Intelligent traffic control method, control system and storage medium based on Internet of Things

Abstract

The present invention discloses a smart traffic control method, control system and storage medium based on the Internet of Things. The method is applied to an Internet of Things server, including: obtaining the traffic flow data of a road traffic intersection, and the adjacent traffic flow data of an adjacent intersection corresponding to the road traffic intersection, and generating a traffic light control plan for the road traffic intersection based on the traffic flow data and the adjacent traffic flow data; obtaining the remaining power of an electric vehicle, and determining multiple target parking lots when the remaining power is less than a preset power threshold; generating multiple charging plans for the electric vehicle based on the remaining power and each target parking lot, and generating guidance information for guiding the driving path of the electric vehicle based on each charging plan; and performing smart traffic control based on the traffic light control plan and the guidance information. The present invention provides effective support for solving the problems of traffic congestion and difficulty in charging electric vehicles by finely controlling smart traffic in traffic lights at intersections and charging of electric vehicles.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an intelligent traffic control method, a control system and a storage medium based on the Internet of Things. Background Art

[0002] In recent years, with the improvement of economic level, the per capita car ownership in my country has increased year by year, and in order to protect the environment, the proportion of electric vehicles has also increased. Along with this comes the problem of traffic congestion and charging convenience. The development of smart transportation is an effective way to solve these problems.

[0003] Smart transportation is the full use of technologies such as the Internet of Things, spatial perception, artificial intelligence, automatic control, and mobile Internet in the field of transportation to provide all-round control and support for transportation management, transportation, public travel, and other transportation fields, so that the transportation system has the ability to perceive, interconnect, analyze, predict, and control in regions, cities, and even larger time and space ranges.

[0004] At present, urban traffic problems are mainly concentrated on traffic congestion and difficulty in charging electric vehicles. Smart transportation only makes simple adjustments to this problem, increasing the travel time when the traffic volume is large, and shortening the travel time when the traffic volume is small. For charging electric vehicles, it is only to find parking lots with charging piles for charging, and no refined control is carried out. Therefore, the current smart transportation control does not provide relatively effective support for solving the problems of traffic congestion and difficulty in charging electric vehicles. Summary of the invention

[0005] The main purpose of the present invention is to provide an intelligent traffic control method, a control system and a storage medium based on the Internet of Things, aiming to solve the technical problem of how to carry out refined control of intelligent traffic and provide effective support for solving the problems of traffic congestion and difficulty in charging electric vehicles.

[0006] To achieve the above object, the present invention provides an intelligent traffic control method based on the Internet of Things, which is applied to an Internet of Things server. The intelligent traffic control method based on the Internet of Things includes:

[0007] The Internet of Things server obtains the traffic flow data of the road traffic intersection and the adjacent traffic flow data of the adjacent intersection corresponding to the road traffic intersection, and generates a traffic light control plan for the road traffic intersection according to the traffic flow data and the adjacent traffic flow data;

[0008] The Internet of Things server obtains the remaining power of the electric vehicle, and when the remaining power is less than a preset power threshold, determines a plurality of target parking lots corresponding to the electric vehicle;

[0009] The IoT server generates a plurality of charging schemes for the electric vehicle based on the remaining power and each of the target parking lots, and generates guidance information for guiding the driving path of the electric vehicle based on each of the charging schemes;

[0010] The Internet of Things server performs intelligent traffic control based on the traffic light control scheme and the guidance information.

[0011] Preferably, the step of generating a traffic light control scheme for the road traffic intersection according to the traffic flow data and the adjacent traffic flow data comprises:

[0012] Identifying the adjacent vehicle flow data as adjacent inflow data and adjacent outflow data, wherein the adjacent inflow data includes variable inflow data corresponding to variable lanes in the adjacent intersection, and immutable inflow data corresponding to immutable lanes in the adjacent intersection;

[0013] Identify the generation time of the traffic flow data, obtain the historical traffic flow data of the road traffic intersection corresponding to the generation time, and search for weather parameters and road condition parameters corresponding to the generation time;

[0014] The variable inflow data, the immutable inflow data, the adjacent outflow data, the historical vehicle flow data, the weather parameters, the road condition parameters and the vehicle flow data are generated as an input vector, and the input vector is predicted and calculated based on a preset prediction model to generate the vehicle flow change data of the road traffic intersection, wherein the formula used for prediction calculation in the preset prediction model is:

[0015] pt=g(w xo x t +w co (i t *tan(w xc x t +b c ))+b o );

[0016] Among them, pt represents the traffic flow change data, g represents the activation function of the preset prediction model, and w xo Represents the weight matrix between the input layer and the output layer of the preset prediction model, x t represents the input vector, w co Represents the weight matrix between the hidden layer and the output layer of the preset prediction model, i t Represents the hidden layer vector of the preset prediction model, w XC represents the weight matrix between the input layer and the hidden layer of the preset prediction model, b c represents the hidden layer bias vector of the preset prediction model, b o Represents the output layer bias vector of the preset prediction model;

[0017] The traffic light control plan is generated according to the traffic flow change data.

[0018] Preferably, the step of generating a plurality of charging schemes for the electric vehicle based on the remaining power and each of the target parking lots by the Internet of Things server comprises:

[0019] Determine the battery loss parameter of the electric vehicle according to the historical charging information of the electric vehicle, and find the charging attenuation factor corresponding to the battery loss parameter;

[0020] According to the predicted queue time of each target parking lot, the charging efficiency, charging current and charging power of the idle charging piles in each target parking lot, the charging parameters of the electric vehicle, the remaining power and the charging attenuation factor, the charging time of the idle charging piles in each target parking lot for charging the electric vehicle is calculated, and the calculation formula is:

[0021] hi=ln I1 / 12 *((EE x -si*θ) / Wi)*τi*μ+Hi;

[0022] Where hi represents the charging time corresponding to the i-th target parking lot, I1 represents the charging current of the idle charging pile, I2 represents the maximum acceptable charging current of the electric vehicle in the charging parameters, E represents the battery capacity in the charging parameters, and E x represents the remaining power, si represents the driving distance between the electric vehicle and the i-th target parking lot, θ represents the power consumption per unit mileage in the charging parameters, Wi represents the charging power of the idle charging piles in the i-th target parking lot, τi represents the charging efficiency of the idle charging piles in the i-th target parking lot, μ represents the charging attenuation factor, and Hi represents the predicted queuing time of the i-th target parking lot;

[0023] According to each of the charging times, a plurality of charging plans for the electric vehicle are generated.

[0024] Preferably, the step of generating a plurality of charging schemes for the electric vehicle according to each of the charging durations comprises:

[0025] Determine whether each of the target parking lots includes a replacement battery corresponding to the electric vehicle, and if so, generate a charging plan for the electric vehicle to charge at the target parking lot according to the charging duration and the corresponding second location information of the target parking lot, as well as the replacement battery;

[0026] If the corresponding replacement battery is not included, the charging duration corresponding to the target parking lot and the corresponding second location information are generated as a charging plan for the electric vehicle to be charged at the target parking lot.

[0027] Preferably, the step of determining the battery loss parameter of the electric vehicle according to the historical charging information of the electric vehicle comprises:

[0028] Searching for the number of DC charging times and the number of AC charging times in the historical charging information, and counting the total DC charging durations corresponding to each of the DC charging times, and the total AC charging durations corresponding to each of the AC charging times;

[0029] Acquire a first loss coefficient corresponding to the total DC charging time and a second loss coefficient corresponding to the total AC charging time;

[0030] The mileage of the electric vehicle is obtained, and the battery loss parameter is calculated according to the first loss coefficient, the second loss coefficient, the mileage and the power consumption per unit mileage in the charging parameter, and the calculation formula is:

[0031] w=m1*m2*(q+a*D*θ):

[0032] Among them, w represents the battery loss parameter, m1 represents the first loss coefficient, m2 represents the second loss coefficient, q represents the static loss parameter of the battery of the electric vehicle, a represents the driving loss parameter of the battery of the electric vehicle, D represents the mileage, and θ represents the power consumption per unit mileage in the charging parameter.

[0033] Preferably, the step of searching for the charging attenuation factor corresponding to the battery loss parameter includes:

[0034] For each of the target parking lots, obtaining the number of historical vehicles to be charged that are within a preset range from the target parking lot, and generating a charging probability corresponding to the target parking lot based on the number of historical vehicles to be charged;

[0035] Determine the average number of vehicles to be charged in the target parking lot according to the historical number of vehicles to be charged and the charging probability;

[0036] The predicted queuing time is determined according to the charging efficiency of the idle charging piles in the target parking lot, the average number of cars to be charged, the path distance corresponding to the preset range, and the number of idle charging piles in the target parking lot.

[0037] Preferably, the step of determining a plurality of target parking lots corresponding to the electric vehicle comprises:

[0038] Acquire first location information of the electric vehicle, and determine a plurality of parking lots supporting charging of the electric vehicle according to the first location information;

[0039] The charging status information of each vehicle charging pile in the plurality of parking lots is obtained, and a target parking lot with idle charging piles is determined from each parking lot according to the charging status information.

[0040] Preferably, the step of generating guidance information for guiding the driving path of the electric vehicle based on each of the charging schemes includes:

[0041] Transmitting each of the charging schemes to the electric vehicle, and receiving a selection instruction based on a response from the electric vehicle;

[0042] Determine a target charging scheme from the charging schemes according to the selection instruction;

[0043] The second position information corresponding to the target charging scheme is determined, and guidance information is generated according to the first position information and the second position information to guide the driving path of the electric vehicle.

[0044] Furthermore, to achieve the above-mentioned purpose, the present invention also provides an intelligent traffic control system based on the Internet of Things, wherein the intelligent traffic control system based on the Internet of Things includes an Internet of Things server, wherein the Internet of Things server is provided with a storage device, a processor, a communication bus, and a control program stored on the storage device:

[0045] The communication bus is used to realize the connection and communication between the processor and the storage;

[0046] The processor is used to execute the control program to implement the steps of the smart traffic control method based on the Internet of Things as described above.

[0047] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a storage medium, on which a control program is stored, and when the control program is executed by a processor, the steps of the smart traffic control method based on the Internet of Things as described above are implemented.

[0048] The present invention is based on the intelligent traffic control method, control system and storage medium of the Internet of Things. The method is applied to the Internet of Things server. After obtaining the traffic flow data of the road traffic intersection and the adjacent traffic flow data of the adjacent intersection corresponding to the road traffic intersection, the Internet of Things server generates a traffic light control plan for the road traffic intersection according to the traffic flow data and the adjacent traffic flow data; in addition, the Internet of Things server also obtains the remaining power of the electric vehicle, and when it is detected that the remaining power is less than a preset power threshold, determines a plurality of target parking lots with idle charging piles that can be used for charging the electric vehicle, and then generates a charging plan for the electric vehicle based on the remaining power and each target parking lot, and generates guidance information for guiding the driving path of the electric vehicle according to the charging plan; thus, the Internet of Things server controls the intelligent traffic according to the generated traffic light control plan and guidance information. Among them, the adjacent traffic flow data of the adjacent intersection reflects the impact of the adjacent intersection on the traffic flow of the current road traffic intersection. The larger the traffic flow of the adjacent intersection upstream of the traffic flow direction, the more traffic will flow into the current road traffic intersection. The smaller the traffic flow of the adjacent intersection downstream of the traffic flow direction, the smoother the traffic of vehicles at the current road traffic intersection. The traffic light control scheme generated in this way can accurately match the traffic flow of the road traffic intersection to avoid road traffic congestion. At the same time, the target parking lot determined is a parking lot with idle charging piles that can be directly used for battery cars to charge. The charging scheme generated based on the remaining power and each target parking lot reflects the charging time of the charging car. The guidance information generated based on the charging scheme can guide the driving path of the electric vehicle, which is conducive to the electric vehicle to quickly find the charging pile for efficient charging. In this way, through the refined control of smart transportation in intersection traffic lights and electric vehicle charging, effective support is provided for solving the problems of traffic congestion and difficulty in charging electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flow chart of a first embodiment of a smart traffic control method based on the Internet of Things of the present invention;

[0050] Figure 2 This is a flow chart of a second embodiment of the smart traffic control method based on the Internet of Things of the present invention;

[0051] Figure 3 This is a flow chart of a third embodiment of the smart traffic control method based on the Internet of Things of the present invention;

[0052] Figure 4 This is a structural diagram of the hardware operating environment involved in an embodiment of an intelligent traffic control system based on the Internet of Things of the present invention.

[0053] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] 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.

[0055] The present invention provides a smart traffic control method based on the Internet of Things, which is applied to the Internet of Things server. Figure 1 , Figure 1 It is a flow chart of the first embodiment of the intelligent traffic control method based on the Internet of Things of the present invention.

[0056] The embodiment of the present invention provides an embodiment of a smart traffic control method based on the Internet of Things. It should be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that here. Specifically, the smart traffic control method based on the Internet of Things in this embodiment includes:

[0057] Step S10, the Internet of Things server obtains the traffic flow data of the road traffic intersection and the adjacent traffic flow data of the adjacent intersection corresponding to the road traffic intersection, and generates a traffic light control plan for the road traffic intersection based on the traffic flow data and the adjacent traffic flow data.

[0058] The smart traffic control method based on the Internet of Things in this embodiment is applied to the Internet of Things server, and the refined control of traffic lights and electric vehicle charging at road traffic intersections in smart traffic is realized through the Internet of Things server. Specifically, each road traffic intersection is equipped with a detection device for detecting vehicle flow, such as a camera, and such detection devices are all connected to the Internet of Things server to communicate and transmit the detected vehicle flow data of each road traffic intersection to the Internet of Things server. Among them, the vehicle flow data is the number of vehicles arriving at the road traffic intersection within a set time, for example, identifying the number of vehicles arriving at the road traffic intersection within one minute.

[0059] Furthermore, for each road traffic intersection, after obtaining its traffic flow data, the Internet of Things server searches for the adjacent intersections adjacent to the road traffic intersection, which are the first intersection upstream and the first intersection downstream in the traffic flow direction, including both the north-south direction and the east-west direction. Then, the adjacent traffic flow data collected and transmitted by the adjacent intersection detection device is obtained. According to the traffic flow size of the road traffic intersection represented by the traffic flow data, and the traffic flow size that is about to flow into the road traffic intersection represented by the adjacent traffic flow data, a traffic light control plan for the road traffic intersection is generated to control the road traffic intersection. Among them, the traffic light control plan can be to increase the green light duration in the north-south direction when the traffic flow data and the adjacent traffic flow data indicate that the traffic flow in the north-south direction of the road traffic intersection increases and congestion may occur, and shorten the green light duration in the north-south direction when the traffic flow data and the adjacent traffic flow data indicate that the traffic flow in the north-south direction of the road traffic intersection increases. In this way, congestion at the road traffic intersection due to excessive traffic flow is avoided.

[0060] In step S20, the Internet of Things server obtains the remaining power of the electric vehicle, and when the remaining power is less than a preset power threshold, determines a plurality of target parking lots corresponding to the electric vehicle.

[0061] Furthermore, for electric vehicles, a detection device for detecting power is provided thereon, and this type of detection device is also connected to the IoT server in communication, and transmits the remaining power of the detected electric vehicle to the IoT server. The IoT server is pre-set with a preset power threshold indicating the power level, and the detected remaining power is compared with the preset power threshold to determine whether the remaining power is less than the preset power threshold. If it is less, it means that the power of the electric vehicle is low and needs to be charged. Then, a parking lot near the electric vehicle is searched, and a target parking lot with idle charging piles that can be used to charge the electric vehicle is determined from each parking lot. Specifically, the step of determining multiple target parking lots corresponding to the electric vehicle includes:

[0062] Step S21, acquiring first location information of the electric vehicle, and determining a plurality of parking lots supporting charging of the electric vehicle according to the first location information;

[0063] Step S22, obtaining charging status information of each vehicle charging pile in the plurality of parking lots, and determining a target parking lot with idle charging piles from each parking lot according to the charging status information.

[0064] Furthermore, the location information of the electric vehicle is obtained based on the positioning device that is in communication with the Internet of Things server as the first location information, and the parking lot within the set radius is searched with the first location information as the center. The relevant data of the parking lot has been pre-connected to the Internet of Things server, including but not limited to the number of parking spaces, whether there are parking spaces with charging piles, the number of parking spaces used, the number of remaining available parking spaces, etc. Then, based on the relevant data, the parking lot that supports electric vehicle charging is determined from each parking space, and the parking lot that supports electric vehicle charging is the parking lot that includes charging piles.

[0065] Understandably, even if the parking lot has parking spaces with charging piles, there may be cars parked in such parking spaces, and electric vehicles with charging requirements cannot be parked. Therefore, the charging status information of each car charging pile in the parking lot that supports electric vehicle charging is obtained from the relevant data, and the charging status information indicates whether the car charging pile is in a charging state, and whether there is a car parked in the parking space where the car charging pile is located. If the charging status information indicates that the car charging pile is in a charging state, or a car is parked in the corresponding parking space, it means that the car charging pile is occupied and cannot provide charging for the electric vehicle that needs to be charged. Then, based on each charging status information, a target parking lot with idle charging piles is determined from each parking lot. That is, if it is determined through the charging status information that all car charging piles in the parking lot are occupied and no car charging pile is in an idle state, the parking lot is eliminated; on the contrary, if it is determined that there is at least one car charging pile in the parking lot that is not occupied and is in an idle state, the parking lot is determined as the target parking lot.

[0066] Step S30, the Internet of Things server generates a plurality of charging schemes for the electric vehicle based on the remaining power and each of the target parking lots, and generates guidance information for guiding the driving route of the electric vehicle based on each of the charging schemes.

[0067] Furthermore, each target parking lot is located at a different position relative to the electric vehicle, and each target parking lot has a different number of idle charging piles and a different charging efficiency of the idle charging piles. Therefore, in order to achieve fast charging of the electric vehicle, multiple optional charging plans for the electric vehicle are generated based on the remaining power of the electric vehicle and each target parking lot, the remaining power reflects the driving distance required for the electric vehicle to travel to each target parking lot, the amount of power consumed, and the number of idle charging piles in each target parking lot and the charging time reflected by the charging efficiency of each idle charging pile. After the owner of the electric vehicle selects the charging plan he or she requires, guidance information is generated based on the selected charging plan to guide the driving path of the electric vehicle. Specifically, the step of generating guidance information for guiding the driving path of the electric vehicle based on each of the charging plans includes:

[0068] Step S31, transmitting each of the charging schemes to the electric vehicle, and receiving a selection instruction based on the return of the electric vehicle;

[0069] Step S32, determining a target charging scheme from the charging schemes according to the selection instruction;

[0070] Step S33, determining the second position information corresponding to the target charging scheme, and generating guidance information according to the first position information and the second position information to guide the driving path of the electric vehicle.

[0071] Furthermore, the IoT server transmits each generated charging plan to the electric vehicle, and outputs a prompt message to prompt the electric vehicle owner to view it. The electric vehicle owner can view each charging plan through the display device of the electric vehicle and select the charging plan of his / her needs. After detecting the selection instruction sent by the electric vehicle owner, the IoT server identifies the plan identifier carried by the selection instruction, and finds the target charging plan with the plan identifier from each charging plan. Then, the location of the target parking lot corresponding to the target charging plan is identified and used as the second location information. The driving path between the first location information and the second location information is searched, and the travel time of each driving path is predicted. The route with the shortest travel time is selected as the guidance information output to the electric vehicle to guide the driving path of the electric vehicle.

[0072] Step S40: The IoT server performs intelligent traffic control based on the traffic light control scheme and the guidance information.

[0073] Furthermore, after the IoT server generates the traffic light control scheme and guidance information, it can control the smart traffic according to the traffic light control scheme and guidance information. The two can be controlled separately or in combination. For example, when the owner of an electric car controls the traffic lights at the intersection on the driving path in accordance with the guidance information, or when the owner of the electric car controls the traffic lights at the intersection according to the generated traffic light control scheme, it is detected that the remaining power of the electric car is too low, and the corresponding target parking lot is searched to generate the charging scheme and guidance information. In this way, the refined control of smart traffic on traffic lights at intersections and electric vehicle charging is realized.

[0074] In the IoT-based smart traffic control method implemented in this embodiment, after the IoT server obtains the traffic flow data of the road traffic intersection and the adjacent traffic flow data of the adjacent intersections corresponding to the road traffic intersection, it generates a traffic light control plan for the road traffic intersection based on the traffic flow data and the adjacent traffic flow data; in addition, the IoT server also obtains the remaining power of the electric vehicle, and when it detects that the remaining power is less than a preset power threshold, it determines a plurality of target parking lots with idle charging piles that can be used for charging the electric vehicle, and then generates a charging plan for the electric vehicle based on the remaining power and each target parking lot, and generates guidance information for guiding the driving path of the electric vehicle based on the charging plan; thus, the IoT server controls the smart traffic based on the generated traffic light control plan and guidance information. Among them, the adjacent traffic flow data of the adjacent intersection reflects the impact of the adjacent intersection on the traffic flow of the current road traffic intersection. The larger the traffic flow of the adjacent intersection upstream of the traffic flow direction, the more traffic will flow into the current road traffic intersection. The smaller the traffic flow of the adjacent intersection downstream of the traffic flow direction, the smoother the traffic of vehicles at the current road traffic intersection. The traffic light control scheme generated in this way can accurately match the traffic flow of the road traffic intersection to avoid road traffic congestion. At the same time, the target parking lot determined is a parking lot with idle charging piles that can be directly used for battery cars to charge. The charging scheme generated based on the remaining power and each target parking lot reflects the charging time of the charging car. The guidance information generated based on the charging scheme can guide the driving path of the electric vehicle, which is conducive to the electric vehicle to quickly find the charging pile for efficient charging. In this way, through the refined control of smart transportation in intersection traffic lights and electric vehicle charging, effective support is provided for solving the problems of traffic congestion and difficulty in charging electric vehicles.

[0075] For further information, please refer to Figure 2 Based on the first embodiment of the intelligent traffic control method based on the Internet of Things of the present invention, a second embodiment of the intelligent traffic control method based on the Internet of Things of the present invention is proposed.

[0076] The difference between the second embodiment of the smart traffic control method based on the Internet of Things and the first embodiment of the smart traffic control method based on the Internet of Things is that the step of generating the traffic light control scheme for the road traffic intersection according to the vehicle flow data and the adjacent vehicle flow data includes:

[0077] Step S11, identifying the adjacent vehicle flow data as adjacent inflow data and adjacent outflow data, wherein the adjacent inflow data includes variable inflow data corresponding to variable lanes in the adjacent intersection, and immutable inflow data corresponding to immutable lanes in the adjacent intersection;

[0078] Step S12, identifying the generation time of the traffic flow data, obtaining the historical traffic flow data of the road traffic intersection corresponding to the generation time, and searching for weather parameters and road condition parameters corresponding to the generation time;

[0079] Step S13, generating the variable inflow data, the immutable inflow data, the neighboring outflow data, the historical vehicle flow data, the weather parameters, the road condition parameters and the vehicle flow data as an input vector, and performing a prediction calculation on the input vector based on a preset prediction model to generate vehicle flow change data of the road traffic intersection;

[0080] Step S14, generating the traffic light control plan according to the traffic flow change data.

[0081] It can be understood that the adjacent intersections include an upstream intersection located upstream of the vehicle flow direction and a downstream intersection located downstream of the vehicle direction, the detection device of the upstream intersection carries an upstream intersection identifier, and the detection device of the downstream intersection carries a downstream intersection identifier. The IoT server can identify and distinguish the acquired adjacent vehicle flow data based on the upstream intersection identifier and the downstream intersection identifier, identify the data carrying the upstream intersection identifier as adjacent inflow data, and identify the data carrying the downstream intersection identifier as adjacent outflow data.

[0082] Furthermore, for the upstream intersection, it usually includes multiple lanes, and not all lanes of vehicles will drive to the current road traffic intersection. There may be vehicles turning left or right, and the vehicles turning left or right will not affect the traffic flow of the current road traffic intersection. The lanes that support left turns or right turns in the adjacent intersection are regarded as variable lanes, and the lanes that only support straight driving are regarded as immutable lanes. Then the adjacent inflow data is divided into variable inflow data corresponding to the variable lanes, and immutable inflow data corresponding to the immutable lanes. Among them, the division can be carried out by the lane identification carried by the adjacent inflow data. For example, different detection devices are set for different lanes, and different detection devices have identifications corresponding to the lanes, and then divided into variable inflow data and immutable inflow data according to the lane identification carried by the adjacent inflow data. In addition, considering that the variable lanes of some intersections can go straight in addition to turning left or turning, the straight driving ratio of the lane is pre-monitored and evaluated. After the adjacent inflow data is divided into variable inflow data and immutable inflow data, the variable inflow data and the immutable inflow data are corrected according to the straight driving ratio. For variable inflow data, the amount corresponding to the proportion of straight lines is reduced, and for immutable inflow data, the amount corresponding to the proportion of straight lines is increased.

[0083] Furthermore, the traffic volume at a road traffic intersection has a time characteristic, for example, the traffic volume at the morning rush hour is larger than that at the non-rush hour. Therefore, in order to reflect the time characteristic, the generation time of the traffic volume data is identified, and the historical traffic volume data of the road traffic intersection at the generation time on previous dates is obtained. The historical traffic volume data can be data from multiple previous dates, such as the traffic volume data of the previous three days.

[0084] Furthermore, considering that both weather and road conditions have an impact on road traffic congestion, such as foggy or rainy weather, slow vehicles driving and causing road congestion; traffic accidents or road construction leading to road congestion, etc., these factors all have an impact on the traffic flow at road intersections. Therefore, the IoT server also searches for weather parameters and road condition parameters at the time of generation.

[0085] Furthermore, a preset prediction model is pre-set in the IoT server. The preset prediction model is pre-trained through a large number of training samples. The training samples are all related to the factors affecting the traffic flow at the road traffic intersection and are used to predict the change of the traffic flow at the road traffic intersection. The weather parameters and road condition parameters found are generated together with the variable inflow data, the immutable inflow data, the adjacent outflow data, the historical traffic flow data, and the traffic flow data as an input vector, and the input vector is predicted and calculated by the preset prediction model to obtain the traffic flow change data at the road traffic intersection. The formula used for the prediction calculation can be seen in the following formula (1).

[0086] pt=g(w xo x t +w co (i t *tan(w xc x t +b c ))+b o ) (1);

[0087] Among them, pt represents the traffic flow change data, g represents the activation function of the preset prediction model, and w xo Represents the weight matrix between the input layer and the output layer of the preset prediction model, x t represents the input vector, w co Represents the weight matrix between the hidden layer and the output layer of the preset prediction model, i t Represents the hidden layer vector of the preset prediction model, w xc represents the weight matrix between the input layer and the hidden layer of the preset prediction model, b c represents the hidden layer bias vector of the preset prediction model, b o Represents the output layer bias vector of the preset prediction model.

[0088] Furthermore, after obtaining the traffic flow change data, the IoT server can generate a traffic light control plan based on it. The traffic light control plan is used to control the duration of traffic lights at road traffic intersections. When the traffic flow change data indicates that more vehicles are about to gather at the road traffic intersection, the straight green light time is extended, or the turn green light time is extended. When the traffic flow change data indicates that the number of vehicles at the road traffic intersection is reduced, the straight green light time is shortened. In this way, according to the changes in the traffic flow at the road traffic intersection, the traffic lights at the road traffic intersection can be accurately controlled to ensure smooth road traffic and avoid congestion.

[0089] This embodiment predicts the traffic flow change data at the road traffic intersection by combining the current traffic flow data at the road traffic intersection with the variable inflow data, immutable inflow data, and adjacent outflow data at the adjacent intersections, and taking into account factors that affect the traffic flow at the road traffic intersection, such as historical traffic flow data, weather parameters, and road condition parameters. By comprehensively considering various factors, the prediction is more accurate, thereby making the generated traffic light control valve stem more accurate, which is conducive to the precise control of traffic lights at road traffic intersections.

[0090] For further information, please refer to Figure 3 Based on the first and second embodiments of the smart traffic control method based on the Internet of Things of the present invention, a third embodiment of the smart traffic control method based on the Internet of Things of the present invention is proposed.

[0091] The third embodiment of the smart traffic control method based on the Internet of Things is different from the first and second embodiments of the smart traffic control method based on the Internet of Things in that the steps of generating multiple charging schemes for the electric vehicle based on the remaining power and each of the target parking lots by the Internet of Things server include:

[0092] Step S34, determining a battery loss parameter of the electric vehicle according to historical charging information of the electric vehicle, and searching for a charging attenuation factor corresponding to the battery loss parameter;

[0093] It is understandable that the battery of an electric vehicle will be damaged during charging and discharging. In order to determine the degree of battery damage, the historical charging information of the electric vehicle is obtained. The historical charging information at least includes the number of charging times and the charging time. Based on this type of historical charging information, the battery damage parameter of the electric vehicle is determined. Specifically, the step of determining the battery damage parameter of the electric vehicle based on the historical charging information of the electric vehicle includes:

[0094] Step S341, searching the DC charging times and AC charging times in the historical charging information, and counting the total DC charging durations corresponding to the DC charging times and the total AC charging durations corresponding to the AC charging times;

[0095] Step S342, obtaining a first loss coefficient corresponding to the total DC charging time and a second loss coefficient corresponding to the total AC charging time;

[0096] Step S343, obtaining the mileage of the electric vehicle, and calculating the battery loss parameter according to the first loss coefficient, the second loss coefficient, the mileage and the power consumption per unit mileage in the charging parameter.

[0097] Furthermore, the charging of electric vehicles can be fast charging or slow charging. Fast charging is to charge the battery with direct current, which has a fast charging speed but causes greater loss to the battery. Slow charging is to charge the battery with alternating current, which has a slow charging speed but causes less loss to the battery. The number of DC charging times and AC charging times are screened out from the historical charging information, and the duration of each DC charging is counted to obtain the total DC charging time corresponding to each DC charging number; and the duration of each AC charging is counted to obtain the total AC charging time corresponding to each AC charging number.

[0098] Furthermore, for different DC charging time intervals, loss coefficients indicating the magnitude of the loss caused to the battery by the time intervals are pre-set, and for different AC charging time intervals, loss coefficients indicating the magnitude of the loss caused to the battery by the time intervals are also pre-set. The total DC charging time is compared with each DC charging time interval to determine the DC charging time interval in which the total DC charging time is located, and then the loss coefficient corresponding to the DC charging time interval is found as the first loss coefficient corresponding to the total DC charging time. Similarly, the total AC charging time is compared with each AC charging time interval to determine the AC charging time interval in which the total AC charging time is located, and the loss coefficient corresponding to the AC charging time interval is found as the second loss coefficient corresponding to the total AC charging time.

[0099] Furthermore, the driving mileage of an electric vehicle and the power consumption per unit mileage are also related to the battery loss of the electric vehicle. The longer the driving mileage, the greater the power consumption, and the greater the battery loss. Therefore, the driving mileage of the electric vehicle is obtained, and the obtained driving mileage is combined with the first loss coefficient, the second loss coefficient, and the battery static loss parameter, battery driving loss parameter, and the power consumption per unit mileage in the charging parameter of the electric vehicle itself to calculate the battery loss parameter. The calculation formula can be found in the following formula (2).

[0100] hi=ln I1 / I2 *((EE x -si*θ) / Wi)*τi*μ+Hi (2);

[0101] Where hi represents the charging time corresponding to the i-th target parking lot, I1 represents the charging current of the idle charging pile, I2 represents the maximum acceptable charging current of the electric vehicle in the charging parameters, E represents the battery capacity in the charging parameters, and E x represents the remaining power, si represents the driving distance between the electric vehicle and the i-th target parking lot, θ represents the power consumption per unit mileage in the charging parameters, Wi represents the charging power of the idle charging piles in the i-th target parking lot, τi represents the charging efficiency of the idle charging piles in the i-th target parking lot, μ represents the charging attenuation factor, and Hi represents the predicted queuing time of the i-th target parking lot.

[0102] Furthermore, the battery loss parameter represents the loss of the battery of the electric vehicle due to charging and discharging, which is related to the battery capacity and, in turn, to the duration of subsequent charging. The greater the loss, the smaller the battery capacity and the shorter the duration of subsequent charging. In order to reflect the impact of battery loss on charging duration, the corresponding charging attenuation factors are set in advance for different battery loss parameters, and then the charging attenuation factors corresponding to the calculated battery loss parameters are obtained by comparing the calculated battery loss parameters with the battery loss parameters in each corresponding relationship.

[0103] Understandably, different target parking lots are located in different locations, have different numbers of idle charging piles, and the charging efficiency of idle charging piles may also be different. These factors are related to whether the electric vehicle needs to wait before charging. The waiting time is also a factor that affects the charging time of the electric vehicle. It needs to be determined based on the location of the above-mentioned target parking lot, the number of idle charging piles, the charging efficiency of the idle charging piles, and the number of electric vehicles that choose the target parking lot for charging. Specifically, the step of finding the charging attenuation factor corresponding to the battery loss parameter includes:

[0104] Step S344, for each of the target parking lots, obtaining the number of historical vehicles to be charged that are located within a preset range from the target parking lot, and generating a charging probability corresponding to the target parking lot based on the number of historical vehicles to be charged;

[0105] Step S345, determining the average number of cars to be charged in the target parking lot according to the historical number of cars to be charged and the charging probability;

[0106] Step S346, determining the predicted queuing time according to the charging efficiency of the idle charging piles in the target parking lot, the average number of cars to be charged, the path distance corresponding to the preset range, and the number of idle charging piles in the target parking lot.

[0107] Furthermore, for each target parking lot, if the electric car owner chooses it to charge the electric car, the target parking lot is usually not far from the location of the electric car. That is, electric car owners within a certain range of the target parking lot may choose the target parking lot for charging. Therefore, the preset range is determined in advance by statistics, and then the number of electric vehicles that have been located within the preset range from the target parking lot with charging needs is counted to obtain the historical number of cars to be charged. At the same time, the number of cars that choose to charge at the target parking lot in each historical number of cars to be charged is counted, and the ratio operation is performed between the counted number of cars and the corresponding historical initial number of cars to be charged to obtain multiple probability data, and then the average operation is performed on the multiple probability data to obtain the charging probability corresponding to the target parking lot. For example, the historical data of cars to be charged obtained include data from the previous 5 days, and the historical data of cars to be charged corresponding to the previous 5 days are a1, a2, a3, a4, and a5, respectively. The number of cars counted for these 5 days are b1, b2, b3, b4, and b5, respectively. After ratio calculation, the probability data obtained are a1 / b1, a2 / b2, a3 / b3, a4 / b4, and a5 / b5. The average calculation is performed on the 5 probability data to obtain the charging probability corresponding to the target parking lot.

[0108] Furthermore, the average number of cars to be charged in the target parking lot is determined based on the historical number of cars to be charged and the charging probability. The average number of cars to be charged in the target parking lot can be determined based on the multiplication of the historical number of cars to be charged and the charging probability, or can be determined based on the change pattern of the number of cars with charging demand reflected by the historical number of cars to be charged and the change pattern of the number of cars that choose the target parking lot for charging reflected by the charging probability.

[0109] Furthermore, the charging efficiency of the idle charging piles in the target parking lot is obtained, and based on the obtained charging efficiency, combined with the average number of cars to be charged, the path distance corresponding to the preset range, and the number of idle parking spaces in the target parking lot, the possible queue time in the target parking lot is predicted as the predicted queue time. Among them, the higher the charging efficiency, the more idle charging piles there are, the fewer the average number of cars to be charged, the shorter the path distance corresponding to the preset range, the shorter the predicted queue time, and the shorter the time it takes for electric vehicles to queue up to wait for charging in the target parking lot. Specifically, the historical factors corresponding to such factors can be formed as training samples in advance, and the relevant prediction model can be formed through training, and then the prediction model can be used to make predictions based on such factors to obtain the predicted queue time.

[0110] Step S35, calculating the charging time of the electric vehicle at the idle charging piles in each of the target parking lots according to the predicted queuing time of each of the target parking lots, the charging efficiency, charging current and charging power of the idle charging piles in each of the target parking lots, the charging parameters of the electric vehicle, the remaining power and the charging attenuation factor;

[0111] Step S36, generating multiple charging plans for the electric vehicle according to the charging times.

[0112] Furthermore, different electric vehicles have different battery capacities and maximum acceptable charging currents, and the power consumption per unit mileage is also different. The battery capacity, maximum acceptable charging current and power consumption per unit mileage are used as charging parameters of electric vehicles. After determining the predicted queue time of each target parking lot, for each target parking lot, the predicted queue time can be combined with the charging efficiency, charging current and charging power of its idle charging piles, as well as the charging parameters of the electric vehicle, the remaining power of the electric vehicle and the charging attenuation factor, to calculate the charging time of the electric vehicle at the idle charging piles in each target parking lot. The calculation formula can be found in the following formula (3).

[0113] w=m1*m2*(q+a*D*θ) (3);

[0114] Among them, w represents the battery loss parameter, m1 represents the first loss coefficient, m2 represents the second loss coefficient, q represents the static loss parameter of the battery of the electric vehicle, a represents the driving loss parameter of the battery of the electric vehicle, D represents the mileage, and θ represents the power consumption per unit mileage in the charging parameter.

[0115] Among them, the charging efficiency of an idle charging pile refers to the proportion of electric energy that can actually be converted into electric vehicle battery storage during the charging process of an idle charging pile. For example, a charging efficiency of 90% means that 90% of the electric energy output by an idle charging pile can be converted into electric energy stored in the electric vehicle battery. By considering the driving distance and the power consumption per unit mileage, the power consumption of the electric vehicle when it travels to the target parking lot is determined. On this basis, the actual remaining current and the actual required charging amount of the electric vehicle when it arrives at the target parking lot are determined, and then the charging time required to charge the electric vehicle with the required amount of electricity is determined based on the actual required charging amount and the charging power of the idle charging pile. In addition, the charging attenuation factor of the battery charging and discharging loss, as well as the parameters formed by the charging current output by the idle charging pile and the maximum acceptable charging current of the electric vehicle are also considered to correct the required charging time, and combined with the waiting time before starting charging, the final charging time with high accuracy is formed.

[0116] Furthermore, after obtaining the charging time corresponding to each target parking lot, each charging time is formed into a corresponding relationship with the target parking lot from which it originates, and each corresponding relationship is used as a plurality of charging schemes for the electric vehicle. In addition, considering that some target parking lots are provided with replacement batteries in addition to charging electric vehicles through charging piles, electric vehicle owners can rent replacement batteries when they do not have enough time to wait for the car to charge, and replace the batteries in the electric vehicle by replacing the replacement batteries so that the electric vehicle has sufficient power. Based on this, when generating a charging scheme, it is necessary to consider whether the target parking lot contains replaceable batteries. Specifically, the step of generating a plurality of charging schemes for the electric vehicle according to each of the charging times includes:

[0117] Step S361, determining whether each of the target parking lots includes a replacement battery corresponding to the electric vehicle, and if so, generating a charging plan for the electric vehicle to charge at the target parking lot according to the charging duration and the corresponding second location information of the target parking lot, as well as the replacement battery;

[0118] Step S362: If the corresponding replacement battery is not included, the charging time corresponding to the target parking lot and the corresponding second location information are generated as a charging plan for the electric vehicle to charge at the target parking lot.

[0119] Furthermore, the IoT server analyzes whether there is a battery for replacement of the electric vehicle in the target parking lot based on the relevant data of the received target parking lot. If there is a battery for replacement, the battery model is obtained from the relevant data, and the battery model is compared with the obtained battery model of the electric vehicle to determine whether the two are consistent. If they are consistent, it is determined that the target parking lot contains a replacement battery corresponding to the electric vehicle. On the contrary, if there is no battery for replacement or the model is inconsistent, it can be determined that the target parking lot does not contain a replacement battery corresponding to the electric vehicle.

[0120] Furthermore, for a target parking lot that includes a replacement battery, the corresponding charging time, the second location information, and the replacement battery are generated together as a charging plan for the electric vehicle to charge at the target parking lot. The electric vehicle owner can choose to rent a replacement battery for replacement according to the plan, or go to the location of the target parking lot to charge the electric vehicle according to the second location information when the charging time is acceptable in the plan. For a target parking lot that does not include a replacement battery, the corresponding charging time and the second location information are generated together as a charging plan for the electric vehicle to charge at the target parking lot. The electric vehicle owner can go to the location of the target parking lot to charge the electric vehicle according to the second location information when the charging time is acceptable in the plan.

[0121] This embodiment calculates the charging time required for charging electric vehicles at each target parking lot by combining factors such as the impact of electric vehicle battery loss on charging time, the waiting time for charging, and the charging efficiency of charging piles in the target parking lot. It comprehensively considers various factors that affect the charging time, making the calculation of charging time more accurate. At the same time, a charging plan is generated based on whether each target parking lot has replaceable batteries. While electric vehicle owners choose the target parking lot with the shortest charging time to charge based on the charging time, they can also choose a more time-saving replacement battery to meet the charging needs of different users.

[0122] In addition, the embodiment of the present invention also provides an intelligent traffic control system based on the Internet of Things, and the intelligent traffic control system based on the Internet of Things includes an Internet of Things server. Figure 4 , Figure 4 It is a structural schematic diagram of the equipment hardware operating environment involved in the implementation scheme of the intelligent traffic control system based on the Internet of Things of the present invention.

[0123] like Figure 4 As shown, the Internet of Things server in the smart traffic control system based on the Internet of Things may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a storage 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The storage 1005 may be a high-speed RAM storage, or it may be a stable storage (non-volatile memory), such as a disk storage. The storage 1005 may also be a storage device independent of the aforementioned processor 1001.

[0124] Those skilled in the art will understand that Figure 4 The hardware structure of the Internet of Things server in the Internet of Things-based smart traffic control system shown in the figure does not constitute a limitation of the Internet of Things-based smart traffic control system, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0125] like Figure 4As shown, the storage 1005 as a storage medium may include an operating system, a network communication module, a user interface module and a control program. The operating system is a program for managing and controlling the IoT server and software resources in the IoT-based smart traffic control system, and supports the operation of the network communication module, the user interface module, the control program and other programs or software; the network communication module is used to manage and control the network interface 1004; the user interface module is used to manage and control the user interface 1003.

[0126] exist Figure 4 In the hardware structure of the IoT server of the IoT-based smart traffic control system shown, the network interface 1004 is mainly used to connect to other system servers and communicate data with other system servers; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; the processor 1001 can call the control program stored in the storage 1005 and perform the following operations:

[0127] Acquire traffic flow data of a road traffic intersection and adjacent traffic flow data of an adjacent intersection corresponding to the road traffic intersection, and generate a traffic light control plan for the road traffic intersection based on the traffic flow data and the adjacent traffic flow data;

[0128] Acquiring the remaining power of the electric vehicle, and when the remaining power is less than a preset power threshold, determining a plurality of target parking lots corresponding to the electric vehicle;

[0129] Based on the remaining power and each of the target parking lots, generating a plurality of charging plans for the electric vehicle, and based on each of the charging plans, generating guidance information for guiding a driving path of the electric vehicle;

[0130] Intelligent traffic control is performed based on the traffic light control scheme and the guidance information.

[0131] Furthermore, the step of generating a traffic light control scheme for the road traffic intersection according to the traffic flow data and the adjacent traffic flow data includes:

[0132] Identifying the adjacent vehicle flow data as adjacent inflow data and adjacent outflow data, wherein the adjacent inflow data includes variable inflow data corresponding to variable lanes in the adjacent intersection, and immutable inflow data corresponding to immutable lanes in the adjacent intersection;

[0133] Identify the generation time of the traffic flow data, obtain the historical traffic flow data of the road traffic intersection corresponding to the generation time, and search for weather parameters and road condition parameters corresponding to the generation time;

[0134] The variable inflow data, the immutable inflow data, the adjacent outflow data, the historical vehicle flow data, the weather parameters, the road condition parameters and the vehicle flow data are generated as an input vector, and the input vector is predicted and calculated based on a preset prediction model to generate the vehicle flow change data of the road traffic intersection, wherein the formula used for prediction calculation in the preset prediction model is:

[0135] pt=g(w xo x t +w co (i t *tan(w xc x t +b c ))+b o );

[0136] Among them, pt represents the traffic flow change data, g represents the activation function of the preset prediction model, and w xo Represents the weight matrix between the input layer and the output layer of the preset prediction model, x t represents the input vector, w co Represents the weight matrix between the hidden layer and the output layer of the preset prediction model, i t Represents the hidden layer vector of the preset prediction model, w xc represents the weight matrix between the input layer and the hidden layer of the preset prediction model, b c represents the hidden layer bias vector of the preset prediction model, b o Represents the output layer bias vector of the preset prediction model;

[0137] The traffic light control plan is generated according to the traffic flow change data.

[0138] Furthermore, the IoT server generates a plurality of charging schemes for the electric vehicle based on the remaining power and each of the target parking lots, comprising:

[0139] Determine the battery loss parameter of the electric vehicle according to the historical charging information of the electric vehicle, and find the charging attenuation factor corresponding to the battery loss parameter;

[0140] According to the predicted queue time of each target parking lot, the charging efficiency, charging current and charging power of the idle charging piles in each target parking lot, the charging parameters of the electric vehicle, the remaining power and the charging attenuation factor, the charging time of the idle charging piles in each target parking lot for charging the electric vehicle is calculated, and the calculation formula is:

[0141] hi=ln I1 / I2 *((EE x -si*θ) / Wi)*τi*μ+Hi;

[0142] Where hi represents the charging time corresponding to the i-th target parking lot, I1 represents the charging current of the idle charging pile, I2 represents the maximum acceptable charging current of the electric vehicle in the charging parameters, E represents the battery capacity in the charging parameters, and E x represents the remaining power, si represents the driving distance between the electric vehicle and the i-th target parking lot, θ represents the power consumption per unit mileage in the charging parameters, Wi represents the charging power of the idle charging piles in the i-th target parking lot, τi represents the charging efficiency of the idle charging piles in the i-th target parking lot, μ represents the charging attenuation factor, and Hi represents the predicted queuing time of the i-th target parking lot;

[0143] According to each of the charging times, a plurality of charging plans for the electric vehicle are generated.

[0144] Furthermore, the step of generating a plurality of charging schemes for the electric vehicle according to each of the charging times includes:

[0145] Determine whether each of the target parking lots includes a replacement battery corresponding to the electric vehicle, and if so, generate a charging plan for the electric vehicle to charge at the target parking lot according to the charging duration and the corresponding second location information of the target parking lot, as well as the replacement battery;

[0146] If the corresponding replacement battery is not included, the charging duration corresponding to the target parking lot and the corresponding second location information are generated as a charging plan for the electric vehicle to be charged at the target parking lot.

[0147] Furthermore, the step of determining the battery loss parameter of the electric vehicle according to the historical charging information of the electric vehicle comprises:

[0148] Searching for the number of DC charging times and the number of AC charging times in the historical charging information, and counting the total DC charging durations corresponding to each of the DC charging times, and the total AC charging durations corresponding to each of the AC charging times;

[0149] Acquire a first loss coefficient corresponding to the total DC charging time and a second loss coefficient corresponding to the total AC charging time;

[0150] The mileage of the electric vehicle is obtained, and the battery loss parameter is calculated according to the first loss coefficient, the second loss coefficient, the mileage and the power consumption per unit mileage in the charging parameter, and the calculation formula is:

[0151] w=m1*m2*(q+a*D*θ):

[0152] Among them, w represents the battery loss parameter, m1 represents the first loss coefficient, m2 represents the second loss coefficient, q represents the static loss parameter of the battery of the electric vehicle, a represents the driving loss parameter of the battery of the electric vehicle, D represents the mileage, and θ represents the power consumption per unit mileage in the charging parameter.

[0153] Further, after the step of searching for the charging attenuation factor corresponding to the battery loss parameter, the processor 1001 may call the control program stored in the storage 1005 and perform the following operations:

[0154] For each of the target parking lots, obtaining the number of historical vehicles to be charged that are within a preset range from the target parking lot, and generating a charging probability corresponding to the target parking lot based on the number of historical vehicles to be charged;

[0155] Determine the average number of vehicles to be charged in the target parking lot according to the historical number of vehicles to be charged and the charging probability;

[0156] The predicted queuing time is determined according to the charging efficiency of the idle charging piles in the target parking lot, the average number of cars to be charged, the path distance corresponding to the preset range, and the number of idle charging piles in the target parking lot.

[0157] Furthermore, the step of determining a plurality of target parking lots corresponding to the electric vehicle comprises:

[0158] Acquire first location information of the electric vehicle, and determine a plurality of parking lots supporting charging of the electric vehicle according to the first location information;

[0159] The charging status information of each vehicle charging pile in the plurality of parking lots is obtained, and a target parking lot with idle charging piles is determined from each parking lot according to the charging status information.

[0160] Furthermore, the step of generating guidance information for guiding the driving path of the electric vehicle based on each of the charging schemes includes:

[0161] Transmitting each of the charging schemes to the electric vehicle, and receiving a selection instruction based on a response from the electric vehicle;

[0162] Determine a target charging scheme from the charging schemes according to the selection instruction;

[0163] The second position information corresponding to the target charging scheme is determined, and guidance information is generated according to the first position information and the second position information to guide the driving path of the electric vehicle.

[0164] The specific implementation methods of the smart traffic control system based on the Internet of Things of the present invention are basically the same as the above-mentioned embodiments of the smart traffic control method based on the Internet of Things, and will not be repeated here.

[0165] The embodiment of the present invention further provides a storage medium having a control program stored thereon, and when the control program is executed by a processor, the steps of the above-mentioned smart traffic control method based on the Internet of Things are implemented.

[0166] The storage medium of the present invention may be a computer-readable storage medium, and its implementation method is basically the same as the above-mentioned embodiments of the smart traffic control method based on the Internet of Things, and will not be repeated here.

[0167] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims. All equivalent structures or equivalent process changes made using the contents of the specification and drawings of the present invention, or directly or indirectly used in other related technical fields, are protected by the present invention.

Claims

1. A smart traffic control method based on the Internet of Things, characterized in that: Applied to the Internet of Things server, the smart traffic control method includes: The Internet of Things server obtains the traffic flow data of the road traffic intersection and the adjacent traffic flow data of the adjacent intersection corresponding to the road traffic intersection, and generates a traffic light control plan for the road traffic intersection according to the traffic flow data and the adjacent traffic flow data; The Internet of Things server obtains the remaining power of the electric vehicle, and when the remaining power is less than a preset power threshold, determines a plurality of target parking lots corresponding to the electric vehicle; The IoT server generates a plurality of charging schemes for the electric vehicle based on the remaining power and each of the target parking lots, and generates guidance information for guiding the driving path of the electric vehicle based on each of the charging schemes; The Internet of Things server performs intelligent traffic control based on the traffic light control scheme and the guidance information; The step of generating a plurality of charging schemes for the electric vehicle based on the remaining power and each of the target parking lots by the IoT server includes: Determine the battery loss parameter of the electric vehicle according to the historical charging information of the electric vehicle, and find the charging attenuation factor corresponding to the battery loss parameter; According to the predicted queuing time of each target parking lot, the charging efficiency, charging current and charging power of the idle charging piles in each target parking lot, the charging parameters of the electric vehicle, the remaining power and the charging attenuation factor, the charging time of the idle charging piles in each target parking lot for charging the electric vehicle is calculated, and the calculation formula is: hi / ln I1 / I2 *((YES x -si*θ) / Wi)*τi*μ+Hi Where hi represents the charging time corresponding to the i-th target parking lot, I1 represents the charging current of the idle charging pile, I2 represents the maximum acceptable charging current of the electric vehicle in the charging parameters, E represents the battery capacity in the charging parameters, and E x represents the remaining power, si represents the driving distance between the electric vehicle and the i-th target parking lot, θ represents the power consumption per unit mileage in the charging parameters, Wi represents the charging power of the idle charging piles in the i-th target parking lot, τi represents the charging efficiency of the idle charging piles in the i-th target parking lot, μ represents the charging attenuation factor, and Hi represents the predicted queuing time of the i-th target parking lot; According to each of the charging times, a plurality of charging plans for the electric vehicle are generated.

2. The intelligent traffic control method according to claim 1, characterized in that: The step of generating a traffic light control scheme for the road traffic intersection according to the traffic flow data and the adjacent traffic flow data comprises: Identifying the adjacent vehicle flow data as adjacent inflow data and adjacent outflow data, wherein the adjacent inflow data includes variable inflow data corresponding to variable lanes in the adjacent intersection, and immutable inflow data corresponding to immutable lanes in the adjacent intersection; Identify the generation time of the traffic flow data, obtain the historical traffic flow data of the road traffic intersection corresponding to the generation time, and search for weather parameters and road condition parameters corresponding to the generation time; The variable inflow data, the immutable inflow data, the adjacent outflow data, the historical vehicle flow data, the weather parameters, the road condition parameters and the vehicle flow data are generated as an input vector, and the input vector is predicted and calculated based on a preset prediction model to generate the vehicle flow change data of the road traffic intersection, wherein the formula used for prediction calculation in the preset prediction model is: pt=g(w xo x t +w co (i t *tan(w xc x t +b c ))+b o ); Among them, pt represents the traffic flow change data, g represents the activation function of the preset prediction model, and w xo Represents the weight matrix between the input layer and the output layer of the preset prediction model, x t represents the input vector, w co Represents the weight matrix between the hidden layer and the output layer of the preset prediction model, i t Represents the hidden layer vector of the preset prediction model, w xc represents the weight matrix between the input layer and the hidden layer of the preset prediction model, b c represents the hidden layer bias vector of the preset prediction model, b o Represents the output layer bias vector of the preset prediction model; The traffic light control plan is generated according to the traffic flow change data.

3. The intelligent traffic control method according to claim 1, characterized in that: The step of generating a plurality of charging schemes for the electric vehicle according to each of the charging durations comprises: Determine whether each of the target parking lots includes a replacement battery corresponding to the electric vehicle, and if so, generate a charging plan for the electric vehicle to charge at the target parking lot according to the charging duration and the corresponding second location information of the target parking lot, as well as the replacement battery; If the corresponding replacement battery is not included, the charging duration corresponding to the target parking lot and the corresponding second location information are generated as a charging plan for the electric vehicle to be charged at the target parking lot.

4. The intelligent traffic control method according to claim 1, characterized in that: The step of determining the battery loss parameter of the electric vehicle according to the historical charging information of the electric vehicle comprises: Searching for the number of DC charging times and the number of AC charging times in the historical charging information, and counting the total DC charging durations corresponding to each of the DC charging times, and the total AC charging durations corresponding to each of the AC charging times; Acquire a first loss coefficient corresponding to the total DC charging time and a second loss coefficient corresponding to the total AC charging time; The mileage of the electric vehicle is obtained, and the battery loss parameter is calculated according to the first loss coefficient, the second loss coefficient, the mileage and the power consumption per unit mileage in the charging parameter, and the calculation formula is: w=m1*m2*(q+a*D*θ): Among them, w represents the battery loss parameter, m1 represents the first loss coefficient, m2 represents the second loss coefficient, q represents the static loss parameter of the battery of the electric vehicle, a represents the driving loss parameter of the battery of the electric vehicle, D represents the mileage, and θ represents the power consumption per unit mileage in the charging parameter.

5. The intelligent traffic control method according to claim 1, characterized in that: The step of searching for the charging attenuation factor corresponding to the battery loss parameter includes: For each of the target parking lots, obtaining the number of historical vehicles to be charged that are within a preset range from the target parking lot, and generating a charging probability corresponding to the target parking lot based on the number of historical vehicles to be charged; Determine the average number of vehicles to be charged in the target parking lot according to the historical number of vehicles to be charged and the charging probability; The predicted queuing time is determined according to the charging efficiency of the idle charging piles in the target parking lot, the average number of cars to be charged, the path distance corresponding to the preset range, and the number of idle charging piles in the target parking lot.

6. The intelligent traffic control method according to any one of claims 1 to 5, characterized in that: The step of determining a plurality of target parking lots corresponding to the electric vehicle comprises: Acquire first location information of the electric vehicle, and determine a plurality of parking lots supporting charging of the electric vehicle according to the first location information; The charging status information of each vehicle charging pile in the plurality of parking lots is obtained, and a target parking lot with idle charging piles is determined from each parking lot according to the charging status information.

7. The intelligent traffic control method according to claim 6, characterized in that: The step of generating guidance information for guiding the driving path of the electric vehicle based on each of the charging schemes includes: Transmitting each of the charging schemes to the electric vehicle, and receiving a selection instruction based on a response from the electric vehicle; Determine a target charging scheme from the charging schemes according to the selection instruction; The second position information corresponding to the target charging scheme is determined, and guidance information is generated according to the first position information and the second position information to guide the driving path of the electric vehicle.

8. An intelligent traffic control system based on the Internet of Things, characterized in that: The IoT-based intelligent traffic control system includes an IoT server, which is provided with a storage, a processor, a communication bus, and a control program stored on the storage: The communication bus is used to realize the connection and communication between the processor and the storage; The processor is used to execute the control program to implement the steps of the smart traffic control method based on the Internet of Things as described in any one of claims 1-7.

9. A storage medium, characterized in that: The storage medium stores a control program, and when the control program is executed by the processor, the steps of the smart traffic control method based on the Internet of Things as described in any one of claims 1 to 7 are implemented.

Images