CN114202131B - Method and device for predicting charging waiting time of pure electric bus - Google Patents

Method and device for predicting charging waiting time of pure electric bus Download PDF

Info

Publication number
CN114202131B
CN114202131B CN202210144586.3A CN202210144586A CN114202131B CN 114202131 B CN114202131 B CN 114202131B CN 202210144586 A CN202210144586 A CN 202210144586A CN 114202131 B CN114202131 B CN 114202131B
Authority
CN
China
Prior art keywords
vehicle
charging
waiting
data
time
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN202210144586.3A
Other languages
Chinese (zh)
Other versions
CN114202131A (en
Inventor
孔维峰
邵强
刘宝来
倪丹
孙鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Public Transport Holdings Group Co ltd
Original Assignee
Beijing Public Transport Holdings Group Co ltd
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 Beijing Public Transport Holdings Group Co ltd filed Critical Beijing Public Transport Holdings Group Co ltd
Priority to CN202210144586.3A priority Critical patent/CN114202131B/en
Publication of CN114202131A publication Critical patent/CN114202131A/en
Application granted granted Critical
Publication of CN114202131B publication Critical patent/CN114202131B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Primary Health Care (AREA)
  • Development Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computational Linguistics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Biophysics (AREA)
  • Educational Administration (AREA)
  • Molecular Biology (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

The invention provides a method and a device for predicting the charging waiting time of a pure electric bus, wherein the method comprises the following steps: acquiring vehicle dispatching record data or a vehicle dispatching plan, inputting a charging waiting time prediction model, and outputting a corresponding charging waiting time; the charging waiting duration prediction model is obtained after training based on a sample set, the sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration; the calculation of the charging waiting time is to obtain an accurate calculation result of the charging waiting time by processing and analyzing the vehicle operation data and the charging data. The method and the device for predicting the charging waiting time of the pure electric bus, provided by the embodiment of the invention, can be used for accurately predicting the charging waiting time of the pure electric bus after the pure electric bus arrives at a station, realizing the evaluation of the current charging queuing state of the pure electric bus and improving the operation efficiency of the pure electric bus.

Description

Method and device for predicting charging waiting time of pure electric bus
Technical Field
The invention relates to the technical field of new energy vehicles, in particular to a method and a device for predicting charging waiting time of a pure electric bus.
Background
The bus is an important component of urban public transport, and the pure electric bus is pollution-free, low in noise and significant for low-carbon traffic, and the wide application of the bus is an important way for realizing energy conservation and environmental protection. However, the driving range of the pure electric bus is short at present, and the pure electric bus needs to be charged frequently in the operation process. Electricelectric moves bus charging station and generally lies in inside the bus station, makes things convenient for the bus to charge after the operation. Generally speaking, the quantity of station bus charging pile configuration can satisfy the demand of charging of bus under general driving condition, and when driving condition changes, if meet traffic jam or extremely cold weather and lead to single trip operation energy consumption to rise, the frequency of charging of bus also risees thereupon, appears the phenomenon that bus charges and lines up in the station. The occurrence of the problems greatly influences the operation efficiency of the public transport vehicle and brings great inconvenience to the trip of people
In order to solve the problem of bus charging queuing, the current charging waiting situation of the bus needs to be accurately evaluated and predicted, in the prior art, the charging waiting time of the bus is calculated mainly by collecting the description of a driver on the waiting time in a queuing peak period, so that the method is strong in subjectivity, low in accuracy and incapable of evaluating the queuing waiting time in a comprehensive and accurate quantitative manner. In the prior art, a charging waiting time period is not predicted by a prediction method, the charging waiting time period cannot be predicted according to vehicle shift, and charging queuing is easy to cause.
Disclosure of Invention
For solving the problems in the prior art, embodiments of the present invention provide a method and an apparatus for predicting a charging wait time of a pure electric bus, which can at least partially solve the problems in the prior art.
On one hand, the invention provides a method for predicting the charging waiting time of a pure electric bus, which comprises the following steps:
acquiring vehicle dispatching record data or a vehicle dispatching plan, wherein the vehicle dispatching record data comprises vehicle arrival time, and the vehicle dispatching plan comprises predicted arrival time;
inputting the vehicle scheduling record data or the vehicle scheduling plan data into a charging waiting duration prediction model, and outputting a charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data; the charging waiting duration prediction model is obtained after training based on a vehicle charging waiting data sample set, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration.
Further, the vehicle charge waiting data further includes: the temperature data is the average temperature of the arrival time on the current day and is obtained through normalization calculation;
the vehicle charging waiting data sample also comprises temperature data, and the temperature data is the average temperature of the arrival time on the current day and is obtained through normalization calculation.
Further, the formula of the normalization calculation is as follows:
T’ =T-μ/σ
wherein, T is a temperature value of the arrival time or the day of the charging start time, T' is a normalized value of the temperature value, μ is a mean value of the temperatures in the data set, and σ is a standard deviation of the temperatures in the data set.
Further, the step of training and obtaining the charge-waiting time prediction model based on the vehicle charge-waiting data sample set includes:
acquiring a vehicle charge waiting data sample set;
and training a neural network model based on the vehicle charging waiting data sample set to obtain the charging waiting duration prediction model.
Further, the charging wait duration is obtained by:
judging a vehicle charging scene according to the charging starting time to obtain a vehicle charging scene judgment result;
and calculating the charging waiting time according to the vehicle charging scene judgment result, the arrival time and the charging starting time.
Further, the determining the vehicle charging scene according to the vehicle arrival time and the corresponding recorded number of the charging start time includes:
if the number of the starting charging time records between the current arrival time of the vehicle and the next arrival time of the vehicle is more than one, the vehicle charging scene is a first charging scene;
and if the number of the starting charging time records between the current arrival time of the vehicle and the next arrival time of the vehicle is one, the vehicle charging scene is a second charging scene.
Further, the calculating the charge waiting time according to the vehicle charge scene determination result, the arrival time, and the charge starting time includes:
if the vehicle charging scene judgment result is a first charging scene, the charging waiting time is the difference value between the first charging starting time and the arrival time;
and if the vehicle charging scene judgment result is a second charging scene, the charging waiting time is the difference value between the charging starting time and the arrival time.
Further, the inputting the vehicle scheduling record data or the vehicle scheduling plan data into a charging waiting duration prediction model, and outputting the charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data includes:
if the corresponding date of the vehicle scheduling record or the vehicle scheduling plan data is judged and known to be a working day, inputting the vehicle scheduling record data or the vehicle scheduling plan data into a first charging waiting duration prediction model, and outputting the charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data; the first charging waiting duration prediction model is obtained based on vehicle charging waiting data sample set training, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration.
If the corresponding date of the vehicle scheduling record data or the vehicle scheduling plan data is judged and known to be a non-working day, inputting the vehicle scheduling record data or the vehicle scheduling plan data into a second charging waiting duration prediction model, and outputting the charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data; the second charging waiting duration prediction model is obtained based on vehicle charging waiting data sample set training, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration.
Further, the training of obtaining the first charge-waiting duration prediction model and the second charge-waiting duration prediction model based on the vehicle charge-waiting data sample set includes:
classifying the vehicle charge waiting data samples in the vehicle charge waiting data sample set according to time to obtain a first vehicle charge waiting data sample set and a second vehicle charge waiting data sample set; wherein the first set of vehicle charge-waiting data samples comprises vehicle charge-waiting data samples for a weekday, and the second set of vehicle charge-waiting data samples comprises vehicle charge-waiting data samples for a non-weekday;
training a neural network model by using the first vehicle charging waiting data sample set to obtain a first charging waiting duration prediction model; and training a neural network model by using the second vehicle charging waiting data sample set to obtain the second charging waiting duration prediction model.
On the other hand, the invention provides a device for predicting the charging waiting time of a pure electric bus, which comprises the following components:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring vehicle dispatching record data or vehicle dispatching plan data, the vehicle dispatching record data comprises vehicle arrival time, and the vehicle dispatching plan comprises predicted arrival time;
the prediction unit is used for inputting the vehicle scheduling record data or the vehicle scheduling plan data into a charging waiting duration prediction model and outputting a charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data; the charging waiting duration prediction model is obtained after training based on a vehicle charging waiting data sample set, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration.
In another aspect, the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method for predicting the charging waiting time of the pure electric bus when executing the computer program.
In still another aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the method for predicting a charge waiting time period of an electric-only bus.
The embodiment of the invention provides a method and a device for predicting the charging waiting time of a pure electric bus, which comprises the following steps: acquiring vehicle scheduling record data, wherein the vehicle scheduling record data comprises vehicle arrival time; inputting the vehicle scheduling record data into a charging waiting time prediction model, and outputting a charging waiting time corresponding to the vehicle scheduling record data; the charging waiting duration prediction model is obtained after training based on a vehicle charging waiting data sample set, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration. The charging waiting time of the pure electric bus is accurately calculated by processing and analyzing the vehicle operation data and the charging data, the charging waiting time of the pure electric bus is accurately predicted by using a machine learning method after the pure electric vehicle arrives at a station, the charging queuing current situation of the pure electric vehicle is evaluated, and the operation efficiency of the pure electric bus is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a flowchart illustrating a method for predicting a charging wait period of a pure electric bus according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart of a charging-waiting duration prediction model obtained by training based on a vehicle charging-waiting data sample set according to an embodiment of the present invention.
Fig. 3 is a flowchart illustrating an embodiment of obtaining a charging wait duration according to the present invention.
Fig. 4 is a schematic diagram of a typical charging scenario in a vehicle operation process according to an embodiment of the present invention.
Fig. 5 is a schematic flowchart of an algorithm of the charging wait period according to the embodiment of the present invention.
Fig. 6 is a flowchart illustrating a method for predicting a charging wait period of a pure electric bus according to an embodiment of the present invention.
Fig. 7 is a flowchart illustrating a method for obtaining a charge-waiting duration prediction model based on vehicle charge-waiting data sample set training according to an embodiment of the present invention.
Fig. 8 is a schematic structural diagram of a device for predicting a charging wait period of a pure electric bus according to an embodiment of the present invention.
Fig. 9 is a schematic structural diagram of a device for predicting a charging wait time of a pure electric bus according to an embodiment of the present invention.
Fig. 10 is a schematic structural diagram of a device for predicting a charging wait period of a pure electric bus according to an embodiment of the present invention.
Fig. 11 is a schematic structural diagram of a device for predicting a charging wait period of a pure electric bus according to an embodiment of the present invention.
Fig. 12 is a schematic structural diagram of a device for predicting a charging wait period of a pure electric bus according to an embodiment of the present invention.
Fig. 13 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
The execution main body of the method for predicting the charging waiting time of the pure electric bus provided by the embodiment of the invention comprises but is not limited to a computer.
Fig. 1 is a schematic flow chart of a method for predicting a charging waiting time of a pure electric bus according to an embodiment of the present invention, and as shown in fig. 1, the method for predicting the charging waiting time of the pure electric bus according to the embodiment of the present invention includes:
s101: acquiring vehicle dispatching record data or a vehicle dispatching plan, wherein the vehicle dispatching record data comprises vehicle arrival time, and the vehicle dispatching plan comprises predicted arrival time;
in the step, vehicle dispatching record data is obtained after a vehicle arrives at a station, and a vehicle dispatching plan is obtained before actual operation starts.
Specifically, the vehicle dispatching record data is stored in a dispatching system, the dispatching system can record and store data such as arrival time of the vehicle and the like in real time, and when the vehicle arrives at a station, the required vehicle dispatching record data is called from the dispatching system. The vehicle dispatch plan is stored in a dispatch system that stores the formulated dispatch plan, including the predicted arrival time of the vehicle.
Specifically, the vehicle dispatching record data includes vehicle arrival time, and the vehicle dispatching plan includes predicted arrival time.
S102: inputting the vehicle scheduling record data or the vehicle scheduling plan data into a charging waiting duration prediction model, and outputting a charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data; the charging waiting duration prediction model is obtained after training based on a vehicle charging waiting data sample set, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration.
In the step, the vehicle scheduling record data or the vehicle scheduling plan data acquired from the scheduling system are input into a charging waiting duration prediction model for predicting the charging waiting duration, wherein the charging waiting duration prediction model is obtained by training a vehicle charging waiting data sample set.
Specifically, after vehicle arrival time data is acquired from a scheduling system, the vehicle arrival time is input into a charging waiting time prediction model, and the charging waiting time corresponding to the vehicle arrival time can be obtained through processing of the charging waiting time prediction model, wherein the charging waiting time is used for operation scheduling of vehicles, and subsequent arrangement of the vehicles after arrival at a station is determined according to the vehicle charging waiting time.
Specifically, the charge waiting duration prediction model is obtained after training based on a vehicle charge waiting data sample set, the vehicle charge waiting data sample set is composed of a plurality of vehicle charge waiting data samples, and each vehicle charge waiting data sample comprises vehicle arrival time, at least one charge starting time and charge waiting duration. The vehicle arrival time and the charge start time are stored within a dispatch system and a charging system.
Specifically, the charge waiting time period is calculated from the arrival time of the vehicle and the charge start time. The vehicle arrival time, the charging start time and the corresponding charging waiting duration obtained by calculation in the vehicle completion one-time charging period are used as a group of vehicle charging waiting data samples, a corresponding number of vehicle charging waiting data samples are obtained from a scheduling system and a charging system to form a vehicle charging waiting data sample set, and the number of the vehicle charging waiting data samples included in the vehicle charging waiting data sample set is set according to actual needs. The specific calculation process of the charging wait time is described below, and is not described herein.
The method for predicting the charging waiting time of the pure electric bus provided by the embodiment of the invention can realize accurate calculation of the charging waiting time of the pure electric bus by processing and analyzing the vehicle operation data and the charging data, accurately predict the charging waiting time of the pure electric vehicle after arriving at the station by using a machine learning method, realize the evaluation of the current charging queuing state of the pure electric vehicle, and further improve the operation efficiency of the pure electric bus.
On the basis of the foregoing embodiments, further, the vehicle charge waiting data further includes: the temperature data is the average temperature of the arrival time on the current day and is obtained through normalization calculation; the vehicle dispatching record data samples further comprise temperature data, and the temperature data are average temperatures of the arrival time on the same day and are obtained through normalization calculation.
Specifically, when the driving condition and the charging condition of the vehicle change, the frequency and the charging time of the vehicle are changed correspondingly, so that the charging waiting time of the vehicle is influenced.
For example, when the air temperature of the vehicle operation environment and/or the charging environment is reduced, the power consumption of the vehicle operation is increased, so that the vehicle charging frequency is increased, and the vehicle needs to be charged frequently in the operation process; in a low-temperature environment, the charging time of the vehicle in the station increases, and the like, which all affect the charging waiting time of the vehicle.
Specifically, when the charging waiting time is predicted based on a charging waiting time prediction model obtained by training the vehicle charging waiting data samples including the temperature data, the vehicle arrival time and the temperature data corresponding to the vehicle arrival time are acquired from the scheduling system, the charging waiting time prediction model is input, and the corresponding vehicle waiting time prediction result is output.
The vehicle charging waiting duration prediction method based on the temperature data has the advantages that the influence of temperature on vehicle charging is considered when the model is trained by adding the temperature data into the vehicle scheduling record data sample, the influence of temperature change on battery charging can be reduced due to the fact that the temperature data corresponding to the vehicle arrival time is input when the vehicle charging waiting duration prediction model obtained through training of the vehicle charging waiting data sample is used for predicting the vehicle charging waiting duration, interference caused by temperature change on battery charging is further caused, and the accuracy of the charging waiting duration prediction is improved.
Specifically, the arrival time of the vehicle includes an arrival date and an arrival time.
For example, the vehicle arrival time format is 2021 year 11 month 1 day 17 hour 30 minutes.
Specifically, the temperature data is determined according to the arrival date in the arrival time of the vehicle, and the temperature data is the current day average air temperature corresponding to the arrival date.
Specifically, in order to facilitate calculation of the temperature data, the average temperature on the day corresponding to the arrival date is normalized to obtain the temperature data.
On the basis of the foregoing embodiments, further, the formula of the normalization calculation is:
T’ =T-μ/σ
wherein, T is the temperature value of the arrival time or the day of the charging start time, T' is the normalized value of the temperature value, μ is the average value of all temperature values in the vehicle charging waiting data set, and σ is the standard deviation of all temperature values in the vehicle charging waiting data set.
Fig. 2 is a schematic flow chart of obtaining a charge-waiting duration prediction model based on vehicle schedule record data sample set training according to an embodiment of the present invention, and based on the above embodiments, further, the step of obtaining the charge-waiting duration prediction model based on vehicle charge-waiting data sample set training includes:
s201: acquiring a vehicle charge waiting data sample set;
in this step, an appropriate number of vehicle charge waiting data samples are acquired to constitute a vehicle charge waiting data sample set.
Specifically, the vehicle arrival time and the charging start time are obtained from a scheduling system and a charging system, the vehicle waiting time is calculated according to the vehicle arrival time and the charging start time, the vehicle waiting time is obtained, the vehicle charging waiting data sample is obtained, and a plurality of vehicle charging waiting data samples form a vehicle charging waiting data sample set.
Specifically, the specific calculation process of the charging wait time is described below, and is not described herein again.
S202: and training a neural network model based on the vehicle charging waiting data sample set to obtain the charging waiting duration prediction model.
In the step, a neural network model is trained by using the vehicle charging waiting data sample set, so as to obtain a charging waiting duration prediction model.
Specifically, the arrival time of each vehicle in the vehicle charging waiting data sample set is used as input data of a training model, and the charging waiting duration of each vehicle in the vehicle charging waiting data sample set is used as output of the training model, so that the training model is trained.
Further, step S201 may further obtain a vehicle arrival time and a charging start time from the scheduling system, calculate a vehicle waiting time according to the vehicle arrival time and the charging start time to obtain the vehicle waiting time, obtain corresponding temperature data according to the vehicle arrival time to obtain the vehicle charging waiting data sample, and form a vehicle charging waiting data sample set with the plurality of vehicle charging waiting data samples.
Specifically, the specific calculation process of the charging wait time is described below, and is not described herein again.
On the basis of the step S202, further, the arrival time of each vehicle in the vehicle charge waiting data sample set including the temperature data and the corresponding temperature data may be used as input data of a training model, and each charge waiting duration in the vehicle charge waiting data sample set may be used as an output of the training model, so as to train the training model. The training model is trained by adding the temperature data corresponding to the arrival time, so that the influence of temperature change on vehicle energy consumption and battery charging can be reduced, the interference on the prediction of the charging waiting time is further caused, and the accuracy of the prediction of the charging waiting time is improved.
Preferably, the neural network model may adopt a long-term memory neural network model.
Fig. 3 is a schematic flowchart of an embodiment of obtaining a charging wait duration, where on the basis of the foregoing embodiments, the charging wait duration is further obtained through the following steps:
s301: judging a vehicle charging scene according to the charging starting time to obtain a vehicle charging scene judgment result;
in this step, a vehicle charging scene is determined according to the charging start time.
Specifically, as the situation of multiple charging exists in the actual operation, for example, the charging is continued after the charging is interrupted at one charging pile; and after one charging pile is charged, the charging pile is transferred to another charging pile for charging, and the like. The scheduling system records the charge start time once after each charge, and thus the charge start time in each of the vehicle charge wait data samples may be multiple.
Specifically, the charging scene is judged according to the number of the charging start time in each vehicle charging waiting data sample, and a charging scene judgment result is obtained.
Fig. 4 is a schematic diagram of a typical charging scenario in a vehicle operation process according to an embodiment of the present invention, where ta (time of arrival) represents a vehicle arrival time, and tc (time of charging) represents a charging start time, as shown in fig. 4, step S301 is described by taking a typical charging scenario in an operation process of a vehicle as an example:
as shown in fig. 4, see TA in the figure1、TA2And TC1Two uninterrupted vehicle arrival time records TA exist for a vehicle1And TA2And at TA2After the moment, a charging start time record TC is generated1. The above scenario shows that the vehicle is at TA1After the time arrives at the station for the first time, the charging is not carried out, but the next round of operation is directly started, and after the round of operation is finished, the TA (tracking area) is carried out2The electric quantity is insufficient, the vehicle needs to be charged, and after waiting for a certain time, the electric quantity reaches the station at the moment1And starting charging at any moment until the vehicle is put into operation after charging is finished, namely, continuously putting into operation after the vehicle is charged for one time after multiple times of operation.
Continuing with FIG. 4 as an example, as shown in FIG. 4, see TA5、TC2、TC3Vehicle at TA5Two uninterrupted charging start time records TC are generated after arrival2And TC3. The above scenario shows that the vehicle is at TA5When the time arrives at the station, the station starts to queue for charging, and at TC2At the moment, the first charging after the arrival of the current time is started, from TC2After charging for a certain time, the vehicle is charged at TC due to the fact that the charging pile is disconnected and then is reconnected for charging or other charging piles are replaced for charging and the like due to the fact that vehicle charging scheduling is carried out in a station3And continuously starting charging at all times, and putting the battery into operation after charging is finished. Namely, after the vehicle operation is finished, the vehicle is charged for a plurality of times and then put into operation again.
Continuing with FIG. 4 as an example, as shown in FIG. 4, see TA6、TC4Vehicle at TA6The station arrives at the time and waits for charging for a period of time, and then at TC4At the moment, the vehicle starts to be charged for the first time after arriving at the station, and is put into operation after charging is finished, namely, the vehicle is put into operation again after being charged for one time after one-time operation is finished.
S302: and calculating the charging waiting time according to the vehicle charging scene judgment result, the arrival time and the charging starting time.
In this step, according to the determination result of the charging scenario in S301, the charging wait duration is calculated using the arrival time and the charging start time
Specifically, the charging waiting time is a difference between the charging start time and the arrival time.
On the basis of the foregoing embodiments, further, the determining a vehicle charging scenario according to the vehicle arrival time and the number of records of the corresponding charging start time, and obtaining a vehicle charging scenario determination result includes:
if the number of the starting charging time records between the current arrival time of the vehicle and the next arrival time of the vehicle is more than one, the vehicle charging scene is a first charging scene;
and if the number of the starting charging time records between the current arrival time of the vehicle and the next arrival time of the vehicle is 1, the vehicle charging scene is a second charging scene.
Specifically, if the fact that the charging starting time in a vehicle charging waiting data sample is greater than one and no other vehicle arrival time record exists between the charging starting times is judged, it is indicated that the vehicle arrives and then is charged for multiple times, the charging starting times are the situations of repeated charging such as continuous charging after interruption when the vehicle appears in the charging of one charging pile or charging of one charging pile and then going to another charging pile, and the like, and the charging scene of the vehicle at the moment is judged to be a first charging scene.
Specifically, if it is determined that only one charging start time exists in one vehicle charging waiting data sample, it is indicated that the vehicle is charged in one charging pile after arriving at a station, the whole charging process is completed, the situation of multiple charging does not exist, and the charging scene of the vehicle at the moment is determined to be a second charging scene.
Continuing with FIG. 4 as an example, as shown in FIG. 4, see TA5、TC2、TC3In part (a)That is, in the scenario where the vehicle is charged a plurality of times after the vehicle operation is completed and then put into operation again, the charging scenario of the vehicle at this time includes a plurality of charging start time records, and thus the charging scenario of the vehicle at this time is the first charging scenario.
Also taking FIG. 4 as an example, see TA in the figure1、TA2And TC1Part of the content, namely the scene that the vehicle is continuously put into operation after being charged once after being operated for multiple times, at the moment, only one charging start time record TC exists in the charging scene of the vehicle1Therefore, the vehicle charging scenario at this time is the second charging scenario.
See TA in FIG. 46、TC4As described above, this scenario may be considered as a subset of a set of scenarios in which the vehicle continues to be put into operation after being charged once after the aforementioned multiple operations have been performed, and therefore the vehicle charging scenario at this time is also the second charging scenario.
On the basis of the foregoing embodiments, further, the calculating the charge waiting time according to the vehicle charging scenario determination result, the arrival time, and the charging start time includes:
if the vehicle charging scene judgment result is a first charging scene, the charging waiting time is the difference value between the first charging starting time and the arrival time;
and if the vehicle charging scene judgment result is a second charging scene, the charging waiting time is the difference value between the charging starting time and the arrival time.
Specifically, if the vehicle charging scene is judged and known to be the first charging scene, the group of vehicle charging waiting data samples are data samples for charging for multiple times after the vehicle arrives at the station, and the charging starting time in the charging waiting time calculation is the earliest starting time in the multiple charging starting times.
Specifically, if the vehicle charging scene is judged to be the second charging scene, the group of vehicle scheduling record data samples are data samples for charging only once after the vehicle arrives at the station, and the charging starting time in the charging waiting time calculation is the charging starting time of the charging.
Fig. 5 is a schematic diagram of an algorithm flow of a charging wait duration according to an embodiment of the present invention, wherein TA isj(Time of Arrival) represents the vehicle Arrival Time, j =1 … n; TC (tungsten carbide)i(Time of Charging) denotes a charge start Time, i =1 … n; "<"represents that the previous time is earlier than the next time">"represents that the previous time is later than the next time.
TC for first Charge, as shown in FIG. 51If TC1<TA2If the charging time is TC, the charging is carried out after the vehicle is operated once, and the charging is carried out after the vehicle is operated once in the second charging scene, so that the waiting time of the first charging is TC1And TA1Time difference (T) of1=TC1-TA1) Value of waiting time T1Is time of arrival TA1The waiting time of (c); if TC1>TA2If yes, the vehicle is not charged after once operation, but continues to be put into operation, TC1>TA3、TC1>TA4The same applies, i.e. multiple operations are performed and charging is not performed. Until there is TC1<TAj+1If the operation time is j times, the first time of charging is carried out, and the waiting time T of the first time of charging can be obtained1=TC1-TAjWaiting for a time value T1Is TA time of arrivaljThe charging wait time of (1);
for charging in the following when TCi< TAj+1The description is that the vehicle is not put into operation after the i-1 th charging, but is immediately charged for the ith time, and belongs to a first charging scene that the vehicle is put into operation again after the operation is finished and the charging record is generated, wherein the charging is continued due to charging interruption or the charging is respectively recorded by two charging guns, so the record of the charging start time for the ith time is not used for calculating the charging waiting time.
For the last charging, if the last charging is carried out for a plurality of times after the operation is finished, the operation is put againEntering a first charging scene of operation, wherein no corresponding charging waiting time length exists; if the charging system belongs to a second charging scene that once charging is carried out after one or more times of operation, the charging system works as TCi>TAj>TCi-1When the time is longer, the vehicle is charged after the jth operation, and the ith charging waiting time is Ti=TCi-TAj。
After scenes that the vehicle is charged sequentially or for multiple times after arriving at a station are judged, the charging waiting time is calculated according to different charging scenes, so that the charging waiting time is calculated more accurately, the model is trained by using the more accurate charging waiting time, the accuracy of predicting the charging waiting time is improved, and the vehicle is operated and scheduled more efficiently.
Fig. 6 is a schematic flowchart of a method for predicting a charging wait duration of a pure electric bus according to an embodiment of the present invention, where on the basis of the foregoing embodiments, the inputting the vehicle scheduling record data into the charging wait duration prediction model and outputting the charging wait duration corresponding to the vehicle scheduling record data includes:
s601: if the corresponding date of the vehicle scheduling record data or the vehicle scheduling plan data is judged and known to be a working day, inputting the vehicle scheduling record data or the vehicle scheduling plan data into a first charging waiting duration prediction model, and outputting the charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data; the first charging waiting duration prediction model is obtained by training based on a vehicle charging waiting data sample set, the vehicle charging waiting data samples included in the vehicle charging waiting data sample set comprise vehicle arrival time, at least one charging starting time and charging waiting duration;
in the step, the corresponding date of the vehicle scheduling record data is judged and obtained as a working day, the vehicle scheduling record data is input into a first charging waiting duration prediction model for predicting the charging waiting duration of the working day to predict the charging waiting duration, and the charging waiting duration corresponding to the vehicle scheduling record data is output.
Specifically, if the corresponding date of the vehicle scheduling record data is judged and known to be a working day, the vehicle scheduling record data is input into a first charging waiting duration prediction model, the charging waiting duration of the working day is predicted, and the charging waiting duration corresponding to the vehicle scheduling record data is output; the first charging waiting duration prediction model is obtained by training a vehicle charging waiting data sample set of a working day, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples of the working day, and each vehicle charging waiting data sample of the working day comprises vehicle arrival time, at least one charging starting time and charging waiting duration.
S602: if the corresponding date of the vehicle scheduling record data or the vehicle scheduling plan data is judged and known to be a non-working day, inputting the vehicle scheduling record data or the vehicle scheduling plan data into a second charging waiting duration prediction model, and outputting the charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data; the second charging waiting duration prediction model is obtained based on vehicle charging waiting data sample set training, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration.
In the step, the corresponding date of the vehicle scheduling record data is judged and known to be a non-working day, the vehicle scheduling record data is input into a second charging waiting duration prediction model for predicting the charging waiting duration of the non-working day to predict the charging waiting duration, and the charging waiting duration corresponding to the vehicle scheduling record data is output.
Specifically, if the date corresponding to the vehicle scheduling record data is judged and known to be a non-working day, the vehicle scheduling record data is input into a second charging waiting duration prediction model, the charging waiting duration of the non-working day is predicted, and the charging waiting duration corresponding to the second vehicle scheduling record data is output; the second charging waiting duration prediction model is obtained by training a vehicle charging waiting data sample set of a non-working day, the vehicle charging waiting data sample set of the non-working day comprises vehicle charging waiting data samples of the non-working day, and each vehicle charging waiting data sample of the non-working day comprises vehicle arrival time, at least one charging starting time and charging waiting duration.
Specifically, the operation characteristics of the public transport vehicles on working days and weekends are different, the demand on the transport capacity of the public transport vehicles is high during the working days, and the operation times of the public transport vehicles are frequent; and the operation frequency of the bus is lower due to lower demand on the transportation capacity of the bus at weekends. Therefore, the vehicle scheduling record data is split according to the date, the charging waiting time of the working day and the charging waiting time of the non-working day are respectively predicted by using the corresponding charging waiting time prediction models, and the accuracy of the prediction result is improved.
Fig. 7 is a schematic flowchart of a process of obtaining a charge-waiting time period prediction model based on vehicle charge-waiting data sample set training according to an embodiment of the present invention, where on the basis of the above embodiments, the obtaining of the first charge-waiting time period prediction model and the second charge-waiting time period prediction model based on vehicle charge-waiting data sample set training further includes:
s701: classifying the vehicle charge waiting data samples in the vehicle charge waiting data sample set according to time to obtain a first vehicle charge waiting data sample set and a second vehicle charge waiting data sample set; wherein the first set of vehicle charge-waiting data samples comprises vehicle charge-waiting data samples for a weekday, and the second set of vehicle charge-waiting data samples comprises vehicle charge-waiting data samples for a non-weekday;
in this step, the vehicle charge waiting data samples in the vehicle charge waiting data sample set are classified according to time.
Specifically, the vehicle charge waiting data samples in the vehicle charge waiting data sample set are classified according to whether the date corresponding to the arrival time is a working day or a non-working day, so as to obtain a first vehicle charge waiting data sample set, that is, a vehicle charge waiting data sample set of the working day and a second vehicle charge waiting data sample set, that is, a vehicle charge waiting data sample set of the non-working day.
For example, the arrival time corresponds to a date of 2021 year, 12 month, 27 day monday, and the vehicle charge waiting data sample at which the arrival time is located should belong to the first vehicle charge waiting data sample set, i.e., the vehicle charge waiting data sample set of the working day.
For another example, the arrival time corresponds to a date of 2021 year, 12 month, 26 days, sunday, and the vehicle charge waiting data sample at which the arrival time is located should belong to a second vehicle charge waiting data sample set, that is, a vehicle charge waiting data sample set on a non-working day.
S702: training a neural network model by using the first vehicle charging waiting data sample set to obtain a first charging waiting duration prediction model; and training a neural network model by using the second vehicle charging waiting data sample set to obtain the second charging waiting duration prediction model.
In the step, a vehicle charging waiting data sample set consisting of vehicle charging waiting data samples classified according to time is used for carrying out model training on the neural network model, and a corresponding charging waiting duration prediction model is obtained.
Specifically, a first vehicle charge waiting data sample set, namely a vehicle charge waiting data sample set of a working day, is used for training a neural network model to obtain a first charge waiting duration prediction model, namely a charge waiting duration prediction model of the working day.
Specifically, a second vehicle charging waiting data sample set, that is, a vehicle charging waiting data sample set on a non-working day, is used to train the neural network model, so as to obtain a second charging waiting duration prediction model, that is, a charging waiting duration prediction model on a non-working day.
Preferably, the neural network model may adopt a long-term memory neural network model.
The vehicle waiting time of the working day and the vehicle waiting time of the non-working day are predicted by respectively using a first charging waiting time prediction model obtained by training a vehicle scheduling data set based on the working day and a second charging waiting time prediction model obtained by training a vehicle scheduling data set based on the non-working day, and different charging waiting time prediction models are selected for prediction according to the characteristics of operation of the bus on the working day and the non-working day, so that the accuracy of vehicle waiting time prediction is improved.
Fig. 8 is a schematic structural diagram of a device for predicting a charging waiting duration of a pure electric bus according to an embodiment of the present invention, and as shown in fig. 8, the device for predicting a charging waiting duration of a pure electric bus according to an embodiment of the present invention includes an obtaining unit 801 configured to obtain vehicle scheduling record data or vehicle scheduling plan data, where the vehicle scheduling record data includes a vehicle arrival time, and the vehicle scheduling plan data includes a vehicle scheduled arrival time; the prediction unit 802 is configured to input the vehicle scheduling record data or the vehicle scheduling plan data into a charging waiting duration prediction model, and output a charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data; the charging waiting duration prediction model is obtained after training based on a vehicle charging waiting data sample set, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration. Wherein:
the acquisition unit 801 acquires vehicle schedule record data after the arrival of the vehicle.
The prediction unit 802 inputs the vehicle scheduling record data acquired from the scheduling system into a charging waiting duration prediction model for predicting the charging waiting duration, wherein the charging waiting duration prediction model is obtained by training a vehicle charging waiting data sample set.
Fig. 9 is a schematic structural diagram of a device for predicting a charging waiting time of a pure electric bus according to an embodiment of the present invention, as shown in fig. 9, based on the foregoing embodiments, further, the device for predicting a charging waiting time of a pure electric bus further includes a charging waiting time prediction model training unit, where the charging waiting time prediction model training unit includes an obtaining subunit 901 for obtaining a vehicle charging waiting data sample set; a training subunit 702, configured to train a neural network model based on a vehicle charging waiting data sample set, to obtain the charging waiting duration prediction model. Wherein:
the obtaining subunit 901 obtains an appropriate amount of vehicle dispatching data samples from the dispatching system to form a vehicle charging waiting data sample set.
The training subunit 902 trains a neural network model based on the vehicle charging wait data sample set, and obtains the charging wait duration prediction model.
Fig. 10 is a schematic structural diagram of a device for predicting a charging wait time of a pure electric bus according to an embodiment of the present invention, as shown in fig. 10, on the basis of the foregoing embodiments, further, the obtaining sub-unit 901 further includes a charging wait time calculating unit, where the charging wait time calculating unit includes a scene determining sub-unit 1001 for determining a vehicle charging scene according to the charging start time to obtain a vehicle charging scene determination result; and the calculating subunit 1002 is configured to calculate the charge waiting time according to the vehicle charge scene determination result, the arrival time, and the charge starting time. Wherein:
the scene determination subunit 1001 determines the vehicle charging scene from the charging start time.
The calculating subunit 1002 calculates the charge waiting time period according to the vehicle charge scene determination result, the arrival time, and the charge start time.
Fig. 11 is a schematic structural diagram of a device for predicting a charging wait time of a pure electric bus according to an embodiment of the present invention, as shown in fig. 11, on the basis of the foregoing embodiments, further, the predicting unit 802 includes a first predicting subunit 8021, configured to determine that the date corresponding to the vehicle scheduling record data is a working day, input the vehicle scheduling record data into a first charging wait time prediction model, and output a charging wait time corresponding to the vehicle scheduling record data; the first charging waiting duration prediction model is obtained based on vehicle scheduling record data sample set training, the vehicle scheduling record data sample set comprises vehicle scheduling record data samples, and each vehicle scheduling record data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration; a second prediction subunit 8022, configured to determine that the date corresponding to the vehicle scheduling record data is a non-working day, input the vehicle scheduling record data into a second charging waiting duration prediction model, and output a charging waiting duration corresponding to the second vehicle scheduling record data; the second charge waiting duration prediction model is obtained based on vehicle charge waiting data sample set training, the vehicle charge waiting data sample set comprises vehicle charge waiting data samples, and each vehicle charge waiting data sample comprises vehicle arrival time, at least one charge starting time and charge waiting duration. Wherein:
the first prediction subunit 8021 determines that the date corresponding to the vehicle scheduling record data is the working day, inputs the vehicle scheduling record data into a first charging waiting duration prediction model for predicting the charging waiting duration of the working day to predict the charging waiting duration, and outputs the charging waiting duration corresponding to the vehicle scheduling record data.
The second prediction subunit 8022 determines that the date corresponding to the vehicle scheduling record data is a non-working day, inputs the vehicle scheduling record data into a second charging waiting duration prediction model for predicting the charging waiting duration of the non-working day to predict the charging waiting duration, and outputs the charging waiting duration corresponding to the vehicle scheduling record data.
Fig. 12 is a schematic structural diagram of a device for predicting a charging wait time of a pure electric bus according to an embodiment of the present invention, as shown in fig. 12, based on the foregoing embodiments, further, the charging wait time prediction model training unit further includes a classification subunit 1201, configured to classify the vehicle charging wait data samples in the vehicle charging wait data sample set according to time, so as to obtain a first vehicle charging wait data sample set and a second vehicle charging wait data sample set; wherein the first set of vehicle charge-waiting data samples comprises vehicle charge-waiting data samples for a weekday, and the second set of vehicle charge-waiting data samples comprises vehicle charge-waiting data samples for a non-weekday;
the classification subunit 1201 classifies the vehicle charge waiting data samples in the vehicle charge waiting data sample set according to time.
The training subunit 902 trains the neural network models respectively by using the vehicle charging waiting data sample sets classified by the classification subunit 1201, and obtains corresponding charging waiting duration prediction models.
The embodiment of the server provided in the embodiment of the present invention may be specifically configured to execute the processing flows of the foregoing method embodiments, and its functions are not described herein again, and reference may be made to the detailed description of the foregoing method embodiments.
Fig. 13 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 13, the electronic device may include: a processor (processor)1301, a communication Interface (Communications Interface)1302, a memory (memory)1103 and a communication bus 1304, wherein the processor 1301, the communication Interface 1302 and the memory 1303 complete communication with each other through the communication bus 1304. Processor 1301 may call logic instructions in memory 1303 to perform the following method: acquiring vehicle scheduling record data, wherein the vehicle scheduling record data comprises vehicle arrival time; inputting the vehicle scheduling record data into a charging waiting duration prediction model, and outputting a charging waiting duration corresponding to the vehicle scheduling record data; the charging waiting duration prediction model is obtained after training based on a vehicle charging waiting data sample set, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration.
In addition, the logic instructions in the memory 1303 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The present embodiment discloses a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method provided by the above-mentioned method embodiments, for example, comprising: acquiring vehicle scheduling record data, wherein the vehicle scheduling record data comprises vehicle arrival time; inputting the vehicle scheduling record data into a charging waiting duration prediction model, and outputting a charging waiting duration corresponding to the vehicle scheduling record data; the charging waiting duration prediction model is obtained after training based on a vehicle charging waiting data sample set, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration.
The present embodiment provides a computer-readable storage medium, which stores a computer program, where the computer program causes the computer to execute the method provided by the above method embodiments, for example, the method includes: acquiring vehicle scheduling record data, wherein the vehicle scheduling record data comprises vehicle arrival time; inputting the vehicle scheduling record data into a charging waiting duration prediction model, and outputting a charging waiting duration corresponding to the vehicle scheduling record data; the charging waiting duration prediction model is obtained after training based on a vehicle charging waiting data sample set, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may 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, and the like) having computer-usable program code embodied therein.
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 will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may 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, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description herein, reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," "an example," "a particular example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (10)

1. The method for predicting the charging waiting time of the pure electric bus is characterized by comprising the following steps of:
acquiring vehicle dispatching record data or vehicle dispatching plan data, wherein the vehicle dispatching record data comprises vehicle arrival time, and the vehicle dispatching plan comprises predicted arrival time;
inputting the vehicle dispatching record data or the vehicle dispatching plan data into a charging waiting duration prediction model, and outputting a charging waiting duration corresponding to the vehicle dispatching record data or the vehicle dispatching plan data; the charging waiting duration prediction model is obtained after training based on a vehicle charging waiting data sample set, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration;
the step of inputting the vehicle scheduling record data or the vehicle scheduling plan data into a charging waiting duration prediction model, and the step of outputting the charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data comprises the following steps:
if the corresponding date of the vehicle dispatching record data or the vehicle dispatching plan data is judged and known to be a working day, inputting the vehicle dispatching record data or the vehicle dispatching plan data into a first charging waiting duration prediction model, and outputting the charging waiting duration corresponding to the vehicle dispatching record data or the vehicle dispatching plan data; the first charging waiting duration prediction model is obtained by training based on a vehicle charging waiting data sample set, the vehicle charging waiting data samples included in the vehicle charging waiting data sample set comprise vehicle arrival time, at least one charging starting time and charging waiting duration;
if the corresponding date of the vehicle scheduling record data or the vehicle scheduling plan data is judged and known to be a non-working day, inputting the vehicle scheduling record data or the vehicle scheduling plan data into a second charging waiting duration prediction model, and outputting the charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data; the second charging waiting duration prediction model is obtained based on vehicle charging waiting data sample set training, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration;
the charging wait time is obtained by the following steps:
judging a vehicle charging scene according to the charging starting time to obtain a vehicle charging scene judgment result;
and calculating the charging waiting time according to the vehicle charging scene judgment result, the arrival time and the charging starting time.
2. The method for predicting the charging waiting time of the pure electric bus according to claim 1,
the vehicle dispatch log data further comprises: the temperature data in the vehicle scheduling record data is the average temperature of the arrival time on the current day and is obtained through normalization calculation;
the vehicle charging waiting data samples also comprise temperature data, and the temperature data in the vehicle charging waiting data samples are average temperatures of the arrival time on the day and are obtained through normalization calculation.
3. The method for predicting the charging waiting time of the pure electric bus according to claim 2, wherein the formula of the normalized calculation is as follows:
T’ =T-μ/σ
wherein, T is a temperature value of the arrival time or the day of the charging start time, T' is a normalized value of the temperature value, μ is a mean value of the temperatures in the data set, and σ is a standard deviation of the temperatures in the data set.
4. The method for predicting the charging waiting time of the pure electric bus according to any one of claims 1 and 2, wherein the step of training and obtaining the charging waiting time prediction model based on the vehicle charging waiting data sample set comprises:
acquiring a vehicle charge waiting data sample set;
and training a neural network model based on the vehicle charging waiting data sample set to obtain the charging waiting duration prediction model.
5. The method for predicting the charging waiting time of the pure electric bus according to claim 1, wherein the step of judging the charging scene of the vehicle according to the arrival time of the vehicle and the number of records of the corresponding charging starting time to obtain the judgment result of the charging scene of the vehicle comprises the following steps:
if the number of the starting charging time records between the current arrival time of the vehicle and the next arrival time of the vehicle is more than one, the vehicle charging scene is a first charging scene;
and if the number of the starting charging time records between the current arrival time of the vehicle and the next arrival time of the vehicle is one, the charging scene of the vehicle is a second charging scene.
6. The method for predicting the charging waiting time of the pure electric bus according to claim 1, wherein the calculating the charging waiting time according to the vehicle charging scene determination result, the arrival time and the charging start time comprises:
if the vehicle charging scene judgment result is a first charging scene, the charging waiting time is the difference value between the first charging starting time and the arrival time;
and if the vehicle charging scene judgment result is a second charging scene, the charging waiting time is the difference value between the charging starting time and the arrival time.
7. The method for predicting the charging waiting time of the pure electric bus according to claim 1, wherein the training of obtaining the first charging waiting time prediction model and the second charging waiting time prediction model based on the vehicle charging waiting data sample set comprises:
classifying the vehicle charge waiting data samples in the vehicle charge waiting data sample set according to time to obtain a first vehicle charge waiting data sample set and a second vehicle charge waiting data sample set; wherein the first set of vehicle charge-waiting data samples comprises vehicle charge-waiting data samples for weekdays, and the second set of vehicle charge-waiting data samples comprises vehicle charge-waiting data samples for non-weekdays;
training a neural network model by using the first vehicle charging waiting data sample set to obtain a first charging waiting duration prediction model; and training a neural network model by using the second vehicle charging waiting data sample set to obtain the second charging waiting duration prediction model.
8. The utility model provides a prediction unit of pure electric bus charge waiting time duration which characterized in that includes:
the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring vehicle dispatching record data or vehicle dispatching plan data, the vehicle dispatching record data comprises vehicle arrival time, and the vehicle dispatching plan data comprises vehicle planned arrival time;
the prediction unit is used for inputting the vehicle scheduling record data or the vehicle scheduling plan data into a charging waiting duration prediction model and outputting a charging waiting duration corresponding to the vehicle scheduling record data or the vehicle scheduling plan data; the charging waiting duration prediction model is obtained after training based on a vehicle charging waiting data sample set, the vehicle charging waiting data sample set comprises vehicle charging waiting data samples, and each vehicle charging waiting data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration;
the prediction unit includes:
the first prediction subunit is used for judging that the corresponding date of the vehicle scheduling record data is the working day, inputting the vehicle scheduling record data into a first charging waiting duration prediction model and outputting the charging waiting duration corresponding to the vehicle scheduling record data; the first charging waiting duration prediction model is obtained based on vehicle scheduling record data sample set training, the vehicle scheduling record data sample set comprises vehicle scheduling record data samples, and each vehicle scheduling record data sample comprises vehicle arrival time, at least one charging starting time and charging waiting duration;
the second prediction subunit is used for judging and knowing that the corresponding date of the vehicle scheduling record data is a non-working day, inputting the vehicle scheduling record data into a second charging waiting duration prediction model, and outputting the charging waiting duration corresponding to the second vehicle scheduling record data; the second charge waiting duration prediction model is obtained based on vehicle charge waiting data sample set training, the vehicle charge waiting data sample set comprises vehicle charge waiting data samples, and each vehicle charge waiting data sample comprises vehicle arrival time, at least one charge starting time and charge waiting duration;
the prediction unit further includes:
the scene judging subunit is used for judging the vehicle charging scene according to the charging starting time to obtain a vehicle charging scene judging result;
and the calculating subunit is used for calculating the charging waiting time according to the vehicle charging scene judgment result, the arrival time and the charging starting time.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
CN202210144586.3A 2022-02-17 2022-02-17 Method and device for predicting charging waiting time of pure electric bus Active CN114202131B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210144586.3A CN114202131B (en) 2022-02-17 2022-02-17 Method and device for predicting charging waiting time of pure electric bus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210144586.3A CN114202131B (en) 2022-02-17 2022-02-17 Method and device for predicting charging waiting time of pure electric bus

Publications (2)

Publication Number Publication Date
CN114202131A CN114202131A (en) 2022-03-18
CN114202131B true CN114202131B (en) 2022-05-24

Family

ID=80645584

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210144586.3A Active CN114202131B (en) 2022-02-17 2022-02-17 Method and device for predicting charging waiting time of pure electric bus

Country Status (1)

Country Link
CN (1) CN114202131B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011214930A (en) * 2010-03-31 2011-10-27 Honda Motor Co Ltd Device for providing information on waiting time for charge, and car navigation apparatus
CN104217605A (en) * 2013-05-31 2014-12-17 张伟伟 Bus arrival time estimation method and device
CN111325483A (en) * 2020-03-17 2020-06-23 郑州天迈科技股份有限公司 Electric bus scheduling method based on battery capacity prediction
CN112819576A (en) * 2021-01-27 2021-05-18 北京百度网讯科技有限公司 Training method and device for charging station recommendation model and recommendation method for charging station

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011214930A (en) * 2010-03-31 2011-10-27 Honda Motor Co Ltd Device for providing information on waiting time for charge, and car navigation apparatus
CN104217605A (en) * 2013-05-31 2014-12-17 张伟伟 Bus arrival time estimation method and device
CN111325483A (en) * 2020-03-17 2020-06-23 郑州天迈科技股份有限公司 Electric bus scheduling method based on battery capacity prediction
CN112819576A (en) * 2021-01-27 2021-05-18 北京百度网讯科技有限公司 Training method and device for charging station recommendation model and recommendation method for charging station

Also Published As

Publication number Publication date
CN114202131A (en) 2022-03-18

Similar Documents

Publication Publication Date Title
CN108162771B (en) Intelligent charging navigation method for electric automobile
CN110570014B (en) Electric vehicle charging load prediction method based on Monte Carlo and deep learning
Chen et al. Managing truck arrivals with time windows to alleviate gate congestion at container terminals
EP3076512B1 (en) Electricity-demand prediction device, electricity supply system, electricity-demand prediction method, and program
CN110176142B (en) Vehicle track prediction model building and prediction method
CN110723029B (en) Method and device for determining charging strategy
CN110658460B (en) Battery life prediction method and device for battery pack
CN107678803A (en) Using management-control method, device, storage medium and electronic equipment
CN106063067A (en) Electricity-demand prediction device, electricity supply system, electricity-demand prediction method, and program
CN110491124B (en) Vehicle flow prediction method, device, equipment and storage medium
CN111815096B (en) Shared automobile throwing method, electronic equipment and storage medium
CN116937581B (en) Intelligent scheduling method of charging station
CN103761870B (en) A kind of bus load metering system
CN109308538A (en) Conclusion of the business conversion ratio prediction technique and device
CN115860185A (en) Power grid load prediction method considering charging modes of various types of electric automobiles in extremely high temperature weather
CN115700717A (en) Power distribution analysis method based on electric automobile power consumption demand
CN113147506B (en) Big data-based vehicle-to-vehicle mutual learning charging remaining time prediction method and device
CN114202131B (en) Method and device for predicting charging waiting time of pure electric bus
Xu et al. FMS-dispatch: a fast maximum stability dispatch policy for shared autonomous vehicles including exiting passengers under stochastic travel demand
WO2024060539A1 (en) Annual carbon emission amount estimation method and device for power battery
CN110543967B (en) Electric vehicle waiting time distribution short-time prediction method in network connection charging station environment
CN113204858A (en) Evaluation method for battery use health degree and establishment method of evaluation model
CN117151368A (en) Power conversion scheduling method and device, electronic equipment and power conversion scheduling system
CN114966452B (en) Battery state determination method and related device
CN112116241B (en) Intelligent public traffic scheduling method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant