CN114407661B - Electric vehicle energy consumption prediction method, system, equipment and medium based on data driving - Google Patents
Electric vehicle energy consumption prediction method, system, equipment and medium based on data driving Download PDFInfo
- Publication number
- CN114407661B CN114407661B CN202210126508.0A CN202210126508A CN114407661B CN 114407661 B CN114407661 B CN 114407661B CN 202210126508 A CN202210126508 A CN 202210126508A CN 114407661 B CN114407661 B CN 114407661B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- running
- data
- time
- energy consumption
- 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
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 96
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 238000000342 Monte Carlo simulation Methods 0.000 claims abstract description 12
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 239000012634 fragment Substances 0.000 claims description 77
- 238000012360 testing method Methods 0.000 claims description 47
- 238000012549 training Methods 0.000 claims description 36
- 238000004146 energy storage Methods 0.000 claims description 20
- 238000013145 classification model Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 4
- 208000019901 Anxiety disease Diseases 0.000 abstract description 6
- 230000036506 anxiety Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
- B60L3/12—Recording operating variables ; Monitoring of operating variables
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
- B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L2260/00—Operating Modes
- B60L2260/40—Control modes
- B60L2260/50—Control modes by future state prediction
- B60L2260/54—Energy consumption estimation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention provides a data-driven-based electric vehicle energy consumption prediction method, a system, equipment and a medium, wherein the method comprises the following steps: acquiring operation monitoring data of a vehicle to be tested through the Internet of vehicles, acquiring historical operation data, and constructing a vehicle running time-space electric quantity relation model by combining a Monte Carlo method to acquire a running time-space electric quantity relation of the vehicle to be tested; acquiring external factors according to historical operation data, constructing a vehicle running condition prediction model based on a KNN algorithm according to the external factors, and predicting the future running condition of the tested vehicle by acquiring the current external factors of the tested vehicle; and according to the historical operation data, an energy consumption prediction model is constructed based on a machine learning algorithm, and the energy consumption requirement of the tested vehicle is predicted by combining the running time-space electric quantity relation and the future running working condition of the tested vehicle. The method improves the real-time performance of the predicted data, can accurately reach the tested vehicle individuals, can provide real-time data support for the travel of the user, and relieves the mileage anxiety.
Description
Technical Field
The invention relates to the technical field of new energy automobile application, in particular to a data-driven electric vehicle energy consumption prediction method, a data-driven electric vehicle energy consumption prediction system, data-driven electric vehicle energy consumption prediction equipment and a data-driven electric vehicle energy consumption prediction medium.
Background
With the increasing attention of the society to energy and environment, the number of electric automobiles in the market is gradually increased. Thanks to the national incentives of repair policies, vehicle purchasing offers and environmental protection requirements, new energy automobile industry has come to the explosive growth, and China has become the global maximum pure electric automobile market. With the continuous popularization of electric vehicles, the performance of the electric vehicles is receiving more and more attention. The technical problems in front of the current development situation of electric automobiles in all countries in the world are mainly in the aspect of battery performance.
The user cannot meet the requirement of free travel due to the influence of battery performance and inconvenient charging, and the travel route must be planned before travel, so that whether the residual electric quantity of the vehicle can meet the travel requirement is measured. Because the energy consumption of the electric automobile is greatly influenced by the driving road and the weather air temperature, the driving range provided by the vehicle enterprise often has quite different from the actual driving range, and the driving range cannot provide good driving guidance for a driver, so that the driver generates 'mileage anxiety', and the use confidence of people on the electric automobile is reduced.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, a system, a device and a medium for predicting energy consumption of an electric vehicle based on data driving.
The method for predicting the energy consumption of the electric vehicle based on data driving comprises the following steps: acquiring operation monitoring data of a tested vehicle through the Internet of vehicles, and acquiring historical operation data of the tested vehicle; according to the historical operation data, a vehicle running time-space electric quantity relation model is built based on a Monte Carlo method, and a running time-space electric quantity relation of a tested vehicle is obtained; acquiring external factors influencing the running of the tested vehicle according to the historical running data, constructing a vehicle running condition prediction model based on a KNN algorithm according to the external factors, acquiring the current external factors of the tested vehicle, inputting the current external factors into the vehicle running condition prediction model, and predicting the future running condition of the tested vehicle; and according to the historical operation data, an energy consumption prediction model is constructed based on a machine learning algorithm, and the energy consumption demand of the tested vehicle in a future period of time is predicted through the energy consumption prediction model by combining the running time-space electric quantity relation and the future running working condition of the tested vehicle.
In one embodiment, the acquiring operation monitoring data of the vehicle to be tested through the internet of vehicles, and acquiring historical operation data of the vehicle to be tested specifically includes: the method comprises the steps of collecting historical operation data of a tested vehicle in a period of time through the Internet of vehicles, wherein the historical operation data comprise a plurality of driving fragment data, and each driving fragment data correspondingly comprises a vehicle unique identifier, a fragment starting time, a fragment ending time, a fragment duration, a starting longitude, a starting latitude, an ending longitude, an ending latitude, a fragment starting state of charge, a fragment ending state of charge, a fragment starting mileage and a fragment ending mileage.
In one embodiment, the building a model of the vehicle running space-time electric quantity relation based on the monte carlo method according to the historical running data, and obtaining the running space-time electric quantity relation of the tested vehicle specifically includes: extracting the date of the starting time of the detected vehicle segment according to a date preset format, and recoding and grouping according to month, week and working day to obtain a date field, a month field, a week field and a working day field; extracting a time point of the starting time of the detected vehicle segment according to a time preset format, and recoding and grouping according to the starting time point, the early peak and the late peak of the driving to obtain a starting time field, an early peak field and a late peak field; the method comprises the steps of collecting the highest speed of a tested vehicle in a segment, calculating the average speed of the segment according to running data, obtaining a highest speed field and an average speed field, calculating the ratio of mileage with the speed exceeding a predicted speed threshold value to the total mileage of the segment according to a preset period, and obtaining a segment high-speed running time ratio field; analyzing longitude and latitude information according to the starting longitude and the starting latitude, acquiring provinces, cities and counties where the fragments start, inquiring weather and temperature information of the corresponding regions, wherein the temperature information is the average temperature of the starting time and date of the fragments, and acquiring weather fields and temperature fields; acquiring vehicle registration time and energy storage device types, calculating the number of days of the registration time from the current date as the vehicle age, and acquiring a vehicle age field and an energy storage device type field; combining the operation data, calculating the power consumption of the unit mileage under different working conditions, and obtaining a power consumption field; and constructing a vehicle running space-time electric quantity relation model according to the vehicle unique identifier, the month field, the week field, the working day field, the starting time field, the early peak field, the late peak field, the fragment high-speed running time duty ratio field, the weather field, the temperature field, the vehicle age field, the energy storage device type field and the power consumption field, and acquiring the running space-time electric quantity relation of the tested vehicle.
In one embodiment, the date preset format is a format of year, month and day, wherein month is 1 to 12, week is 1 to 7, driving start date is 1 for working diary, and non-working diary is 0; the time preset format is a time minute second format, wherein a driving start time point is represented as 0 to 23; the starting time point of the running is the early peak when the starting time point is from 7 points to 9 points, and is recorded as 1, otherwise, is recorded as 0; the travel start time point is a late peak at 17 to 19 points, and is denoted as 1, otherwise is denoted as 0.
In one embodiment, the acquiring, according to the historical operation data, an external factor that affects the running of the tested vehicle specifically includes: acquiring the historical running speed of the tested vehicle according to the historical running data, and labeling the historical running speed as a data set label; calling a geographic position information system and a network application program interface according to the acquisition time and longitude and latitude coordinate information of the historical operation data to acquire driving environment data, wherein the driving environment data comprises weather types, road types and temperatures as a first data set; dividing the historical operation data according to the working day, the week, the driving starting time, the early peak and the late peak to obtain a second data set; and selecting the longitude and latitude of the history running road condition of the tested vehicle as a third data set according to the history running data.
In one embodiment, the method includes constructing a vehicle running condition prediction model based on a KNN algorithm according to the external factors, obtaining a current external factor of the vehicle to be tested, inputting the current external factor into the vehicle running condition prediction model, and predicting a future running condition of the vehicle to be tested, and specifically includes: combining the first data set, the second data set and the third data set to be used as KNN classification characteristics, and dividing the combined data sets according to a first preset proportion to obtain a first training set and a first testing set; constructing a KNN classification model based on a KNN algorithm, taking a data set label as an output result of a first training set, training the KNN classification model according to the first training set, testing the trained KNN classification model through a first testing set, and acquiring a vehicle driving condition prediction model after the test is passed; and acquiring the current external factors of the tested vehicle, inputting the current external factors into the vehicle running condition prediction model, and predicting the future running condition of the tested vehicle.
In one embodiment, the building an energy consumption prediction model based on a machine learning algorithm according to the historical operation data, and predicting the energy consumption requirement of the tested vehicle in a future period of time by using the energy consumption prediction model in combination with the running space-time electric quantity relation and the future running working condition of the tested vehicle specifically includes: inputting the current external factors of the tested vehicle into a vehicle running condition prediction model to obtain the future running condition of the tested vehicle, wherein the external factors comprise temperature, weather, week, working day, running starting time point, early peak, late peak, starting longitude and starting latitude; acquiring vehicle unique identification, fragment starting charge state, fragment starting mileage, fragment ending mileage, working day, speed, temperature, weather and road type information of a tested vehicle as a data set, randomly dividing the data set according to a second preset proportion, and acquiring a second training set and a second testing set; constructing an initial energy consumption prediction model based on a machine learning algorithm, inputting the second training set to train the initial energy consumption prediction model, and testing the trained initial energy consumption prediction model through the second testing set to obtain an energy consumption prediction model; and predicting the energy consumption requirement of the detected vehicle in a future period of time based on the energy consumption prediction model by combining the future running working condition of the detected vehicle and the running time-space electric quantity relation.
An electric vehicle energy consumption prediction system based on data driving, comprising: the historical operation data acquisition module is used for acquiring operation monitoring data of the tested vehicle through the Internet of vehicles and acquiring historical operation data of the tested vehicle; the space-time electric quantity relation model construction module is used for constructing a vehicle running space-time electric quantity relation model based on a Monte Carlo method according to the historical operation data and obtaining a running space-time electric quantity relation of the tested vehicle; the future running condition prediction module is used for acquiring external factors influencing the running of the tested vehicle according to the historical running data, constructing a vehicle running condition prediction model based on a KNN algorithm according to the external factors, acquiring the current external factors of the tested vehicle, inputting the current external factors into the vehicle running condition prediction model, and predicting the future running condition of the tested vehicle; and the energy consumption demand prediction module is used for constructing an energy consumption prediction model based on a machine learning algorithm according to the historical operation data, and predicting the energy consumption demand of the tested vehicle in a future period of time by combining the running time-space electric quantity relation and the future running working condition of the tested vehicle.
An apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the data-driven electric vehicle energy consumption prediction method described in the above embodiments when the program is executed.
A medium having stored thereon a computer program which, when executed by a processor, implements the steps of the data-driven electric vehicle energy consumption prediction method described in the above embodiments.
Compared with the prior art, the invention has the advantages that: according to the method, the operation detection data of the tested vehicle can be acquired through the Internet of vehicles, the historical operation data of the tested vehicle can be acquired, the vehicle running time-space electric quantity relation model is built based on the Monte Carlo method according to the historical operation data, the running time-space electric quantity relation of the tested vehicle is acquired, the external factors influencing the running of the tested vehicle are acquired according to the historical operation data, the vehicle running condition prediction model is built based on the KNN algorithm according to the external factors, the current external factors of the tested vehicle are acquired, the current external factors are input into the vehicle running condition prediction model, the future running condition of the tested vehicle is predicted, the energy consumption prediction model is built based on the machine learning algorithm according to the historical operation data, the energy consumption demand of the tested vehicle in a future period is predicted by combining the form time-space electric quantity relation and the future running condition of the tested vehicle, the real-time performance of the prediction data is improved, the individual running of the tested vehicle can be accurately achieved, effective real-time data support can be provided for a user of the electric vehicle, and the mileage anxiety is relieved.
Drawings
FIG. 1 is a schematic flow chart of a method for predicting energy consumption of an electric vehicle based on data driving in an embodiment;
FIG. 2 is a schematic diagram of a data-driven electric vehicle energy consumption prediction system according to an embodiment;
fig. 3 is a schematic diagram of the internal structure of the apparatus in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail by the following detailed description with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In one embodiment, as shown in fig. 1, there is provided a data-driven-based electric vehicle energy consumption prediction method, including the steps of:
step S101, operation monitoring data of a tested vehicle are collected through the Internet of vehicles, and historical operation data of the tested vehicle are obtained.
Specifically, operation monitoring data of the tested vehicle are acquired through the Internet of vehicles, historical operation data of the tested vehicle are acquired, and future driving conditions and energy consumption requirements of the vehicle are predicted by adopting vehicle end data, so that the accuracy and instantaneity of the data are improved. The vehicle to be tested can be a private electric vehicle purchased for more than half a year, and the running data can be a plurality of running fragment data of the vehicle to be tested in a period of time.
The operating data may include vehicle static data and dynamic operating data, among other things. The vehicle static data comprises information such as a vehicle unique identifier, the type of the energy storage device and the like; the dynamic operation data includes data such as a segment start time, a segment end time, a segment duration, a start longitude, a start latitude, an end longitude, an end latitude, a segment start state of charge, a segment end state of charge, a segment start mileage, and a segment end mileage.
Step S102, a vehicle running time-space electric quantity relation model is built based on a Monte Carlo method according to historical running data, and a running time-space electric quantity relation of a tested vehicle is obtained.
Specifically, recoding and calculating historical running data of the tested vehicle to obtain corresponding fields including fields such as month, date, week, working day, running start time, early peak, late peak, average speed, highest speed, segment high-speed running time duty ratio, weather, temperature, vehicle age, energy storage device type, power consumption and the like, constructing a vehicle running time-space electric quantity relation model based on a Monte Carlo method according to all the fields, and obtaining the running time-space electric quantity relation of the tested vehicle.
Step S103, obtaining external factors influencing the running of the tested vehicle according to the historical running data, constructing a vehicle running condition prediction model based on a KNN algorithm according to the external factors, obtaining the current external factors of the tested vehicle, inputting the current external factors into the vehicle running condition prediction model, and predicting the future running condition of the tested vehicle.
Specifically, external factors that affect the running of the vehicle under test, such as weather, road, temperature, day of the week, working day, early or late peak, longitude and latitude of the running, etc., are acquired based on the historical running data of the vehicle under test. And combining the external factors as a KNN classification characteristic data set, dividing the data set according to a preset proportion, obtaining a corresponding training set and a testing set, taking the historical driving speed corresponding to the tested vehicle as an output result of the training set, constructing a KNN classification model based on a KNN algorithm, training the KNN classification model according to the training set, testing the trained KNN classification model by adopting the testing set, obtaining a corresponding vehicle driving condition prediction model after the test is passed, and predicting the future driving condition of the tested vehicle according to the vehicle driving condition prediction model. The future running condition of the tested vehicle is predicted by external factors, so that the adverse effect on the prediction result caused by unknown future conditions in the traditional prediction method is effectively reduced, the individual tested vehicle can be accurately detected, and the timeliness of the prediction result is high.
The KNN (K-Nearest Neighbor) algorithm is a machine learning algorithm, and can be classified by measuring the distance between different characteristic values.
Step S104, according to the historical operation data, an energy consumption prediction model is built based on a machine learning algorithm, and the energy consumption demand of the tested vehicle in a future period of time is predicted through the energy consumption prediction model by combining the running space-time electric quantity relation and the future running working condition of the tested vehicle.
Specifically, the current external factors of the tested vehicle, such as temperature, weather, week, working day, driving start time, early peak, late peak, start longitude and start latitude, are acquired, and are input into a vehicle running condition prediction model to acquire future running conditions of the tested vehicle within a period of time; according to historical operation data of the tested vehicle, such as the starting charge state of a segment, the starting mileage of the segment, the ending mileage of the segment, whether the information is workday, speed, temperature, weather, road type and the like, an energy consumption prediction model is constructed based on a machine learning algorithm, and the energy consumption requirement of the tested vehicle in a future period is predicted by combining the running space-time electric quantity relation and the future running working condition of the tested vehicle, so that an electric vehicle user can reasonably plan a travel route, and the mileage anxiety is relieved.
In the embodiment, operation detection data of a detected vehicle is acquired through the Internet of vehicles, historical operation data of the detected vehicle is acquired, a vehicle running time-space electric quantity relation model is built based on a Monte Carlo method according to the historical operation data, a running time-space electric quantity relation of the detected vehicle is acquired, external factors influencing running of the detected vehicle are acquired according to the historical operation data, a vehicle running condition prediction model is built based on a KNN algorithm according to the external factors, current external factors of the detected vehicle are acquired, the current external factors are input into the vehicle running condition prediction model to predict future running conditions of the detected vehicle, an energy consumption prediction model is built based on historical operation data, energy consumption requirements of the detected vehicle in a future period are predicted through the energy consumption prediction model in combination with the form time-space electric quantity relation and the future running conditions of the detected vehicle, real-time performance of the prediction data is improved, an individual detected vehicle can be accurately obtained, effective real-time data support can be provided for a user of the electric vehicle, and trip mileage anxiety is relieved.
The step S101 specifically includes: the method comprises the steps of collecting historical operation data of a tested vehicle in a period of time through the Internet of vehicles, wherein the historical operation data comprise a plurality of driving fragment data, and each driving fragment data correspondingly comprises a vehicle unique identifier, a fragment starting time, a fragment ending time, a fragment duration, a starting longitude, a starting latitude, an ending longitude, an ending latitude, a fragment starting state of charge, a fragment ending state of charge, a fragment starting mileage and a fragment ending mileage.
Specifically, historical operation data of the tested vehicle in a period of time, for example, in two years, are collected through the Internet of vehicles, the historical operation data are composed of a plurality of driving fragment data, and each driving fragment data correspondingly comprises information such as a vehicle unique identifier, a fragment starting time, a fragment ending time, a fragment duration, a starting longitude, a starting latitude, an ending longitude, an ending latitude, a fragment starting state of charge, a fragment ending state of charge, a fragment starting mileage, a fragment ending mileage and the like, and the data information of the tested vehicle is obtained through the Internet of vehicles, so that the accuracy and the instantaneity of the data are improved.
The step S102 specifically includes: extracting the date of the starting time of the detected vehicle segment according to a date preset format, and recoding and grouping according to month, week and working day to obtain a date field, a month field, a week field and a working day field; extracting a time point of the starting time of the detected vehicle segment according to a time preset format, and recoding and grouping according to the starting time point, the early peak and the late peak of the driving to obtain a starting time field, an early peak field and a late peak field; the method comprises the steps of collecting the highest speed of a tested vehicle in a segment, calculating the average speed of the segment according to running data, obtaining a highest speed field and an average speed field, calculating the ratio of mileage with the speed exceeding a predicted speed threshold value to the total mileage of the segment according to a preset period, and obtaining a segment high-speed running time ratio field; analyzing longitude and latitude information according to the starting longitude and the starting latitude, acquiring provinces, cities and counties where the fragments start, inquiring weather and temperature information of corresponding regions, wherein the temperature information is the average temperature of the starting time and date of the fragments, and acquiring weather fields and temperature fields; acquiring vehicle registration time and energy storage device types, calculating the number of days of the registration time from the statistical date as the vehicle age, and acquiring a vehicle age field and an energy storage device type field; combining the operation data, calculating the power consumption of the unit mileage under different working conditions, and obtaining a power consumption field; and constructing a vehicle running space-time electric quantity relation model according to the vehicle unique identifier, the month field, the week field, the working day field, the starting time field, the early peak field, the late peak field, the fragment high-speed running time duty ratio field, the weather field, the temperature field, the vehicle age field, the energy storage device type field and the electric quantity field.
Specifically, a date part of a driving section start time of a vehicle to be measured is extracted, taken out in a format of YYYYMMDD for the year, month, day of week, and whether or not to recode for the driving start date, and a date field, a month field, a day of week field, and a day of week field are acquired. And meanwhile, extracting the time point of the starting time of the driving fragment of the tested vehicle, taking out according to the format of HH: MM: SS of the time minute and second, recording the time point as the driving starting time point, and grouping according to the driving starting time point, whether the peak is early or late and whether the peak is late, so as to acquire a starting time field, an early peak field and a late peak field.
Wherein the date preset format is a format of year, month and day, month is 1 to 12, week is 1 to 7, driving start date is 1 of working diary, and non-working diary is 0; the time preset format is a time minute second format, and the running start time point is expressed as 0 to 23; the starting time point of the running is the early peak from 7 to 9, and is marked as 1, otherwise, is marked as 0; the travel start time point is a late peak at 17 to 19 points, and is denoted as 1, otherwise, is denoted as 0. It should be noted that when the rounding operation is performed at the driving start time point, for example, the driving start time is 11:20:22, the corresponding driving start time point is 11.
Because the measured running speeds are different and the power consumption is different, the highest speed of the measured vehicle in the running section is required to be acquired, the average speed of the running section is calculated according to the running time and the mileage, and an average speed field and a highest speed field are acquired; and calculating the ratio of mileage with speed exceeding a preset speed threshold to the total mileage of the fragments according to a preset period, and obtaining the high-speed driving time ratio field of the fragments. For example, if the preset period is two hours and the preset speed threshold is 80km/h, the duty ratio of the mileage of the measured vehicle speed exceeding 80km/h to the total mileage of the section is calculated every two hours.
In addition, under different weather and temperatures, the energy consumption of the detected vehicle is also different, so that the starting longitude and the starting latitude of the detected vehicle segment are required to be obtained in the operation data, the longitude and latitude information of the segment start is analyzed, the weather and temperature information of the province, the city and the county where the segment starts are obtained, and the weather field and the temperature field are obtained through the network, wherein the average value of the highest temperature and the lowest temperature in the starting time period is selected as the temperature.
With the increase of the service life of the detected vehicle and the difference of the types of the energy storage devices, the energy storage conditions of the energy storage devices have certain difference, the time interval between the two needs to be calculated according to the registration time and the current date of the detected vehicle, the time interval is taken as the vehicle age, the types of the energy storage devices are acquired according to the static information of the vehicle, and the vehicle age field and the type field of the energy storage devices are acquired.
After the fields are obtained, the power consumption of the running unit mileage of the tested vehicle under different working conditions is calculated according to the combination of the fragment start state of charge field, the fragment end state of charge field, the fragment start mileage field, the fragment end mileage field, the working day field, the speed field, the temperature field and the like of the tested vehicle, and the power consumption field is obtained.
The vehicle running time-space electric quantity relation model is built by combining the vehicle unique identification and running condition information such as month, week, working day, early peak, late peak, average speed, highest speed, segment high-speed running time duty ratio, weather, temperature, vehicle age, energy storage device type and the like, and the power consumption is combined, so that the running time-space electric quantity relation of the tested vehicle is obtained, and the energy consumption of the tested vehicle is conveniently predicted subsequently.
The method comprises the steps of obtaining external factors influencing the running of the tested vehicle according to historical running data, wherein the external factors specifically comprise: the method specifically comprises the following steps: acquiring the historical running speed of the tested vehicle according to the running data, and labeling the historical running speed to be used as a data set label; according to the historical operation data acquisition time and longitude and latitude coordinate information, calling a geographic position information system and a network application program interface to acquire driving environment data, wherein the driving environment data comprises weather types, road types and temperatures as a first data set; dividing historical operation data according to working days, weeks, running starting time, early peak and late peak to obtain a second data set; and selecting the longitude and latitude of the historical running road condition of the tested vehicle as a third data set.
Specifically, external factors that affect the running of the vehicle under test include weather type, road type, temperature, whether to work day, day of week, running start time, whether to peak early, whether to peak late, longitude and latitude information, and the like. Before a vehicle running condition prediction model is constructed, the external factors are required to be correspondingly preprocessed, firstly, the historical running speed is obtained according to the historical running data of the tested vehicle, and the historical running speed is labeled to be used as a data set label; secondly, according to the acquisition time and longitude and latitude coordinate information of the historical operation data, calling geographic position information and a network application program interface to acquire corresponding running environment data including corresponding weather, road type and temperature, and taking the corresponding running environment data as a first data set; thirdly, grouping historical operation data according to the aspects of whether the working day, the day of the week, the driving starting time, whether the peak is early or late and whether the peak is late to acquire a second data set; and finally, selecting the longitude and latitude of the historical running road condition of the tested vehicle, including the segment start longitude, the segment start latitude, the segment end longitude and the segment end latitude, as a third data set according to the historical running data, so that the data arrangement of the running working conditions in the historical data is realized, and the subsequent construction of a vehicle running working condition prediction model is facilitated.
When the vehicle driving condition prediction model is built based on the KNN algorithm according to external factors, the method specifically comprises the following steps: combining the first data set, the second data set and the third data set to be used as KNN classification characteristics, and dividing the combined data set according to a first preset proportion to obtain a first training set and a first testing set; constructing a KNN classification model based on a KNN algorithm, taking a data set label as an output result of a first training set, training the KNN classification model according to the first training set, testing the trained KNN classification model through a first testing set, and acquiring a vehicle driving condition prediction model after the test is passed; and acquiring the current external factors of the tested vehicle, inputting the current external factors into a vehicle running condition prediction model, and predicting the future running condition of the tested vehicle.
Specifically, after finishing the data of the external factors affecting the running of the tested vehicle, according to the formats of the first data set, the second data set and the third data set, carrying out data set combination, and taking the data set combination as the KNN classification characteristic, according to a first preset proportion, for example, a training set: the method comprises the steps of dividing a combined data set according to a test set=7:3 ratio, obtaining a first training set and a first test set, constructing a KNN classification model based on a KNN algorithm, training the KNN classification model through the first training set by taking a data set label as an output result, testing the KNN classification model through the first test set after training is finished, and obtaining a vehicle driving condition prediction model after the test is passed. After the current external factors of the tested vehicle are obtained, the future running condition of the tested vehicle can be predicted through the vehicle running condition prediction model, the adverse effect on the estimation result caused by unknown future conditions in the traditional prediction method is reduced, corresponding condition predictions can be carried out for different vehicles, and the timeliness of the prediction result is strong.
The step S104 specifically includes: inputting the current external factors of the tested vehicle into a vehicle running condition prediction model to obtain the future running condition of the tested vehicle, wherein the external factors comprise temperature, weather, week, working day, running starting time point, early peak, late peak, starting longitude and starting latitude; acquiring vehicle unique identification, fragment starting charge state, fragment starting mileage, fragment ending mileage, working day, speed, temperature, weather and road type information of a tested vehicle as a data set, randomly dividing the data set according to a second preset proportion, and acquiring a second training set and a second testing set; constructing an initial energy consumption prediction model based on a machine learning algorithm, inputting a second training set to train the initial energy consumption prediction model, and testing the trained initial energy consumption prediction model through a second testing set to obtain an energy consumption prediction model; and predicting the energy consumption requirement of the detected vehicle in a future period of time based on the energy consumption prediction model by combining the future running working condition of the detected vehicle and the running time-space electric quantity relation.
Specifically, when the energy consumption requirement of the tested vehicle is predicted, the running condition of the tested vehicle in a future period is obtained by adopting a vehicle running condition prediction model according to external factors influencing the running of the tested vehicle, such as the regional temperature of the running date of the vehicle, weather, week, working day, running starting time point, whether the peak is early, whether the peak is late, starting longitude and starting latitude, and the like.
According to historical operation data of the vehicle, screening out factors influencing the energy consumption of the vehicle, such as the start-of-segment charge state, the start-of-segment mileage, the end-of-segment mileage, the working day, the speed, the temperature, the weather, the road type and other information, combining the unique identification of the vehicle as a data set, and according to a second preset proportion, such as a training set: test set = 7:3, the data set is partitioned, and a second training set and a second test set are obtained.
The initial energy consumption prediction model is built based on a machine learning algorithm, wherein the machine learning algorithm can be a regression algorithm such as linear regression, logistic regression, polynomial regression and the like, the initial energy consumption prediction model is trained through a second training set, and the trained initial energy consumption prediction model is tested through a second testing set to obtain the energy consumption prediction model.
After the energy consumption prediction model of the tested vehicle is obtained, the energy consumption demand of the tested vehicle in a period of time in the future is predicted by combining the predicted future running working condition and the predicted running time-space electric quantity relation of the tested vehicle, so that a user can reasonably plan travel, and mileage anxiety is relieved.
As shown in fig. 2, there is provided a data-driven-based electric vehicle energy consumption prediction system 20, including: the system comprises a historical operation data acquisition module 21, a space-time electric quantity relation model construction module 22, a future driving condition prediction module 23 and an energy consumption demand prediction module 24, wherein:
A historical operation data acquisition module 21, configured to acquire operation monitoring data of a vehicle under test through the internet of vehicles, and acquire historical operation data of the vehicle under test;
the space-time electric quantity relation model construction module 22 is used for constructing a vehicle running space-time electric quantity relation model based on a Monte Carlo method according to historical operation data, and acquiring a running space-time electric quantity relation of the tested vehicle;
the future running condition prediction module 23 is configured to obtain external factors affecting running of the tested vehicle according to the historical running data, construct a vehicle running condition prediction model based on a KNN algorithm according to the external factors, obtain current external factors of the tested vehicle, input the current external factors into the vehicle running condition prediction model, and predict a future running condition of the tested vehicle;
the energy consumption demand prediction module 24 is configured to construct an energy consumption prediction model based on a machine learning algorithm according to historical operation data, and predict an energy consumption demand of the measured vehicle in a future period of time through the energy consumption prediction model in combination with a running space-time electric quantity relation and a future running condition of the measured vehicle.
In one embodiment, the historical operating data acquisition module 21 is specifically configured to: the method comprises the steps of collecting historical operation data of a tested vehicle in a period of time through the Internet of vehicles, wherein the historical operation data comprise a plurality of driving fragment data, and each driving fragment data correspondingly comprises a vehicle unique identifier, a fragment starting time, a fragment ending time, a fragment duration, a starting longitude, a starting latitude, an ending longitude, an ending latitude, a fragment starting state of charge, a fragment ending state of charge, a fragment starting mileage and a fragment ending mileage.
In one embodiment, the spatiotemporal power relationship model building module 22 is specifically configured to: extracting the date of the starting time of the detected vehicle segment according to a date preset format, and recoding and grouping according to month, week and working day to obtain a date field, a month field, a week field and a working day field; extracting a time point of the starting time of the detected vehicle segment according to a time preset format, and recoding and grouping according to the starting time point, the early peak and the late peak of the driving to obtain a starting time field, an early peak field and a late peak field; the method comprises the steps of collecting the highest speed of a tested vehicle in a segment, calculating the average speed of the segment according to running data, obtaining a highest speed field and an average speed field, calculating the ratio of mileage with the speed exceeding a predicted speed threshold value to the total mileage of the segment according to a preset period, and obtaining a segment high-speed running time ratio field; analyzing longitude and latitude information according to the starting longitude and the starting latitude, acquiring provinces, cities and counties where the fragments start, inquiring weather and temperature information of corresponding regions, wherein the temperature information is the average temperature of the starting time and date of the fragments, and acquiring weather fields and temperature fields; acquiring vehicle registration time and energy storage device types, calculating the number of days of the registration time from the statistical date as the vehicle age, and acquiring a vehicle age field and an energy storage device type field; combining the operation data, calculating the power consumption of the unit mileage under different working conditions, and obtaining a power consumption field; and constructing a vehicle running space-time electric quantity relation model according to the vehicle unique identifier, the month field, the week field, the working day field, the starting time field, the early peak field, the late peak field, the fragment high-speed running time duty ratio field, the weather field, the temperature field, the vehicle age field, the energy storage device type field and the electric quantity field.
In one embodiment, the energy consumption demand prediction module 24 is specifically configured to: inputting the current external factors of the tested vehicle into a vehicle running condition prediction model to obtain the future running condition of the tested vehicle, wherein the external factors comprise temperature, weather, week, working day, running starting time point, early peak, late peak, starting longitude and starting latitude; acquiring vehicle unique identification, fragment starting charge state, fragment starting mileage, fragment ending mileage, working day, speed, temperature, weather and road type information of a tested vehicle as a data set, randomly dividing the data set according to a second preset proportion, and acquiring a second training set and a second testing set; constructing an initial energy consumption prediction model based on a machine learning algorithm, inputting a second training set to train the initial energy consumption prediction model, and testing the trained initial energy consumption prediction model through a second testing set to obtain an energy consumption prediction model; and predicting the energy consumption requirement of the detected vehicle in a future period of time based on the energy consumption prediction model by combining the future running working condition of the detected vehicle and the running time-space electric quantity relation.
In one embodiment, an apparatus is provided, which may be a server, the internal structure of which may be as shown in fig. 3. The device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the device is configured to provide computing and control capabilities. The memory of the device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the device is used for storing configuration templates and can also be used for storing target webpage data. The network interface of the device is used for communicating with an external terminal through a network connection. The computer program, when executed by the processor, implements a data-driven based electric vehicle energy consumption prediction method.
It will be appreciated by persons skilled in the art that the structure shown in fig. 3 is merely a block diagram of a portion of the structure associated with the present inventive arrangements and does not constitute a limitation of the apparatus to which the present inventive arrangements are applied, and that a particular apparatus may include more or less components than those shown in the drawings, or may combine certain components, or have a different arrangement of components.
In one embodiment, a medium may also be provided, the medium storing a computer program comprising program instructions that, when executed by a computer, cause the computer to perform a method as described in the previous embodiment, the computer may be part of the above mentioned data-driven based electric vehicle energy consumption prediction system.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device, or distributed across a network of computing devices, or they may alternatively be implemented in program code executable by computing devices, such that they may be stored on a computer storage medium (ROM/RAM, magnetic or optical disk) for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than what is shown or described herein, or they may be individually manufactured as individual integrated circuit modules, or a plurality of modules or steps in them may be manufactured as a single integrated circuit module. Therefore, the present invention is not limited to any specific combination of hardware and software.
The foregoing is a further detailed description of the invention in connection with specific embodiments, and is not intended to limit the practice of the invention to such descriptions. It will be apparent to those skilled in the art that several simple deductions or substitutions may be made without departing from the spirit of the invention, and these should be considered to be within the scope of the invention.
Claims (8)
1. The method for predicting the energy consumption of the electric vehicle based on data driving is characterized by comprising the following steps of:
acquiring operation monitoring data of a tested vehicle through the Internet of vehicles, and acquiring historical operation data of the tested vehicle;
according to the historical operation data, a vehicle running time-space electric quantity relation model is built based on a Monte Carlo method, and a running time-space electric quantity relation of a tested vehicle is obtained;
obtaining external factors influencing the running of the tested vehicle according to the historical running data, wherein the external factors comprise: acquiring the historical running speed of the tested vehicle according to the historical running data, and labeling the historical running speed as a data set label; calling a geographic position information system and a network application program interface according to the acquisition time and longitude and latitude coordinate information of the historical operation data to acquire driving environment data, wherein the driving environment data comprises weather types, road types and temperatures as a first data set; dividing the historical operation data according to the working day, the week, the driving starting time, the early peak and the late peak to obtain a second data set; selecting the longitude and latitude of the history running road condition of the tested vehicle as a third data set according to the history running data;
Constructing a vehicle running condition prediction model based on a KNN algorithm according to the external factors, acquiring the current external factors of the tested vehicle, inputting the current external factors into the vehicle running condition prediction model, and predicting the future running condition of the tested vehicle, wherein the method comprises the following steps: combining the first data set, the second data set and the third data set to be used as KNN classification characteristics, and dividing the combined data sets according to a first preset proportion to obtain a first training set and a first testing set; constructing a KNN classification model based on a KNN algorithm, taking a data set label as an output result of a first training set, training the KNN classification model according to the first training set, testing the trained KNN classification model through a first testing set, and acquiring a vehicle driving condition prediction model after the test is passed; acquiring the current external factors of the tested vehicle, inputting the current external factors into the vehicle running condition prediction model, and predicting the future running condition of the tested vehicle;
and according to the historical operation data, an energy consumption prediction model is constructed based on a machine learning algorithm, and the energy consumption demand of the tested vehicle in a future period of time is predicted through the energy consumption prediction model by combining the running time-space electric quantity relation and the future running working condition of the tested vehicle.
2. The method for predicting energy consumption of an electric vehicle based on data driving according to claim 1, wherein the collecting operation monitoring data of the vehicle under test through the internet of vehicles, and obtaining historical operation data of the vehicle under test, specifically comprises:
the method comprises the steps of collecting historical operation data of a tested vehicle in a period of time through the Internet of vehicles, wherein the historical operation data comprise a plurality of driving fragment data, and each driving fragment data correspondingly comprises a vehicle unique identifier, a fragment starting time, a fragment ending time, a fragment duration, a starting longitude, a starting latitude, an ending longitude, an ending latitude, a fragment starting state of charge, a fragment ending state of charge, a fragment starting mileage and a fragment ending mileage.
3. The method for predicting energy consumption of an electric vehicle based on data driving according to claim 2, wherein the constructing a model of a vehicle running space-time electric quantity relation based on a monte carlo method according to the historical operation data, and obtaining the running space-time electric quantity relation of the measured vehicle, specifically comprises:
extracting the date of the starting time of the detected vehicle segment according to a date preset format, and recoding and grouping according to month, week and working day to obtain a date field, a month field, a week field and a working day field;
Extracting a time point of the starting time of the detected vehicle segment according to a time preset format, and recoding and grouping according to the starting time point, the early peak and the late peak of the driving to obtain a starting time field, an early peak field and a late peak field;
the method comprises the steps of collecting the highest speed of a tested vehicle in a segment, calculating the average speed of the segment according to running data, obtaining a highest speed field and an average speed field, calculating the ratio of mileage with the speed exceeding a predicted speed threshold value to the total mileage of the segment according to a preset period, and obtaining a segment high-speed running time ratio field;
analyzing longitude and latitude information according to the starting longitude and the starting latitude, acquiring provinces, cities and counties where the fragments start, inquiring weather and temperature information of the corresponding regions, wherein the temperature information is the average temperature of the starting time and date of the fragments, and acquiring weather fields and temperature fields;
acquiring vehicle registration time and energy storage device types, calculating the number of days of the registration time from the current date as the vehicle age, and acquiring a vehicle age field and an energy storage device type field;
combining the operation data, calculating the power consumption of the unit mileage under different working conditions, and obtaining a power consumption field;
And constructing a vehicle running space-time electric quantity relation model according to the vehicle unique identifier, the month field, the week field, the working day field, the starting time field, the early peak field, the late peak field, the fragment high-speed running time duty ratio field, the weather field, the temperature field, the vehicle age field, the energy storage device type field and the power consumption field, and acquiring the running space-time electric quantity relation of the tested vehicle.
4. The data-driven electric vehicle energy consumption prediction method according to claim 3, wherein the date preset format is a format of year, month and day, wherein month is represented by 1 to 12, week is represented by 1 to 7, driving start date is 1 on working diary, and non-working diary is 0;
the time preset format is a time minute second format, wherein a driving start time point is represented as 0 to 23; the starting time point of the running is the early peak when the starting time point is from 7 points to 9 points, and is recorded as 1, otherwise, is recorded as 0; the travel start time point is a late peak at 17 to 19 points, and is denoted as 1, otherwise is denoted as 0.
5. The method for predicting energy consumption of electric vehicle based on data driving of claim 3, wherein the building an energy consumption prediction model based on machine learning algorithm according to the historical operation data, and combining the running space-time electric quantity relation and the future running working condition of the measured vehicle, predicting the energy consumption requirement of the measured vehicle in a future period of time through the energy consumption prediction model specifically comprises:
Inputting the current external factors of the tested vehicle into a vehicle running condition prediction model to obtain the future running condition of the tested vehicle, wherein the external factors comprise temperature, weather, week, working day, running starting time point, early peak, late peak, starting longitude and starting latitude;
acquiring vehicle unique identification, fragment starting charge state, fragment starting mileage, fragment ending mileage, working day, speed, temperature, weather and road type information of a tested vehicle as a data set, randomly dividing the data set according to a second preset proportion, and acquiring a second training set and a second testing set;
constructing an initial energy consumption prediction model based on a machine learning algorithm, inputting the second training set to train the initial energy consumption prediction model, and testing the trained initial energy consumption prediction model through the second testing set to obtain an energy consumption prediction model;
and predicting the energy consumption requirement of the detected vehicle in a future period of time based on the energy consumption prediction model by combining the future running working condition of the detected vehicle and the running time-space electric quantity relation.
6. An electric vehicle energy consumption prediction system based on data driving, comprising:
The historical operation data acquisition module is used for acquiring operation monitoring data of the tested vehicle through the Internet of vehicles and acquiring historical operation data of the tested vehicle;
the space-time electric quantity relation model construction module is used for constructing a vehicle running space-time electric quantity relation model based on a Monte Carlo method according to the historical operation data and obtaining a running space-time electric quantity relation of the tested vehicle;
the future running condition prediction module is used for acquiring external factors influencing the running of the tested vehicle according to the historical running data, and comprises the following steps: acquiring the historical running speed of the tested vehicle according to the historical running data, and labeling the historical running speed as a data set label; calling a geographic position information system and a network application program interface according to the acquisition time and longitude and latitude coordinate information of the historical operation data to acquire driving environment data, wherein the driving environment data comprises weather types, road types and temperatures as a first data set; dividing the historical operation data according to the working day, the week, the driving starting time, the early peak and the late peak to obtain a second data set; selecting the longitude and latitude of the history running road condition of the tested vehicle as a third data set according to the history running data; constructing a vehicle running condition prediction model based on a KNN algorithm according to the external factors, acquiring the current external factors of the tested vehicle, inputting the current external factors into the vehicle running condition prediction model, and predicting the future running condition of the tested vehicle, wherein the method comprises the following steps: combining the first data set, the second data set and the third data set to be used as KNN classification characteristics, and dividing the combined data sets according to a first preset proportion to obtain a first training set and a first testing set; constructing a KNN classification model based on a KNN algorithm, taking a data set label as an output result of a first training set, training the KNN classification model according to the first training set, testing the trained KNN classification model through a first testing set, and acquiring a vehicle driving condition prediction model after the test is passed; acquiring the current external factors of the tested vehicle, inputting the current external factors into the vehicle running condition prediction model, and predicting the future running condition of the tested vehicle;
And the energy consumption demand prediction module is used for constructing an energy consumption prediction model based on a machine learning algorithm according to the historical operation data, and predicting the energy consumption demand of the tested vehicle in a future period of time by combining the running time-space electric quantity relation and the future running working condition of the tested vehicle.
7. An apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
8. A medium having stored thereon a computer program, which when executed by a processor performs the steps of the method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210126508.0A CN114407661B (en) | 2022-02-10 | 2022-02-10 | Electric vehicle energy consumption prediction method, system, equipment and medium based on data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210126508.0A CN114407661B (en) | 2022-02-10 | 2022-02-10 | Electric vehicle energy consumption prediction method, system, equipment and medium based on data driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114407661A CN114407661A (en) | 2022-04-29 |
| CN114407661B true CN114407661B (en) | 2023-11-07 |
Family
ID=81279610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210126508.0A Active CN114407661B (en) | 2022-02-10 | 2022-02-10 | Electric vehicle energy consumption prediction method, system, equipment and medium based on data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114407661B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114919433B (en) * | 2022-05-27 | 2022-12-09 | 深圳先进技术研究院 | Electric vehicle cluster charging and discharging control method, system and related equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102014222007A1 (en) * | 2013-10-31 | 2015-04-30 | Ford Global Technologies, Llc | PHEV power management control with trip-oriented energy consumption planning |
| CN110610260A (en) * | 2019-08-21 | 2019-12-24 | 南京航空航天大学 | Driving energy consumption prediction system, method, storage medium and equipment |
| CN111301426A (en) * | 2020-03-13 | 2020-06-19 | 南通大学 | Method for predicting energy consumption in future driving process based on GRU network model |
| CN111666715A (en) * | 2020-06-05 | 2020-09-15 | 北京理工大学 | Electric automobile energy consumption prediction method and system |
| CN111806240A (en) * | 2020-07-24 | 2020-10-23 | 江淮大众汽车有限公司 | China working condition-based electric automobile driving range prediction method |
| CN112046335A (en) * | 2020-09-09 | 2020-12-08 | 北京航空航天大学 | Method for calculating remaining driving mileage of electric automobile based on driving energy consumption model |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8706416B2 (en) * | 2012-04-03 | 2014-04-22 | Ford Global Technologies, Llc | System and method for determining a vehicle route |
| CN106515478B (en) * | 2016-10-27 | 2017-10-20 | 合肥工业大学 | Electric automobile remaining driving mileage on-line prediction method and device |
-
2022
- 2022-02-10 CN CN202210126508.0A patent/CN114407661B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102014222007A1 (en) * | 2013-10-31 | 2015-04-30 | Ford Global Technologies, Llc | PHEV power management control with trip-oriented energy consumption planning |
| CN110610260A (en) * | 2019-08-21 | 2019-12-24 | 南京航空航天大学 | Driving energy consumption prediction system, method, storage medium and equipment |
| CN111301426A (en) * | 2020-03-13 | 2020-06-19 | 南通大学 | Method for predicting energy consumption in future driving process based on GRU network model |
| CN111666715A (en) * | 2020-06-05 | 2020-09-15 | 北京理工大学 | Electric automobile energy consumption prediction method and system |
| WO2021244632A1 (en) * | 2020-06-05 | 2021-12-09 | 北京理工大学 | Electric automobile energy consumption prediction method and system |
| CN111806240A (en) * | 2020-07-24 | 2020-10-23 | 江淮大众汽车有限公司 | China working condition-based electric automobile driving range prediction method |
| CN112046335A (en) * | 2020-09-09 | 2020-12-08 | 北京航空航天大学 | Method for calculating remaining driving mileage of electric automobile based on driving energy consumption model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114407661A (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tong et al. | A framework for developing driving cycles with on‐road driving data | |
| Wang et al. | A big data approach for smart transportation management on bus network | |
| CN116013087B (en) | Traffic flow statistical method based on urban moving vehicle detection | |
| US20180045526A1 (en) | System and Method for Estimating and Predicting Vehicle Trip Energy Consumption | |
| CN110969861B (en) | Vehicle identification method, device, equipment and computer storage medium | |
| CN114407661B (en) | Electric vehicle energy consumption prediction method, system, equipment and medium based on data driving | |
| Nie et al. | Public curb parking demand estimation with poi distribution | |
| CN111723835A (en) | Vehicle movement track distinguishing method and device and electronic equipment | |
| CN112509317A (en) | Bus real-time arrival prediction method, device and equipment based on machine learning algorithm | |
| CN111091215A (en) | Vehicle identification method and device, computer equipment and storage medium | |
| Karimpour et al. | Estimating pedestrian delay at signalized intersections using high-resolution event-based data: a finite mixture modeling method | |
| Xing et al. | Operation Energy Consumption Estimation Method of Electric Bus Based on CNN Time Series Prediction | |
| Erhardt et al. | A big data mashing tool for measuring transit system performance | |
| Kim et al. | Data-driven parking decisions: Proposal of parking availability prediction model | |
| Duan et al. | Multitype highway mobility analytics for efficient learning model design: A case of station traffic prediction | |
| Wang et al. | Short-term travel time estimation and prediction for long freeway corridor using NN and regression | |
| Shen et al. | Real-time road traffic fusion and prediction with GPS and fixed-sensor data | |
| Elhattab et al. | Leveraging real-world data sets for qoe enhancement in public electric vehicles charging networks | |
| Xia et al. | Link-based traffic estimation and simulation for road networks using electronic registration identification data | |
| CN111680888B (en) | Method for determining road network capacity based on RFID data | |
| Banik et al. | Mapping of bus travel time to traffic stream travel time using econometric modeling | |
| Taniarza et al. | Anomalous trajectory detection from taxi GPS traces using combination of iBAT and DTW | |
| CN114611622B (en) | Method for identifying urban-crossing commute crowd by utilizing mobile phone data | |
| Golze et al. | Impact analysis of accidents on the traffic flow based on massive floating car data | |
| Chen et al. | Stay of interest: A dynamic spatiotemporal stay behavior perception method for private car users |
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 |