Intelligent traffic management and control system based on Internet of Things

Abstract

The invention discloses an intelligent traffic management and control system based on the Internet of Things, relates to the technical field of traffic management and control, and aims to optimize urban traffic flow through accurate monitoring and dynamic regulation and control. The system comprises a traffic data acquisition module which monitors the vehicle flow in real time by using a monitoring camera and calculates the average vehicle flow in combination with a sampling period; the traffic signal initial regulation module analyzes flow change in a monitoring period, draws a flow broken line and determines initial regulation green light time; the regulation and control signal control module monitors the current flow in real time and triggers a regulation and control mechanism when the current flow exceeds the saturated flow; the traffic advanced regulation and control module calculates a demand weight according to parameters such as current flow and saturation flow, dynamically adjusts green light duration and ensures smooth traffic; the system integrates real-time monitoring and data analysis, realizes fine management of traffic signals, improves urban road traffic efficiency, reduces congestion, and provides technical support for intelligent traffic construction.

Description

Technical Field

[0001] The present invention belongs to the technical field of traffic control, and specifically relates to an intelligent traffic control system based on the Internet of Things. Background Art

[0002] Although the existing traffic control system has alleviated traffic pressure to a certain extent, it still has some shortcomings compared with the smart traffic control system based on the Internet of Things. The traditional traffic control system mainly relies on fixed traffic signal light durations and cannot be dynamically adjusted according to traffic flow in real time. This leads to the green light time being insufficient to evacuate vehicles during peak traffic hours or special periods, causing congestion. During periods of low traffic flow, excessive green light time causes a waste of road resources. In addition, the existing system usually only controls traffic lights based on fixed durations or simple historical data, lacks the ability to fine-tune the control of different time periods and different nodes, and is difficult to adapt to the complex changes in urban traffic flow.

[0003] In order to solve the above problems, the present invention proposes an intelligent traffic control system based on the Internet of Things. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides an intelligent traffic control system based on the Internet of Things to solve the problem that the traffic light time in the existing traffic control system is fixed and rigid and cannot adapt to changes in traffic flow in real time.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The intelligent traffic control system based on the Internet of Things includes the following:

[0007] The traffic data collection module obtains an urban traffic road, uses traffic lights as nodes, obtains the urban traffic road segment between any two adjacent nodes, monitors and extracts the total number of vehicles in the corresponding urban traffic road segment in real time, and determines the average vehicle flow associated with the current urban traffic road segment;

[0008] The traffic signal initial adjustment module obtains the monitoring period and determines the average vehicle flow associated with all hours in this monitoring period;

[0009] Select several monitoring periods, determine the average vehicle flow in all hours associated with the several monitoring periods, and lock the fitted vehicle flow associated with any hour in a monitoring period;

[0010] Determine, based on the fitted vehicle flows in different hours, the preliminary control green light time associated with the second node of the urban traffic road segment in different hours;

[0011] The control signal control module monitors the average vehicle flow in the current urban traffic road section in real time and verifies it. If the saturated vehicle flow of this urban traffic road section is exceeded, an advanced control signal will be issued. Otherwise, continuous monitoring will be carried out;

[0012] The advanced traffic control module receives the control signal and performs advanced control on the green light time of the second node based on the determined average vehicle flow in the current urban traffic road section, so that the green light time of the current urban traffic road section conforms to the current average vehicle flow.

[0013] As a further solution of the present invention, in the traffic data collection module, the traffic light where the vehicle enters the urban traffic road section is marked as the first node;

[0014] The traffic light where the vehicle leaves the urban traffic road section is marked as the second node.

[0015] As a further solution of the present invention, in the traffic data collection module, the specific method of determining the average vehicle flow associated with the current urban traffic road segment is:

[0016] S31, obtain the preset sampling period, the sampling period time is recorded as T sap , where the sampling period T sap Less than 10 minutes;

[0017] S32, determine the sampling period T sap The total number of moments within is denoted as j;

[0018] S33, within the sampling period, monitoring in real time the incoming vehicle flow ITF of the urban traffic road segment entering through the first node and the outgoing vehicle flow DVF of the urban traffic road segment exiting through the second node;

[0019] S34, determine the j incoming vehicle flows associated with the j moments in this sampling period, sort them in the order of the timeline, and obtain the incoming vehicle flow sequence ITF1, ITF2, ..., ITF j ;

[0020] Similarly, we can get the leaving vehicle flow sequence DVF1, DVF2, ..., DVF j ;

[0021] S35, extract ITF1, ITF2, ..., ITF j Any one of the incoming vehicle flows is recorded as ITF i Similarly, determine the departure vehicle flow at the corresponding time, recorded as DVF i , where i is a counting index, 1≤i≤j, representing any moment among j moments;

[0022] S36, DVFi with the ITF i The accumulated vehicle flow rate RAT associated with time i i ;

[0023] S37, repeat steps S35 to S36, determine the j-time vehicle flows associated with the j-times and summarize them to obtain the sampling period vehicle flows associated with the sampling period;

[0024] S38. Obtain the total number n of continuous sampling cycles preset by the operator, where 1≤n≤6;

[0025] Continuously monitor n sampling periods to obtain the vehicle flow in n sampling periods;

[0026] The average vehicle flow rate of n sampling periods is taken as the average vehicle flow rate associated with the urban traffic road segment, which is recorded as

[0027] As a further solution of the present invention, in the traffic signal initial adjustment module, the specific method of locking the fitted vehicle flow associated with any hour in a monitoring cycle is:

[0028] Determine the monitoring period;

[0029] The monitoring period is 24 hours, from 0:00 to 24:00 a.m.

[0030] The average vehicle flow associated with each hour in a monitoring period is determined by the method described in steps S31 to S38, and the 24 average vehicle flows obtained are sorted in chronological order to obtain an average vehicle flow sequence.

[0031] Obtain m average vehicle flow sequences associated with urban traffic road segments within m monitoring periods, where m is an integer preset by an operator and is greater than 0;

[0032] The average of the 24m average vehicle flows in the m average vehicle flow sequences is taken according to the corresponding hour as the fitted vehicle flow associated with the corresponding hour.

[0033] As a further solution of the present invention, in the traffic signal preliminary adjustment module, the specific method of determining the preliminary adjustment green light time associated with the second node of the urban traffic road section in different hours is:

[0034] Construct a two-dimensional coordinate system with the timeline as the horizontal axis and the average vehicle flow value as the vertical axis;

[0035] Mark the 24 fitted vehicle flows in the form of bars in the two-dimensional coordinate system in the order of the time line to obtain 24 bars, and obtain the top midpoints of the 24 bars to obtain 24 data points;

[0036] Connect two adjacent data points with short lines to get the fitted vehicle flow line Z;

[0037] Then take the average of the 24 fitted vehicle flows and record it as the quadratic average vehicle flow;

[0038] Determine the scale of the quadratic average vehicle flow on the vertical axis, and construct a straight line L perpendicular to the vertical axis and parallel to the horizontal axis through the scale;

[0039] Determine the portion of Z above line L and label it Z1;

[0040] Determine the portion of Z below line L and label it Z2;

[0041] Count the total number of hours in Z1, denoted as o;

[0042] The total number of hours in Z2 is 24-o. When an hour is completely below the line L, it is classified as Z2, otherwise it is classified as Z1.

[0043] The preliminary green light time of the second node of the urban traffic road section associated with 24-o hours in Z2 is adjusted to the second node basic green light time G preset by the operator found2 ;

[0044] Then determine the fitted vehicle flow associated with o hours, subtract the quadratic average vehicle flow, and obtain o over-limit vehicle flows;

[0045] Take any one of the o over-limit vehicle flows and mark it as OVF u , where u represents any one of the o overloaded vehicle flows;

[0046] Determine OVF u The associated upward adjustment ratio α u , and use the increase ratio α u Get the initial green light time associated with the uth hour in o hours;

[0047] Repeat the above steps and perform the same processing on o hours to obtain the preliminary control green light time associated with each o hour.

[0048] As a further solution of the present invention, in the traffic signal initial adjustment module, the increase ratio α is used u The specific method of obtaining the initial green light time associated with the uth hour in o hours is:

[0049] Based on the determined over-limit vehicle flow OVF u and the secondary average vehicle flow, adopt to obtain the associated upward adjustment ratio α for the u-th hour in o hours u ;

[0050] Utilize the upward adjustment ratio α u to adjust G found2 upward, and obtain the preliminary regulated green light time G found2 *α u .

[0051] As a further solution of the present invention, the regulation signal control module monitors the average vehicle flow of the current urban traffic road section in real time, denoted as Q;

[0052] Compare the monitored average vehicle flow Q with the saturated vehicle flow S of this urban traffic road section, where the saturated vehicle flow S is obtained by the operator combining experience and actual measurement;

[0053] If Q≥S, generate an advanced regulation signal and send it to the traffic signal advanced regulation module;

[0054] If Q<S, regulate the green light time of the second node of the urban traffic road section to the preliminary regulated green light time associated with the corresponding hour, and continuously monitor.

[0055] As a further solution of the present invention, in the traffic advanced regulation module, the specific methods for respectively performing advanced regulation on the green light times of the first node and the second node are as follows:

[0056] Obtain the basic green light time G found2 of the second node of the urban traffic road section;

[0057] Obtain the current green light time of the second node, denoted as G now2 ;

[0058] Adopt: Calculate the demand weight ω2 associated with the basic green light time of the second node;

[0059] Obtain the total green light time G total2 of the second node, where the total green light time G total2 is a value preset by the operator.

[0060] Utilize G total2 minus G now2 to obtain the total available green light time G avai at the current time of the second node; ​​​​​​avai *ω2) Get the green light time G after regulation new , where G new ≤G total2 ;

[0062] To control the green light time G new2 , and regulate the second node of the urban traffic road section.

[0063] Beneficial effects of the present invention:

[0064] (1) The present invention monitors the flow of incoming and outgoing vehicles in real time by setting a first node and a second node, and then calculates the average vehicle flow, thereby clarifying the vehicle traffic conditions of urban traffic road sections; secondly, setting a sampling period ensures the real-time and timeliness of data collection, which can quickly reflect changes in traffic flow and enable management and control measures to respond to dynamic changes in traffic conditions in a timely manner; furthermore, the average vehicle flow is determined by taking the average value of continuous sampling periods, which effectively reduces the error caused by short-term traffic fluctuations and improves the accuracy and reliability of the data;

[0065] (2) The present invention significantly improves the operating efficiency and response accuracy of the intelligent transportation system through the intelligent processing and dynamic control mechanism of multi-period vehicle flow data; its core advantages are: first, based on multi-day historical data, the traffic flow pattern is fitted, and through the 24-hour monitoring cycle and the average processing of multiple sequences, random fluctuations are effectively filtered out to generate a more stable benchmark traffic flow model (fitted vehicle flow), providing a high-credibility basis for decision-making; second, the "quadratic average vehicle flow" is innovatively adopted as the dynamic control baseline, and combined with the upper and lower area divisions of the fitted vehicle flow line, the traffic peak and valley periods are intelligently identified, making the signal timing more in line with actual needs; finally, the green light duration is accurately increased according to the proportion of over-limit vehicle flow, realizing the refined control of "the greater the traffic flow, the longer the green light", avoiding the disadvantages of fixed timing or extensive grading; this reduces peak congestion, shortens vehicle delays, and reduces invalid green light time, thereby improving the overall road network resource utilization;

[0066] (3) The present invention effectively copes with sudden congestion by introducing a saturated flow threshold to trigger advanced control. It uses a demand weight algorithm to accurately quantify the degree of congestion and dynamically reallocates green light resources accordingly. On the premise of ensuring the basic travel time, the remaining green light time is intelligently allocated according to the weight ratio. This maximizes the intersection throughput in extreme congestion and avoids the cycle disorder caused by blindly extending the green light, thus realizing on-demand resource allocation and rapid congestion relief. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The present invention will be further described below with reference to the accompanying drawings.

[0068] Figure 1It is a structural diagram of the system of the present invention;

[0069] Figure 2 Schematic diagram of the process of the method described in Example 2 of the present invention;

[0070] Figure 3 Schematic diagram of the process of the method described in Example 3 of the present invention. DETAILED DESCRIPTION

[0071] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0072] Example 1

[0073] Smart traffic control system based on the Internet of Things, such as Figure 1 As shown, this system includes the following:

[0074] This solution: An intelligent traffic control system based on the Internet of Things focuses on regulating traffic lights (traffic lights) on urban traffic roads, so that traffic lights on different urban traffic road sections can adapt to the vehicle flow of the current urban traffic road section.

[0075] This system mainly includes traffic data acquisition module, traffic signal initial adjustment module, traffic signal control module and traffic advanced adjustment module.

[0076] Among them, the traffic data collection module adopts the form of an edge computing gateway to collect data, divides the urban traffic roads by traffic lights, and takes the urban traffic road between two adjacent traffic lights as an urban traffic road segment, and marks the traffic light where the vehicle enters the urban traffic road segment as the first node, and the traffic light where the vehicle leaves the urban traffic road segment as the second node.

[0077] Utilize edge computing gateways in conjunction with surveillance cameras installed on traffic lights (the total number of vehicles can be accurately counted through AI video analyzers, and this technology is currently feasible, so it is not elaborated on in this solution) to monitor and extract the total number of vehicles entering and leaving the corresponding urban traffic road section in real time, and further obtain the average vehicle flow associated with the current urban traffic road section.

[0078] Next, in the traffic signal initial adjustment module, the above method is used to determine the average vehicle flow associated with all hours (a total of 24 hours) within a monitoring period (the time span of a monitoring period is from 0:00 to 24:00 a.m. a day, i.e. 24 hours) (calculate the average vehicle flow associated with each hour).

[0079] Next, determine when the corresponding urban traffic road section is in a normal traffic state (this is a limiting condition to avoid special circumstances from interfering with the data), monitor several monitoring cycles, and then determine the average vehicle flow of all hours associated with each of the several monitoring cycles (determine the average vehicle flow associated with each hour of the 24 hours in each monitoring cycle).

[0080] The average vehicle flow of the corresponding hours in several monitoring periods is fitted to obtain the fitted vehicle flow associated with 24 hours.

[0081] For example: there are 100 monitoring cycles. The average vehicle flow within 0-1 hours in the 100 monitoring cycles is taken to obtain 100 average vehicle flows. The 100 average vehicle flows are then fitted to obtain a final average vehicle flow. The fitted average vehicle flow within 0-1 hours of this day is recorded as the fitted vehicle flow associated with 0-1 hours.

[0082] The purpose of the fitted vehicle flow for each hour of the day obtained in the above steps is to obtain an equilibrium value, which represents the vehicle flow in each hour when the current urban traffic roads are in a normal traffic state.

[0083] Based on the fitted vehicle flow associated with different hours of the day, the preliminary control green light time of the second node of this urban traffic road section within the corresponding hour is further determined (the preliminary control green light time is derived from the fitted vehicle flow, the principle is: the greater the fitted vehicle flow within the corresponding hour, the longer the preliminary control green light time within the corresponding hour, and the maximum preliminary control green light time shall not exceed the prescribed time).

[0084] At this point, the preliminary control of traffic lights on any urban traffic road section has been completed. However, in reality, urban traffic road sections are not in a very stable vehicle flow situation. If the vehicle flow surges or the number of people traveling on holidays increases, traffic jams often occur, which greatly increases the risk of traffic accidents. Based on this, this solution provides a signal control module and an advanced traffic control module to handle the above situations.

[0085] The control signal control module also relies on the edge computing gateway combined with the surveillance cameras installed on the traffic lights to conduct real-time monitoring of the corresponding urban traffic road sections, obtain the average vehicle flow in the urban traffic road section, and verify and compare it with the saturated vehicle flow preset by the operator. If the saturated vehicle flow of this urban traffic road section is exceeded, an advanced control signal will be issued, otherwise continuous monitoring will be carried out. Among them, the saturated vehicle flow is obtained by the operator based on experience and actual measurements, indicating the maximum average vehicle flow that the current urban traffic road can carry under the initial control green light time associated with the fitted vehicle flow of the corresponding hour (the initial control green light time associated with the fitted vehicle flow has a certain redundancy).

[0086] When an advanced control signal is issued, it means that the current preliminary control green light time cannot bear the average vehicle flow of the current corresponding urban traffic road.

[0087] The advanced traffic control module receives the control signal sent by the control signal control module and obtains the average vehicle flow of the corresponding urban traffic road section monitored in real time by the control signal control module, and performs advanced control on the green light time of the second node (the reason for only the green light time of the second node here is that the first node of the corresponding urban traffic road section is also the second node of the previous urban traffic road section, so the advanced control is performed on the previous urban traffic road section, so here only the green light time of the second node of the urban traffic road section is advanced controlled) to make the green light time of the second node of the current urban traffic road section consistent with the current average vehicle flow.

[0088] This embodiment aims to optimize traffic flow by adaptively regulating traffic lights on urban traffic road sections; as described above, this system includes a traffic data acquisition module, a traffic signal initial adjustment module, a signal control module, and an advanced traffic regulation module.

[0089] This system uses edge computing gateways and surveillance cameras to collect vehicle data from each road section, calculates the average vehicle flow in each time period, and determines the preliminary green light time for regulation; at the same time, by comparing the average vehicle flow in real time with the preset saturated vehicle flow, if traffic overload occurs, it triggers advanced regulation and further adjusts the green light time.

[0090] The purpose of this solution is to improve urban traffic efficiency, reduce congestion and potential accidents, enable traffic light durations to flexibly match actual traffic conditions, and achieve intelligent and dynamic management of traffic signals.

[0091] Example 2

[0092] This embodiment further discloses a method for determining the average vehicle flow associated with a corresponding urban traffic road segment based on embodiment 1, such as Figure 2As shown, the specific steps include:

[0093] First, in this embodiment, it is necessary to determine the sampling period first. The specific value of the sampling period is determined by the operator (set in combination with the actual situation). Generally, the duration of a sampling period is less than 10 minutes (the reason is: vehicle flow is dynamic and real-time, especially during peak hours, the vehicle flow may fluctuate greatly in a short period of time. If the sampling period is too long, the data will not be able to reflect the actual traffic flow changes in a timely manner, thereby affecting the system's precise control of traffic signals; a shorter sampling period can more keenly capture the real-time changes in traffic flow, allowing the system to quickly respond to changes in traffic conditions).

[0094] Next, obtain the sampling period and the time of the sampling period preset by the operator, and mark the time of the sampling period as: T sap .

[0095] Then determine a sampling period T sap The total number of moments within is denoted as j.

[0096] According to the content described in the embodiment, a first node and a second node corresponding to the urban traffic road are determined, and the incoming vehicle flow passing through the first node and entering the urban traffic road segment is monitored in real time by a surveillance camera equipped on the first node within a sampling period, and marked as: ITF;

[0097] Similarly, the surveillance camera equipped on the second node is used to monitor in real time the flow of vehicles leaving the urban traffic road section passing through the second node, which is marked as DVF.

[0098] Combined with a sampling period T sap At j moments in the time series, determine the incoming vehicle flows associated with the j moments, and sort the j incoming vehicle flows associated with the j moments in the order of the timeline to obtain the incoming vehicle flow sequence, which is expressed as: ITF1, ITF2, ..., ITF j ;

[0099] Similarly, determine the j outgoing vehicle flows associated with j moments in this sampling period and sort them in the order of the timeline to obtain the outgoing vehicle flow sequence, which is expressed as: DVF1, DVF2, ..., DVF j .

[0100] Next, determine any moment i among the j moments in this sampling period, where i is a counting index and the value range of i is 1 to j;

[0101] Then obtain the incoming vehicle flow ITF associated with time i i and the departing vehicle flow DVFi , by using the ITF of the incoming vehicle flow i and departing vehicle flow DVF i The vehicle flow associated with time i is obtained by adding them together, which is expressed as: RAT i .

[0102] At this point, the calculation of the vehicle flow RAT corresponding to time i is completed i Repeat this step and perform the same operation on the j outgoing vehicle flows and j incoming vehicle flows associated with j moments in the sampling period. Finally, the vehicle flows at a total of j moments can be obtained. The vehicle flows at j moments are accumulated and summarized to obtain the sampling period vehicle flows associated with this sampling period.

[0103] Next, the total number n of consecutive sampling cycles associated with the average vehicle flow preset by the operator is obtained, where the total number n of consecutive sampling cycles is greater than 1 and less than 6 (the calculation time associated with the average vehicle flow is controlled within one hour, because the sampling cycle time is less than 10 minutes, which is convenient for subsequent processing of Pinjun vehicle flow within one hour).

[0104] According to the method described above, n sampling periods are continuously monitored to finally obtain the vehicle flow of n sampling periods. Then, the vehicle flow of n sampling periods is averaged to obtain the average value of the vehicle flow of n sampling periods. The average value is used as the average vehicle flow associated with the current urban traffic road segment, which is recorded as

[0105] Example 3

[0106] This embodiment further discloses a method for determining the preliminary green light time associated with any hour in a day by the traffic signal preliminary adjustment module based on the embodiment 1 and the embodiment 2, such as Figure 3 As shown, specifically including the following:

[0107] First, the monitoring cycle needs to be determined. In this solution, the duration of a monitoring cycle is set to 24 hours, and the time span of the monitoring cycle is from 0:00 to 24:00 a.m., that is, one day is a monitoring cycle.

[0108] Determine any monitoring period and the corresponding urban traffic road segment (the same traffic road segment as described in Example 2 and Example 1).

[0109] According to the content described in Example 2, the average vehicle flow associated with each hour in this monitoring period is determined, and finally 24 average vehicle flows are obtained. The 24 determined average vehicle flows are sorted in chronological order to obtain an average vehicle flow sequence, which is expressed as:

[0110] Then continue to determine m monitoring cycles, and monitor the current urban traffic road section for m monitoring cycles, and finally determine m average vehicle flow sequences, where m is an integer preset by the operator, and m is greater than 0 (as described in Example 1, within the m monitoring cycles, the corresponding urban traffic road sections must all be in a normal traffic state).

[0111] So far, a total of m average vehicle flow sequences have been obtained. Each average vehicle flow sequence contains 24 average vehicle flows, so a total of 24m average vehicle flows are obtained.

[0112] Next, obtain m average vehicle flows corresponding to one hour (for example, the average vehicle flows from 0 o'clock to 1 o'clock in the sequence of m average vehicle flows), and then take the average of the m average vehicle flows in the corresponding hour (fitting processing) to obtain the fitted vehicle flows associated with the corresponding hour. The average vehicle flows associated with other hours are processed in the same way, and finally 24 fitted vehicle flows after averaging processing are obtained.

[0113] Next, a two-dimensional coordinate system is constructed, wherein the horizontal axis of the two-dimensional coordinate system represents the time line (0 o'clock to 24 o'clock), and the vertical axis of the two-dimensional coordinate system represents the value of the average vehicle flow.

[0114] The 24 fitted vehicle flows associated with the 24 hours of the day obtained above are marked in the form of bars in the constructed two-dimensional coordinate system in the order of the timeline, and finally 24 bars are obtained. Then, the top midpoints of the 24 bars are determined, and finally 24 data points are obtained;

[0115] Get any two adjacent data points and connect them with a short line. Similarly, for 24 data points, connect any two adjacent data points with a short line, and finally get a straight line, which is recorded as the fitted vehicle flow line, denoted by Z.

[0116] Then obtain 24 fitting vehicle flows and average the 24 fitting vehicle flows to get an average value, which is recorded as the quadratic average vehicle flow. Then, determine the scale of the quadratic average vehicle flow on the vertical axis in the constructed two-coordinate system, and construct a straight line perpendicular to the vertical axis and parallel to the horizontal axis through the scale, and record it as L.

[0117] Next, the portion of the fitted vehicle flow broken line Z located above the straight line L is further determined and marked as Z1. Similarly, the portion of the fitted vehicle flow broken line Z located below the straight line L is determined and marked as Z2.

[0118] Next, based on the determined Z1, the total number of hours is extracted and recorded as o, so the total number of hours in Z2 is 24-o (it needs to be explained here that only when an hour is completely below the straight line L will it be considered as an hour in Z2, that is, as long as a part of the fitted vehicle flow curve associated with an hour is above the straight line L, then this hour will be classified into Z1).

[0119] Get the second node basic green light time G preset by the operator found2 , the second node basic green light time G found2 It refers to the green light time of the corresponding urban traffic road section under normal traffic conditions, which actually needs to be determined by the operator based on the actual situation.

[0120] The preliminary green light time of the second node of the urban traffic road section associated with 24-o hours in Z2 is adjusted to the basic green light time G of the second node found2 .

[0121] Then, the fitted vehicle flows associated with the remaining o hours are further determined, and the quadratic average vehicle flows are subtracted from the fitted vehicle flows associated with the o hours, and finally o over-limit vehicle flows are obtained.

[0122] The following steps are to extract any one of the o over-limit vehicle flows for example processing, and the remaining over-limit vehicle flows are processed in the same way;

[0123] Mark any extracted over-limit vehicle flow as OVF u , where u represents any one of the o overloaded vehicle flows.

[0124] Obtain overload vehicle flow OVF u and the quadratic average vehicle flow, by adopting:

[0125]

[0126] Calculate the increase ratio α associated with the uth hour in o hours u , based on the determined increase ratio α u Basic green time G for the second node found2 Execute the upward adjustment operation to obtain the initial green light time G associated with the uth hour in o hours found2 *α u ;

[0127] Repeat the above steps and perform the same processing on o hours to obtain the preliminary control green light time associated with each o hour.

[0128] This embodiment analyzes the vehicle flow of urban traffic road segments within a monitoring period (24 hours) to determine the process for preliminary green light time regulation. First, the average vehicle flow for each hour within a monitoring period is determined to form an average vehicle flow sequence. Then, by fitting data from multiple monitoring periods, a fitted vehicle flow for each hour is obtained. Next, a coordinate system is constructed based on these fitted vehicle flows, a fitted vehicle flow polyline is plotted, and a quadratic average vehicle flow is calculated. Hours with a vehicle flow below the quadratic average are classified, and the green light time of the corresponding second node is set as the base green light time of the second node.

[0129] For hours above the average, the excess vehicle flow and the upward adjustment ratio are calculated to adjust the green light time at the second node; the purpose of this process is to achieve intelligent control of traffic lights, so that the green light duration matches the actual flow to optimize traffic flow.

[0130] Example 4

[0131] This embodiment further discloses a method for advanced control of the green light time of the second node based on the first, second, and third embodiments, which specifically includes the following:

[0132] This embodiment is mainly aimed at the situation where the vehicle flow on urban traffic road sections surges.

[0133] First, the average vehicle flow of this urban traffic road section is monitored in real time, denoted as Q, and the monitored average vehicle flow is compared with the saturated vehicle flow of this urban traffic road section (denoted as S);

[0134] If the average vehicle flow Q is greater than or equal to the saturated vehicle flow S, an advanced control signal is generated and sent to the traffic signal advanced control module;

[0135] If the average vehicle flow Q is less than the saturated vehicle flow S, the green light time of the second node of the current urban traffic road segment is adjusted to the preliminary adjusted green light time associated with the corresponding hour and continuously monitored.

[0136] When the average vehicle flow Q is greater than or equal to the saturated vehicle flow S, advanced control is required, which mainly includes the following steps:

[0137] First, obtain the second node basic green light time G of the current urban traffic road segment found2 , get the current green light time of the second node and mark it as G now2 .

[0138] Calculate the demand weight ω2 associated with the basic green time of the second node. The specific calculation method is:

[0139]

[0140] Among them, Q is the average vehicle flow associated with the current urban traffic road segment, and S is the saturated vehicle flow of the current urban traffic road segment.

[0141] Then get the total green light time G of the second node total2 (Generally, each traffic light has a fixed maximum green light time, which is named the total green light time in this solution, and the total green light time G total2 preset by the operator).

[0142] Then, by using: G avai =G total2 -G now2 Calculate the total available green time G associated with the current time of the second node avai ;

[0143] Then, by using: G new =G now2 +round(G avai *ω2) Get the green light time G after regulation new , where G new Less than or equal to G total2 ;

[0144] At this point, the real-time associated green light time G of the second node is obtained. new2 , adjust the green light time of the second node of the urban traffic road section to the green light time G new2 .

[0145] Some of the data in the formulas described above are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0146] The above contents are merely examples and explanations of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in similar ways. As long as they do not deviate from the invention or exceed the scope defined by the claims, they should all fall within the scope of protection of the present invention.

[0147] It is important to note that all user data collected in this application is collected with the user's consent and authorization. Furthermore, the use of user data is legal and compliant, and the use and processing of user data complies with the relevant laws, regulations, and standards of the relevant regions.

Claims

1. The intelligent traffic control system based on the Internet of Things is characterized by: This system includes the following: The traffic data collection module obtains an urban traffic road, uses traffic lights as nodes, obtains the urban traffic road segment between any two adjacent nodes, monitors and extracts the total number of vehicles in the corresponding urban traffic road segment in real time, and determines the average vehicle flow associated with the current urban traffic road segment; The traffic signal initial adjustment module obtains the monitoring period and determines the average vehicle flow associated with all hours in this monitoring period; Select several monitoring periods, determine the average vehicle flow in all hours associated with the several monitoring periods, and lock the fitted vehicle flow associated with any hour in a monitoring period; Determine, based on the fitted vehicle flows in different hours, the preliminary control green light time associated with the second node of the urban traffic road segment in different hours; The control signal control module monitors the average vehicle flow in the current urban traffic road section in real time and verifies it. If the saturated vehicle flow of this urban traffic road section is exceeded, an advanced control signal will be issued. Otherwise, continuous monitoring will be carried out; The advanced traffic control module receives the control signal and performs advanced control on the green light time of the second node based on the determined average vehicle flow in the current urban traffic road section, so that the green light time of the current urban traffic road section conforms to the current average vehicle flow.

2. The intelligent traffic control system based on the Internet of Things according to claim 1 is characterized in that: In the traffic data collection module, the traffic light where the vehicle enters the urban traffic road section is marked as the first node; The traffic light where the vehicle leaves the urban traffic road section is marked as the second node.

3. The intelligent traffic control system based on the Internet of Things according to claim 1 is characterized in that: In the traffic data collection module, the specific method for determining the average vehicle flow associated with the current urban traffic road segment is: S31, obtain the preset sampling period, the sampling period time is recorded as T sap , where the sampling period T sap Less than 10 minutes; S32, determine the sampling period T sap The total number of moments within is denoted as j; S33, within the sampling period, monitoring in real time the incoming vehicle flow ITF of the urban traffic road segment entering through the first node and the outgoing vehicle flow DVF of the urban traffic road segment exiting through the second node; S34, determine the j incoming vehicle flows associated with the j moments in this sampling period, sort them in the order of the timeline, and obtain the incoming vehicle flow sequence ITF1, ITF2, ..., ITF j ; Similarly, we can get the leaving vehicle flow sequence DVF1, DVF2, ..., DVF j ; S35, extract ITF1, ITF2, ..., ITF j Any one of the incoming vehicle flows is recorded as ITF i Similarly, determine the departure vehicle flow at the corresponding time, recorded as DVF i , where i is a counting index, 1≤i≤j, representing any moment among j moments; S36, DVF i with the ITF i The accumulated vehicle flow rate RAT associated with time i i ; S37, repeat steps S35 to S36, determine the j-time vehicle flows associated with the j-times and summarize them to obtain the sampling period vehicle flows associated with the sampling period; S38. Obtain the total number n of continuous sampling cycles preset by the operator, where 1≤n≤6; Continuously monitor n sampling periods to obtain the vehicle flow in n sampling periods; The average vehicle flow rate of n sampling periods is taken as the average vehicle flow rate associated with the urban traffic road segment, which is recorded as 4. The intelligent traffic control system based on the Internet of Things according to claim 3 is characterized in that: In the traffic signal initial adjustment module, the specific method of locking the fitted vehicle flow associated with any hour in a monitoring cycle is: Determine the monitoring period; The monitoring period is 24 hours, from 0:00 to 24:00 a.m. The average vehicle flow associated with each hour in a monitoring period is determined by the method described in steps S31 to S38, and the 24 average vehicle flows obtained are sorted in chronological order to obtain an average vehicle flow sequence. Obtain m average vehicle flow sequences associated with urban traffic road segments within m monitoring periods, where m is an integer preset by an operator and is greater than 0; The average of the 24m average vehicle flows in the m average vehicle flow sequences is taken according to the corresponding hour as the fitted vehicle flow associated with the corresponding hour.

5. The intelligent traffic control system based on the Internet of Things according to claim 4 is characterized in that: In the traffic signal preliminary adjustment module, the specific method for determining the preliminary adjustment green light time associated with the second node of this urban traffic road section in different hours is as follows: Construct a two-dimensional coordinate system with the timeline as the horizontal axis and the average vehicle flow value as the vertical axis; Mark 24 fitted vehicle flows in the form of histogram bars in order along the timeline in a two-dimensional coordinate system to obtain 24 histogram bars, and obtain the midpoints of the tops of the 24 histogram bars respectively to get 24 data points; Connect two adjacent data points with short lines to obtain the fitted vehicle flow line Z; Then take the average of the 24 fitted vehicle flows and denote it as the secondary average vehicle flow; Determine the scale of the secondary average vehicle flow on the vertical axis, and construct a straight line L perpendicular to the vertical axis and parallel to the horizontal axis through this scale; Determine the part of Z above the straight line L and mark it as Z1; Determine the part of Z below the straight line L and mark it as Z2; Count the total number of hours in Z1 and denote it as o; The total number of hours in Z2 is 24 - o. When an hour is completely below the straight line L, it is classified into Z2, otherwise it is classified into Z1; The preliminary green light time of the second node of the urban traffic road section associated with 24-o hours in Z2 is adjusted to the second node basic green light time G preset by the operator found2 ; Then determine the fitted vehicle flows associated with the o hours, and subtract the secondary average vehicle flow from each of them to obtain o over-limit vehicle flows; Take any one of the o over-limit vehicle flows and mark it as OVF u , where u represents any one of the o overloaded vehicle flows; Determine OVF u The associated upward adjustment ratio α u , and use the increase ratio α u Get the initial green light time associated with the uth hour in o hours; Repeat the above steps and perform the same processing on the o hours to obtain the preliminary regulated green light times associated with each of the o hours.

6. The intelligent traffic control system based on the Internet of Things according to claim 5 is characterized in that: In the traffic signal initial adjustment module, the increase ratio α is used u The specific method of obtaining the initial green light time associated with the uth hour in o hours is: Based on the determined over-limit vehicle flow OVF u and the quadratic average vehicle flow, using Get the increase ratio α associated with the uth hour in o hours u ; Using the upward adjustment ratio α u To G found2 Adjust upward to obtain the initial green light time G associated with the uth hour found2 *α u .

7. The intelligent traffic control system based on the Internet of Things according to claim 6 is characterized in that: The regulation signal control module monitors the average vehicle flow of the current urban traffic road section in real time and denotes it as Q; Compare the monitored average vehicle flow Q with the saturated vehicle flow S of this urban traffic road section, where the saturated vehicle flow S is obtained by the operator combining experience and actual measurement; If Q≥S, generate an advanced regulation signal and send it to the traffic signal advanced regulation module; If Q<S, regulate the green light time of the second node of the urban traffic road section to the preliminary regulated green light time associated with the corresponding hour, and continue to monitor.

8. The intelligent traffic control system based on the Internet of Things according to claim 1 is characterized in that: In the traffic advanced regulation module, the specific ways to respectively perform advanced regulation on the green light times of the first node and the second node are as follows: Get the second node basic green light time G of the urban traffic road segment found2 ; Get the current green light time of the second node, recorded as G now2 ; use: Calculate the demand weight ω2 associated with the basic green time of the second node; Get the total green light time G of the second node total2 , where the total green light time G total2 Values ​​preset for the operator. Using G total2 Subtract G now2 , get the total available green time G of the second node at the current time avai ; Then through G new =G now2 +round(G avai *ω2) Get the green light time G after regulation new , where G new ≤G total2 ; To control the green light time G new2 , and regulate the second node of the urban traffic road section.

Images