A charging facility planning system and method based on intelligent transportation system

Abstract

The present invention discloses a charging facility planning system and method based on a smart transportation system, and relates to the field of electric vehicle charging station planning. The system comprises: a cloud monitoring platform, a vehicle flow monitoring subsystem, a charging station management subsystem, a vehicle data processing subsystem and a distribution network data acquisition subsystem; the cloud monitoring platform: receives the running status of electric vehicles in real time, predicts the short-term charging load of electric vehicles, and then combines the relevant data of charging stations and distribution networks and the growth data of electric vehicles to predict the charging demand of electric vehicles at each node of the road network in the planned year, and then makes an optimal charging station layout plan for the planning area with the goal of minimizing the fluctuation of charging load and optimizing the power flow of the distribution network; the present invention can accurately predict the load of regional electric vehicle charging facilities.

Description

Technical Field

[0001] The present invention belongs to the field of electric vehicle charging station planning, and in particular relates to a charging facility planning system and method based on an intelligent transportation system. Background Art

[0002] With the energy crisis and global warming, in order to reduce the use of fossil fuels and reduce automobile exhaust emissions, electric vehicles driven by electricity have received great attention from countries around the world. Electric vehicles can not only save fossil fuels, but also do not produce exhaust gas like fuel vehicles during driving, which can achieve "zero emissions" and reduce the pollution of automobile exhaust to the environment. Therefore, the development of electric vehicles is the development trend of future automobiles, and countries around the world have also successively issued relevant policies to promote the development of electric vehicles.

[0003] However, with the rapid development of electric vehicles, related problems caused by the large-scale development of electric vehicles have also followed. Due to the rapid increase in the number of electric vehicles, it is urgent to build a large number of charging facilities to support the charging needs of electric vehicles. However, due to the mobility of electric vehicles, the charging load of electric vehicles is random in both time and space. A large number of electric vehicle charging loads are connected to the power grid in an unordered manner, which inevitably leads to "peaks on top of peaks" in the distribution network load, causing a huge impact on the distribution network. In this context, the planning of charging stations must not only meet the charging needs of electric vehicle users, but also meet the stable and economic operation of the distribution network. Therefore, how to reasonably and effectively plan electric vehicle charging stations will be an effective way to alleviate the "peaks on top of peaks" in the distribution network and promote the development of the electric vehicle industry. Summary of the invention

[0004] The main technical problem solved by the present invention is to solve the technical problem that the power consumption model of electric vehicles in mountainous cities is missing and the charging load of electric vehicles in mountainous cities cannot be predicted in a refined time and space manner.

[0005] The technical solution adopted by the present invention is as follows:

[0006] The mountain city charging station planning system based on electric vehicle charging demand prediction includes a cloud monitoring platform, a vehicle flow monitoring subsystem, a charging station management subsystem, an on-board data processing subsystem and a distribution network data acquisition subsystem:

[0007] The vehicle flow monitoring subsystem is used to collect the vehicle flow data at each node in the road network at different time points in a day, process the vehicle flow data at each node, predict the fast charging prediction data of electric vehicles with fast charging demand, and upload the electric vehicle fast charging prediction data to the cloud monitoring platform;

[0008] The charging station management subsystem is used to collect the charging pile usage information of the charging piles in the charging station, and the charging pile usage information includes: the annual average charging volume of various types of vehicles, the time when the electric vehicle is connected to the charging pile, the time when the electric vehicle leaves the charging pile, and the charging efficiency of the charging pile, and upload the processed charging pile usage information to the cloud monitoring platform;

[0009] The vehicle-mounted data processing subsystem is used to monitor the remaining power data of the electric vehicle in real time and receive the location information of the charging station and the road network data. When a charging demand is generated, the charging station is searched for charging with the minimum power consumption as the goal and the power consumed in the process is calculated. The time when the charging demand is generated and the estimated time to arrive at the charging station, the location data of the found charging station, and the power consumption data during driving are uploaded to the cloud monitoring platform;

[0010] The distribution network data acquisition subsystem is used to collect distribution network load changes, combine the distribution network historical load data, predict the distribution network daily load curve for the planned year, obtain the distribution network daily load prediction curve for the planned year, and upload the distribution network daily load prediction curve for the planned year to the cloud monitoring platform;

[0011] The cloud monitoring platform is used to receive in real time the time when charging demand is generated, the estimated time of arrival at the charging station, the location data of the charging station found, and the power consumption data during driving, which are sent by the on-board data processing subsystem; receive the charging pile usage information sent by the charging station management subsystem; receive the electric vehicle fast charging prediction data sent by the vehicle flow monitoring subsystem, receive the distribution network daily load prediction curve for the planned year sent by the distribution network data acquisition subsystem, and predict the short-term charging load of electric vehicles based on the mountain city charging station planning method, and then combine the charging station, distribution network related data and electric vehicle growth data to predict the charging demand of electric vehicles at each node of the road network in the planned year, and then make the optimal charging station layout plan for the planning area with the goal of minimizing the charging load fluctuation and optimizing the distribution network flow.

[0012] Optionally, the vehicle-mounted data processing subsystem includes a driving data acquisition module, a road network data acquisition module, a driving path control module, and a vehicle-mounted communication module;

[0013] The driving data acquisition module is used to collect vehicle SOC information, air conditioning operation status, vehicle position, and vehicle speed information with a period of Δt;

[0014] The road network data collection module is used to collect the location information of the vehicle in the road network, the location information of the charging station in the road network, the congestion situation of each road in the road network and the road slope information in real time;

[0015] The driving path control module is used to determine whether the electric vehicle has a charging demand based on the vehicle battery remaining power information collected by the driving data collection module; if the electric vehicle has a charging demand, the power consumption and time required to reach each charging station are calculated based on the charging station location information and road network road condition information, and the charging station and path with the minimum power consumption are used as the target charging station and path;

[0016] The vehicle-mounted communication module is used to upload the data collected and processed by the driving data collection module, the road network data collection module, and the driving path control module to the cloud monitoring platform.

[0017] Optionally, the cloud monitoring platform includes an electric vehicle short-term load forecasting module, a charging station long-term planning module, a cloud platform communication module, and a cloud platform database;

[0018] The electric vehicle short-term load prediction module is used to predict the electric vehicle charging load based on the real-time collected electric vehicle driving data and road network road data, and send the predicted data to the user terminal to achieve the purpose of off-peak charging for electric vehicle users;

[0019] The charging station long-term planning module is used to obtain the number of electric vehicles in the planned year based on vehicle data and the growth rate of electric vehicles; obtain the number of electric vehicles with charging demand at each road network node and each time node based on vehicle driving data, and obtain the electric vehicle charging decision based on the on-board data processing subsystem, so as to calculate the charging load of each charging station; predict the basic load data of the distribution network in the planned year based on the historical load data of the distribution network, and obtain the total load data of the distribution network in the planned year in combination with the charging load data, with the goal of minimizing the fluctuation of charging load and the optimal power flow of the distribution network, and optimize the optimal layout plan of the charging station;

[0020] The cloud platform communication module is used to realize data interaction between the cloud monitoring platform and the vehicle flow monitoring subsystem, the vehicle data processing subsystem, the charging station management subsystem, and the distribution network data acquisition subsystem;

[0021] The cloud platform database is used to retain data collected and processed by the vehicle flow monitoring subsystem, the vehicle data processing subsystem, the charging station management subsystem, and the distribution network data acquisition subsystem for short-term charging load prediction and long-term charging station planning.

[0022] Optionally, the charging station management subsystem includes: a charging station communication module, a charging station database and a charging station data acquisition module;

[0023] The charging station data acquisition module is used to acquire the charging pile usage information of the charging piles in the charging station; the charging pile usage information includes: the annual average total charging amount of various vehicle types, the time when the electric vehicle accesses the charging pile, the time when the electric vehicle leaves the charging pile, the charging efficiency of the charging pile, and processes the charging pile usage information;

[0024] The charging station communication module is used to upload the processed charging pile usage information to the cloud monitoring platform;

[0025] The charging station database is used to store the charging pile usage information collected by the charging station data acquisition module and the processed charging pile usage information.

[0026] Optionally, the distribution network data acquisition subsystem includes: a distribution network communication module, a distribution network data acquisition module, a distribution network database, and a distribution network data processing and control module;

[0027] The distribution network data acquisition module is used to acquire the load change of the distribution network;

[0028] The distribution network data processing and control module is used to predict the daily load curve of the distribution network in the planned year based on the load change of the distribution network and the historical load of the distribution network, and obtain the daily load prediction curve of the distribution network in the planned year;

[0029] The distribution network database is used to store the load change of the distribution network and the daily load prediction curve of the distribution network in the planned year;

[0030] The distribution network communication module is used to send the daily load prediction curve of the distribution network in the planned year to the cloud monitoring platform.

[0031] Optionally, it further includes a number of first cameras installed in the vehicle, a number of second cameras installed in the vehicle, and a number of video monitors installed at road intersections; the first cameras are communicatively connected to the in-vehicle data processing subsystem through the CAN bus, and the second cameras are communicatively connected to the in-vehicle data processing subsystem through the CAN bus; the video monitors are communicatively connected to the traffic flow monitoring subsystem through 5G communication technology;

[0032] The first camera is used to acquire the historical data of the owner's expression, and the first camera is installed on the triangular pillar of the vehicle; the second camera is used for the historical data of the owner's head angle, and the second camera is installed on the instrument panel assembly of the vehicle; the video monitor is used to collect the traffic video data on the road;

[0033] The vehicle-mounted data processing subsystem is also used to obtain several odometer remaining power data in the vehicle, several owner's expression history data sent by the first cameras, and several owner's head angle history data sent by the first cameras, and send the owner's expression history data, the owner's head angle history data and the odometer remaining power data to the cloud monitoring platform.

[0034] In addition, to achieve the above purpose, the present invention also provides a charging facility planning method based on a smart transportation system, the method comprising the following steps:

[0035] Step S10, select several nodes from the road network as charging station equipment selection nodes, predict the number of charging stations to be planned based on the average annual total amount of electric vehicle charging and the planned annual number of electric vehicles, predict the charging demand of electric vehicles in the planned year based on the road network node traffic flow monitoring and the planned annual number of electric vehicles, select the charging station with the lowest power consumption for charging, and make the optimal layout plan of electric vehicle charging stations with the goal of minimizing the daily load fluctuation of the distribution network to alleviate the load on the power grid;

[0036] Step S20, based on the acquired data related to electric vehicles, charging stations, and distribution networks, an optimal electric vehicle charging station planning model is constructed with the minimum grid daily load variance fluctuation as the planning target; the electric vehicle charging station planning includes the layout location of the electric vehicle charging station and the power and number of charging piles planned for each station;

[0037] Step S30, predict the number of charging stations to be planned based on the forecast of the number of electric vehicles in the planned year and the annual average charging volume of each type of electric vehicles; monitor the traffic volume of each node in each time period based on the candidate charging station nodes pre-set in the road network, and make the daily charging demand of each road network node in the planned year in combination with the forecast of the number of electric vehicles; predict the time and place of access to the charging station based on the time and place when the electric vehicles generate the charging demand, and make the load forecast of the charging station based on this; predict the basic load of the power grid in the planned year based on the historical load data of the distribution network, and predict the load of the distribution network in the planned year in combination with the charging load forecast curve of the charging station;

[0038] Step S40, solving the optimal solution of the electric vehicle planning model according to the constraint conditions of the electric vehicle charging station planning model; determining the layout location and capacity of the charging station according to the optimal solution under the conditions.

[0039] Optionally, step S10 is specifically:

[0040] Step S101, by monitoring the vehicle flow Nv(t,i) at different time points of each node in the current road network, and adding a correction coefficient according to the vehicle growth rate and the electric vehicle penetration rate, the number of electric vehicles Ne(t,i)′ with charging demand at each node in the planned road network at each time point is predicted, and the constructed electric vehicle charging demand prediction model is:

[0041]

[0042]

[0043] Among them, Ne(t,i)′ is the number of electric vehicles with charging demand at the i node of the road network at time t in the planning year, Nv(t,i) is the traffic volume at the i node of the road network at time t in the current year, p is the average growth rate of vehicles this year, and N evc is the number of electric vehicles that need charging, N ev is the number of electric vehicles; N v is the total number of cars; r is the correction coefficient, L i-j is the distance between any two road network nodes, ΔT is the time interval for monitoring vehicle flow, and v is the vehicle speed;

[0044] Step S102: After predicting the electric vehicles with charging needs according to step S101, the electric vehicles select the charging station with the lowest power consumption during driving for charging according to the power consumption model. Considering the influence of the mountainous city terrain characteristics on the power consumption of the electric vehicles, the power consumption model is:

[0045]

[0046] Among them, E o,d is the power consumption from the departure point to the destination, X is the path from the departure point to the destination, L i,j is the distance between two adjacent nodes in the path, H i,j is the altitude difference between two adjacent nodes in the path, β is the average mileage power consumption of electric vehicles on flat ground, and α i,j is the climbing coefficient of the electric vehicle when it travels between nodes i and j, and η is the energy recovery efficiency of the electric vehicle;

[0047] Step S103, according to the charging demand prediction and power consumption model constructed in steps S101 and S102, after the electric vehicle generates charging demand and selects the optimal charging station, the time model of the electric vehicle charging load connecting to the charging station is:

[0048]

[0049] Among them, t 0 The time when charging demand is generated for electric vehicles, t 1 is the time when the electric vehicle is connected to the charging station, V 0 is the average speed of electric vehicles;

[0050] Step S104, based on the electric vehicle charging load prediction model constructed in steps S101, S102, and S103.

[0051] Optionally, step S104 is specifically:

[0052] Step S1041: The electric vehicle battery cannot be overcharged or over-discharged, and the constraints are:

[0053]

[0054] in, The minimum amount of electricity required to charge an electric vehicle. is the current power of the electric vehicle, Charge electric vehicles to the highest capacity;

[0055] Step S1042: The distance between the electric vehicle charging station and the charging demand point cannot exceed the electric vehicle's cruising range, and the constraints are:

[0056] 0≤L o,d (t)≤M i (t)

[0057] Among them, L o,d (t) is the distance from the charging demand point to the charging station of the electric vehicle, M i (t) is the range of the electric vehicle when charging demand occurs.

[0058] Optionally, after determining the layout location and capacity of the charging station in step S40, the step further includes:

[0059] Step S50, determining the number of electric vehicle charging stations to be built, and the determination model is:

[0060]

[0061] Among them, N sta is the number of charging stations to be planned, E ev is the total annual charging volume of electric vehicles, N ev is the number of electric vehicles in the planned year, t z is the average daily usage hours of the charging pile, p z is the charging power of the charging pile, n z The average number of charging piles that need to be planned for each station.

[0062] Optionally, in step S1011, the number of electric vehicles N ev The specific steps of obtaining include:

[0063] Collecting the traffic video data on the road according to the video surveillance of the road intersection;

[0064] The traffic video data is monitored in real time using the yolo v4 algorithm, and the color and length of the license plate number of the electric vehicle are identified according to the image recognition algorithm to determine whether the vehicle is an electric vehicle, thereby determining the number of electric vehicles on the road;

[0065] The total number of cars N v The specific steps of obtaining include:

[0066] Collecting the traffic video data on the road according to the video surveillance of the road intersection;

[0067] The traffic video data is monitored in real time using the yolo v4 algorithm, and the license plates of cars are identified according to the image recognition algorithm, thereby determining the total number of cars on the road;

[0068] The number of electric vehicles with charging demand N evc The specific steps of obtaining include:

[0069] Collecting the traffic video data on the road according to the video surveillance of the road intersection;

[0070] The traffic video data is read to obtain the facial expression data and head angle data of the vehicle owner traveling on the monitored road;

[0071] The owner's facial expression data and the owner's head angle data are input into the vehicle remaining power model to obtain the number of electric vehicles that need to be charged;

[0072] The specific steps of training the vehicle remaining power model are:

[0073] The vehicle-mounted data acquisition control subsystem obtains the owner's facial expression history data collected by the first camera in the vehicle, the owner's head angle history data collected by the second camera, and the odometer remaining power data;

[0074] The owner's facial expression history data, the owner's head angle history data and the odometer remaining power data are processed through time series, and then the processed owner's facial expression history data, the owner's head angle history data and the odometer remaining power data are input into the BP neural network for training to calculate the vehicle remaining power model.

[0075] The beneficial effects of the present invention are as follows:

[0076] 1. The present invention predicts the charging load of regional charging stations based on a method based on data rules, and introduces a model of electric vehicle power consumption in mountainous cities to make a refined time-space prediction of the charging load of electric vehicles in mountainous cities, thereby planning charging stations.

[0077] 2. The present invention can accurately predict the load of regional electric vehicle charging facilities, providing a basis for studying the impact of the load of electric vehicle charging facilities on the power grid, and also providing a basis for the planning of electric vehicle charging facilities.

[0078] 3. The present invention conducts comprehensive data mining on various factors that can affect the charging load of electric vehicles, and quantitatively analyzes the impact of various factors on the charging load of electric vehicles, so that the electric vehicle charging load prediction model of the method of the present invention is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the proportional relationship of the various components in the drawings of this specification does not represent the proportional relationship in actual material selection and design, which is only a schematic diagram of the structure or position, wherein:

[0080] Figure 1 It is an architecture diagram of the electric vehicle charging station planning system of the present invention;

[0081] Figure 2 It is a flow chart of charging facility planning based on the intelligent transportation system of the present invention. DETAILED DESCRIPTION

[0082] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention, that is, the embodiments described are only part of the embodiments of the present invention, rather than all of the embodiments.

[0083] Example 1

[0084] like Figure 1 As shown, a mountain city charging station planning system based on electric vehicle charging demand prediction includes a cloud monitoring platform, a vehicle flow monitoring subsystem, a charging station management subsystem, an on-board data processing subsystem, and a distribution network data acquisition subsystem:

[0085] The vehicle flow monitoring subsystem is used to collect the vehicle flow data at each node in the road network at different time points in a day, process the vehicle flow data at each node, predict the fast charging prediction data of electric vehicles with fast charging demand, and upload the electric vehicle fast charging prediction data to the cloud monitoring platform;

[0086] The charging station management subsystem is used to collect the charging pile usage information of the charging piles in the charging station, and the charging pile usage information includes: the annual average charging volume of various types of vehicles, the time when the electric vehicle is connected to the charging pile, the time when the electric vehicle leaves the charging pile, and the charging efficiency of the charging pile, and upload the processed charging pile usage information to the cloud monitoring platform;

[0087] The vehicle-mounted data processing subsystem is used to monitor the remaining power data of the electric vehicle in real time and receive the location information of the charging station and the road network data. When a charging demand is generated, the charging station is searched for charging with the minimum power consumption as the goal and the power consumed in the process is calculated. The time when the charging demand is generated and the estimated time to arrive at the charging station, the location data of the found charging station, and the power consumption data during driving are uploaded to the cloud monitoring platform;

[0088] The distribution network data acquisition subsystem is used to collect distribution network load changes, combine the distribution network historical load data, predict the distribution network daily load curve for the planned year, obtain the distribution network daily load prediction curve for the planned year, and upload the distribution network daily load prediction curve for the planned year to the cloud monitoring platform;

[0089] The cloud monitoring platform is used to receive in real time the time when charging demand is generated, the estimated time of arrival at the charging station, the location data of the charging station found, and the power consumption data during driving, which are sent by the on-board data processing subsystem; receive the charging pile usage information sent by the charging station management subsystem; receive the electric vehicle fast charging prediction data sent by the vehicle flow monitoring subsystem, receive the distribution network daily load prediction curve for the planned year sent by the distribution network data acquisition subsystem, and predict the short-term charging load of electric vehicles based on the mountain city charging station planning method, and then combine the charging station, distribution network related data and electric vehicle growth data to predict the charging demand of electric vehicles at each node of the road network in the planned year, and then make the optimal charging station layout plan for the planning area with the goal of minimizing the charging load fluctuation and optimizing the distribution network flow.

[0090] Furthermore, the cloud monitoring platform includes an electric vehicle short-term load forecasting module, a charging station long-term planning module, a cloud platform communication module, and a cloud platform database;

[0091] The electric vehicle short-term load prediction module is used to predict the electric vehicle charging load based on the real-time collected electric vehicle driving data and road network road data, and send the predicted data to the user terminal to achieve the purpose of off-peak charging for electric vehicle users;

[0092] The charging station long-term planning module is used to obtain the number of electric vehicles in the planned year based on vehicle data and the growth rate of electric vehicles; obtain the number of electric vehicles with charging demand at each road network node and each time node based on vehicle driving data, and obtain the electric vehicle charging decision based on the on-board data processing subsystem, so as to calculate the charging load of each charging station; predict the basic load data of the distribution network in the planned year based on the historical load data of the distribution network, and obtain the total load data of the distribution network in the planned year in combination with the charging load data, with the goal of minimizing the fluctuation of charging load and the optimal power flow of the distribution network, and optimize the optimal layout plan of the charging station;

[0093] The cloud platform communication module is used to realize data interaction between the cloud monitoring platform and the vehicle flow monitoring subsystem, the vehicle data processing subsystem, the charging station management subsystem, and the distribution network data acquisition subsystem;

[0094] The cloud platform database is used to retain data collected and processed by the vehicle flow monitoring subsystem, the vehicle data processing subsystem, the charging station management subsystem, and the distribution network data acquisition subsystem for short-term charging load prediction and long-term charging station planning.

[0095] Furthermore, the vehicle-mounted data processing subsystem includes a driving data acquisition module, a road network data acquisition module, a driving path control module, and a vehicle-mounted communication module;

[0096] The driving data acquisition module is used to collect vehicle SOC information, air conditioning operation status, vehicle position, and vehicle speed information with a period of Δt;

[0097] The road network data collection module is used to collect the location information of the vehicle in the road network, the location information of the charging station in the road network, the congestion situation of each road in the road network and the road slope information in real time;

[0098] The driving path control module is used to determine whether the electric vehicle has a charging demand based on the vehicle battery remaining power information collected by the driving data collection module; if the electric vehicle has a charging demand, the power consumption and time required to reach each charging station are calculated based on the charging station location information and road network road condition information, and the charging station and path with the minimum power consumption are used as the target charging station and path;

[0099] The vehicle-mounted communication module is used to use the 5G network to upload the data collected and processed by the driving data acquisition module, the road network data acquisition module, and the driving path control module to the cloud monitoring platform.

[0100] Further, the charging station management subsystem includes: a charging station communication module, a charging station database and a charging station data acquisition module;

[0101] The charging station data acquisition module is used to collect the charging pile usage information of the charging piles in the charging station; the charging pile usage information includes: the annual average total charging amount of various vehicle types, the time when the electric vehicle accesses the charging pile, the time when the electric vehicle leaves the charging pile, the charging efficiency of the charging pile, and processes the charging pile usage information;

[0102] The charging station communication module is used to upload the processed charging pile usage information to the cloud monitoring platform;

[0103] The charging station database is used to store the charging pile usage information collected by the charging station data acquisition module and the processed charging pile usage information.

[0104] Furthermore, the distribution network data acquisition subsystem includes: a distribution network communication module, a distribution network data acquisition module, a distribution network database, and a distribution network data processing and control module;

[0105] The distribution network data acquisition module is used to collect the load changes of the distribution network;

[0106] The distribution network data processing and control module is used to predict the daily load curve of the distribution network in the planned year based on the load changes of the distribution network and the historical load of the distribution network, and obtain the daily load prediction curve of the distribution network in the planned year;

[0107] The distribution network database is used to store the load changes of the distribution network and the daily load prediction curve of the distribution network in the planned year;

[0108] The distribution network communication module is used to send the daily load prediction curve of the distribution network in the planned year to the cloud monitoring platform.

[0109] The charging facility planning system based on the intelligent transportation system further includes a number of first cameras installed in the vehicle, a number of second cameras installed in the vehicle, and a number of video monitors installed at road intersections; the first cameras are communicatively connected to the in-vehicle data processing subsystem through the CAN bus, and the second cameras are communicatively connected to the in-vehicle data processing subsystem through the CAN bus; the video monitors are communicatively connected to the vehicle flow monitoring subsystem through 5G communication technology;

[0110] The first camera is used to obtain the historical data of the owner's expression, and the first camera is installed on the triangular pillar of the vehicle; the second camera is used for the historical data of the owner's head angle, and the second camera is installed on the instrument panel assembly of the vehicle; the video monitor is used to collect the traffic video data on the road;

[0111] The vehicle-mounted data processing subsystem is also used to obtain several odometer remaining power data in the vehicle, several owner's expression history data sent by the first cameras, and several owner's head angle history data sent by the first cameras, and send the owner's expression history data, the owner's head angle history data and the odometer remaining power data to the cloud monitoring platform.

[0112] Combination Figure 2 The charging facility planning method based on the intelligent transportation system includes the following steps:

[0113] Step S10, select several nodes from the road network as charging station equipment selection nodes, predict the number of charging stations to be planned based on the average annual total amount of electric vehicle charging and the planned annual number of electric vehicles, predict the charging demand of electric vehicles in the planned year based on the road network node traffic flow monitoring and the planned annual number of electric vehicles, select the charging station with the lowest power consumption for charging, and make the optimal layout plan of electric vehicle charging stations with the goal of minimizing the daily load fluctuation of the distribution network to alleviate the load on the power grid;

[0114] Step S20, based on the acquired data related to electric vehicles, charging stations, and distribution networks, an optimal electric vehicle charging station planning model is constructed with the minimum grid daily load variance fluctuation as the planning target; the electric vehicle charging station planning includes the layout location of the electric vehicle charging station and the power and number of charging piles planned for each station;

[0115] Step S30, predict the number of charging stations to be planned based on the forecast of the number of electric vehicles in the planned year and the annual average charging volume of each type of electric vehicles; monitor the traffic volume of each node in each time period based on the candidate charging station nodes pre-set in the road network, and make the daily charging demand of each road network node in the planned year in combination with the forecast of the number of electric vehicles; predict the time and place of access to the charging station based on the time and place when the electric vehicles generate the charging demand, and make the load forecast of the charging station based on this; predict the basic load of the power grid in the planned year based on the historical load data of the distribution network, and predict the load of the distribution network in the planned year in combination with the charging load forecast curve of the charging station;

[0116] Step S40, solving the optimal solution of the electric vehicle planning model according to the constraint conditions of the electric vehicle charging station planning model; determining the layout location and capacity of the charging station according to the optimal solution under the conditions.

[0117] The present invention is based on a charging facility planning method for a smart transportation system, and the steps are as follows: Step S101, firstly, the total number of electric vehicles in the planning area in the planning year is calculated according to the automobile growth rate and electric vehicle penetration rate in previous years, and the number of electric vehicle charging stations that need to be planned is predicted according to the annual average total amount of electric vehicle charging;

[0118]

[0119] Among them, N sta is the number of charging stations to be planned, E ev is the total annual charging volume of electric vehicles, N ev is the number of electric vehicles in the planned year, t z is the average daily usage hours of the charging pile, p z is the charging power of the charging pile, n z The average number of charging piles that need to be planned for each station.

[0120] Step S102, determining whether the number of existing charging stations in the planning area can meet the charging demand of electric vehicles in the planned year, if yes, proceeding to step S109, if not, proceeding to step S103;

[0121] Step S103, now the site selection planning of the electric vehicle charging station is carried out, a node is selected at every distance in the road network as a candidate node for the site selection of the charging station, and all the candidate road network nodes belong to the set X;

[0122] Step S104, the electric vehicle charging station planning method based on vehicle flow monitoring predicts the number of electric vehicles in the planning area in the planning year according to the electric vehicle growth rate, and predicts the number of new charging stations that need to be built in the planning year in combination with the collected annual charging totals of various types of electric vehicles and the charging pile power settings; predicts the number of electric vehicles with charging needs at different time points at each road network node in the planning year according to the vehicle flow data obtained by the vehicle flow monitoring subsystem and the electric vehicle growth rate, and then predicts the charging load of each charging station under different planning schemes in combination with the charging path data obtained by the vehicle data processing subsystem; obtains the distribution network load forecast data for the planning year under different planning schemes according to the basic load data of the distribution network in each region in the planning year predicted by the distribution network data acquisition subsystem and the electric vehicle charging load data, and uses an intelligent algorithm to obtain the optimal planning layout with the goal of minimizing the charging load fluctuation and the optimal power flow of the distribution network;

[0123] Step S1041, monitoring the traffic flow at each road network node at regular intervals in the current year to obtain a traffic flow curve of each node for one day, continuously monitoring for multiple days, clustering the traffic flow data, and obtaining a regular daily traffic flow data curve of each road network node, which is used to predict the traffic flow data of each road network node in the planning year;

[0124] Step S1042, by monitoring the vehicle flow Nv(t,i) at different time points of each node in the current road network, and adding a correction coefficient according to the vehicle growth rate and the electric vehicle penetration rate, the number of electric vehicles Ne(t,i)′ with charging demand at each node in the planned road network at each time point is predicted, and the constructed electric vehicle charging demand prediction model is:

[0125]

[0126]

[0127] Among them, Ne(t,i)′ is the number of electric vehicles with charging demand at the i node of the road network at time t in the planning year, Nv(t,i) is the traffic volume at the i node of the road network at time t in the current year, p is the average growth rate of vehicles this year, and N evc is the number of electric vehicles that need charging, N ev is the number of electric vehicles; N v is the total number of cars; r is the correction coefficient, L i-j is the distance between any two road network nodes, ΔT is the time interval for monitoring vehicle flow, and v is the vehicle speed;

[0128] In order to avoid detecting the same vehicle multiple times when monitoring traffic flow data, which leads to repeated calculation of some vehicles and errors in charging demand prediction, a correction coefficient is introduced. Combined with the driving speed of the electric vehicle, the number of road network nodes that the vehicle will pass through within the traffic flow monitoring time interval ΔT is calculated, that is, the number of times the vehicle will be repeatedly calculated by the charging demand prediction module. The correction coefficient is brought into the calculation to make the charging demand prediction more accurate.

[0129] The number of electric vehicles N ev The specific steps of obtaining include:

[0130] Collecting the traffic video data on the road according to the video surveillance of the road intersection;

[0131] The traffic video data is monitored in real time using the yolo v4 algorithm, and the color and length of the license plate number of the electric vehicle are identified according to the image recognition algorithm to determine whether the vehicle is an electric vehicle, thereby determining the number of electric vehicles on the road;

[0132] The total number of cars N v The specific steps of obtaining include:

[0133] Collecting the traffic video data on the road according to the video surveillance of the road intersection;

[0134] The traffic video data is monitored in real time using the yolo v4 algorithm, and the license plates of cars are identified according to the image recognition algorithm, thereby determining the total number of cars on the road;

[0135] The number of electric vehicles with charging demand N evc The specific steps of obtaining include:

[0136] Collecting the traffic video data on the road according to the video surveillance of the road intersection;

[0137] The traffic video data is read to obtain the facial expression data and head angle data of the vehicle owner traveling on the monitored road;

[0138] The owner's facial expression data and the owner's head angle data are input into the vehicle remaining power model to obtain the number of electric vehicles that need to be charged;

[0139] The specific steps of training the vehicle remaining power model are:

[0140] The vehicle-mounted data acquisition control subsystem obtains the owner's facial expression history data collected by the first camera in the vehicle, the owner's head angle history data collected by the second camera, and the odometer remaining power data;

[0141] The owner's facial expression history data, the owner's head angle history data and the odometer remaining power data are processed through time series, and then the processed owner's facial expression history data, the owner's head angle history data and the odometer remaining power data are input into the BP neural network for training to calculate the vehicle remaining power model.

[0142] Step S105, among the selected road network nodes, according to the predicted number of electric vehicle charging stations to be planned, randomly select an equal number of nodes from the candidate nodes as the initial values ​​for charging station planning;

[0143] Step S106, when the initial location of the charging station is selected, a cluster prediction is performed on the charging load of the electric vehicle, and combined with the basic load of the distribution network predicted by the distribution network data acquisition subsystem, the overall load of the distribution network is predicted to see whether the load fluctuation is too large. If the load fluctuation is large, it means that the site selection is unreasonable and a new site selection is required. The distribution network load is predicted again, and the optimal charging station site with the smallest load fluctuation is selected through multiple planning;

[0144] Step S1061, after the vehicle flow monitoring subsystem and the vehicle data processing subsystem detect that the electric vehicle has a charging demand and record the time, location and remaining power of the electric vehicle, the vehicle data processing subsystem selects the charging station with the lowest power consumption from the charging demand generation point to the charging station for charging, and the vehicle data processing subsystem predicts the time to arrive at the charging station, the remaining power, and the expected departure time and transmits the data to the cloud monitoring platform. The power consumption model is:

[0145]

[0146] Among them, E o,d is the power consumption from the departure point to the destination, X is the path from the departure point to the destination, L i,j is the distance between two adjacent nodes in the path, H i,j is the altitude difference between two adjacent nodes in the path, β is the average mileage power consumption of electric vehicles on flat ground, and α i,j is the climbing coefficient of the electric vehicle when it travels between nodes i and j, and η is the energy recovery efficiency of the electric vehicle;

[0147] Step S1062, based on the electric vehicle power consumption model for mountainous cities established in step S1061, the electric vehicle arrival time prediction model is:

[0148]

[0149] Among them, t 0 The time when charging demand is generated for electric vehicles, t 1 is the time when the electric vehicle is connected to the charging station, V 0 is the average speed of electric vehicles;

[0150] The predicted departure time of electric vehicles is:

[0151]

[0152] Among them, t 2 is the estimated time for the electric vehicle to leave the station, t 1 is the time for electric vehicles to access the charging station, Q is the capacity of the electric vehicle, and p z is the power of the charging pile, η z The charging efficiency of the charging pile;

[0153] Step S1063, during the load forecasting process, the electric vehicle constraint condition is:

[0154] Electric vehicle batteries cannot be overcharged or over-discharged, and the constraints are:

[0155]

[0156] in, The minimum amount of electricity required to charge an electric vehicle. is the current power of the electric vehicle, Charge electric vehicles to the highest capacity;

[0157] The distance between the electric vehicle charging station and the charging demand point cannot exceed the electric vehicle's range, and the constraints are:

[0158] 0≤L o,d (t)≤M i (t)

[0159] Among them, L o,d (t) is the distance from the charging demand point to the charging station of the electric vehicle, M i (t) The range of the electric vehicle when charging is required;

[0160] Step S107, based on the electric vehicle power consumption model and time prediction model established in step S106, it is possible to predict when and where the electric vehicle will be charged after a charging demand is generated, and the charging loads of all candidate nodes in a day are accumulated to obtain the charging load curves of all charging station nodes in the planning area;

[0161] Step S108, based on the charging load prediction curve obtained in step S107, combined with the basic load of the distribution network obtained by the distribution network data acquisition subsystem, the distribution network grid load is predicted, and the planning cost is taken into consideration to calculate the charging station planning scheme with the minimum load fluctuation and the minimum cost;

[0162] Step S1081, the minimum distribution network grid load fluctuation model is:

[0163]

[0164] Among them, P base (t) is the basic load in the power grid, P EV (t) is the electric vehicle charging load, is the average load of the power grid;

[0165] Step S1082: the minimum cost model for charging station construction is:

[0166] minZ=C con +C main +C exp

[0167] Among them, Z is the total cost of charging station planning, C con is the annual construction cost of charging facilities, C main is the annual operation and maintenance cost of the charging facility, C exp Cost of expansion of the distribution network;

[0168] Step S109: After the cloud monitoring platform calculates the number of charging stations that need to be planned according to steps S101 and S102 and selects the initial position in the road network node, it predicts the charging load of electric vehicles according to steps S103-S107, and predicts the grid load of the distribution network in combination with the basic load forecast data of the distribution network. With step S108 as the objective function, the optimal charging station layout plan is obtained by searching for the best solution; the capacity of each charging station is determined according to the daily average charging load of each charging station in the optimal charging station layout plan, and the site selection and capacity determination of the charging station are completed.

[0169] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A charging facility planning system based on a smart transportation system. It is characterized in that The mountain city charging station planning system based on electric vehicle charging demand forecasting includes a cloud monitoring platform, a vehicle flow monitoring subsystem, a charging station management subsystem, an on-board data processing subsystem, and a distribution network data acquisition subsystem: The vehicle flow monitoring subsystem is used to collect the vehicle flow data at each node in the road network at different time points in a day, process the vehicle flow data at each node, predict the fast charging prediction data of electric vehicles with fast charging demand, and upload the electric vehicle fast charging prediction data to the cloud monitoring platform; The charging station management subsystem is used to collect the charging pile usage information of the charging piles in the charging station, and the charging pile usage information includes: the annual average charging volume of various types of vehicles, the time when the electric vehicle is connected to the charging pile, the time when the electric vehicle leaves the charging pile, and the charging efficiency of the charging pile, and upload the processed charging pile usage information to the cloud monitoring platform; The vehicle-mounted data processing subsystem is used to monitor the remaining power data of the electric vehicle in real time and receive the location information of the charging station and the road network data. When a charging demand is generated, the charging station is searched for charging with the minimum power consumption as the goal and the power consumed in the process is calculated. The time when the charging demand is generated and the estimated time to arrive at the charging station, the location data of the found charging station, and the power consumption data during driving are uploaded to the cloud monitoring platform; The distribution network data acquisition subsystem is used to collect distribution network load changes, combine the distribution network historical load data, predict the distribution network daily load curve for the planned year, obtain the distribution network daily load prediction curve for the planned year, and upload the distribution network daily load prediction curve for the planned year to the cloud monitoring platform; The cloud monitoring platform is used to receive in real time the time when charging demand is generated, the estimated time of arrival at the charging station, the location data of the charging station found, and the power consumption data during driving, which are sent by the on-board data processing subsystem; receive the charging pile usage information sent by the charging station management subsystem; receive the electric vehicle fast charging prediction data sent by the vehicle flow monitoring subsystem, receive the distribution network daily load prediction curve for the planned year sent by the distribution network data acquisition subsystem, and predict the short-term charging load of electric vehicles based on the mountain city charging station planning method, and then combine the charging station, distribution network related data and electric vehicle growth data to predict the charging demand of electric vehicles at each node of the road network in the planned year, and then make the optimal charging station layout plan for the planning area with the goal of minimizing the charging load fluctuation and optimizing the distribution network flow.

2. According to the charging facility planning system based on the intelligent transportation system of claim 1, It is characterized in that The vehicle-mounted data processing subsystem includes a driving data acquisition module, a road network data acquisition module, a driving path control module, and a vehicle-mounted communication module; The driving data acquisition module is used to collect vehicle SOC information, air conditioning operation status, vehicle position, and vehicle speed information with a period of Δt; The road network data collection module is used to collect the location information of the vehicle in the road network, the location information of the charging station in the road network, the congestion situation of each road in the road network and the road slope information in real time; The driving path control module is used to determine whether the electric vehicle has a charging demand based on the vehicle battery remaining power information collected by the driving data collection module; if the electric vehicle has a charging demand, the power consumption and time required to reach each charging station are calculated based on the charging station location information and road network road condition information, and the charging station and path with the minimum power consumption are used as the target charging station and path; The vehicle-mounted communication module is used to upload the data collected and processed by the driving data collection module, the road network data collection module, and the driving path control module to the cloud monitoring platform.

3. The charging facility planning system based on the intelligent transportation system according to claim 1, It is characterized in that The cloud monitoring platform includes an electric vehicle short-term load forecasting module, a charging station long-term planning module, a cloud platform communication module, and a cloud platform database; The electric vehicle short-term load prediction module is used to predict the electric vehicle charging load based on the real-time collected electric vehicle driving data and road network road data, and send the predicted data to the user terminal to achieve the purpose of off-peak charging for electric vehicle users; The charging station long-term planning module is used to obtain the planned annual number of electric vehicles based on vehicle data and the electric vehicle growth rate; obtain the number of electric vehicles with charging demand at each road network node and each time node based on vehicle driving data, and obtain the electric vehicle charging decision based on the vehicle data processing subsystem, thereby calculating the charging load of each charging station; The basic load data of the distribution network in the planned year is predicted based on the historical load data of the distribution network. The total load data of the distribution network in the planned year is obtained by combining the charging load data. The optimal layout plan of the charging station is obtained by optimizing the charging load fluctuation to minimize the fluctuation and the optimal power flow of the distribution network. The cloud platform communication module is used to realize data interaction between the cloud monitoring platform and the vehicle flow monitoring subsystem, the vehicle data processing subsystem, the charging station management subsystem, and the distribution network data acquisition subsystem; The cloud platform database is used to retain data collected and processed by the vehicle flow monitoring subsystem, the vehicle data processing subsystem, the charging station management subsystem, and the distribution network data acquisition subsystem for short-term charging load prediction and long-term charging station planning.

4. The charging facility planning system based on the intelligent transportation system according to claim 1, It is characterized in that The charging station management subsystem includes: a charging station communication module, a charging station database and a charging station data acquisition module; The charging station data collection module is used to collect the charging pile usage information of the charging piles in the charging station; the charging pile usage information includes: the annual average charging volume of various types of vehicles, the time when the electric vehicle is connected to the charging pile, the time when the electric vehicle leaves the charging pile, and the charging efficiency of the charging pile, and the charging pile usage information is processed; The charging station communication module is used to upload the processed charging pile usage information to the cloud monitoring platform; The charging station database is used to store the charging pile usage information collected by the charging station data collection module and the processed charging pile usage information.

5. The charging facility planning system based on the intelligent transportation system according to claim 1, It is characterized in that The distribution network data acquisition subsystem includes: a distribution network communication module, a distribution network data acquisition module, a distribution network database and a distribution network data processing and control module; The distribution network data acquisition module is used to collect distribution network load changes; The distribution network data processing and control module is used to predict the distribution network daily load curve in the planned year according to the distribution network load change and the distribution network historical load, and obtain the distribution network daily load prediction curve in the planned year; The distribution network database is used to store distribution network load changes and distribution network daily load forecast curves for the planned year; The distribution network communication module is used to send the planned annual distribution network daily load forecast curve to the cloud monitoring platform.

6. The charging facility planning system based on the intelligent transportation system according to claim 2, It is characterized in that It also includes a plurality of first cameras arranged in the vehicle, a plurality of second cameras arranged in the vehicle, and a plurality of video surveillance cameras arranged at road intersections; the first cameras are connected to the vehicle data processing subsystem through a CAN bus, and the second cameras are connected to the vehicle data processing subsystem through a CAN bus; the video surveillance cameras are connected to the vehicle flow monitoring subsystem through a 5G communication technology; The first camera is used to obtain the historical data of the owner's expression, and the first camera is set on the triangular column of the car; the second camera is used for the historical data of the owner's head angle, and the second camera is set on the dashboard assembly of the car; the video monitoring is used to collect traffic video data on the road; The vehicle-mounted data processing subsystem is also used to obtain several odometer remaining power data in the vehicle, several owner's expression history data sent by the first cameras, and several owner's head angle history data sent by the first cameras, and send the owner's expression history data, the owner's head angle history data and the odometer remaining power data to the cloud monitoring platform.

7. A charging facility planning method based on intelligent transportation system, It is characterized in that The charging facility planning method is based on the charging facility planning system according to any one of claims 1 to 6, and comprises the following steps: Step S10, select several nodes from the road network as charging station equipment selection nodes, predict the number of charging stations to be planned based on the average annual total amount of electric vehicle charging and the planned annual number of electric vehicles, predict the charging demand of electric vehicles in the planned year based on the road network node traffic flow monitoring and the planned annual number of electric vehicles, select the charging station with the lowest power consumption for charging, and make the optimal layout plan of electric vehicle charging stations with the goal of minimizing the daily load fluctuation of the distribution network to alleviate the load on the power grid; Step S20, based on the acquired data related to electric vehicles, charging stations, and distribution networks, an optimal electric vehicle charging station planning model is constructed with the minimum grid daily load variance fluctuation as the planning target; the electric vehicle charging station planning includes the layout location of the electric vehicle charging station and the power and number of charging piles planned for each station; Step S30, predict the number of charging stations to be planned based on the forecast of the number of electric vehicles in the planned year and the annual average charging volume of each type of electric vehicles; monitor the traffic volume of each node in each time period based on the candidate charging station nodes pre-set in the road network, and make the daily charging demand of each road network node in the planned year in combination with the forecast of the number of electric vehicles; predict the time and place of access to the charging station based on the time and place when the electric vehicles generate the charging demand, and make the load forecast of the charging station based on this; predict the basic load of the power grid in the planned year based on the historical load data of the distribution network, and predict the load of the distribution network in the planned year in combination with the charging load forecast curve of the charging station; Step S40, solving the optimal solution of the electric vehicle planning model according to the constraint conditions of the electric vehicle charging station planning model; determining the layout location and capacity of the charging station according to the optimal solution under the conditions.

8. The charging facility planning method based on the intelligent transportation system according to claim 7, It is characterized in that Step S10 is specifically as follows: Step S101, by monitoring the vehicle flow Nv(t,i) at different time points of each node in the current road network, and adding a correction coefficient according to the vehicle growth rate and the electric vehicle penetration rate, the number of electric vehicles Ne(t,i)′ with charging demand at each node in the planned road network at each time point is predicted, and the constructed electric vehicle charging demand prediction model is: Among them, Ne(t,i)′ is the number of electric vehicles with charging demand at the i node of the road network at time t in the planning year, Nv(t,i) is the traffic volume at the i node of the road network at time t in the current year, p is the average growth rate of vehicles this year, and N evc is the number of electric vehicles that need charging, N ev is the number of electric vehicles; N v is the total number of cars; r is the correction coefficient, L i-j is the distance between any two road network nodes, ΔT is the time interval for monitoring vehicle flow, and v is the vehicle speed; Step S102: After predicting the electric vehicles with charging needs according to step S101, the electric vehicles select the charging station with the lowest power consumption during driving for charging according to the power consumption model. Considering the influence of the mountainous city terrain characteristics on the power consumption of the electric vehicles, the power consumption model is: Among them, E o,d is the power consumption from the departure point to the destination, X is the path from the departure point to the destination, L i,j is the distance between two adjacent nodes in the path, H i,j is the altitude difference between two adjacent nodes in the path, β is the average mileage power consumption of electric vehicles on flat ground, and α i,j is the climbing coefficient of the electric vehicle when it travels between nodes i and j, and η is the energy recovery efficiency of the electric vehicle; Step S103, according to the charging demand prediction and power consumption model constructed in steps S101 and S102, after the electric vehicle generates charging demand and selects the optimal charging station, the time model of the electric vehicle charging load connecting to the charging station is: Among them, t 0 The time when charging demand is generated for electric vehicles, t 1 is the time when the electric vehicle is connected to the charging station, V 0 is the average speed of electric vehicles; Step S104, based on the electric vehicle charging load prediction model constructed in steps S101, S102, and S103; Step S104 is specifically as follows: Step S1041: The electric vehicle battery cannot be overcharged or over-discharged, and the constraints are: in, The minimum amount of electricity required to charge an electric vehicle. is the current power of the electric vehicle, Charge electric vehicles to the highest capacity; Step S1042: The distance between the electric vehicle charging station and the charging demand point cannot exceed the electric vehicle's cruising range, and the constraints are: 0≤L o,d (t)≤M i (t) Among them, L o,d (t) is the distance from the charging demand point to the charging station of the electric vehicle, M i (t) is the range of the electric vehicle when charging demand occurs.

9. The charging facility planning method based on the intelligent transportation system according to claim 8, It is characterized in that After step S40 determines the layout location and capacity of the charging station, the following steps are also included: Step S50, determining the number of electric vehicle charging stations to be built, and the determination model is: Among them, N sta is the number of charging stations to be planned, E ev is the total annual charging volume of electric vehicles, N ev is the number of electric vehicles in the planned year, t z is the average daily usage hours of the charging pile, p z is the charging power of the charging pile, n z The average number of charging piles that need to be planned for each station.

10. The charging facility planning method based on the intelligent transportation system according to claim 9, It is characterized in that Step S1011: the number of electric vehicles N ev The specific steps of obtaining include: Collect traffic video data on the road based on video surveillance at road intersections; The traffic video data is monitored in real time using the yolo v4 algorithm, and the color and length of the license plate number of the electric vehicle are identified according to the image recognition algorithm to determine whether the vehicle is an electric vehicle, thereby determining the number of electric vehicles on the road; The total number N of the automobiles v The obtaining method specifically comprises the following steps: Collecting the traffic video data on the road according to the video surveillance of the road intersection; The traffic video data is monitored in real time using the yolo v4 algorithm, and the license plates of cars are identified according to the image recognition algorithm, thereby determining the total number of cars on the road; The number of electric vehicles with charging demand N evc The specific steps of obtaining include: Collecting the traffic video data on the road according to the video surveillance of the road intersection; The traffic video data is read to obtain the facial expression data and head angle data of the vehicle owner traveling on the monitored road; The owner's facial expression data and the owner's head angle data are input into the vehicle remaining power model to obtain the number of electric vehicles that need to be charged; The specific steps for training the vehicle remaining power model are: The vehicle-mounted data acquisition control subsystem obtains the owner's facial expression history data collected by the first camera in the vehicle, the owner's head angle history data collected by the second camera, and the odometer remaining power data; The owner's facial expression history data, the owner's head angle history data and the odometer remaining power data are processed through time series, and then the processed owner's facial expression history data, the owner's head angle history data and the odometer remaining power data are input into the BP neural network for training to calculate the vehicle remaining power model.

Images