WO2023082474A1 - Method and apparatus for predicting travel time of electric vehicle user - Google Patents

Method and apparatus for predicting travel time of electric vehicle user Download PDF

Info

Publication number
WO2023082474A1
WO2023082474A1 PCT/CN2022/073914 CN2022073914W WO2023082474A1 WO 2023082474 A1 WO2023082474 A1 WO 2023082474A1 CN 2022073914 W CN2022073914 W CN 2022073914W WO 2023082474 A1 WO2023082474 A1 WO 2023082474A1
Authority
WO
WIPO (PCT)
Prior art keywords
electric vehicle
travel
vehicle user
day
current type
Prior art date
Application number
PCT/CN2022/073914
Other languages
French (fr)
Chinese (zh)
Inventor
王文
杨烨
张晓晴
李帅华
王凌飞
吴帆
郑冰洁
Original Assignee
国网电动汽车服务有限公司
国家电网有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 国网电动汽车服务有限公司, 国家电网有限公司 filed Critical 国网电动汽车服务有限公司
Publication of WO2023082474A1 publication Critical patent/WO2023082474A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q50/40—

Definitions

  • the invention relates to the technical field of interaction between an electric vehicle and a power grid, in particular to a method and device for predicting travel time of an electric vehicle user.
  • Private passenger vehicles are the most active and important incremental factor in the new energy vehicle market.
  • the current market share has reached 72%, and it will exceed 90% by 2040, with a scale of more than 270 million vehicles.
  • the community scene is private passenger vehicles The main battlefield of charging.
  • the peak load of charging at night may coincide with the peak load of electricity consumption at night, increasing the peak-valley difference of the power system.
  • Within the station area due to the insufficient capacity of the transformer in the old community, simple disorderly charging is prone to exceed the limit of the transformer capacity in the station area during the evening peak hours.
  • the electric vehicle charging plan ensures that the charging capacity of users can fully meet the needs of users when traveling.
  • the commonly used method of orderly charging is that the user is required to manually enter the travel time in the user interaction section, causing most users to give up orderly charging directly due to cumbersome operations and request to start the charging service immediately;
  • the power of all orderly charging piles is reduced by default during the time period, and the charging load reduction method is extensive, which often cannot match the user's charging needs, seriously affecting the user's charging experience.
  • the present invention proposes a method and device for predicting travel time of electric vehicle users.
  • a method for predicting the travel time of an electric vehicle user includes:
  • the travel time of the electric vehicle user is predicted according to the travel probability of the electric vehicle user at the current networking moment.
  • the type of days includes at least one of the following: weekdays, weekends and holidays.
  • the acquisition process of the travel probability curve corresponding to the electric vehicle user on the current type of day includes:
  • the travel state of the electric vehicle user in each unit period in the nth historical day corresponding to the current type day is ⁇ S n,1 ,S n,2 ,S n,3 ,...,S n,m ⁇ , wherein, S n,m is the travel status of the electric vehicle user in the mth unit period in the nth historical day corresponding to the current type day, if the vehicle of the electric vehicle user is in the current type day corresponding to the first
  • pm is the travel probability of the electric vehicle user in the mth unit period in the current type of day.
  • the obtaining the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user includes:
  • the travel probability corresponding to the unit period of the electric vehicle user's current network connection moment on the travel probability curve corresponding to the current type day of the electric vehicle user is taken as the travel probability of the electric vehicle user at the current network connection moment.
  • the electric vehicle user is a new user, based on the basic information of the electric vehicle user, the electric vehicle user is matched with each pre-acquired cluster, and the cluster center of the corresponding cluster is matched at the current
  • the travel status of each unit time period in each historical day corresponding to the type day is taken as the travel status of the electric vehicle user in each unit time period in each historical day corresponding to the current type day.
  • the matching of the electric vehicle user with each pre-acquired cluster based on the basic information of the electric vehicle user includes:
  • the basic information includes at least one of the following: vehicle model, vehicle type, battery capacity, remaining power, mileage, average daily mileage and power consumption per 100 kilometers.
  • the process of obtaining the pre-acquired clusters includes: using a clustering algorithm to cluster the electric vehicle users based on the basic information of the electric vehicle users.
  • the predicting the travel time of the electric vehicle user according to the travel probability of the electric vehicle user at the current networking moment includes:
  • the time period when electric vehicle users are less than the first threshold on the travel probability curve corresponding to the current type of day as the low travel time period, and define the period when the electric vehicle user is greater than the first threshold and less than the second threshold on the travel probability curve corresponding to the current type of day
  • the time period is defined as the middle travel time period, and the time period when the electric vehicle user is greater than the second threshold on the travel probability curve corresponding to the current type of day is defined as the high travel time period;
  • the electric vehicle user If the travel probability of the electric vehicle user at the current networking moment belongs to the low travel period, then the electric vehicle user’s transition time from the low travel period to the middle travel period on the travel probability curve corresponding to the current type of day or the transition time from the middle travel period to the high
  • the turning point of the travel period step is used as the travel time of the electric vehicle user
  • the electric vehicle user If the travel probability of the electric vehicle user at the current networking moment belongs to the middle travel time period, then the electric vehicle user’s transition time from the middle travel time period to the high travel time period on the travel probability curve corresponding to the current type day is taken as the electric vehicle user travel time;
  • the travel time of the electric vehicle user is the corresponding time after the current network connection moment extends the average charging time of the electric vehicle user in the current type of day .
  • an electric vehicle user travel time prediction device in a second aspect, includes:
  • the acquisition module is used to obtain the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user;
  • the predicting module is used to predict the travel time of the electric vehicle user according to the travel probability at the moment when the electric vehicle user is connected to the network.
  • a storage device in which a plurality of program codes are stored, and the program codes are adapted to be loaded and run by a processor to perform the electric vehicle user travel time prediction described in any one of the above technical solutions method.
  • control device includes a processor and a storage device, the storage device is suitable for storing a plurality of program codes, and the program codes are suitable for being loaded and run by the processor to perform any of the above-mentioned A method for predicting travel time of an electric vehicle user described in a technical solution.
  • the present invention provides a method and device for predicting travel time of an electric vehicle user, comprising: obtaining the travel probability of the electric vehicle user at the current networking time on the travel probability curve corresponding to the current type day of the electric vehicle user; Travel probabilities at connected moments predict travel times for electric vehicle users.
  • the method for predicting the travel time of electric vehicle users proposed in the present invention can effectively reduce the cumbersomeness of user charging interaction and eliminate the user's bad feelings, and at the same time make full use of the user's networking time to control charging power and participate in power grid peak shaving Fill the valley and so on. The application effect is good in the actual business system.
  • Fig. 1 is a schematic flow chart of the main steps of the method for predicting travel time of an electric vehicle user according to an embodiment of the present invention
  • Fig. 2 is the acquisition flowchart of the travel probability curve corresponding to the current type day of the new electric vehicle user in the embodiment of the present invention
  • Fig. 3 is the travel probability curve of the embodiment of the present invention and the corresponding relationship diagram of the travel probability period division;
  • Fig. 4 is a main structural block diagram of an electric vehicle user travel time prediction device according to an embodiment of the present invention.
  • the present invention proposes a method for predicting the travel time of electric vehicle users, which predicts the travel time after the user plugs in the gun and connects to the grid, and provides charging operators with charging plans within the networking time. Input parameters.
  • Fig. 1 is a schematic flowchart of main steps of a method for predicting travel time of an electric vehicle user according to an embodiment of the present invention.
  • the electric vehicle user travel time prediction method in the embodiment of the present invention mainly includes the following steps:
  • Step S101 Obtain the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user;
  • Step S102 Predict the travel time of the electric vehicle user according to the travel probability of the electric vehicle user at the current networking moment.
  • the type of days includes at least one of the following: weekdays, weekends and holidays.
  • the acquisition process of the travel probability curve corresponding to the electric vehicle user on the current type of day includes:
  • the travel state of the electric vehicle user in each unit period in the nth historical day corresponding to the current type day is ⁇ S n,1 ,S n,2 ,S n,3 ,...,S n,m ⁇ , wherein, S n,m is the travel status of the electric vehicle user in the mth unit period in the nth historical day corresponding to the current type day, if the vehicle of the electric vehicle user is in the current type day corresponding to the first
  • pm is the travel probability of the electric vehicle user in the mth unit period in the current type of day.
  • the obtaining the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user includes:
  • the travel probability corresponding to the unit period of the electric vehicle user's current network connection moment on the travel probability curve corresponding to the current type day of the electric vehicle user is taken as the travel probability of the electric vehicle user at the current network connection moment.
  • the prediction method can adopt various prediction methods including artificial intelligence algorithms such as neural network model or support vector machine.
  • artificial intelligence algorithms such as neural network model or support vector machine.
  • the present invention divides electric vehicle users into two categories: users with historical starting and parking data and new users.
  • the user with historical data refers to the user who has used the charging service online.
  • the system can retrieve the user's historical start-stop data, including: vehicle running time, vehicle flameout time, vehicle brake charging time, vehicle flameout charging time.
  • Users with historical starting and parking data and new users can access the basic data of charging travel, including: vehicle model, vehicle type, battery capacity, remaining power, mileage, average daily mileage, power consumption per 100 kilometers, etc.
  • the electric vehicle user is matched with each pre-acquired cluster, and the travel status of the cluster center of the corresponding cluster in each historical day corresponding to the current type day is used as the travel status of the electric vehicle.
  • the obtaining process of the pre-acquired clusters includes: using a clustering algorithm to cluster the electric vehicle users based on the basic information of the electric vehicle users.
  • the acquisition process of the pre-acquired clusters and the acquisition process of the new user's travel status in each unit period in each historical day corresponding to the current type day can be performed according to the steps shown in Figure 2, specifically :
  • cluster analysis is carried out according to the basic data of the historical charging user set N of electric vehicles and the historical start-stop data.
  • the clustering methods can use K-means method, system clustering method, etc.
  • the date type it can be subdivided into subtypes such as weekdays, holidays, and weekends.
  • a characteristic user group of electric vehicles contains historical travel data of several users. The method of using these data to predict the travel probability of this group is the same as the method of predicting the travel probability of historical users based on historical data. Neural network models or support vector machines can be used. A variety of forecasting methods including artificial intelligence algorithms. The method of obtaining high, medium and low travel probability time periods from the travel discrete probability through an adaptive method is the same as that of the aforementioned electric vehicle historical data users.
  • the new user basic data analysis and group matching process firstly, call the new user vehicle basic data, analyze the new user data according to the numerical characteristics obtained by the historical user set N clustering method and type, and analyze the new user data according to the value closest to method, matching the new user group category to the historical user group category set, and determining the new user group category as ci.
  • the new user is classified as ci, and the travel period of the electric vehicle characteristic group ci is the travel period of the new user.
  • the method of determining the travel time prediction value according to the travel period is the same as that of the aforementioned historical users.
  • the prediction of the travel time of the electric vehicle user according to the travel probability at the current networking moment of the electric vehicle user includes:
  • the time period when electric vehicle users are less than the first threshold on the travel probability curve corresponding to the current type of day as the low travel time period, and define the period when the electric vehicle user is greater than the first threshold and less than the second threshold on the travel probability curve corresponding to the current type of day
  • the time period is defined as the middle travel time period, and the time period when the electric vehicle user is greater than the second threshold on the travel probability curve corresponding to the current type of day is defined as the high travel time period;
  • the electric vehicle user If the travel probability of the electric vehicle user at the current networking moment belongs to the low travel period, then the electric vehicle user’s transition time from the low travel period to the middle travel period on the travel probability curve corresponding to the current type of day or the transition time from the middle travel period to the high
  • the turning point of the travel period step is used as the travel time of the electric vehicle user
  • the electric vehicle user If the travel probability of the electric vehicle user at the current networking moment belongs to the middle travel time period, then the electric vehicle user’s transition time from the middle travel time period to the high travel time period on the travel probability curve corresponding to the current type day is taken as the electric vehicle user travel time;
  • the travel time of the electric vehicle user is the corresponding time after the current network connection moment extends the average charging time of the electric vehicle user in the current type of day .
  • the first threshold and the second threshold may be selected based on experience, and the travel time may be predicted accordingly.
  • the predicted travel time and the user's actual travel time are used to calculate the prediction accuracy, and the machine learning method is used to adaptively correct and adjust the time division threshold.
  • the present invention also provides an optimal implementation mode.
  • the electric vehicle obtains the charging service online at 0:00, and the next 24 hours are divided into 288 corresponding time periods according to a period of 5 minutes.
  • the user's 288-point travel probability can be predicted.
  • the travel probability threshold of high, medium and low periods 24 hours can be divided into several probability periods.
  • the first threshold value is 0.1
  • the second threshold value is 0.5
  • 24 hours are divided into three types of high, medium and low probability periods as shown in FIG. 3 .
  • the travel probability and segmentation in Figure 3 when the user connects to the Internet during the low and medium probability periods from 19:00 p.m.
  • the travel time prediction value is point 2.
  • the travel time prediction value is point 3.
  • the daily average charging time of the corresponding type of electric vehicle is taken as the predicted value of the charging time.
  • the present invention provides a travel time prediction device for electric vehicle users, as shown in Figure 4, the travel time prediction device for electric vehicle users includes:
  • the acquisition module is used to obtain the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user;
  • the predicting module is used to predict the travel time of the electric vehicle user according to the travel probability at the moment when the electric vehicle user is connected to the network.
  • the device for predicting the travel time of an electric vehicle user includes: a processor, wherein the processor is configured to execute the above-mentioned program modules stored in the memory, including: an acquisition module and a prediction module.
  • the type of days includes at least one of the following: weekdays, weekends and holidays.
  • the acquisition process of the travel probability curve corresponding to the electric vehicle user on the current type of day includes:
  • the travel state of the electric vehicle user in each unit period in the nth historical day corresponding to the current type day is ⁇ S n,1 ,S n,2 ,S n,3 ,...,S n,m ⁇ , wherein, S n,m is the travel status of the electric vehicle user in the mth unit period in the nth historical day corresponding to the current type day, if the vehicle of the electric vehicle user is in the current type day corresponding to the first
  • pm is the travel probability of the electric vehicle user in the mth unit period in the current type of day.
  • the obtaining the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user includes:
  • the travel probability corresponding to the unit period of the electric vehicle user's current network connection moment on the travel probability curve corresponding to the current type day of the electric vehicle user is taken as the travel probability of the electric vehicle user at the current network connection moment.
  • the electric vehicle user is a new user, based on the basic information of the electric vehicle user, the electric vehicle user is matched with each pre-acquired cluster, and the cluster center of the corresponding cluster is matched at the current
  • the travel status of each unit time period in each historical day corresponding to the type day is taken as the travel status of the electric vehicle user in each unit time period in each historical day corresponding to the current type day.
  • the matching of the electric vehicle user with each pre-acquired cluster based on the basic information of the electric vehicle user includes:
  • the basic information includes at least one of the following: vehicle model, vehicle type, battery capacity, remaining power, mileage, average daily mileage and power consumption per 100 kilometers.
  • the process of obtaining the pre-acquired clusters includes: using a clustering algorithm to cluster the electric vehicle users based on the basic information of the electric vehicle users.
  • the predicting the travel time of the electric vehicle user according to the travel probability of the electric vehicle user at the current networking moment includes:
  • the time period when electric vehicle users are less than the first threshold on the travel probability curve corresponding to the current type of day as the low travel time period, and define the period when the electric vehicle user is greater than the first threshold and less than the second threshold on the travel probability curve corresponding to the current type of day
  • the time period is defined as the middle travel time period, and the time period when the electric vehicle user is greater than the second threshold on the travel probability curve corresponding to the current type of day is defined as the high travel time period;
  • the electric vehicle user If the travel probability of the electric vehicle user at the current networking moment belongs to the low travel period, then the electric vehicle user’s transition time from the low travel period to the middle travel period on the travel probability curve corresponding to the current type of day or the transition time from the middle travel period to the high
  • the turning point of the travel period step is used as the travel time of the electric vehicle user
  • the electric vehicle user If the travel probability of the electric vehicle user at the current networking moment belongs to the middle travel time period, then the electric vehicle user’s transition time from the middle travel time period to the high travel time period on the travel probability curve corresponding to the current type day is taken as the electric vehicle user travel time;
  • the travel time of the electric vehicle user is the corresponding time after the current network connection moment extends the average charging time of the electric vehicle user in the current type of day .
  • the present invention provides a storage device, in which a plurality of program codes are stored, and the program codes are adapted to be loaded and run by a processor to execute the electric vehicle user travel time described in any one of the above technical solutions. method of prediction.
  • control device includes a processor and a storage device
  • storage device is suitable for storing a plurality of program codes
  • the program codes are suitable for being loaded and run by the processor to execute the above-mentioned The method for predicting travel time of an electric vehicle user described in any one of the technical solutions.
  • the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions
  • the device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

Abstract

The present invention relates to the technical field of electric vehicle and power grid interaction, and particularly provides a method and apparatus for predicting travel time of an electric vehicle user. The method comprises: obtaining a travel probability of an electric vehicle user at a current networking moment on a travel probability curve corresponding to the electric vehicle user on the current type of day; and predicting the travel time of the electric vehicle user according to the travel probability of the electric vehicle user at the current networking moment. According to the technical solution provided by the present invention, the travel time after the user inserts a charging gun to be connected to the power grid can be effectively predicted, and input parameters are provided for a charging operator to formulate the charging plan in the networking time.

Description

一种电动汽车用户出行时间预测方法及装置Method and device for predicting travel time of electric vehicle users 技术领域technical field
本发明涉及电动汽车与电网互动技术领域，具体涉及一种电动汽车用户出行时间预测方法及装置。The invention relates to the technical field of interaction between an electric vehicle and a power grid, in particular to a method and device for predicting travel time of an electric vehicle user.
背景技术Background technique
私人乘用车是新能源汽车市场中最活跃、最重要的增量因素，目前市场占比达到72％，到2040年将超过90％，规模超过2.7亿辆，而社区场景是私人乘用车充电的主战场。广域范围内，大量电动汽车无序充电情况下，夜间充电高峰负荷可能与夜间用电高峰负荷重合，加大电力系统的峰谷差。台区范围内，由于老旧小区变压器容量不足，单纯的无序充电在晚高峰时段容易出现台区变压器容量越限等情况。对于私家车，平均每天用于行驶的时间仅为4％左右，其停放充电联网时间也远大于实际充电时间，这为其充电功率调节提供了可能。在满足电动汽车充电需求的前提下，运用实际有效地经济或技术措施引导，控制电动汽车进行充电行为，包括充电启动、充电功率大小，从而实现对电网负荷曲线的削峰填谷，延缓电网扩容建设投资。Private passenger vehicles are the most active and important incremental factor in the new energy vehicle market. The current market share has reached 72%, and it will exceed 90% by 2040, with a scale of more than 270 million vehicles. The community scene is private passenger vehicles The main battlefield of charging. In a wide area, when a large number of electric vehicles are charged out of order, the peak load of charging at night may coincide with the peak load of electricity consumption at night, increasing the peak-valley difference of the power system. Within the station area, due to the insufficient capacity of the transformer in the old community, simple disorderly charging is prone to exceed the limit of the transformer capacity in the station area during the evening peak hours. For private cars, the average daily time spent on driving is only about 4%, and their parking and charging time is much longer than the actual charging time, which makes it possible to adjust their charging power. Under the premise of meeting the charging demand of electric vehicles, use practical and effective economic or technical measures to guide and control the charging behavior of electric vehicles, including charging start-up and charging power, so as to realize peak-shaving and valley-filling of the load curve of the power grid and delay the expansion of the power grid Construction Investment.
采用上述有序充电方式，对联网充电期间的电动汽车充电启停、充电功率进行调节，需要不影响用户的充电需求、用车需求，这就需要较为准确地预测用户的出行时间，以便安排合理的电动汽车充电计划，确保用户出行时的充电量能够充分满足用户出行需求。目前有序充电常用的方法，一是在用户交互段要求用户手动输入出行时间，导致大部分用户由于操作繁琐直接放弃有序充电、要求立刻开启充电服务；另一种方法是机械地在高电价时段默认降低所有有序充电桩功率，充电负荷降低方法粗放，常常无法匹配用户充电需求，严重影响用户充电体验。Using the above-mentioned orderly charging method to adjust the charging start and stop and charging power of electric vehicles during the networked charging period, it is necessary not to affect the user's charging demand and car demand, which requires a more accurate prediction of the user's travel time in order to make reasonable arrangements The electric vehicle charging plan ensures that the charging capacity of users can fully meet the needs of users when traveling. At present, the commonly used method of orderly charging is that the user is required to manually enter the travel time in the user interaction section, causing most users to give up orderly charging directly due to cumbersome operations and request to start the charging service immediately; The power of all orderly charging piles is reduced by default during the time period, and the charging load reduction method is extensive, which often cannot match the user's charging needs, seriously affecting the user's charging experience.
发明内容Contents of the invention
为了克服上述缺陷，本发明提出了一种电动汽车用户出行时间预测方法及装置。In order to overcome the above defects, the present invention proposes a method and device for predicting travel time of electric vehicle users.
第一方面，提供一种电动汽车用户出行时间预测方法，所述电动汽车用户出行时间预测方法包括：In the first aspect, a method for predicting the travel time of an electric vehicle user is provided, and the method for predicting the travel time of an electric vehicle user includes:
在电动汽车用户在当前类型日对应的出行概率曲线上获取电动汽车用户当前联网时刻的出行概率；Obtain the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user;
根据所述电动汽车用户当前联网时刻的出行概率预测电动汽车用户的出行时间。The travel time of the electric vehicle user is predicted according to the travel probability of the electric vehicle user at the current networking moment.
优选的，所述类型日包括下述中的至少一种：工作日、周末和节假日。Preferably, the type of days includes at least one of the following: weekdays, weekends and holidays.
进一步的，所述电动汽车用户在当前类型日对应的出行概率曲线的获取过程包括：Further, the acquisition process of the travel probability curve corresponding to the electric vehicle user on the current type of day includes:
获取电动汽车用户在当前类型日对应的各历史日中各单位时段的出行状态；Obtain the travel status of electric vehicle users in each unit period in each historical day corresponding to the current type day;
基于电动汽车用户在当前类型日对应的各历史日中各单位时段的出行状态计算电动汽车用户在当前类型日中各单位时段的出行概率；Calculate the travel probability of electric vehicle users for each unit period in the current type day based on the travel status of the electric vehicle user in each unit period in each historical day corresponding to the current type day;
利用所述电动汽车用户在当前类型日中各单位时段的出行概率构建所述电动汽车用户在当前类型日对应的出行概率曲线；Constructing the travel probability curve corresponding to the electric vehicle user on the current type day by using the travel probability of each unit period of the electric vehicle user on the current type day;
其中，所述电动汽车用户在当前类型日对应的第n个历史日中各单位时段的出行状态为{S n,1,S n,2,S n,3,...,S n,m}，其中，S n,m为所述电动汽车用户在当前类型日对应的第n个历史日中第m个单位时段的出行状态，若所述电动汽车用户的车辆在当前类型日对应的第n个历史日中第m个单位时段的出行状态为停止状态，则S n,m＝0，否则，S n,m＝1，m为一日内单位时段总数，n为历史日总数。 Wherein, the travel state of the electric vehicle user in each unit period in the nth historical day corresponding to the current type day is {S n,1 ,S n,2 ,S n,3 ,...,S n,m }, wherein, S n,m is the travel status of the electric vehicle user in the mth unit period in the nth historical day corresponding to the current type day, if the vehicle of the electric vehicle user is in the current type day corresponding to the first The travel state of the mth unit period in n historical days is the stop state, then S n,m =0, otherwise, S n,m =1, m is the total number of unit periods in one day, and n is the total number of historical days.
进一步的，所述电动汽车用户在当前类型日中各单位时段的出行概率的计算公式如下：Further, the calculation formula of the travel probability of each unit period of the electric vehicle user in the current type of day is as follows:
pm＝(S 1,m+S 2,m+…+S n-1,m+S n,m)/n pm=(S 1,m +S 2,m +...+S n-1,m +S n,m )/n
上式中，pm为所述电动汽车用户在当前类型日中第m个单位时段的出行概率。In the above formula, pm is the travel probability of the electric vehicle user in the mth unit period in the current type of day.
优选的，所述在电动汽车用户在当前类型日对应的出行概率曲线上获取电动汽车用户当前联网时刻的出行概率，包括：Preferably, the obtaining the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user includes:
获取电动汽车用户当前联网时刻所属的单位时段；Obtain the unit time period to which the electric vehicle user's current networking moment belongs;
将电动汽车用户在当前类型日对应的出行概率曲线上所述电动汽车用户当前联网时刻所属的单位时段对应的出行概率作为电动汽车用户当前联网时刻的出行概率。The travel probability corresponding to the unit period of the electric vehicle user's current network connection moment on the travel probability curve corresponding to the current type day of the electric vehicle user is taken as the travel probability of the electric vehicle user at the current network connection moment.
进一步的，当电动汽车用户为新用户时，基于电动汽车用户的基础信息，将该电动汽车用户与各预先获取的聚类簇进行匹配，并将匹配对应的聚类簇的聚类中心在当前类型日对应的各历史日中各单位时段的出行状态作为该电动汽车用户在当前类型日对应的各历史日中各单位时段的出行状态。Further, when the electric vehicle user is a new user, based on the basic information of the electric vehicle user, the electric vehicle user is matched with each pre-acquired cluster, and the cluster center of the corresponding cluster is matched at the current The travel status of each unit time period in each historical day corresponding to the type day is taken as the travel status of the electric vehicle user in each unit time period in each historical day corresponding to the current type day.
进一步的，所述基于电动汽车用户的基础信息，将该电动汽车用户与各预先获取的聚类簇进行匹配，包括：Further, the matching of the electric vehicle user with each pre-acquired cluster based on the basic information of the electric vehicle user includes:
基于电动汽车用户的基础信息计算该电动汽车用户与各预先获取的聚类簇之间的欧式距离，并选择欧氏距离最小的一个聚类簇作为该电动汽车用户匹配对应的聚类簇。Calculate the Euclidean distance between the electric vehicle user and each pre-acquired cluster based on the basic information of the electric vehicle user, and select a cluster with the smallest Euclidean distance as the corresponding cluster for the electric vehicle user.
进一步的，所述基础信息包括下述中的至少一种：车辆型号、车辆类型、电池容量、剩 余电量、续航里程、日均行驶里程和百公里耗电。Further, the basic information includes at least one of the following: vehicle model, vehicle type, battery capacity, remaining power, mileage, average daily mileage and power consumption per 100 kilometers.
进一步的，所述预先获取的聚类簇的获取过程包括：采用聚类算法，基于各电动汽车用户的基础信息对各电动汽车用户进行聚类。Further, the process of obtaining the pre-acquired clusters includes: using a clustering algorithm to cluster the electric vehicle users based on the basic information of the electric vehicle users.
优选的，所述根据所述电动汽车用户当前联网时刻的出行概率预测电动汽车用户的出行时间，包括：Preferably, the predicting the travel time of the electric vehicle user according to the travel probability of the electric vehicle user at the current networking moment includes:
设置第一阈值和第二阈值，其中，0≤第一阈值≤第二阈值≤1；Setting a first threshold and a second threshold, where 0≤first threshold≤second threshold≤1;
将电动汽车用户在当前类型日对应的出行概率曲线上小于第一阈值的时段定义为低出行时段，将电动汽车用户在当前类型日对应的出行概率曲线上大于第一阈值且小于第二阈值的时段定义为中出行时段，将电动汽车用户在当前类型日对应的出行概率曲线上大于第二阈值的时段定义为高出行时段；Define the time period when electric vehicle users are less than the first threshold on the travel probability curve corresponding to the current type of day as the low travel time period, and define the period when the electric vehicle user is greater than the first threshold and less than the second threshold on the travel probability curve corresponding to the current type of day The time period is defined as the middle travel time period, and the time period when the electric vehicle user is greater than the second threshold on the travel probability curve corresponding to the current type of day is defined as the high travel time period;
若所述电动汽车用户当前联网时刻的出行概率属于低出行时段，则将电动汽车用户在当前类型日对应的出行概率曲线上低出行时段向中出行时段阶跃的转折时刻或中出行时段向高出行时段阶跃的转折时刻作为所述电动汽车用户的出行时间；If the travel probability of the electric vehicle user at the current networking moment belongs to the low travel period, then the electric vehicle user’s transition time from the low travel period to the middle travel period on the travel probability curve corresponding to the current type of day or the transition time from the middle travel period to the high The turning point of the travel period step is used as the travel time of the electric vehicle user;
若所述电动汽车用户当前联网时刻的出行概率属于中出行时段，则将电动汽车用户在当前类型日对应的出行概率曲线上中出行时段向高出行时段阶跃的转折时刻作为所述电动汽车用户的出行时间；If the travel probability of the electric vehicle user at the current networking moment belongs to the middle travel time period, then the electric vehicle user’s transition time from the middle travel time period to the high travel time period on the travel probability curve corresponding to the current type day is taken as the electric vehicle user travel time;
若所述电动汽车用户当前联网时刻的出行概率属于高出行时段，则所述电动汽车用户的出行时间为当前联网时刻向后延长所述电动汽车用户在当前类型日的平均充电时长后对应的时刻。If the travel probability of the electric vehicle user at the current networking moment belongs to the high travel time period, then the travel time of the electric vehicle user is the corresponding time after the current network connection moment extends the average charging time of the electric vehicle user in the current type of day .
第二方面，提供一种电动汽车用户出行时间预测装置，所述电动汽车用户出行时间预测装置包括：In a second aspect, an electric vehicle user travel time prediction device is provided, and the electric vehicle user travel time prediction device includes:
获取模块，用于在电动汽车用户在当前类型日对应的出行概率曲线上获取电动汽车用户当前联网时刻的出行概率；The acquisition module is used to obtain the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user;
预测模块，用于根据所述电动汽车用户当前联网时刻的出行概率预测电动汽车用户的出行时间。The predicting module is used to predict the travel time of the electric vehicle user according to the travel probability at the moment when the electric vehicle user is connected to the network.
第三方面，提供一种存储装置，该存储装置其中存储有多条程序代码，所述程序代码适于由处理器加载并运行以执行上述任一项技术方案所述的电动汽车用户出行时间预测方法。In a third aspect, a storage device is provided, in which a plurality of program codes are stored, and the program codes are adapted to be loaded and run by a processor to perform the electric vehicle user travel time prediction described in any one of the above technical solutions method.
第四方面，提供一种控制装置，该控制装置包括处理器和存储装置，所述存储装置适于存储多条程序代码，所述程序代码适于由所述处理器加载并运行以执行上述任一项技术方案所述的电动汽车用户出行时间预测方法。In a fourth aspect, there is provided a control device, the control device includes a processor and a storage device, the storage device is suitable for storing a plurality of program codes, and the program codes are suitable for being loaded and run by the processor to perform any of the above-mentioned A method for predicting travel time of an electric vehicle user described in a technical solution.
本发明上述一个或多个技术方案，至少具有如下一种或多种有益效果：The above-mentioned one or more technical solutions of the present invention have at least one or more of the following beneficial effects:
本发明提供了一种电动汽车用户出行时间预测方法及装置，包括：在电动汽车用户在当前类型日对应的出行概率曲线上获取电动汽车用户当前联网时刻的出行概率；根据所述电动汽车用户当前联网时刻的出行概率预测电动汽车用户的出行时间。与当前有序充电策略相比，本发明提出的电动汽车用户出行时间预测方法，能够有效减少用户充电交互繁琐性、消除用户不良感受，同时充分利用用户联网时间进行充电功率控制、参与电网削峰填谷等。在实际业务系统中应用效果良好。The present invention provides a method and device for predicting travel time of an electric vehicle user, comprising: obtaining the travel probability of the electric vehicle user at the current networking time on the travel probability curve corresponding to the current type day of the electric vehicle user; Travel probabilities at connected moments predict travel times for electric vehicle users. Compared with the current orderly charging strategy, the method for predicting the travel time of electric vehicle users proposed in the present invention can effectively reduce the cumbersomeness of user charging interaction and eliminate the user's bad feelings, and at the same time make full use of the user's networking time to control charging power and participate in power grid peak shaving Fill the valley and so on. The application effect is good in the actual business system.
附图说明Description of drawings
图1是本发明实施例的电动汽车用户出行时间预测方法的主要步骤流程示意图；Fig. 1 is a schematic flow chart of the main steps of the method for predicting travel time of an electric vehicle user according to an embodiment of the present invention;
图2是本发明实施例的新电动汽车用户在当前类型日对应的出行概率曲线的获取流程图；Fig. 2 is the acquisition flowchart of the travel probability curve corresponding to the current type day of the new electric vehicle user in the embodiment of the present invention;
图3是本发明实施例的出行概率曲线与出行概率时段划分对应关系图；Fig. 3 is the travel probability curve of the embodiment of the present invention and the corresponding relationship diagram of the travel probability period division;
图4是本发明实施例的电动汽车用户出行时间预测装置的主要结构框图。Fig. 4 is a main structural block diagram of an electric vehicle user travel time prediction device according to an embodiment of the present invention.
具体实施方式Detailed ways
下面结合附图对本发明的具体实施方式作进一步的详细说明。The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings.
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
为较为准确得掌握电动汽车用户充电出行时间，本发明提出一种电动汽车用户出行时间预测方法，预测出用户插枪与电网连接后的出行时间，为充电运营商制定其联网时间内充电计划提供输入参数。In order to more accurately grasp the travel time of electric vehicle users, the present invention proposes a method for predicting the travel time of electric vehicle users, which predicts the travel time after the user plugs in the gun and connects to the grid, and provides charging operators with charging plans within the networking time. Input parameters.
参阅附图1，图1是本发明的一个实施例的电动汽车用户出行时间预测方法的主要步骤流程示意图。如图1所示，本发明实施例中的电动汽车用户出行时间预测方法主要包括以下步骤：Referring to accompanying drawing 1, Fig. 1 is a schematic flowchart of main steps of a method for predicting travel time of an electric vehicle user according to an embodiment of the present invention. As shown in Figure 1, the electric vehicle user travel time prediction method in the embodiment of the present invention mainly includes the following steps:
步骤S101：在电动汽车用户在当前类型日对应的出行概率曲线上获取电动汽车用户当前联网时刻的出行概率；Step S101: Obtain the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user;
步骤S102：根据所述电动汽车用户当前联网时刻的出行概率预测电动汽车用户的出行时 间。Step S102: Predict the travel time of the electric vehicle user according to the travel probability of the electric vehicle user at the current networking moment.
本实施例中，所述类型日包括下述中的至少一种：工作日、周末和节假日。In this embodiment, the type of days includes at least one of the following: weekdays, weekends and holidays.
在一个实施方式中，所述电动汽车用户在当前类型日对应的出行概率曲线的获取过程包括：In one embodiment, the acquisition process of the travel probability curve corresponding to the electric vehicle user on the current type of day includes:
获取电动汽车用户在当前类型日对应的各历史日中各单位时段的出行状态；Obtain the travel status of electric vehicle users in each unit period in each historical day corresponding to the current type day;
基于电动汽车用户在当前类型日对应的各历史日中各单位时段的出行状态计算电动汽车用户在当前类型日中各单位时段的出行概率；Calculate the travel probability of electric vehicle users for each unit period in the current type day based on the travel status of the electric vehicle user in each unit period in each historical day corresponding to the current type day;
利用所述电动汽车用户在当前类型日中各单位时段的出行概率构建所述电动汽车用户在当前类型日对应的出行概率曲线；Constructing the travel probability curve corresponding to the electric vehicle user on the current type day by using the travel probability of each unit period of the electric vehicle user on the current type day;
其中，所述电动汽车用户在当前类型日对应的第n个历史日中各单位时段的出行状态为{S n,1,S n,2,S n,3,...,S n,m}，其中，S n,m为所述电动汽车用户在当前类型日对应的第n个历史日中第m个单位时段的出行状态，若所述电动汽车用户的车辆在当前类型日对应的第n个历史日中第m个单位时段的出行状态为停止状态，则S n,m＝0，否则，S n,m＝1，m为一日内单位时段总数，n为历史日总数。 Wherein, the travel state of the electric vehicle user in each unit period in the nth historical day corresponding to the current type day is {S n,1 ,S n,2 ,S n,3 ,...,S n,m }, wherein, S n,m is the travel status of the electric vehicle user in the mth unit period in the nth historical day corresponding to the current type day, if the vehicle of the electric vehicle user is in the current type day corresponding to the first The travel state of the mth unit period in n historical days is the stop state, then S n,m =0, otherwise, S n,m =1, m is the total number of unit periods in one day, and n is the total number of historical days.
进一步的，所述电动汽车用户在当前类型日中各单位时段的出行概率的计算公式如下：Further, the calculation formula of the travel probability of each unit period of the electric vehicle user in the current type of day is as follows:
pm＝(S 1,m+S 2,m+…+S n-1,m+S n,m)/n pm=(S 1,m +S 2,m +...+S n-1,m +S n,m )/n
上式中，pm为所述电动汽车用户在当前类型日中第m个单位时段的出行概率。In the above formula, pm is the travel probability of the electric vehicle user in the mth unit period in the current type of day.
优选的，所述在电动汽车用户在当前类型日对应的出行概率曲线上获取电动汽车用户当前联网时刻的出行概率，包括：Preferably, the obtaining the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user includes:
获取电动汽车用户当前联网时刻所属的单位时段；Obtain the unit time period to which the electric vehicle user's current networking moment belongs;
将电动汽车用户在当前类型日对应的出行概率曲线上所述电动汽车用户当前联网时刻所属的单位时段对应的出行概率作为电动汽车用户当前联网时刻的出行概率。The travel probability corresponding to the unit period of the electric vehicle user's current network connection moment on the travel probability curve corresponding to the current type day of the electric vehicle user is taken as the travel probability of the electric vehicle user at the current network connection moment.
在一个最优实施方式中，例如：预测联网车辆自联网时刻开始未来24小时内的出行概率：In an optimal implementation, for example: to predict the travel probability of the networked vehicle within the next 24 hours from the moment of network connection:
预测方法可采用神经网络模型或支持向量机等包含人工智能算法在内多种预测方法，此处仅以概率统计方法为例。以S表征车辆当前状态，当车辆处于运行状态，S＝1；当车辆处于停止状态，S＝0。可以根据实际预测需要和充电策略执行周期需要，选取某一时间段作为最小状态时段。如选择5分钟为最小状态时段，则24小时对应某车辆出行状态为60/5*24＝288点对应的状态集合Q＝{S1,S2,S3,...,S287,S288}。当某一车辆存在n个24小时状态数据样本时，则对应n个状态集合，Q1＝{S 1,1,S 1,2,S 1,3,...,S 1,287,S 1,288},Q2＝{S 2,1,S 2,2,S 2,3,...,S 2,287,S 2,288},..., Qn＝{S n,1,S n,2,S n,3,...,S n,287,S n,288}。此时第m(0<m<＝288)个状态点的车辆出行概率pm＝(S 1,m+S 2,m+…+S n-1,m+S n,m)/n。则该车辆未来24小时的288点出行概率集为P＝{p1,p2,...pm,...,p287,p288}。包含但不限于上述出行概率计算方法。 The prediction method can adopt various prediction methods including artificial intelligence algorithms such as neural network model or support vector machine. Here, only the probability and statistics method is used as an example. The current state of the vehicle is represented by S, when the vehicle is running, S=1; when the vehicle is stopped, S=0. A certain period of time can be selected as the minimum state period according to actual forecast needs and charging strategy execution cycle needs. If 5 minutes is selected as the minimum state period, then 24 hours corresponds to a certain vehicle travel state as 60/5*24=288 points corresponding to the state set Q={S1, S2, S3,..., S287, S288}. When there are n 24-hour state data samples for a certain vehicle, it corresponds to n state sets, Q1={S 1,1 ,S 1,2 ,S 1,3 ,...,S 1,287, S 1,288} , Q2={S 2,1 ,S 2,2 ,S 2,3 ,...,S 2,287 ,S 2,288 },..., Qn={S n,1 ,S n,2 ,S n,3 ,...,Sn ,287, Sn ,288 }. At this time, the vehicle travel probability pm of the mth (0<m<=288) state point=(S 1,m +S 2,m +...+S n-1,m +S n,m )/n. Then the travel probability set of 288 points of the vehicle in the next 24 hours is P={p1,p2,...pm,...,p287,p288}. Including but not limited to the above-mentioned travel probability calculation methods.
用户出行与日期类型具有明显关联关系，应考虑分类型日分别进行概率计算。例如，考虑目前电动汽车没有周期性限行政策，用户出行规律与工作日、周末、节假日成明显关联关系，将车辆状态集合分类Q工作日、Q周末、Q节假日三类，其对应的出行概率也分为P工作日、P周末、P节假日分别计算。包括但不限于上述类型日划分方法。There is an obvious correlation between user travel and date type, and the probability calculation should be carried out by considering the type of day. For example, considering that there is currently no periodic travel restriction policy for electric vehicles, and the travel patterns of users are clearly related to weekdays, weekends, and holidays, the vehicle status set is classified into three categories: Q weekdays, Q weekends, and Q holidays, and the corresponding travel probabilities are also Divided into P working days, P weekends, and P holidays are calculated separately. Including but not limited to the above-mentioned type day division method.
进一步的，本发明将电动汽车用户分为两类：有历史启停车数据用户和新用户。其中，有历史数据用户指的是用户联网使用过充电服务，系统能够调取该用户的历史启停数据，包括：车辆运行时段，车辆熄火时段，车辆刹车充电时段，车辆熄火充电时段。有历史启停车数据用户和新用户均可被调取充电出行基础数据，包括：车辆型号、车辆类型、电池容量、剩余电量、续航里程、日均行驶里程、百公里耗电等。Further, the present invention divides electric vehicle users into two categories: users with historical starting and parking data and new users. Among them, the user with historical data refers to the user who has used the charging service online. The system can retrieve the user's historical start-stop data, including: vehicle running time, vehicle flameout time, vehicle brake charging time, vehicle flameout charging time. Users with historical starting and parking data and new users can access the basic data of charging travel, including: vehicle model, vehicle type, battery capacity, remaining power, mileage, average daily mileage, power consumption per 100 kilometers, etc.
在一个实施方式中，由于没有该车辆历史出行启停出具参考，需首先进行电动汽车历史用户的聚类分析，获得不用群类的出行概率分布与概率时段划分。其次，将该电动汽车用户与各预先获取的聚类簇进行匹配，并将匹配对应的聚类簇的聚类中心在当前类型日对应的各历史日中各单位时段的出行状态作为该电动汽车用户在当前类型日对应的各历史日中各单位时段的出行状态。In one embodiment, since there is no reference issued for the start and stop of the vehicle's historical travel history, it is first necessary to perform a cluster analysis of the historical electric vehicle users to obtain the travel probability distribution and probability period division of different groups. Secondly, the electric vehicle user is matched with each pre-acquired cluster, and the travel status of the cluster center of the corresponding cluster in each historical day corresponding to the current type day is used as the travel status of the electric vehicle. The travel status of the user in each unit period in each historical day corresponding to the current type of day.
在一个实施方式中，所述预先获取的聚类簇的获取过程包括：采用聚类算法，基于各电动汽车用户的基础信息对各电动汽车用户进行聚类。In one embodiment, the obtaining process of the pre-acquired clusters includes: using a clustering algorithm to cluster the electric vehicle users based on the basic information of the electric vehicle users.
具体的，所述各预先获取的聚类簇的获取过程以及新用户在当前类型日对应的各历史日中各单位时段的出行状态的获取过程可以按照如图2所示的步骤执行，具体为：Specifically, the acquisition process of the pre-acquired clusters and the acquisition process of the new user's travel status in each unit period in each historical day corresponding to the current type day can be performed according to the steps shown in Figure 2, specifically :
1)首先根据电动汽车历史充电用户集N的基础数据和历史启停数据进行聚类分析，聚类方法可采用K-means法、系统聚类法等。依据聚类情况，可将电动汽车历史用户划分为多种特征行为群类，形成电动汽车历史用户群类集C＝{c1,c2,...,ck}，如私家车、公交车、物流车、公务车、网约车，各群类根据实际聚类情况可能包含子类型，如不同日间营运和夜间营运的网约车可能聚类形成网约车1型、网约车2型，如根据日期类型细分类工作日、节假日、周末等子类型。1) Firstly, cluster analysis is carried out according to the basic data of the historical charging user set N of electric vehicles and the historical start-stop data. The clustering methods can use K-means method, system clustering method, etc. According to the clustering situation, the historical users of electric vehicles can be divided into various characteristic behavior groups to form a cluster of historical user groups of electric vehicles C={c1,c2,...,ck}, such as private cars, buses, logistics Vehicles, official vehicles, online car-hailing, each group may contain subtypes according to the actual clustering situation, for example, online car-hailing vehicles with different daytime operations and nighttime operations may be clustered to form online car-hailing type 1 and online car-hailing type 2, For example, according to the date type, it can be subdivided into subtypes such as weekdays, holidays, and weekends.
2)计算历史用户聚类后群类出行概率及高中低出行概率时段。某一电动汽车特征用户群类含有若干用户的历史出行数据，使用这些数据预测该群类出行概率方法，与历史用户根据历史数据预测出行概率方法相同，可采用神经网络模型或支持向量机等包含人工智能算法 在内多种预测方法。由出行离散概率通过自适应方法获得高中低出行概率时段的方法与前述电动汽车历史数据用户中相同。2) Calculate the group travel probability and the high, medium and low travel probability periods after historical user clustering. A characteristic user group of electric vehicles contains historical travel data of several users. The method of using these data to predict the travel probability of this group is the same as the method of predicting the travel probability of historical users based on historical data. Neural network models or support vector machines can be used. A variety of forecasting methods including artificial intelligence algorithms. The method of obtaining high, medium and low travel probability time periods from the travel discrete probability through an adaptive method is the same as that of the aforementioned electric vehicle historical data users.
进一步的，基于电动汽车用户的基础信息计算该电动汽车用户与各预先获取的聚类簇之间的欧式距离，并选择欧氏距离最小的一个聚类簇作为该电动汽车用户匹配对应的聚类簇。Further, calculate the Euclidean distance between the electric vehicle user and each pre-acquired cluster based on the basic information of the electric vehicle user, and select a cluster with the smallest Euclidean distance as the corresponding cluster for the electric vehicle user cluster.
在一个实施方式中，新用户基础数据分析与群类匹配过程，首先，调取新用户车辆基础数据，按照历史用户集N聚类方法及类型所得数值特征，分析新用户数据，按照数值最接近方法，将新用户群类匹配到历史用户群类集中，确定新用户群类为ci。In one embodiment, the new user basic data analysis and group matching process, firstly, call the new user vehicle basic data, analyze the new user data according to the numerical characteristics obtained by the historical user set N clustering method and type, and analyze the new user data according to the value closest to method, matching the new user group category to the historical user group category set, and determining the new user group category as ci.
新用户归类群类为ci，则使用电动汽车特征群类ci的出行时段为新用户出行时段，根据出行时段确定出行时间预测值的方法与前述历史用户相同。The new user is classified as ci, and the travel period of the electric vehicle characteristic group ci is the travel period of the new user. The method of determining the travel time prediction value according to the travel period is the same as that of the aforementioned historical users.
本实施例中，所述根据所述电动汽车用户当前联网时刻的出行概率预测电动汽车用户的出行时间，包括：In this embodiment, the prediction of the travel time of the electric vehicle user according to the travel probability at the current networking moment of the electric vehicle user includes:
设置第一阈值和第二阈值，其中，0≤第一阈值≤第二阈值≤1；Setting a first threshold and a second threshold, where 0≤first threshold≤second threshold≤1;
将电动汽车用户在当前类型日对应的出行概率曲线上小于第一阈值的时段定义为低出行时段，将电动汽车用户在当前类型日对应的出行概率曲线上大于第一阈值且小于第二阈值的时段定义为中出行时段，将电动汽车用户在当前类型日对应的出行概率曲线上大于第二阈值的时段定义为高出行时段；Define the time period when electric vehicle users are less than the first threshold on the travel probability curve corresponding to the current type of day as the low travel time period, and define the period when the electric vehicle user is greater than the first threshold and less than the second threshold on the travel probability curve corresponding to the current type of day The time period is defined as the middle travel time period, and the time period when the electric vehicle user is greater than the second threshold on the travel probability curve corresponding to the current type of day is defined as the high travel time period;
若所述电动汽车用户当前联网时刻的出行概率属于低出行时段，则将电动汽车用户在当前类型日对应的出行概率曲线上低出行时段向中出行时段阶跃的转折时刻或中出行时段向高出行时段阶跃的转折时刻作为所述电动汽车用户的出行时间；If the travel probability of the electric vehicle user at the current networking moment belongs to the low travel period, then the electric vehicle user’s transition time from the low travel period to the middle travel period on the travel probability curve corresponding to the current type of day or the transition time from the middle travel period to the high The turning point of the travel period step is used as the travel time of the electric vehicle user;
若所述电动汽车用户当前联网时刻的出行概率属于中出行时段，则将电动汽车用户在当前类型日对应的出行概率曲线上中出行时段向高出行时段阶跃的转折时刻作为所述电动汽车用户的出行时间；If the travel probability of the electric vehicle user at the current networking moment belongs to the middle travel time period, then the electric vehicle user’s transition time from the middle travel time period to the high travel time period on the travel probability curve corresponding to the current type day is taken as the electric vehicle user travel time;
若所述电动汽车用户当前联网时刻的出行概率属于高出行时段，则所述电动汽车用户的出行时间为当前联网时刻向后延长所述电动汽车用户在当前类型日的平均充电时长后对应的时刻。If the travel probability of the electric vehicle user at the current networking moment belongs to the high travel time period, then the travel time of the electric vehicle user is the corresponding time after the current network connection moment extends the average charging time of the electric vehicle user in the current type of day .
其中，对于高出行概率时段联网请求充电用户，因为其随时可能出行，一般不限制其充电功率，默认以系统支持的最大功率进行充电。Among them, for users who request charging through the Internet during periods of high travel probability, because they may travel at any time, their charging power is generally not limited, and charging is performed at the maximum power supported by the system by default.
在一个实施方式中，可以先根据经验选择第一阈值和第二阈值，并据此预测出行时间。在充电试验或实际运行中，使用预测出行时间和用户实际出行时间计算预测准确性，使用机器学习方法自适应修正调整时段划分阈值。In one embodiment, the first threshold and the second threshold may be selected based on experience, and the travel time may be predicted accordingly. In the charging test or actual operation, the predicted travel time and the user's actual travel time are used to calculate the prediction accuracy, and the machine learning method is used to adaptively correct and adjust the time division threshold.
本发明还提供了一种最优实施方式，如图3所示，电动汽车于0时刻联网获取充电服务，对按照5分钟一个时段，未来24小时被划为288点对应时段。根据用户历史启停车数据，可预测出用户288点出行概率，根据出行概率高中低时段阈值，可将24小时划分为若干概率时段。本实施例中，第一阈值为0.1，第二阈值为0.5,则24小时被划分为如图3所示的提出高、中、低三类概率时段。依据图3的出行概率及分段，当用户在晚19：00-早6点所处低、中概率时段联网时，出行时间预测值均为点1时刻。用户在6：00-7：00联网时，出行时间预测值为点2时刻。用户在9：00-17：00所处中概率时段联网时，出行时间预测值为点3时刻。当用户于高概率时段联网时，取该电动汽车对应类型日平均充电时长作为本次充电时长预测值。The present invention also provides an optimal implementation mode. As shown in FIG. 3 , the electric vehicle obtains the charging service online at 0:00, and the next 24 hours are divided into 288 corresponding time periods according to a period of 5 minutes. According to the user's historical starting and parking data, the user's 288-point travel probability can be predicted. According to the travel probability threshold of high, medium and low periods, 24 hours can be divided into several probability periods. In this embodiment, the first threshold value is 0.1, and the second threshold value is 0.5, then 24 hours are divided into three types of high, medium and low probability periods as shown in FIG. 3 . According to the travel probability and segmentation in Figure 3, when the user connects to the Internet during the low and medium probability periods from 19:00 p.m. When the user connects to the Internet from 6:00 to 7:00, the travel time prediction value is point 2. When the user connects to the Internet during the medium probability period of 9:00-17:00, the travel time prediction value is point 3. When the user connects to the Internet during a high-probability time period, the daily average charging time of the corresponding type of electric vehicle is taken as the predicted value of the charging time.
基于同一发明构思，本发明提供一种电动汽车用户出行时间预测装置，如图4所示，所述电动汽车用户出行时间预测装置包括：Based on the same inventive concept, the present invention provides a travel time prediction device for electric vehicle users, as shown in Figure 4, the travel time prediction device for electric vehicle users includes:
获取模块，用于在电动汽车用户在当前类型日对应的出行概率曲线上获取电动汽车用户当前联网时刻的出行概率；The acquisition module is used to obtain the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user;
预测模块，用于根据所述电动汽车用户当前联网时刻的出行概率预测电动汽车用户的出行时间。The predicting module is used to predict the travel time of the electric vehicle user according to the travel probability at the moment when the electric vehicle user is connected to the network.
在另一个实施示例中，电动汽车用户出行时间预测装置包括：处理器，其中所述处理器用于执行存在存储器的上述程序模块，包括：获取模块和预测模块。In another implementation example, the device for predicting the travel time of an electric vehicle user includes: a processor, wherein the processor is configured to execute the above-mentioned program modules stored in the memory, including: an acquisition module and a prediction module.
优选的，所述类型日包括下述中的至少一种：工作日、周末和节假日。Preferably, the type of days includes at least one of the following: weekdays, weekends and holidays.
进一步的，所述电动汽车用户在当前类型日对应的出行概率曲线的获取过程包括：Further, the acquisition process of the travel probability curve corresponding to the electric vehicle user on the current type of day includes:
获取电动汽车用户在当前类型日对应的各历史日中各单位时段的出行状态；Obtain the travel status of electric vehicle users in each unit period in each historical day corresponding to the current type day;
基于电动汽车用户在当前类型日对应的各历史日中各单位时段的出行状态计算电动汽车用户在当前类型日中各单位时段的出行概率；Calculate the travel probability of electric vehicle users for each unit period in the current type day based on the travel status of the electric vehicle user in each unit period in each historical day corresponding to the current type day;
利用所述电动汽车用户在当前类型日中各单位时段的出行概率构建所述电动汽车用户在当前类型日对应的出行概率曲线；Constructing the travel probability curve corresponding to the electric vehicle user on the current type day by using the travel probability of each unit period of the electric vehicle user on the current type day;
其中，所述电动汽车用户在当前类型日对应的第n个历史日中各单位时段的出行状态为{S n,1,S n,2,S n,3,...,S n,m}，其中，S n,m为所述电动汽车用户在当前类型日对应的第n个历史日中第m个单位时段的出行状态，若所述电动汽车用户的车辆在当前类型日对应的第n个历史日中第m个单位时段的出行状态为停止状态，则S n,m＝0，否则，S n,m＝1，m为一日内单位时段总数，n为历史日总数。 Wherein, the travel state of the electric vehicle user in each unit period in the nth historical day corresponding to the current type day is {S n,1 ,S n,2 ,S n,3 ,...,S n,m }, wherein, S n,m is the travel status of the electric vehicle user in the mth unit period in the nth historical day corresponding to the current type day, if the vehicle of the electric vehicle user is in the current type day corresponding to the first The travel state of the mth unit period in n historical days is the stop state, then S n,m =0, otherwise, S n,m =1, m is the total number of unit periods in one day, and n is the total number of historical days.
进一步的，所述电动汽车用户在当前类型日中各单位时段的出行概率的计算公式如下：Further, the calculation formula of the travel probability of each unit period of the electric vehicle user in the current type of day is as follows:
pm＝(S 1,m+S 2,m+…+S n-1,m+S n,m)/n pm=(S 1,m +S 2,m +...+S n-1,m +S n,m )/n
上式中，pm为所述电动汽车用户在当前类型日中第m个单位时段的出行概率。In the above formula, pm is the travel probability of the electric vehicle user in the mth unit period in the current type of day.
优选的，所述在电动汽车用户在当前类型日对应的出行概率曲线上获取电动汽车用户当前联网时刻的出行概率，包括：Preferably, the obtaining the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user includes:
获取电动汽车用户当前联网时刻所属的单位时段；Obtain the unit time period to which the electric vehicle user's current networking moment belongs;
将电动汽车用户在当前类型日对应的出行概率曲线上所述电动汽车用户当前联网时刻所属的单位时段对应的出行概率作为电动汽车用户当前联网时刻的出行概率。The travel probability corresponding to the unit period of the electric vehicle user's current network connection moment on the travel probability curve corresponding to the current type day of the electric vehicle user is taken as the travel probability of the electric vehicle user at the current network connection moment.
进一步的，当电动汽车用户为新用户时，基于电动汽车用户的基础信息，将该电动汽车用户与各预先获取的聚类簇进行匹配，并将匹配对应的聚类簇的聚类中心在当前类型日对应的各历史日中各单位时段的出行状态作为该电动汽车用户在当前类型日对应的各历史日中各单位时段的出行状态。Further, when the electric vehicle user is a new user, based on the basic information of the electric vehicle user, the electric vehicle user is matched with each pre-acquired cluster, and the cluster center of the corresponding cluster is matched at the current The travel status of each unit time period in each historical day corresponding to the type day is taken as the travel status of the electric vehicle user in each unit time period in each historical day corresponding to the current type day.
进一步的，所述基于电动汽车用户的基础信息，将该电动汽车用户与各预先获取的聚类簇进行匹配，包括：Further, the matching of the electric vehicle user with each pre-acquired cluster based on the basic information of the electric vehicle user includes:
基于电动汽车用户的基础信息计算该电动汽车用户与各预先获取的聚类簇之间的欧式距离，并选择欧氏距离最小的一个聚类簇作为该电动汽车用户匹配对应的聚类簇。Calculate the Euclidean distance between the electric vehicle user and each pre-acquired cluster based on the basic information of the electric vehicle user, and select a cluster with the smallest Euclidean distance as the corresponding cluster for the electric vehicle user.
进一步的，所述基础信息包括下述中的至少一种：车辆型号、车辆类型、电池容量、剩余电量、续航里程、日均行驶里程和百公里耗电。Further, the basic information includes at least one of the following: vehicle model, vehicle type, battery capacity, remaining power, mileage, average daily mileage and power consumption per 100 kilometers.
进一步的，所述预先获取的聚类簇的获取过程包括：采用聚类算法，基于各电动汽车用户的基础信息对各电动汽车用户进行聚类。Further, the process of obtaining the pre-acquired clusters includes: using a clustering algorithm to cluster the electric vehicle users based on the basic information of the electric vehicle users.
优选的，所述根据所述电动汽车用户当前联网时刻的出行概率预测电动汽车用户的出行时间，包括：Preferably, the predicting the travel time of the electric vehicle user according to the travel probability of the electric vehicle user at the current networking moment includes:
设置第一阈值和第二阈值，其中，0≤第一阈值≤第二阈值≤1；Setting a first threshold and a second threshold, where 0≤first threshold≤second threshold≤1;
将电动汽车用户在当前类型日对应的出行概率曲线上小于第一阈值的时段定义为低出行时段，将电动汽车用户在当前类型日对应的出行概率曲线上大于第一阈值且小于第二阈值的时段定义为中出行时段，将电动汽车用户在当前类型日对应的出行概率曲线上大于第二阈值的时段定义为高出行时段；Define the time period when electric vehicle users are less than the first threshold on the travel probability curve corresponding to the current type of day as the low travel time period, and define the period when the electric vehicle user is greater than the first threshold and less than the second threshold on the travel probability curve corresponding to the current type of day The time period is defined as the middle travel time period, and the time period when the electric vehicle user is greater than the second threshold on the travel probability curve corresponding to the current type of day is defined as the high travel time period;
若所述电动汽车用户当前联网时刻的出行概率属于低出行时段，则将电动汽车用户在当前类型日对应的出行概率曲线上低出行时段向中出行时段阶跃的转折时刻或中出行时段向高出行时段阶跃的转折时刻作为所述电动汽车用户的出行时间；If the travel probability of the electric vehicle user at the current networking moment belongs to the low travel period, then the electric vehicle user’s transition time from the low travel period to the middle travel period on the travel probability curve corresponding to the current type of day or the transition time from the middle travel period to the high The turning point of the travel period step is used as the travel time of the electric vehicle user;
若所述电动汽车用户当前联网时刻的出行概率属于中出行时段，则将电动汽车用户在当 前类型日对应的出行概率曲线上中出行时段向高出行时段阶跃的转折时刻作为所述电动汽车用户的出行时间；If the travel probability of the electric vehicle user at the current networking moment belongs to the middle travel time period, then the electric vehicle user’s transition time from the middle travel time period to the high travel time period on the travel probability curve corresponding to the current type day is taken as the electric vehicle user travel time;
若所述电动汽车用户当前联网时刻的出行概率属于高出行时段，则所述电动汽车用户的出行时间为当前联网时刻向后延长所述电动汽车用户在当前类型日的平均充电时长后对应的时刻。If the travel probability of the electric vehicle user at the current networking moment belongs to the high travel time period, then the travel time of the electric vehicle user is the corresponding time after the current network connection moment extends the average charging time of the electric vehicle user in the current type of day .
进一步的，本发明提供一种存储装置，该存储装置其中存储有多条程序代码，所述程序代码适于由处理器加载并运行以执行上述任一项技术方案所述的电动汽车用户出行时间预测方法。Further, the present invention provides a storage device, in which a plurality of program codes are stored, and the program codes are adapted to be loaded and run by a processor to execute the electric vehicle user travel time described in any one of the above technical solutions. method of prediction.
进一步的，本发明提供一种控制装置，该控制装置包括处理器和存储装置，所述存储装置适于存储多条程序代码，所述程序代码适于由所述处理器加载并运行以执行上述任一项技术方案所述的电动汽车用户出行时间预测方法。Further, the present invention provides a control device, the control device includes a processor and a storage device, the storage device is suitable for storing a plurality of program codes, and the program codes are suitable for being loaded and run by the processor to execute the above-mentioned The method for predicting travel time of an electric vehicle user described in any one of the technical solutions.
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.
最后应当说明的是：以上实施例仅用以说明本发明的技术方案而非对其限制，尽管参照上述实施例对本发明进行了详细的说明，所属领域的普通技术人员应当理解：依然可以对本发明的具体实施方式进行修改或者等同替换，而未脱离本发明精神和范围的任何修改或者等同替换，其均应涵盖在本发明的权利要求保护范围之内。Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the present invention can still be Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall fall within the protection scope of the claims of the present invention.

Claims (13)

  1. 一种电动汽车用户出行时间预测方法，其特征在于，所述方法包括：A method for predicting travel time of an electric vehicle user, characterized in that the method comprises:
    在电动汽车用户在当前类型日对应的出行概率曲线上获取电动汽车用户当前联网时刻的出行概率；Obtain the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user;
    根据所述电动汽车用户当前联网时刻的出行概率预测电动汽车用户的出行时间。The travel time of the electric vehicle user is predicted according to the travel probability of the electric vehicle user at the current networking moment.
  2. 如权利要求1所述的方法，其特征在于，所述类型日包括下述中的至少一种：工作日、周末和节假日。The method according to claim 1, wherein the types of days include at least one of the following: weekdays, weekends and holidays.
  3. 如权利要求2所述的方法，其特征在于，所述电动汽车用户在当前类型日对应的出行概率曲线的获取过程包括：The method according to claim 2, wherein the acquisition process of the travel probability curve corresponding to the electric vehicle user on the current type day comprises:
    获取电动汽车用户在当前类型日对应的各历史日中各单位时段的出行状态；Obtain the travel status of electric vehicle users in each unit period in each historical day corresponding to the current type day;
    基于电动汽车用户在当前类型日对应的各历史日中各单位时段的出行状态计算电动汽车用户在当前类型日中各单位时段的出行概率；Calculate the travel probability of electric vehicle users for each unit period in the current type day based on the travel status of the electric vehicle user in each unit period in each historical day corresponding to the current type day;
    利用所述电动汽车用户在当前类型日中各单位时段的出行概率构建所述电动汽车用户在当前类型日对应的出行概率曲线；Constructing the travel probability curve corresponding to the electric vehicle user on the current type day by using the travel probability of each unit period of the electric vehicle user on the current type day;
    其中，所述电动汽车用户在当前类型日对应的第n个历史日中各单位时段的出行状态为{S n,1,S n,2,S n,3,...,S n,m}，其中，S n,m为所述电动汽车用户在当前类型日对应的第n个历史日中第m个单位时段的出行状态，若所述电动汽车用户的车辆在当前类型日对应的第n个历史日中第m个单位时段的出行状态为停止状态，则S n,m＝0，否则，S n,m＝1，m为一日内单位时段总数，n为历史日总数。 Wherein, the travel state of the electric vehicle user in each unit period in the nth historical day corresponding to the current type day is {S n,1 ,S n,2 ,S n,3 ,...,S n,m }, wherein, S n,m is the travel status of the electric vehicle user in the mth unit period in the nth historical day corresponding to the current type day, if the vehicle of the electric vehicle user is in the current type day corresponding to the first The travel state of the mth unit period in n historical days is the stop state, then S n,m =0, otherwise, S n,m =1, m is the total number of unit periods in one day, and n is the total number of historical days.
  4. 如权利要求3所述的方法，其特征在于，所述电动汽车用户在当前类型日中各单位时段的出行概率的计算公式如下：The method according to claim 3, wherein the calculation formula of the travel probability of each unit period of the electric vehicle user in the current type of day is as follows:
    pm＝(S 1,m+S 2,m+…+S n-1,m+S n,m)/n pm=(S 1,m +S 2,m +...+S n-1,m +S n,m )/n
    上式中，pm为所述电动汽车用户在当前类型日中第m个单位时段的出行概率。In the above formula, pm is the travel probability of the electric vehicle user in the mth unit period in the current type of day.
  5. 如权利要求1所述的方法，其特征在于，所述在电动汽车用户在当前类型日对应的出行概率曲线上获取电动汽车用户当前联网时刻的出行概率，包括：The method according to claim 1, wherein the obtaining the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user comprises:
    获取电动汽车用户当前联网时刻所属的单位时段；Obtain the unit time period to which the electric vehicle user's current networking moment belongs;
    将电动汽车用户在当前类型日对应的出行概率曲线上所述电动汽车用户当前联网时刻所属的单位时段对应的出行概率作为电动汽车用户当前联网时刻的出行概率。The travel probability corresponding to the unit period of the electric vehicle user's current network connection moment on the travel probability curve corresponding to the current type day of the electric vehicle user is taken as the travel probability of the electric vehicle user at the current network connection moment.
  6. 如权利要求3所述的方法，其特征在于，当电动汽车用户为新用户时，基于电动汽车用户的基础信息，将该电动汽车用户与各预先获取的聚类簇进行匹配，并将匹配对应的聚类簇的聚类中心在当前类型日对应的各历史日中各单位时段的出行状态作为该电动汽车用户在 当前类型日对应的各历史日中各单位时段的出行状态。The method according to claim 3, wherein when the electric vehicle user is a new user, based on the basic information of the electric vehicle user, the electric vehicle user is matched with each pre-acquired cluster, and the matching The travel status of the cluster center of the clustering center in each historical day corresponding to the current type day is taken as the travel status of the electric vehicle user in each historical day corresponding to the current type day.
  7. 如权利要求6所述的方法，其特征在于，所述基于电动汽车用户的基础信息，将该电动汽车用户与各预先获取的聚类簇进行匹配，包括：The method according to claim 6, wherein said matching the electric vehicle user with each pre-acquired cluster cluster based on the basic information of the electric vehicle user comprises:
    基于电动汽车用户的基础信息计算该电动汽车用户与各预先获取的聚类簇之间的欧式距离，并选择欧氏距离最小的一个聚类簇作为该电动汽车用户匹配对应的聚类簇。Calculate the Euclidean distance between the electric vehicle user and each pre-acquired cluster based on the basic information of the electric vehicle user, and select a cluster with the smallest Euclidean distance as the corresponding cluster for the electric vehicle user.
  8. 如权利要求6所述的方法，其特征在于，所述基础信息包括下述中的至少一种：车辆型号、车辆类型、电池容量、剩余电量、续航里程、日均行驶里程和百公里耗电。The method according to claim 6, wherein the basic information includes at least one of the following: vehicle model, vehicle type, battery capacity, remaining power, mileage, average daily mileage and power consumption per 100 kilometers .
  9. 如权利要求6所述的方法，其特征在于，所述预先获取的聚类簇的获取过程包括：采用聚类算法，基于各电动汽车用户的基础信息对各电动汽车用户进行聚类。The method according to claim 6, wherein the obtaining process of the pre-acquired clusters comprises: using a clustering algorithm to cluster the electric vehicle users based on the basic information of the electric vehicle users.
  10. 如权利要求1所述的方法，其特征在于，所述根据所述电动汽车用户当前联网时刻的出行概率预测电动汽车用户的出行时间，包括：The method according to claim 1, wherein the predicting the travel time of the electric vehicle user according to the travel probability at the current networking moment of the electric vehicle user comprises:
    设置第一阈值和第二阈值，其中，0≤第一阈值≤第二阈值≤1；Setting a first threshold and a second threshold, where 0≤first threshold≤second threshold≤1;
    将电动汽车用户在当前类型日对应的出行概率曲线上小于第一阈值的时段定义为低出行时段，将电动汽车用户在当前类型日对应的出行概率曲线上大于第一阈值且小于第二阈值的时段定义为中出行时段，将电动汽车用户在当前类型日对应的出行概率曲线上大于第二阈值的时段定义为高出行时段；Define the time period when electric vehicle users are less than the first threshold on the travel probability curve corresponding to the current type of day as the low travel time period, and define the period when the electric vehicle user is greater than the first threshold and less than the second threshold on the travel probability curve corresponding to the current type of day The time period is defined as the middle travel time period, and the time period when the electric vehicle user is greater than the second threshold on the travel probability curve corresponding to the current type of day is defined as the high travel time period;
    若所述电动汽车用户当前联网时刻的出行概率属于低出行时段，则将电动汽车用户在当前类型日对应的出行概率曲线上低出行时段向中出行时段阶跃的转折时刻或中出行时段向高出行时段阶跃的转折时刻作为所述电动汽车用户的出行时间；If the travel probability of the electric vehicle user at the current networking moment belongs to the low travel period, then the electric vehicle user’s transition time from the low travel period to the middle travel period on the travel probability curve corresponding to the current type of day or the transition time from the middle travel period to the high The turning point of the travel period step is used as the travel time of the electric vehicle user;
    若所述电动汽车用户当前联网时刻的出行概率属于中出行时段，则将电动汽车用户在当前类型日对应的出行概率曲线上中出行时段向高出行时段阶跃的转折时刻作为所述电动汽车用户的出行时间；If the travel probability of the electric vehicle user at the current networking moment belongs to the middle travel time period, then the electric vehicle user’s transition time from the middle travel time period to the high travel time period on the travel probability curve corresponding to the current type day is taken as the electric vehicle user travel time;
    若所述电动汽车用户当前联网时刻的出行概率属于高出行时段，则所述电动汽车用户的出行时间为当前联网时刻向后延长所述电动汽车用户在当前类型日的平均充电时长后对应的时刻。If the travel probability of the electric vehicle user at the current networking moment belongs to the high travel time period, then the travel time of the electric vehicle user is the corresponding time after the current network connection moment extends the average charging time of the electric vehicle user in the current type of day .
  11. 一种电动汽车用户出行时间预测装置，其特征在于，所述装置包括：A device for predicting travel time of an electric vehicle user, characterized in that the device includes:
    获取模块，用于在电动汽车用户在当前类型日对应的出行概率曲线上获取电动汽车用户当前联网时刻的出行概率；The acquisition module is used to obtain the travel probability of the electric vehicle user at the current networking moment on the travel probability curve corresponding to the current type day of the electric vehicle user;
    预测模块，用于根据所述电动汽车用户当前联网时刻的出行概率预测电动汽车用户的出行时间。The predicting module is used to predict the travel time of the electric vehicle user according to the travel probability of the electric vehicle user at the moment when the electric vehicle is connected to the network.
  12. 一种存储装置，其中存储有多条程序代码，其特征在于，所述程序代码适于由处理器加载并运行以执行权利要求1至10中任一项所述的电动汽车用户出行时间预测方法。A storage device, wherein a plurality of program codes are stored, wherein the program codes are adapted to be loaded and run by a processor to perform the electric vehicle user travel time prediction method described in any one of claims 1 to 10 .
  13. 一种控制装置，包括处理器和存储装置，所述存储装置适于存储多条程序代码，其特征在于，所述程序代码适于由所述处理器加载并运行以执行权利要求1至10中任一项所述的电动汽车用户出行时间预测方法。A control device, comprising a processor and a storage device, the storage device is adapted to store a plurality of program codes, characterized in that the program codes are adapted to be loaded and run by the processor to execute claims 1 to 10 Any one of the electric vehicle user travel time prediction methods.
PCT/CN2022/073914 2021-11-10 2022-01-26 Method and apparatus for predicting travel time of electric vehicle user WO2023082474A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111324505.X 2021-11-10
CN202111324505.XA CN114219124A (en) 2021-11-10 2021-11-10 Method and device for predicting traveling time of electric vehicle user

Publications (1)

Publication Number Publication Date
WO2023082474A1 true WO2023082474A1 (en) 2023-05-19

Family

ID=80696812

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/073914 WO2023082474A1 (en) 2021-11-10 2022-01-26 Method and apparatus for predicting travel time of electric vehicle user

Country Status (2)

Country Link
CN (1) CN114219124A (en)
WO (1) WO2023082474A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116811646A (en) * 2023-08-29 2023-09-29 国网浙江省电力有限公司杭州供电公司 Electric automobile group charging control method, device, equipment and medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6317686B1 (en) * 2000-07-21 2001-11-13 Bin Ran Method of providing travel time
CN108599267A (en) * 2018-04-17 2018-09-28 上海电力学院 A kind of Unit Combination dispatching method considering electric vehicle trip correlation
US20200156619A1 (en) * 2018-11-16 2020-05-21 Toyota Jidosha Kabushiki Kaisha Control device for hybrid vehicle, control method for hybrid vehicle, and recording medium
CN112001564A (en) * 2020-09-04 2020-11-27 国网江西省电力有限公司电力科学研究院 User leaving time prediction method based on long-term and short-term memory network

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6317686B1 (en) * 2000-07-21 2001-11-13 Bin Ran Method of providing travel time
CN108599267A (en) * 2018-04-17 2018-09-28 上海电力学院 A kind of Unit Combination dispatching method considering electric vehicle trip correlation
US20200156619A1 (en) * 2018-11-16 2020-05-21 Toyota Jidosha Kabushiki Kaisha Control device for hybrid vehicle, control method for hybrid vehicle, and recording medium
CN112001564A (en) * 2020-09-04 2020-11-27 国网江西省电力有限公司电力科学研究院 User leaving time prediction method based on long-term and short-term memory network

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZHA, LI ET AL.: "Research of Electric Vehicle Access to Micro-grid Mode", SHANGHAI AUTO, no. 03, 31 March 2014 (2014-03-31), XP009546303, ISSN: 1007-4554 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116811646A (en) * 2023-08-29 2023-09-29 国网浙江省电力有限公司杭州供电公司 Electric automobile group charging control method, device, equipment and medium
CN116811646B (en) * 2023-08-29 2023-11-14 国网浙江省电力有限公司杭州供电公司 Electric automobile group charging control method, device, equipment and medium

Also Published As

Publication number Publication date
CN114219124A (en) 2022-03-22

Similar Documents

Publication Publication Date Title
Akhavan-Rezai et al. Online intelligent demand management of plug-in electric vehicles in future smart parking lots
CN103241130B (en) Energy management method and system for electric bus charging and swap station
CN111422094B (en) Charging and discharging coordination optimization control method for distributed charging pile
CN110667434A (en) Working condition-adaptive pure electric vehicle driving mileage estimation method and system
Long et al. Efficient real-time EV charging scheduling via ordinal optimization
CN112001560B (en) Two-stage bus scheduling algorithm based on iterative neighborhood search
Yao et al. A fuzzy logic based charging scheme for electric vechicle parking station
CN113515884A (en) Distributed electric vehicle real-time optimization scheduling method, system, terminal and medium
CN110751314A (en) Electric vehicle load prediction method considering user charging behavior characteristic data driving
CN111452669A (en) System, method and medium for intelligent charging of public transport
CN112101637B (en) Dynamic charging optimization method based on time-of-use electricity price and energy consumption control and application thereof
TWI763249B (en) Method, device, system and readable storage medium of matching vehicle and battery
WO2023082474A1 (en) Method and apparatus for predicting travel time of electric vehicle user
CN113269372A (en) Cluster electric vehicle schedulable capacity prediction evaluation method considering user will
CN116757877B (en) Power grid line loss reduction optimization method and system for new energy access power distribution network
CN110796286A (en) Flexible planning method of power distribution system suitable for electric automobile large-scale application
CN115577938A (en) Electrified on-demand mobile scheduling method, device and system
CN109950900B (en) Micro-grid load reduction control method based on electric vehicle load minimum peak model
CN117391564B (en) New energy logistics vehicle energy supplementing and scheduling data model and scheduling optimization method
CN110861508B (en) Charging control method and system shared by residential area direct current chargers and storage medium
CN111313449B (en) Cluster electric vehicle power optimization management method based on machine learning
CN111244990B (en) Power distribution network V2G auxiliary service day-ahead scheduling method
CN112736941A (en) Schedulable capacity prediction method and device based on mobile energy storage electric automobile
CN117154792A (en) Day-ahead optimal scheduling method for electric vehicle battery exchange station considering wind-solar uncertainty
Ni et al. Mobility and energy management in electric vehicle based mobility-on-demand systems: Models and solutions

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22891286

Country of ref document: EP

Kind code of ref document: A1