trend feature or the weekly charging trend feature; The time series features of the charging week trend features and the date of the same week in the previous charging week adjacent to the charging week where the current predicted date is located; The average time series characteristics of the three consecutive days preceding the current forecast date in the long-term charging trend characteristics or the weekly charging trend characteristics; The average time series characteristics of the seven consecutive dates preceding the current forecast date in the long-term charging trend characteristics or the weekly charging trend characteristics; The average time series characteristics of the first fifteen consecutive days adjacent to the current forecast date in the long-term charging trend characteristics or the weekly charging trend characteristics; Charging holiday characteristics of the preset time period; The charging weekly trend characteristics of the preset time period.

2. The method according to claim 1, wherein The weather forecast information for the current forecast date includes the maximum forecast temperature, minimum forecast temperature, daily average forecast temperature, and weather type of the environment in which the target charging station is located; The meteorological observation information of the target date of the same week in the previous charging week adjacent to the charging week in which the current predicted date is located within the preset time period includes the maximum temperature, minimum temperature, daily average temperature and weather type of the environment in which the target charging station is located on the target date.

3. The method according to claim 1, wherein The charging capacity corresponding to the target charging time series feature, the weather forecast information of the current forecast date, and the weather observation information of the target date are used as forecast data, and the trained weather factor influence fitting forecast model is input to obtain the forecast charging capacity of the current forecast date, including: The charging amount corresponding to the target charging timing feature, the weather forecast information of the current forecast date, the weather observation information of the target date and the second charging timing feature are used as prediction data, and the trained meteorological factor influence fitting prediction model is input to obtain the predicted charging amount of the current forecast date.

4. The method according to claim 1, wherein After obtaining the predicted charging amount for the current predicted date, the method further includes: Obtain a new preset time period, where the end date of the new preset time period is the current predicted date and the start date is the date immediately following the start date in the preset time period; Determining the date immediately following the current forecast date as a new current forecast date; Based on the new preset time period and the new current predicted date, return to the execution step: based on the charging amount of the target charging station in the preset time period, obtain multiple charging time sequence features and the charging amounts corresponding to the corresponding charging time sequence features.

5. A charging capacity prediction device for a charging station, characterized in that: The device comprises: an acquiring unit, configured to acquire, based on the charging amount of a target charging station during a preset time period, a plurality of charging time sequence characteristics and the charging amounts corresponding to the corresponding charging time sequence characteristics; wherein at an initial moment, the start date and the end date of the preset time period are both historical dates; a determining unit, configured to determine a charging timing sequence feature that satisfies a preset feature selection condition among the plurality of charging timing sequence features as a target charging timing sequence feature associated with a current prediction date; the current prediction date being the first future date adjacent to the preset time period in chronological order; The acquisition unit is further configured to acquire weather forecast information of the environment of the target charging station on the current forecast date, and weather observation information of a target date having the same week as the charging week of the current forecast date in a previous charging week adjacent to the charging week of the current forecast date within the preset time period; the weather forecast information includes a forecast temperature and a forecast weather type; and the weather observation information includes a temperature and a weather type. a prediction unit, configured to input the charge capacity corresponding to the target charging time series characteristics, the weather forecast information for the current forecast date, and the weather observation information for the target date as prediction data, into a trained weather factor impact fitting prediction model, and obtain a predicted charge capacity for the current forecast date; wherein the weather factor impact fitting prediction model is trained based on historical charging time series characteristics within a historical time period, weather forecast information for historical forecast dates, and weather observation information for historical dates on the same week as the historical forecast dates as training samples, and historical charge capacities on historical forecast dates as label data; Acquisition unit, specifically used for: Using a time series fitting prediction model, processing the input charging amount during the preset time period to obtain a plurality of charging time series features corresponding to the charging amount and the charging amount corresponding to the corresponding charging time series features; the charging time series features include a first charging time series feature that is unrelated to temperature and weather type and a second charging time series feature other than the first charging time series feature; The first charging time series features include: long-term charging trend features, weekly charging trend features, and holiday charging features; the second charging time series features include: seasonal charging trend features and error term features, wherein the error term features represent other second charging time series features considered in addition to the seasonal charging trend features; The first charging timing characteristics include: a time series feature of a date preceding the current predicted date in the long-term charging trend feature or the weekly charging trend feature; The time series features of the charging week trend features and the date of the same week in the previous charging week adjacent to the charging week where the current predicted date is located; The average time series characteristics of the three consecutive days preceding the current forecast date in the long-term charging trend characteristics or the weekly charging trend characteristics; The average time series characteristics of the seven consecutive dates preceding the current forecast date in the long-term charging trend characteristics or the weekly charging trend characteristics; The average time series characteristics of the first fifteen consecutive days adjacent to the current forecast date in the long-term charging trend characteristics or the weekly charging trend characteristics; Charging holiday characteristics of the preset time period; The charging weekly trend characteristics of the preset time period.

6. An electronic device, characterized in that: The electronic device includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; A processor, configured to implement the method steps described in any one of claims 1 to 4 when executing a program stored in a memory.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps according to any one of claims 1 to 4 are implemented.

Images