A method and device for predicting travel time for electric vehicle users

By constructing travel probability curves for electric vehicle users and using clustering algorithms to predict travel time, the problem of inaccurate travel time prediction for electric vehicle users in existing technologies has been solved. This enables more efficient charging schedules and grid load regulation, thereby improving user experience and grid efficiency.

CN114219124BActive Publication Date: 2026-11-17STATE GRID ELECTRIC VEHICLE SERVICE CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202111324505.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-10
Publication Date
2026-11-17
Estimated Expiration
2041-11-10

AI Technical Summary

Technical Problem

Existing technologies struggle to accurately predict the travel times of electric vehicle users, leading to cumbersome or unmatched orderly charging strategies that fail to meet user charging needs, thus impacting user experience.

Method used

By constructing the travel probability curve of electric vehicle users on the current type of day, the travel probability of users at the current network connection time is obtained, and their travel time is predicted based on the probability. Clustering algorithm and artificial intelligence algorithm are used to optimize the prediction process, and travel probability thresholds are set to divide the time period.

Benefits of technology

It reduces the complexity of user charging interactions, improves the accuracy of charging plans and the efficiency of grid load regulation, and enhances user experience and grid peak shaving and valley filling effects.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114219124B_ABST
    Figure CN114219124B_ABST
Patent Text Reader

Abstract

This invention relates to the field of electric vehicle and grid interaction technology, specifically providing a method and apparatus for predicting the travel time of electric vehicle users. The method includes: obtaining the travel probability of an electric vehicle user at the current network connection time from a travel probability curve corresponding to the current type of day; and predicting the travel time of the electric vehicle user based on the travel probability at the current network connection time. The technical solution provided by this invention can effectively predict the travel time of a user after the charging station is connected to the grid, providing input parameters for charging operators to formulate charging plans during their network connection period.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of electric vehicle and power grid interaction technology, specifically to a method and device for predicting the travel time of electric vehicle users. Background Technology

[0002] Private passenger vehicles are the most active and important growth factor in the new energy vehicle market, currently accounting for 72% of the market and projected to exceed 90% by 2040, reaching a scale of over 270 million vehicles. Communities are the primary battleground for private passenger vehicle charging. Over a wide area, with a large number of electric vehicles charging haphazardly, peak charging loads at night may overlap with peak electricity consumption at night, increasing the peak-valley difference in the power system. Within a specific substation, due to insufficient transformer capacity in older residential areas, simply charging haphazardly during evening peak hours can easily lead to transformer capacity exceeding limits. For private cars, the average daily driving time is only about 4%, and their parking and charging time is far greater than the actual charging time, providing an opportunity for charging power regulation. Under the premise of meeting the charging needs of electric vehicles, practical and effective economic or technical measures should be used to guide and control the charging behavior of electric vehicles, including charging initiation and charging power, thereby achieving peak shaving and valley filling of the power grid load curve and delaying investment in power grid expansion.

[0003] The aforementioned orderly charging method involves adjusting the start / stop and charging power of electric vehicles during network charging without affecting users' charging and usage needs. This requires accurately predicting users' travel times to arrange reasonable electric vehicle charging plans and ensure that the charging amount during users' trips is sufficient to meet their needs. Currently, common methods for orderly charging include requiring users to manually input their travel time during the user interaction phase, which often leads to most users abandoning orderly charging due to the cumbersome operation and demanding immediate charging service; another method is to mechanically reduce the power of all orderly charging piles by default during periods of high electricity prices. This method of reducing charging load is crude and often fails to match users' charging needs, severely impacting the user charging experience. Summary of the Invention

[0004] To overcome the above-mentioned shortcomings, the present invention proposes a method and apparatus for predicting the travel time of electric vehicle users.

[0005] Firstly, a method for predicting the travel time of electric vehicle users is provided, the method comprising:

[0006] Obtain the travel probability of electric vehicle users at the current network connection time from the travel probability curve corresponding to the current type of day;

[0007] The travel time of electric vehicle users is predicted based on their travel probability at the current internet connection time.

[0008] Preferably, the type of day includes at least one of the following: weekdays, weekends, and public holidays.

[0009] Furthermore, the process of obtaining the travel probability curve for the current type of day for electric vehicle users includes:

[0010] Obtain the travel status of electric vehicle users in each time period of each historical day corresponding to the current type of day;

[0011] The probability of electric vehicle users traveling in each unit of time period on the current type of day is calculated based on the travel status of electric vehicle users in each unit of time period on each historical day corresponding to the current type of day.

[0012] Construct the travel probability curve of the electric vehicle user for the current type of day using the travel probability of the electric vehicle user in each time period of the current type of day;

[0013] Wherein, the travel status of the electric vehicle user in each unit time period of the nth historical day corresponding to the current type day is {S}. n,1 ,S n,2 ,S n,3 ,...,S n,m}, where S n,m S represents the travel status of the electric vehicle user in the m-th unit time period of the n-th historical day corresponding to the current type day. If the travel status of the electric vehicle user's vehicle in the m-th unit time period of the n-th historical day corresponding to the current type day is stationary, then S... n,m =0, otherwise, S n,m =1, m is the total number of time periods within a day, and n is the total number of historical days.

[0014] Furthermore, the formula for calculating the travel probability of electric vehicle users in each time period of the current type of day is as follows:

[0015] pm=(S 1,m +S 2,m +…+S n-1,m +S n,m ) / n

[0016] In the above formula, pm is the probability of the electric vehicle user traveling in the m-th unit time period of the current type of day.

[0017] Preferably, obtaining the travel probability of an electric vehicle user at the current network connection time from the travel probability curve corresponding to the current type of day includes:

[0018] Obtain the time period to which the current online connection time of the electric vehicle user belongs;

[0019] The travel probability of an electric vehicle user at the current online moment is defined as the travel probability of the unit time period corresponding to the current online moment of the electric vehicle user on the travel probability curve corresponding to the current type of day.

[0020] Furthermore, when an electric vehicle user is a new user, based on the user's basic information, the user is matched with each pre-acquired cluster, and the travel status of the cluster center of the matched cluster in each unit time period of each historical day corresponding to the current type day is taken as the travel status of the electric vehicle user in each unit time period of each historical day corresponding to the current type day.

[0021] Furthermore, the matching of the electric vehicle user with each pre-acquired cluster based on the user's basic information includes:

[0022] Based on the basic information of electric vehicle users, the Euclidean distance between the electric vehicle user and each pre-acquired cluster is calculated, and the cluster with the smallest Euclidean distance is selected as the cluster corresponding to the electric vehicle user.

[0023] Furthermore, the basic information includes at least one of the following: vehicle model, vehicle type, battery capacity, remaining battery power, driving range, average daily mileage, and power consumption per 100 kilometers.

[0024] Furthermore, the process of obtaining the pre-acquired clusters includes: using a clustering algorithm to cluster each electric vehicle user based on the basic information of each electric vehicle user.

[0025] Preferably, predicting the travel time of the electric vehicle user based on the travel probability at the current internet connection time includes:

[0026] Set a first threshold and a second threshold, where 0 ≤ first threshold ≤ second threshold ≤ 1;

[0027] The period when the travel probability curve for electric vehicle users on the current type of day is less than the first threshold is defined as a low travel period; the period when the travel probability curve for electric vehicle users on the current type of day is greater than the first threshold and less than the second threshold is defined as a medium travel period; and the period when the travel probability curve for electric vehicle users on the current type of day is greater than the second threshold is defined as a high travel period.

[0028] If the electric vehicle user's travel probability at the current network connection time belongs to a low travel period, then the turning point from low travel period to medium travel period or from medium travel period to high travel period on the travel probability curve corresponding to the current type of day is taken as the electric vehicle user's travel time.

[0029] If the electric vehicle user's travel probability at the current network connection time belongs to the medium travel period, then the turning point from the medium travel period to the high travel period on the travel probability curve corresponding to the current type of day is taken as the electric vehicle user's travel time.

[0030] If the probability of travel for the electric vehicle user at the current internet connection time belongs to a high travel period, then the travel time of the electric vehicle user is the time corresponding to the current internet connection time after extending the average charging time of the electric vehicle user on the current type of day.

[0031] Secondly, a device for predicting the travel time of electric vehicle users is provided, the device comprising:

[0032] The acquisition module is used to obtain the travel probability of electric vehicle users at the current network connection time on the travel probability curve corresponding to the current type of day;

[0033] The prediction module is used to predict the travel time of the electric vehicle user based on the travel probability of the electric vehicle user at the current Internet connection time.

[0034] Thirdly, a storage device is provided, wherein a plurality of program codes are stored, the program codes being adapted to be loaded and run by a processor to perform the electric vehicle user travel time prediction method described in any of the above technical solutions.

[0035] Fourthly, a control device is provided, comprising a processor and a storage device, the storage device being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to execute the electric vehicle user travel time prediction method described in any of the above technical solutions.

[0036] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects:

[0037] This invention provides a method and apparatus for predicting the travel time of electric vehicle users, comprising: obtaining the travel probability of an electric vehicle user at the current network connection time from the travel probability curve corresponding to the current type of day; and predicting the travel time of the electric vehicle user based on the travel probability of the current network connection time. Compared with the current orderly charging strategy, the electric vehicle user travel time prediction method proposed in this invention can effectively reduce the cumbersome charging interaction for users, eliminate negative user experiences, and fully utilize the user's network connection time for charging power control and participation in grid peak shaving and valley filling. It has shown good results in practical business systems. Attached Figure Description

[0038] Figure 1This is a schematic diagram of the main steps of the electric vehicle user travel time prediction method according to an embodiment of the present invention;

[0039] Figure 2 This is a flowchart illustrating the process of obtaining the travel probability curve for a new electric vehicle user on a given type of day, according to an embodiment of the present invention.

[0040] Figure 3 This is a diagram showing the correspondence between the travel probability curve and the travel probability time period division in an embodiment of the present invention;

[0041] Figure 4 This is a main structural block diagram of the electric vehicle user travel time prediction device according to an embodiment of the present invention. Detailed Implementation

[0042] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] To more accurately determine the charging and travel time of electric vehicle users, this invention proposes a method for predicting the travel time of electric vehicle users. This method predicts the travel time after the user's charging port is connected to the power grid, providing input parameters for charging operators to formulate charging plans during their network connection period.

[0045] See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of an electric vehicle user travel time prediction method according to an embodiment of the present invention. Figure 1 As shown, the electric vehicle user travel time prediction method in this embodiment of the invention mainly includes the following steps:

[0046] Step S101: Obtain the travel probability of the electric vehicle user at the current network connection time on the travel probability curve corresponding to the current type of day;

[0047] Step S102: Predict the travel time of the electric vehicle user based on the travel probability of the electric vehicle user at the current network connection time.

[0048] In this embodiment, the type of day includes at least one of the following: weekday, weekend, and public holiday.

[0049] In one implementation, the process of obtaining the travel probability curve for the electric vehicle user on the current type of day includes:

[0050] Obtain the travel status of electric vehicle users in each time period of each historical day corresponding to the current type of day;

[0051] The probability of electric vehicle users traveling in each unit of time period on the current type of day is calculated based on the travel status of electric vehicle users in each unit of time period on each historical day corresponding to the current type of day.

[0052] Construct the travel probability curve of the electric vehicle user for the current type of day using the travel probability of the electric vehicle user in each time period of the current type of day;

[0053] Wherein, the travel status of the electric vehicle user in each unit time period of the nth historical day corresponding to the current type day is {S}. n,1 ,S n,2 ,S n,3 ,...,S n,m}, where S n,m S represents the travel status of the electric vehicle user in the m-th unit time period of the n-th historical day corresponding to the current type day. If the travel status of the electric vehicle user's vehicle in the m-th unit time period of the n-th historical day corresponding to the current type day is stationary, then S... n,m =0, otherwise, S n,m =1, m is the total number of time periods within a day, and n is the total number of historical days.

[0054] Furthermore, the formula for calculating the travel probability of electric vehicle users in each time period of the current type of day is as follows:

[0055] pm=(S 1,m +S 2,m +…+S n-1,m +S n,m ) / n

[0056] In the above formula, pm is the probability of the electric vehicle user traveling in the m-th unit time period of the current type of day.

[0057] Preferably, obtaining the travel probability of an electric vehicle user at the current network connection time from the travel probability curve corresponding to the current type of day includes:

[0058] Obtain the time period to which the current online connection time of the electric vehicle user belongs;

[0059] The travel probability of an electric vehicle user at the current online moment is defined as the travel probability of the unit time period corresponding to the current online moment of the electric vehicle user on the travel probability curve corresponding to the current type of day.

[0060] In a preferred embodiment, for example: predicting the travel probability of a connected vehicle within the next 24 hours starting from the moment the vehicle connects to the network:

[0061] The prediction method may adopt a variety of prediction methods including artificial intelligence algorithms such as a neural network model or a support vector machine, and only a probability statistics method is taken as an example here. Let S represent the current state of the vehicle, where S=1 when the vehicle is in an operating state, and S=0 when the vehicle is in a stopped state. A certain time period may be selected as the minimum state time period according to actual prediction requirements and the execution cycle requirements of the charging strategy. If 5 minutes is selected as the minimum state time period, the travel state of a certain vehicle corresponding to 24 hours is a state set Q={S1,S2,S3,...,S287,S288} corresponding to 60 / 5*24=288 points. When a certain vehicle has n 24-hour state data samples, n corresponding state sets are obtained, 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}. At this time, the vehicle travel probability pm of the m-th (0<m<=288) state point is pm=(S 1,m +S 2,m +…+S n-1,m +S n,m ) / n. Then the 288-point travel probability set of the vehicle in the next 24 hours is P={p1,p2,...pm,...,p287,p288}. The above travel probability calculation methods are included but not limited thereto.

[0062] There is an obvious correlation between user travel and date types, and probability calculation should be performed separately for classified date types. For example, considering that there is no periodic traffic restriction policy for electric vehicles at present, the user travel pattern has an obvious correlation with working days, weekends and holidays, the vehicle state sets are classified into three categories: Q_working day, Q_weekend, and Q_holiday, and the corresponding travel probabilities are also calculated separately as P_working day, P_weekend, and P_holiday. The above type-day division methods are included but not limited thereto.

[0063] Furthermore, this invention categorizes electric vehicle users into two types: users with historical start-stop data and new users. Users with historical data refer to those who have previously used the charging service online, and the system can retrieve their historical start-stop data, including: vehicle running times, vehicle off-peak times, vehicle braking and charging times, and vehicle off-peak charging times. Both users with historical start-stop data and new users can have their basic charging and travel data retrieved, including: vehicle model, vehicle type, battery capacity, remaining battery power, driving range, average daily mileage, and energy consumption per 100 kilometers.

[0064] In one implementation, since there is no historical travel start / stop data for the vehicle, it is necessary to first perform cluster analysis on historical electric vehicle users to obtain the travel probability distribution and probability time period division for different groups. Secondly, the electric vehicle user is matched with each pre-acquired cluster, and the travel status of the cluster center of the matched cluster in each unit time period of each historical day corresponding to the current type of day is taken as the travel status of the electric vehicle user in each unit time period of each historical day corresponding to the current type of day.

[0065] In one embodiment, the process of obtaining the pre-acquired clusters includes: using a clustering algorithm to cluster each electric vehicle user based on the basic information of each electric vehicle user.

[0066] Specifically, the process of obtaining each pre-acquired cluster and the process of obtaining the travel status of the new user in each unit time period of each historical day corresponding to the current type day can be carried out as follows: Figure 2 The steps shown are as follows:

[0067] 1) First, cluster analysis is performed based on the basic data and historical start-stop data of the historical charging user set N for electric vehicles. Clustering methods such as K-means and hierarchical clustering can be used. Based on the clustering results, historical electric vehicle users can be divided into various characteristic behavior groups, forming a set of historical electric vehicle user groups C = {c1, c2, ..., ck}, such as private cars, buses, logistics vehicles, official vehicles, and ride-hailing vehicles. Each group may contain subtypes depending on the actual clustering situation. For example, ride-hailing vehicles operating during different days and nights may be clustered into ride-hailing vehicle type 1 and ride-hailing vehicle type 2. Subtypes can also be further subdivided according to date type, such as weekdays, holidays, and weekends.

[0068] 2) Calculate the travel probability and time periods of high, medium, and low travel probabilities for historical user clusters. A specific electric vehicle user cluster contains historical travel data for several users. The method for predicting the travel probability of this cluster using this data is the same as the method for predicting the travel probability of historical users based on historical data. Various prediction methods, including artificial intelligence algorithms such as neural network models or support vector machines, can be employed. The method for obtaining the high, medium, and low travel probability time periods from the discrete travel probabilities using an adaptive method is the same as that used for historical data users of electric vehicles.

[0069] Furthermore, based on the basic information of the electric vehicle user, the Euclidean distance between the electric vehicle user and each pre-acquired cluster is calculated, and the cluster with the smallest Euclidean distance is selected as the cluster corresponding to the electric vehicle user.

[0070] In one implementation, the new user basic data analysis and group matching process first retrieves the new user vehicle basic data, analyzes the new user data according to the numerical characteristics obtained by the historical user set N clustering method and type, and matches the new user group to the historical user group set according to the closest numerical method, thus determining the new user group as ci.

[0071] If the new user is classified into group ci, then the travel time of the electric vehicle feature group ci is the new user's travel time. The method for determining the travel time prediction value based on the travel time is the same as that for the historical users mentioned above.

[0072] In this embodiment, predicting the travel time of the electric vehicle user based on the travel probability of the electric vehicle user at the current network connection time includes:

[0073] Set a first threshold and a second threshold, where 0 ≤ first threshold ≤ second threshold ≤ 1;

[0074] The period when the travel probability curve for electric vehicle users on the current type of day is less than the first threshold is defined as a low travel period; the period when the travel probability curve for electric vehicle users on the current type of day is greater than the first threshold and less than the second threshold is defined as a medium travel period; and the period when the travel probability curve for electric vehicle users on the current type of day is greater than the second threshold is defined as a high travel period.

[0075] If the electric vehicle user's travel probability at the current network connection time belongs to a low travel period, then the turning point from low travel period to medium travel period or from medium travel period to high travel period on the travel probability curve corresponding to the current type of day is taken as the electric vehicle user's travel time.

[0076] If the electric vehicle user's travel probability at the current network connection time belongs to the medium travel period, then the turning point from the medium travel period to the high travel period on the travel probability curve corresponding to the current type of day is taken as the electric vehicle user's travel time.

[0077] If the probability of travel for the electric vehicle user at the current internet connection time belongs to a high travel period, then the travel time of the electric vehicle user is the time corresponding to the current internet connection time after extending the average charging time of the electric vehicle user on the current type of day.

[0078] For users who request charging during peak travel periods, their charging power is generally not limited as they may travel at any time; the system will charge them at the maximum power it supports by default.

[0079] In one implementation, a first threshold and a second threshold can be selected based on experience, and travel time can be predicted accordingly. During charging tests or actual operation, the predicted travel time and the user's actual travel time are used to calculate the prediction accuracy, and machine learning methods are used to adaptively adjust the time period segmentation thresholds.

[0080] The present invention also provides an optimal implementation method, such as... Figure 3 As shown, electric vehicles connect to the network at time 0 to obtain charging services. Dividing the next 24 hours into 288 time periods (each 5 minutes long), the probability of a user traveling during these 288 time periods can be predicted based on historical user start-stop data. According to thresholds for high, medium, and low travel probabilities, the 24 hours can be divided into several probability periods. In this embodiment, the first threshold is 0.1, and the second threshold is 0.5, so the 24 hours are divided as follows: Figure 3 The diagram illustrates three probability periods: high, medium, and low. Based on... Figure 3 The travel probability and time segments are calculated as follows: When a user connects to the internet during the low-to-medium probability period (7:00 PM - 6:00 AM), the predicted travel time is time point 1. When a user connects to the internet between 6:00 AM and 7:00 AM, the predicted travel time is time point 2. When a user connects to the internet during the medium probability period (9:00 AM - 5:00 PM), the predicted travel time is time point 3. When a user connects to the internet during the high-probability period, the predicted charging time is taken as the average daily charging time for the corresponding type of electric vehicle.

[0081] Based on the same inventive concept, this invention provides a device for predicting the travel time of electric vehicle users, such as... Figure 4 As shown, the electric vehicle user travel time prediction device includes:

[0082] The acquisition module is used to obtain the travel probability of electric vehicle users at the current network connection time on the travel probability curve corresponding to the current type of day;

[0083] The prediction module is used to predict the travel time of the electric vehicle user based on the travel probability of the electric vehicle user at the current Internet connection time.

[0084] Preferably, the type of day includes at least one of the following: weekdays, weekends, and public holidays.

[0085] Furthermore, the process of obtaining the travel probability curve for the current type of day for electric vehicle users includes:

[0086] Obtain the travel status of electric vehicle users in each time period of each historical day corresponding to the current type of day;

[0087] The probability of electric vehicle users traveling in each unit of time period on the current type of day is calculated based on the travel status of electric vehicle users in each unit of time period on each historical day corresponding to the current type of day.

[0088] Construct the travel probability curve of the electric vehicle user for the current type of day using the travel probability of the electric vehicle user in each time period of the current type of day;

[0089] Wherein, the travel status of the electric vehicle user in each unit time period of the nth historical day corresponding to the current type day is {S}. n,1 ,S n,2 ,S n,3 ,...,S n,m}, where S n,m S represents the travel status of the electric vehicle user in the m-th unit time period of the n-th historical day corresponding to the current type day. If the travel status of the electric vehicle user's vehicle in the m-th unit time period of the n-th historical day corresponding to the current type day is stationary, then S... n,m =0, otherwise, S n,m =1, m is the total number of time periods within a day, and n is the total number of historical days.

[0090] Furthermore, the formula for calculating the travel probability of electric vehicle users in each time period of the current type of day is as follows:

[0091] pm=(S 1,m +S 2,m +…+S n-1,m +S n,m ) / n

[0092] In the above formula, pm is the probability of the electric vehicle user traveling in the m-th unit time period of the current type of day.

[0093] Preferably, obtaining the travel probability of an electric vehicle user at the current network connection time from the travel probability curve corresponding to the current type of day includes:

[0094] Obtain the time period to which the current online connection time of the electric vehicle user belongs;

[0095] The travel probability of an electric vehicle user at the current online moment is defined as the travel probability of the unit time period corresponding to the current online moment of the electric vehicle user on the travel probability curve corresponding to the current type of day.

[0096] Furthermore, when an electric vehicle user is a new user, based on the user's basic information, the user is matched with each pre-acquired cluster, and the travel status of the cluster center of the matched cluster in each unit time period of each historical day corresponding to the current type day is taken as the travel status of the electric vehicle user in each unit time period of each historical day corresponding to the current type day.

[0097] Furthermore, the matching of the electric vehicle user with each pre-acquired cluster based on the user's basic information includes:

[0098] Based on the basic information of electric vehicle users, the Euclidean distance between the electric vehicle user and each pre-acquired cluster is calculated, and the cluster with the smallest Euclidean distance is selected as the cluster corresponding to the electric vehicle user.

[0099] Furthermore, the basic information includes at least one of the following: vehicle model, vehicle type, battery capacity, remaining battery power, driving range, average daily mileage, and power consumption per 100 kilometers.

[0100] Furthermore, the process of obtaining the pre-acquired clusters includes: using a clustering algorithm to cluster each electric vehicle user based on the basic information of each electric vehicle user.

[0101] Preferably, predicting the travel time of the electric vehicle user based on the travel probability at the current internet connection time includes:

[0102] Set a first threshold and a second threshold, where 0 ≤ first threshold ≤ second threshold ≤ 1;

[0103] The period when the travel probability curve for electric vehicle users on the current type of day is less than the first threshold is defined as a low travel period; the period when the travel probability curve for electric vehicle users on the current type of day is greater than the first threshold and less than the second threshold is defined as a medium travel period; and the period when the travel probability curve for electric vehicle users on the current type of day is greater than the second threshold is defined as a high travel period.

[0104] If the electric vehicle user's travel probability at the current network connection time belongs to a low travel period, then the turning point from low travel period to medium travel period or from medium travel period to high travel period on the travel probability curve corresponding to the current type of day is taken as the electric vehicle user's travel time.

[0105] If the electric vehicle user's travel probability at the current network connection time belongs to the medium travel period, then the turning point from the medium travel period to the high travel period on the travel probability curve corresponding to the current type of day is taken as the electric vehicle user's travel time.

[0106] If the probability of travel for the electric vehicle user at the current internet connection time belongs to a high travel period, then the travel time of the electric vehicle user is the time corresponding to the current internet connection time after extending the average charging time of the electric vehicle user on the current type of day.

[0107] Furthermore, the present invention provides a storage device storing a plurality of program codes adapted to be loaded and run by a processor to perform the electric vehicle user travel time prediction method described in any of the above technical solutions.

[0108] Furthermore, the present invention provides a control device comprising a processor and a storage device, the storage device being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to execute the electric vehicle user travel time prediction method described in any of the above technical solutions.

[0109] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can 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.) containing computer-usable program code.

[0110] This 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 will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0111] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0112] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0113] 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 it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for predicting travel time for electric vehicle users, characterized in that, The method includes: Obtain the travel probability of electric vehicle users at the current network connection time from the travel probability curve corresponding to the current type of day; Predict the travel time of electric vehicle users based on their travel probability at the current internet connection time. The process of obtaining the travel probability curve for electric vehicle users on the current type of day includes: Obtain the travel status of electric vehicle users in each time period of each historical day corresponding to the current type of day; The probability of electric vehicle users traveling in each unit of time period on the current type of day is calculated based on the travel status of electric vehicle users in each unit of time period on each historical day corresponding to the current type of day. Construct the travel probability curve of the electric vehicle user for the current type of day using the travel probability of the electric vehicle user in each time period of the current type of day; Wherein, the travel status of the electric vehicle user in each unit time period of the nth historical day corresponding to the current type day is {S}. n,1 ,S n,2 , S n,3 ,..., S n,m }, where S n,m S represents the travel status of the electric vehicle user in the m-th unit time period of the n-th historical day corresponding to the current type day. If the travel status of the electric vehicle user's vehicle in the m-th unit time period of the n-th historical day corresponding to the current type day is stationary, then S... n,m =0, otherwise, S n,m =1, m is the total number of time periods within a day, and n is the total number of historical days; The formula for calculating the travel probability of electric vehicle users in each time period of the current type of day is as follows: pm=(S 1,m +S 2,m +…+S n-1,m +S n,m ) / n In the above formula, pm is the probability of the electric vehicle user traveling in the m-th unit time period of the current type of day; The step of predicting the travel time of electric vehicle users based on their current internet connection probability includes: Set a first threshold and a second threshold, where 0 ≤ first threshold ≤ second threshold ≤ 1; The period when the travel probability curve for electric vehicle users on the current type of day is less than the first threshold is defined as a low travel period; the period when the travel probability curve for electric vehicle users on the current type of day is greater than the first threshold and less than the second threshold is defined as a medium travel period; and the period when the travel probability curve for electric vehicle users on the current type of day is greater than the second threshold is defined as a high travel period. If the electric vehicle user's travel probability at the current network connection time belongs to a low travel period, then the turning point from low travel period to medium travel period or from medium travel period to high travel period on the travel probability curve corresponding to the current type of day is taken as the electric vehicle user's travel time. If the electric vehicle user's travel probability at the current network connection time belongs to the medium travel period, then the turning point from the medium travel period to the high travel period on the travel probability curve corresponding to the current type of day is taken as the electric vehicle user's travel time. If the probability of travel for the electric vehicle user at the current internet connection time belongs to a high travel period, then the travel time of the electric vehicle user is the time corresponding to the current internet connection time after extending the average charging time of the electric vehicle user on the current type of day.

2. The method as described in claim 1, characterized in that, The type of day is selected from at least one of the following: weekdays, weekends, and public holidays.

3. The method as described in claim 1, characterized in that, The step of obtaining the travel probability of an electric vehicle user at the current network connection time from the travel probability curve corresponding to the current type of day includes: Obtain the time period to which the current online connection time of the electric vehicle user belongs; The travel probability of an electric vehicle user at the current online moment is defined as the travel probability of the unit time period corresponding to the current online moment of the electric vehicle user on the travel probability curve corresponding to the current type of day.

4. The method as described in claim 3, characterized in that, When an electric vehicle user is a new user, based on the user's basic information, the user is matched with each pre-acquired cluster. The travel status of the cluster center of the matched cluster in each unit time period of each historical day corresponding to the current type day is used as the travel status of the electric vehicle user in each unit time period of each historical day corresponding to the current type day.

5. The method as described in claim 4, characterized in that, The process of matching electric vehicle users with pre-acquired clusters based on their basic information includes: Based on the basic information of electric vehicle users, the Euclidean distance between the electric vehicle user and each pre-acquired cluster is calculated, and the cluster with the smallest Euclidean distance is selected as the cluster corresponding to the electric vehicle user.

6. The method as described in claim 4, characterized in that, The basic information is selected from at least one of the following: vehicle model, vehicle type, battery capacity, remaining power, driving range, average daily mileage, and power consumption per 100 kilometers.

7. The method as described in claim 4, characterized in that, The process of obtaining the pre-acquired clusters includes: using a clustering algorithm to cluster each electric vehicle user based on the basic information of each electric vehicle user.

8. An apparatus based on the method for predicting travel time for electric vehicle users according to any one of claims 1 to 7, characterized in that, The device includes: The acquisition module is used to obtain the travel probability of electric vehicle users at the current network connection time on the travel probability curve corresponding to the current type of day; The prediction module is used to predict the travel time of the electric vehicle user based on the travel probability of the electric vehicle user at the current Internet connection time.

9. A storage device storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the electric vehicle user travel time prediction method according to any one of claims 1 to 7.

10. A control device, comprising a processor and a storage device, said storage device being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to perform the electric vehicle user travel time prediction method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Unit combination dispatching method considering electric vehicle travel correlation

    CN108599267A

  • User departure time prediction method based on long-term and short-term memory network

    CN112001564A