Regional boundary control method and system based on traffic jam index

Abstract

The invention provides a region boundary control method and system based on traffic jam indexes, and relates to the technical field of traffic control. The method comprises the steps of collecting historical traffic data of a target traffic network according to time parameters and constructing a road network topological graph of each time period, clustering each road network topological graph through a spectral clustering algorithm, constructing a three-dimensional macroscopic fundamental graph model according to the road section length, the accumulated vehicle number and the traffic completion rate of each traffic center after clustering, and calculating the traffic completion rate of each traffic center according to the three-dimensional macroscopic fundamental graph model. Current traffic data of a target traffic network are collected, a target road network topological graph is constructed, the target road network topological graph is clustered through a spectral clustering algorithm to obtain a target traffic center area, and traffic lights at boundary intersections of the target traffic center area are regulated and controlled based on a three-dimensional macroscopic fundamental graph model through a sliding mode variable structure control algorithm. The flow in the area is adjusted through boundary flow control, so that the accumulated number of vehicles in the road network of the area is always maintained at the critical number of vehicles, and the traffic flow of the area is ensured to be maximum.

Description

Technical Field

[0001] The present invention mainly relates to the technical field of traffic control, and in particular to a method and system for controlling regional boundaries based on traffic congestion index. Background Art

[0002] The Macro Fundamental Diagram (MFD) describes the relationship between the traffic flow and average density of the traffic road operation network, and can reflect the regional traffic operation status. In the current traffic operation control technology, the target traffic operation area is divided into congestion areas based on the macro basic diagram, and boundary entrance control is implemented at the outer intersections or sections of the congested area to limit the traffic flow entering the congested area avenue to solve the traffic congestion in the area. However, this regional boundary control technology only determines the macro basic diagram of the road network through statistical historical data, lacks the application of using mobile Internet to obtain real-time data, and most of the research statically divides the road network into sub-areas of appropriate size and reasonable structure, ignoring that urban traffic is a complex nonlinear system that changes with time and space, that is, the congestion points in the road network have traffic characteristics that change with time, and the congestion situation spreads to adjacent areas.

[0003] The traditional static zoning control method cannot reflect the regional changes brought about by traffic changes, and it is also easy to cause congestion in non-target traffic operation areas, making it difficult for the entire traffic network to achieve optimal operation. The traditional dynamic zoning control method only considers two factors: vehicle completion rate and cumulative number of vehicles. It does not take into account the impact of changes in the size of the traffic area on the macro basic map, making it difficult to implement accurate traffic control strategies. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for controlling regional boundaries based on traffic congestion index in view of the deficiencies of the prior art.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] A method for controlling regional boundaries based on traffic congestion index comprises the following steps:

[0007] Collect historical traffic data of the target traffic network according to time parameters to obtain the lengths of sections corresponding to multiple roads and the traffic congestion index of each road in multiple different time periods;

[0008] According to multiple different time periods, images of multiple roads and corresponding traffic congestion indexes are constructed to obtain road network topology maps corresponding to each time period, and multiple road network topology maps are clustered by a spectral clustering algorithm to obtain traffic center areas of multiple time periods, wherein the traffic center area is composed of multiple central roads;

[0009] Obtaining the cumulative number of vehicles and the traffic completion rate corresponding to the traffic center area in multiple time periods respectively, and constructing a three-dimensional macro basic graph model according to the multiple cumulative number of vehicles, the multiple traffic completion rates and the section lengths of multiple central roads in each of the traffic center areas;

[0010] The traffic data of the target traffic network at the current time is collected to obtain the target traffic congestion index of each road, an image is constructed for multiple roads and the corresponding target traffic congestion indexes to obtain a target road network topology map, and the target road network topology map is clustered by a spectral clustering algorithm to obtain a target traffic center area, wherein the target traffic center area includes multiple boundary intersections with traffic lights;

[0011] The number of vehicles in the target traffic center area is calculated based on the three-dimensional macro basic graph model through a sliding mode variable structure control algorithm to obtain the number of controlled vehicles, and the change duration of the traffic lights at the multiple boundary intersections is calculated according to the number of controlled vehicles to obtain the green light adjustment durations corresponding to the multiple green lights, and the display durations of the green lights at the corresponding boundary intersections are adjusted according to the multiple green light adjustment durations.

[0012] Another technical solution of the present invention to solve the above technical problems is as follows:

[0013] A regional boundary control system based on traffic congestion index, comprising:

[0014] A collection module is used to collect historical traffic data of the target traffic network according to time parameters, and obtain the lengths of sections corresponding to multiple roads and the traffic congestion index of each road in multiple different time periods;

[0015] A clustering module is used to construct images of multiple roads and corresponding traffic congestion indexes according to multiple different time periods, obtain a road network topology map corresponding to each time period, and cluster the multiple road network topology maps by a spectral clustering algorithm to obtain traffic center areas of multiple time periods, wherein the traffic center area is composed of multiple central roads;

[0016] A modeling module, for respectively obtaining the cumulative number of vehicles and the traffic completion rate corresponding to the traffic center area in multiple time periods, and constructing a three-dimensional macro basic graph model according to the multiple cumulative number of vehicles, the multiple traffic completion rates and the section lengths of the multiple central roads in each of the traffic center areas;

[0017] The collection module is also used to collect the traffic data of the target traffic network at the current time to obtain the target traffic congestion index of each road;

[0018] The clustering module is further used to construct an image of multiple roads and corresponding target traffic congestion indexes to obtain a target road network topology map, cluster the target road network topology map through a spectral clustering algorithm to obtain a target traffic center area, and the target traffic center area includes multiple boundary intersections with traffic lights;

[0019] A control module is used to calculate the number of vehicles in the target traffic center area based on the three-dimensional macro basic graph model through a sliding mode variable structure control algorithm to obtain the number of controlled vehicles, and calculate the change duration of the traffic lights at the multiple boundary intersections according to the number of controlled vehicles to obtain the green light adjustment durations corresponding to the multiple green lights, and adjust the display durations of the green lights at the corresponding boundary intersections according to the multiple green light adjustment durations.

[0020] The beneficial effects of the present invention are as follows: a road network topology map is constructed by obtaining the road network road length and traffic congestion index of the target traffic network, roads with similar congestion conditions are connected in the road network topology map, roads are clustered according to the congestion conditions through a spectral clustering algorithm, and a traffic center area composed of the most congested roads is divided, a three-dimensional macro basic graph model is constructed according to the vehicle operation data of the traffic center area in each time period to reflect the congestion conditions in each time period, the congested road section in the current stage is calculated according to the real-time congestion data of the target traffic network, and the signal light duration at the intersection of the most congested road section in the current stage is adjusted according to the historical congestion data of the three-dimensional macro basic graph model, so that as many vehicles as possible can pass through the congested road section and the number of vehicles entering the congested road section is limited to alleviate road congestion.

[0021] Based on the three-dimensional macro basic graph model, the critical flow of the number of vehicles in the congested area is calculated, and the display time of the signal lights in the congested area is regulated, realizing the precise allocation and optimization management of traffic flow, so that the number of vehicles in the traffic congested area drops rapidly and remains within the critical flow section, alleviating the congestion problem in traditional traffic management, thereby improving the overall operation efficiency of the road network and reducing environmental pollution. The current real-time traffic data is dynamically adjusted, which has strong practicality and flexibility. By dynamically controlling the display time of the signal lights at the boundary intersections of the congested sections in the target traffic center area, the number of congested sections is controlled, and the adaptability and robustness under complex traffic conditions are enhanced, avoiding the phenomenon of local over-congestion in the region caused by the spread of traffic congestion. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flow chart of a method for controlling regional boundaries based on traffic congestion index provided by an embodiment of the present invention;

[0023] Figure 2 A flow chart of a method for controlling area boundaries provided by an embodiment of the present invention;

[0024] Figure 3 A schematic diagram of the control principle of a three-dimensional macro basic graph model provided by an embodiment of the present invention;

[0025] Figure 4 A schematic diagram of a target transportation network provided by an embodiment of the present invention;

[0026] Figure 5 A schematic diagram of a vehicle induction strategy provided by an embodiment of the present invention;

[0027] Figure 6 A module block diagram of a regional boundary control system based on traffic congestion index provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0029] Nowadays, travelers are accustomed to using the Internet and mobile Internet terminals to obtain traffic information for navigation, and make travel decisions based on the induced routes given by the navigation. However, the travel induced routes provided are all based on the user's optimal induced strategy. The provided travel induced strategy is not coordinated with the urban traffic signal control plan, which will cause the traffic delays at intersections to increase and fail to achieve the induction of balanced distribution of traffic flow. It is easy for traffic congestion to occur due to the optimal route recommended by the navigation software.

[0030] Therefore, a traffic network boundary control strategy that takes into account changes in vehicle completion rate, cumulative number of vehicles and area size of traffic areas is needed to improve the completion rate of traffic flow within the controlled traffic network and implement accurate traffic control strategies.

[0031] like Figure 1 and Figure 2 As shown, an embodiment of the present invention provides a method for controlling area boundaries based on traffic congestion index, comprising the following steps:

[0032] Collect historical traffic data of the target traffic network according to time parameters to obtain the lengths of sections corresponding to multiple roads and the traffic congestion index of each road in multiple different time periods;

[0033] According to multiple different time periods, images of multiple roads and corresponding traffic congestion indexes are constructed to obtain road network topology maps corresponding to each time period, and multiple road network topology maps are clustered by a spectral clustering algorithm to obtain traffic center areas of multiple time periods, wherein the traffic center area is composed of multiple central roads;

[0034] Obtaining the cumulative number of vehicles and the traffic completion rate corresponding to the traffic center area in multiple time periods respectively, and constructing a three-dimensional macro basic graph model according to the multiple cumulative number of vehicles, the multiple traffic completion rates and the section lengths of multiple central roads in each of the traffic center areas;

[0035] The traffic data of the target traffic network at the current time is collected to obtain the target traffic congestion index of each road, an image is constructed for multiple roads and the corresponding target traffic congestion indexes to obtain a target road network topology map, and the target road network topology map is clustered by a spectral clustering algorithm to obtain a target traffic center area, wherein the target traffic center area includes multiple boundary intersections with traffic lights;

[0036] The number of vehicles in the target traffic center area is calculated based on the three-dimensional macro basic graph model through a sliding mode variable structure control algorithm to obtain the number of controlled vehicles, and the change duration of the traffic lights at the multiple boundary intersections is calculated according to the number of controlled vehicles to obtain the green light adjustment durations corresponding to the multiple green lights, and the display durations of the green lights at the corresponding boundary intersections are adjusted according to the multiple green light adjustment durations.

[0037] It should be understood that the target traffic network structure data is collected through the API interface of the navigation map software to obtain the connection structure of multiple roads and the corresponding road section lengths, and the time collection parameter is set to 5 minutes. The traffic congestion index, cumulative number of vehicles and traffic completion rate and other traffic data are obtained through the traffic situation query API interface of the navigation map software. The traffic data are obtained by statistics of users using the navigation map software. The scope of the target traffic network is usually the size of a city district at the largest and the smallest is a hot spot, such as the intersection around the railway station.

[0038] The traffic situation query API interface is provided in HTTP format and is used to query the traffic situation in a specified route, circular area, or rectangular area. It can return the traffic situation that the user wants to query based on the content input by the user. This service is suitable for scenarios such as real-time traffic information query, traffic data analysis, and intelligent transportation systems.

[0039] In the embodiment of the present invention, historical traffic data is accurately analyzed, and congested sections in the traffic flow are calculated. A three-dimensional macro basic graph model is constructed according to the vehicle operation data in the congested sections corresponding to each historical period to reflect the congestion conditions at various times and different section lengths, and real-time traffic operation status data is obtained. In combination with the sliding mode variable structure control theory, the real-time traffic data of the target traffic network is regulated and analyzed based on the three-dimensional macro basic graph model, and the traffic flow in the congested area of ​​the road network is reasonably controlled by controlling the duration of signal lights, thereby effectively improving the operation efficiency of the macro road network and providing accurate analysis, prediction and decision-making basis for urban traffic management and control.

[0040] Preferably, the image construction of a plurality of roads and corresponding traffic congestion indexes is performed according to a plurality of different time periods to obtain a road network topology corresponding to each time period, including:

[0041] S11, calculating the similarity between the traffic congestion indexes in any time period respectively by using a similarity function to obtain the congestion similarity corresponding to multiple roads in any time period, wherein the similarity function is:

[0042]

[0043] Among them, w ij is the congestion similarity between the ith road and the jth road, x i is the traffic congestion index of the ith road, x j is the traffic congestion index of the jth road, σ 2 is the variance of the traffic congestion index, ‖·‖2 is the second norm;

[0044] S12, taking the multiple roads as multiple road nodes, taking the congestion similarities corresponding to the multiple roads as weight values ​​of the multiple congested edges, and connecting the multiple congested edges with the corresponding road nodes according to the weight values ​​to construct a road network topology map;

[0045] S13, repeating S11 to S12, processing multiple roads in multiple different time periods and corresponding traffic congestion indexes, and obtaining a road network topology map corresponding to each time period.

[0046] Specifically, each road in the target traffic network is taken as a node V of an undirected graph, and the traffic congestion index of each road is the node value x. The weight w of the edge E of the undirected graph is calculated according to the node value of each node, that is, the congestion similarity between road sections, which is expressed as:

[0047]

[0048] Among them, w ij is the congestion similarity between the ith road and the jth road, V = {1, 2, ..., N} is equivalent to X = (x1, x2, ...x n ), E=W=[w ij ], 1≤i, j≤N, (i,j)∈E means that the i-th node is connected to the j-th node, Indicates that the i-th node and the j-th node are not connected;

[0049] The nodes are connected according to the weights between the nodes to obtain a weighted undirected graph (i.e., a road network topology graph).

[0050] In the embodiment of the present invention, by calculating the similarity of the congestion conditions of various road sections, adjacent sections with similar congestion conditions are classified into one category based on the similarity, so as to cluster the congested sections.

[0051] Preferably, clustering the plurality of road network topology graphs respectively by using a spectral clustering algorithm to obtain traffic center areas in a plurality of time periods comprises:

[0052] S21, summing the edges corresponding to any node of any road network topology graph to obtain a connectivity value, and processing all nodes in this process to obtain a connectivity value of each node;

[0053] S22, segmenting the road network topology map according to the plurality of connectivity values ​​using a spectral clustering calculation expression to obtain an initial segmentation line, minimizing the initial segmentation line using an objective function to obtain a segmentation line, dividing the road network topology map according to the segmentation line to obtain a traffic center area in the road network topology map of any time period, wherein the spectral clustering calculation expression is:

[0054]

[0055] Among them, Ncut(V) is the initial cutting line, A k is the road node of the kth regional category, A k A k The complement of i is the connectivity value of the ith road node, K is the number of regional categories;

[0056] S23, repeat S21 to S22, process all road network topology maps, and obtain traffic center areas in multiple time periods.

[0057] Specifically, the target traffic network is divided into control sub-areas according to the similarity between road sections, including:

[0058] Calculate the connectivity value of each node (that is, the weight of the edge connected to the node). The connectivity calculation expression is:

[0059]

[0060] Among them, d i is the connectivity value of the ith node (i.e., road), w ij is the congestion similarity between the ith road and the jth road, and N is the number of roads.

[0061] The road network topology is segmented according to the connectivity values ​​of each node and the unconnected road nodes in the road network topology to obtain the traffic center area and the corresponding peripheral area. The spectral clustering calculation expression is:

[0062]

[0063] The road network topology graph is segmented as follows:

[0064]

[0065] It should be understood that the spectral clustering algorithm regards all data as points in space, which can be connected by lines. The edge weight between two points that are farther away is lower, while the weight between two points that are closer is higher. By dividing the graph composed of all data points, the sum of the edge weights between different sub-graphs after division is made as small as possible, that is, the congestion conditions are different, and the sum of the edge weights within the sub-graph is made as high as possible, that is, the congestion conditions are similar.

[0066] In an embodiment of the present invention, the congested roads in each period of the historical data of the whole day are clustered to divide the congested central sections, so as to construct a control model according to the traffic flow data of roads with different congestion lengths, so as to facilitate the subsequent vehicle volume adjustment of the congested sections.

[0067] Preferably, the three-dimensional macro basic graph model is constructed according to the plurality of accumulated vehicle numbers, the plurality of traffic completion rates and the section lengths of the plurality of central roads in each of the traffic center areas, including:

[0068] The lengths of the sections of the multiple central roads in each of the traffic center areas are summed up respectively to obtain the total length of the central road sections corresponding to each of the traffic center areas;

[0069] Construct a three-dimensional coordinate system, use the cumulative number of vehicles as the value of the horizontal axis of the three-dimensional coordinate system, use the total length of the central road section as the value of the vertical axis of the three-dimensional coordinate system, and use the traffic completion rate as the value of the vertical axis of the three-dimensional coordinate system, so as to convert the cumulative number of vehicles, traffic completion rate and total length of the central road section corresponding to each traffic center area into three-dimensional coordinates, obtain multiple control points, import the multiple control points into the three-dimensional coordinate system, and complete the construction of the three-dimensional macro basic graph model.

[0070] It should be understood that the common macro basic graph model (MFD model) is constructed by parameters of two dimensions: the cumulative number of vehicles veh and the traffic completion rate veh / s. For a road network with a fixed range, the fixed relationship between the cumulative number of vehicles in the road network and the traffic completion rate is determined by the characteristics of the road network. Therefore, the maximum traffic completion rate is achieved by adjusting the number of vehicles entering and leaving the road network. In traffic control, in order to continuously reduce the scope of congestion, the road network area needs to be used as the third dimension of the MFD model. However, the distribution of road sections in different regions under the same area is different, so the total length of the road section is used to measure the road network area to construct a three-dimensional macro basic graph model (3D-MFD model).

[0071] In an embodiment of the present invention, the total length of the road sections in the road network is used as the third dimension of the MFD model to construct a three-dimensional macro basic graph model, so that when the sliding mode variable structure control algorithm is used to control the traffic flow, the congested sections of the road network are combined to gradually reduce the congested area of ​​the target area.

[0072] Preferably, if Figure 3 As shown, the number of vehicles in the target traffic center area is calculated based on the three-dimensional macro basic graph model by using the sliding mode variable structure control algorithm to obtain the controlled number of vehicles, including:

[0073] A traffic core area is selected from the three-dimensional macro basic graph model, and an increment of the target traffic center area compared with the traffic core area is calculated to obtain a road length to be controlled and a number of vehicles to be controlled;

[0074] A sliding surface state function is constructed according to the length of the road to be controlled, the number of vehicles to be controlled and the set control gain, and the sliding surface state function is solved by a constant velocity convergence law to obtain the number of controlled vehicles.

[0075] Specifically, the cumulative number of vehicles in the target traffic center area after traffic control is implemented is n i The control vehicle threshold should be met. According to the control vehicle threshold, a sliding surface is constructed on the three-dimensional macro basic graph model, and then when solving the sliding surface state function, the number of controlled vehicles Δn is calculated. i Meet the vehicle control threshold. The vehicle control threshold is expressed as:

[0076]

[0077] in, is the critical cumulative number of vehicles, n i is the cumulative number of vehicles in the current area, ε i is the fluctuation range of traffic control, ε i Take N * 1% to 3%;

[0078] The sliding surface state function is expressed as:

[0079] S(q)=S l (L(q))+βS v (q),

[0080] Among them, S(q) is the sliding surface state function, S l (L(q)) is the length of the path to be controlled, S v (q) is the number of vehicles to be controlled, β is the control gain;

[0081] The constant velocity approaching law is used to make the number of regulated vehicles reach the sliding surface, that is, S = 0. The constant velocity approaching law is expressed as:

[0082]

[0083] in, is the approach value, sgn(·) is the step function, μ is the approach rate;

[0084] The process of solving the sliding surface state function through the constant velocity convergence law is expressed as:

[0085]

[0086] Among them, n i (q) is the cumulative number of vehicles in the current area, q is the number of cycles of the constant speed approaching law; Find the number of controlled vehicles Δn i .

[0087] It should be understood that the treatment of the sliding surface by the constant speed approaching law is mainly reflected in ensuring that the control process can approach the sliding surface at a constant speed, that is, the deviation between the state variable and the sliding surface (i.e., the length of the road to be controlled and the number of vehicles to be controlled) can be quickly and stably reduced to zero.

[0088] The goal of the controller (i.e., the sliding mode variable structure control algorithm) is to control the length of the road to be controlled and the number of vehicles to be controlled to tend towards the sliding surface at the same time. After the control target is achieved (i.e., the number of controlled vehicles is within the control vehicle threshold range), the traffic flow entering and leaving the target traffic center area reaches a dynamic balance. At this time, the vehicle traffic completion flow in the target traffic center area reaches the maximum, and the traffic operation state of the target traffic center area reaches the best.

[0089] There is a critical cumulative number of vehicles N inside the target traffic center area * , complete the flow G, so that the target traffic center area has the maximum completed flow G * When the cumulative number of vehicles n i <N * When n i Continue to increase until n i =N * When G = G * , the central roads in the target traffic center area are in the unstable flow stage, that is, the saturation state; when n i >N * When G increases with n i The central roads in the target traffic center area are in the forced flow stage, that is, they are in a congested state. Therefore, the flow inside the area is adjusted by boundary flow control, so that the cumulative number of vehicles in the road network of the area is always maintained near the critical number of vehicles, which can ensure that the regional traffic flow is maximized.

[0090] In an embodiment of the present invention, by solving the constructed sliding surface state function, the current cumulative number of vehicles is controlled within the optimal critical cumulative number of vehicles, and the controlled number of vehicles that can eliminate the difference between the cumulative number of vehicles and the optimal critical cumulative number of vehicles is obtained, and then the duration of the traffic lights is adjusted according to the controlled number of vehicles, thereby reducing congested sections and alleviating traffic congestion.

[0091] Preferably, the method of selecting a traffic core area from the three-dimensional macro basic graph model, calculating the increment of the target traffic center area compared to the traffic core area, and obtaining the road length to be controlled and the number of vehicles to be controlled includes:

[0092] A traffic center area with the smallest total length of central road sections is selected from the three-dimensional macro basic graph model as the traffic core area, and the total length of the core road sections of the traffic core area is obtained, and the section lengths of multiple central roads of the target traffic center area are summed to obtain the total length of the target road section, and the total length of the target road section is subtracted from the total length of the core road section to obtain the road length to be controlled;

[0093] The target cumulative number of vehicles in the target traffic center area at the current time is obtained, and the target cumulative number of vehicles is subtracted from a preset critical cumulative number of vehicles to obtain the number of vehicles to be controlled.

[0094] Specifically, the difference between the length of the road section in the central area and the core area of ​​the real-time road network is calculated. The total length of the road section in the dynamic congestion area and the number of vehicles in the regional road network are expressed as:

[0095] S l (L(q))=L d (q)-L c ,

[0096] S v (q) = n d (q)-N * ,

[0097] Among them, S l (L(q)) is the length of the path to be controlled, L d (q) is the total length of the target section, L c is the total length of the core section, S v (q) is the number of vehicles to be controlled, n d (q) is the target cumulative number of vehicles, and N* is the critical cumulative number of vehicles. The corresponding critical cumulative number of vehicles is pre-set according to the total length of each road section.

[0098] In the embodiment of the present invention, the deviation between the state variable and the sliding surface is calculated according to the three-dimensional macro basic graph model.

[0099] In order to clarify the boundary control strategy, the phase number, signal phase difference, signal cycle and green light loss time of the traffic lights at the intersection of the target traffic center area are set to fixed values, and one cycle t of the control cycle T is equal to the effective duration C of the traffic light cycle (such as 120 seconds).

[0100] Preferably, the boundary control strategy calculates the change duration of the traffic lights at the plurality of boundary intersections according to the number of controlled vehicles to obtain the green light adjustment duration corresponding to the plurality of green lights, including:

[0101] S31, obtaining the green light durations corresponding to the plurality of boundary intersections in the current control cycle and the predicted number of vehicles expected to enter the target traffic center area in the next control cycle, and dividing the controlled number of vehicles by the predicted number of vehicles to obtain a control rate;

[0102] S32, multiplying the control rate by any green light duration to obtain a green light adjustment amount for any boundary intersection, and adding the green light duration and the green light adjustment amount to obtain the green light adjustment duration;

[0103] S33, repeating S31 to S32, processing the green light durations of all boundary intersections, and obtaining green light adjustment durations corresponding to multiple green lights.

[0104] Specifically, the boundary control strategy constructed by the present invention is based on the number of controlled vehicles Δn i Calculate the green light adjustment amount of the green light duration of the road to enter the target traffic center area from the w-th intersection at the boundary of the target traffic center area in the t+1 control cycle. The calculation expression of the green light adjustment amount is:

[0105]

[0106] Where, Δg w,in (t+1) is the green light adjustment amount, Δn i To control the number of vehicles, n in (t+1) is the predicted number of vehicles in the t+1th control period, g w,in (t) is the green light duration, t is the statistical period, t∈kT, k=1,2,3,···,K, T is the control time period, K is the statistical number of times, w∈W, W is the set of intersections to be controlled.

[0107] The green light duration and the green light adjustment amount are summed to obtain the green light adjustment duration g of the traffic light facing the road that is expected to enter the control target traffic center area at the boundary intersection w in the t+1 control week. w,in (t+1), the calculation expression of green light adjustment duration is:

[0108]

[0109] Determine whether the green light adjustment duration faced by any boundary intersection of the target traffic center area and the road to enter the controlled target traffic center area is greater than the set green light maximum value. If so, modify the green light adjustment duration to the said green light maximum value. If not, determine whether the green light adjustment duration is less than the set green light minimum value. If so, modify the green light adjustment duration to the said green light minimum value. If not, keep the green light adjustment duration unchanged (i.e., do not modify it). By analogy, the green light adjustment duration faced by all intersections of the target traffic center area and the roads entering the controlled target traffic center area are judged to obtain the green light adjustment duration.

[0110] It should be understood that the boundary intersection of the target traffic center area is a crossroad composed of four roads. If driving straight from the west road into the east road and turning left from the north road into the east road is to enter the target traffic center area, the vehicles expected to enter the target traffic center area in the next control week are located on the west straight road and the north left turn road of the boundary intersection. The expected number of vehicles expected to enter the target traffic center area in the next control week is obtained based on the navigation data used by the user in the navigation map software. Since some vehicles on the road do not use navigation, the expected number of vehicles is divided by the preset navigation usage rate to obtain the predicted number of vehicles expected to enter the target traffic center area in the next control week. The initial value of the traffic light duration is the green light time initially set for the intersection, and the control process increases or decreases on the initial value.

[0111] Another way to control the duration of traffic lights at the boundary intersections of the target traffic center area is:

[0112] Set the vehicle flow directions at multiple peak hours, obtain the corresponding entry and exit ends at multiple peak hours, and set the traffic lights at multiple boundary intersections corresponding to the entry ends at each peak hour as the lights to be controlled. Figure 4 As shown in FIG. 1 , there are 7 boundary intersections in the target traffic center area. If the main flow direction of vehicles in the target traffic network during the morning peak is from west to east, the traffic lights at the 1st, 2nd, 3rd and 4th boundary intersections on the west side are set as the traffic lights to be controlled. The control rate is multiplied by the traffic light duration of the traffic lights to be controlled to obtain multiple traffic light adjustment amounts. Each traffic light adjustment amount is added to the corresponding traffic light duration of the traffic lights to be controlled to obtain the traffic light adjustment duration of each traffic light to be controlled, so as to adjust the multiple traffic lights at the entry-end boundary intersection according to the traffic light adjustment duration of each traffic light to be controlled.

[0113] In the embodiment of the present invention, by calculating the green light duration of each boundary intersection of the main vehicle import flow direction in the next control cycle, the signal light timing of the boundary intersection of the target traffic center area is adjusted, thereby controlling the vehicle operation flow in the target traffic center area.

[0114] Preferably, if Figure 5 As shown, after the step of adjusting the display duration of the green light at the corresponding boundary intersection according to the plurality of green light durations, the boundary control strategy further includes:

[0115] According to the set prediction parameters, the green light adjustment duration and the number of roads to enter the target traffic center area are calculated respectively to obtain the predicted number of controlled vehicles, the predicted number of vehicles is subtracted from the predicted number of controlled vehicles to obtain the remaining number of vehicles, the remaining number of vehicles is divided by the preset induced compliance rate to obtain the number of induced vehicles, and the vehicles that are expected to enter the target traffic center area in the next control cycle are induced to roads outside the target traffic center area according to the induced number of vehicles.

[0116] Specifically, in the boundary control strategy, when the total vehicle flow expected to enter the target traffic center area in the next control cycle cannot be fully adjusted, the set vehicle induction strategy is started, and the green light adjustment time and the number of roads to enter the target traffic center area are calculated according to the set prediction parameters to obtain the predicted number of controlled vehicles. The vehicle prediction calculation expression is:

[0117]

[0118] Among them, c w (t+1) is the predicted number of controlled vehicles entering the target traffic center area at the w-th intersection on the boundary of the target traffic center area, m is the number of roads to be entered into the target traffic center area, gw,in(t+1) is the green light adjustment duration, t0 is the time when the first vehicle to be entered in the next control cycle starts to pass the stop line after the green light is on, t i is the average time for vehicles to pass the stop line, γ is the reduction coefficient; the set prediction parameters include t0, t i and γ, t0 is set to 2.3 seconds, t i Set to 2.5 seconds, γ is set to 0.9, that is, the vehicle prediction calculation expression can be expressed as:

[0119]

[0120] If driving straight from the west road into one lane on the east side and turning left from the north road into one lane on the east side are considered to enter the target traffic center area, then the number of roads to enter the target traffic center area is 2;

[0121] The number of remaining vehicles is obtained by subtracting the number of predicted controlled vehicles corresponding to all roads entering the target traffic center area at all intersections at the boundary of the target traffic center area from the number of predicted vehicles. The number of remaining vehicles expected to enter the target traffic center area but cannot pass through the intersection of the target traffic center area boundary in the next control cycle is calculated through the induced calculation expression to obtain the induced vehicle number. According to the induced vehicle number, the vehicles expected to enter the target traffic center area are induced to detour in the peripheral area (i.e., the area outside the target traffic center area). The induced calculation expression is:

[0122] Y(t+1)=n′(t+1) / ρ(t+1),

[0123] Among them, Y(t+1) is the number of induced vehicles in the t+1th period, n′(t+1) is the number of remaining vehicles in the t+1th period, ρ(t+1) is the induced compliance rate in the t+1th period, and 0<ρ<1.

[0124] It should be understood that the number of vehicles that are expected to travel from the boundary intersection to the target traffic center area on the original route in the navigation software is subtracted from the number of vehicles that have been adjusted by the green light (i.e., the number of vehicles that travel from the boundary intersection to the target traffic center area through the green light), and the number of remaining vehicles is obtained. The induction strategy is to send a detour reminder to the traffic participants who use the navigation map software and expect to enter the target traffic center area in the next control cycle of the traffic light according to the number of induced vehicles through the advanced path planning API interface configured with the navigation map software, that is, display the road change prompt information and traffic induction route on the user side of the navigation map software. The advanced path planning API interface is an interface provided in the form of HTTP. The service is suitable for scenarios that require real-time traffic information and path planning, helping to optimize routes and improve travel efficiency. Since there may be cases where users using the navigation map software do not accept detour reminders, the induction compliance rate is set to calculate the number of remaining vehicles to be induced, and the number of induced vehicles greater than the number of remaining vehicles is obtained, that is, the detour reminder greater than the number of remaining vehicles is issued to the corresponding number of traffic participants. If the number of remaining vehicles is 5, when the induction compliance rate is set to 0.5, the number of induced vehicles calculated using the induction calculation expression is 10.

[0125] If the traffic light change cycle is 120 seconds and the traffic flow peak period is 2 hours, the control threshold is set to 60 (ie, the cyclic control period of the boundary control process of the target traffic center area is set to 60 times).

[0126] In an embodiment of the present invention, a traffic induction strategy is activated for vehicles located at the boundary of a target traffic center area and about to enter the target traffic center area to guide the vehicles to detour and avoid the target traffic center area to alleviate traffic congestion. By guiding traffic participants, the traffic pressure in the target traffic center area is alleviated, so that the urban traffic flow is in a state of balanced distribution as much as possible, effectively improving the operating efficiency of the macro network.

[0127] like Figure 6 As shown, an embodiment of the present invention provides a regional boundary control system based on traffic congestion index, including:

[0128] A collection module is used to collect historical traffic data of the target traffic network according to time parameters, and obtain the lengths of sections corresponding to multiple roads and the traffic congestion index of each road in multiple different time periods;

[0129] A clustering module is used to construct images of multiple roads and corresponding traffic congestion indexes according to multiple different time periods, obtain a road network topology map corresponding to each time period, and cluster the multiple road network topology maps by a spectral clustering algorithm to obtain traffic center areas of multiple time periods, wherein the traffic center area is composed of multiple central roads;

[0130] A modeling module, for respectively obtaining the cumulative number of vehicles and the traffic completion rate corresponding to the traffic center area in multiple time periods, and constructing a three-dimensional macro basic graph model according to the multiple cumulative number of vehicles, the multiple traffic completion rates and the section lengths of the multiple central roads in each of the traffic center areas;

[0131] The collection module is also used to collect the traffic data of the target traffic network at the current time to obtain the target traffic congestion index of each road;

[0132] The clustering module is further used to construct an image of multiple roads and corresponding target traffic congestion indexes to obtain a target road network topology map, cluster the target road network topology map through a spectral clustering algorithm to obtain a target traffic center area, and the target traffic center area includes multiple boundary intersections with traffic lights;

[0133] A control module is used to calculate the number of vehicles in the target traffic center area based on the three-dimensional macro basic graph model through a sliding mode variable structure control algorithm to obtain the number of controlled vehicles, and calculate the change duration of the traffic lights at the multiple boundary intersections according to the number of controlled vehicles to obtain the green light adjustment durations corresponding to the multiple green lights, and adjust the display durations of the green lights at the corresponding boundary intersections according to the multiple green light adjustment durations.

[0134] The above-mentioned regional boundary control system based on traffic congestion index can refer to the implementation content and beneficial effects of the regional boundary control method based on traffic congestion index specifically described above, which will not be repeated here.

[0135] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0136] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0137] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0138] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0139] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A regional boundary control method based on traffic congestion index, characterized in that: The steps include: Collect historical traffic data of the target traffic network according to time parameters to obtain the lengths of sections corresponding to multiple roads and the traffic congestion index of each road in multiple different time periods; According to multiple different time periods, images of multiple roads and corresponding traffic congestion indexes are constructed to obtain road network topology maps corresponding to each time period, and multiple road network topology maps are clustered by a spectral clustering algorithm to obtain traffic center areas of multiple time periods, wherein the traffic center area is composed of multiple central roads; Obtaining the cumulative number of vehicles and the traffic completion rate corresponding to the traffic center area in multiple time periods respectively, and constructing a three-dimensional macro basic graph model according to the multiple cumulative number of vehicles, the multiple traffic completion rates and the section lengths of multiple central roads in each of the traffic center areas; The traffic data of the target traffic network at the current time is collected to obtain the target traffic congestion index of each road, an image is constructed for multiple roads and the corresponding target traffic congestion indexes to obtain a target road network topology map, and the target road network topology map is clustered by a spectral clustering algorithm to obtain a target traffic center area, wherein the target traffic center area includes multiple boundary intersections with traffic lights; The number of vehicles in the target traffic center area is calculated based on the three-dimensional macro basic graph model through a sliding mode variable structure control algorithm to obtain the number of controlled vehicles, and the change duration of the traffic lights at the multiple boundary intersections is calculated according to the number of controlled vehicles to obtain the green light adjustment durations corresponding to the multiple green lights, and the display durations of the green lights at the corresponding boundary intersections are adjusted according to the multiple green light adjustment durations.

2. The area boundary control method according to claim 1, characterized in that: The method of constructing images of multiple roads and corresponding traffic congestion indexes according to multiple different time periods to obtain a road network topology corresponding to each time period includes: S11, calculating the similarity between the traffic congestion indexes in any time period respectively by using a similarity function to obtain the congestion similarity corresponding to multiple roads in any time period, wherein the similarity function is: Among them, w ij is the congestion similarity between the ith road and the jth road, x i is the traffic congestion index of the ith road, x j is the traffic congestion index of the jth road, σ 2 is the variance of the traffic congestion index, ‖·‖2 is the second norm; S12, taking the multiple roads as multiple road nodes, taking the congestion similarities corresponding to the multiple roads as weight values ​​of the multiple congested edges, and connecting the multiple congested edges with the corresponding road nodes according to the weight values ​​to construct a road network topology map; S13, repeating S11 to S12, processing multiple roads in multiple different time periods and corresponding traffic congestion indexes, and obtaining a road network topology map corresponding to each time period.

3. The area boundary control method according to claim 2, characterized in that: The method of clustering the plurality of road network topology graphs respectively by using a spectral clustering algorithm to obtain traffic center areas in a plurality of time periods includes: S21, summing the edges corresponding to any node of any road network topology graph to obtain a connectivity value, and processing all nodes in this process to obtain a connectivity value of each node; S22, segmenting the road network topology map according to the plurality of connectivity values ​​using a spectral clustering calculation expression to obtain an initial segmentation line, minimizing the initial segmentation line using an objective function to obtain a segmentation line, dividing the road network topology map according to the segmentation line to obtain a traffic center area in the road network topology map of any time period, wherein the spectral clustering calculation expression is: Among them, Ncut(V) is the initial cutting line, A k is the road node of the kth regional category, d i is the connectivity value of the ith road node, K is the number of regional categories; S23, repeat S21 to S22, process all road network topology maps, and obtain traffic center areas in multiple time periods.

4. The area boundary control method according to claim 1, characterized in that: The three-dimensional macro basic graph model is constructed according to the plurality of accumulated vehicle numbers, the plurality of traffic completion rates and the section lengths of the plurality of central roads in each of the traffic center areas, including: The lengths of the sections of the multiple central roads in each of the traffic center areas are summed up respectively to obtain the total length of the central road sections corresponding to each of the traffic center areas; Construct a three-dimensional coordinate system, use the cumulative number of vehicles as the value of the horizontal axis of the three-dimensional coordinate system, use the total length of the central road section as the value of the vertical axis of the three-dimensional coordinate system, and use the traffic completion rate as the value of the vertical axis of the three-dimensional coordinate system, so as to convert the cumulative number of vehicles, traffic completion rate and total length of the central road section corresponding to each traffic center area into three-dimensional coordinates, obtain multiple control points, import the multiple control points into the three-dimensional coordinate system, and complete the construction of the three-dimensional macro basic graph model.

5. The area boundary control method according to claim 4, characterized in that: The method of calculating the number of vehicles in the target traffic center area based on the three-dimensional macro basic graph model by using a sliding mode variable structure control algorithm to obtain the number of controlled vehicles includes: A traffic core area is selected from the three-dimensional macro basic graph model, and an increment of the target traffic center area compared with the traffic core area is calculated to obtain a road length to be controlled and a number of vehicles to be controlled; A sliding surface state function is constructed according to the length of the road to be controlled, the number of vehicles to be controlled and the set control gain, and the sliding surface state function is solved by a constant velocity convergence law to obtain the number of controlled vehicles.

6. The area boundary control method according to claim 5, characterized in that: The method of selecting a traffic core area from the three-dimensional macro basic graph model, calculating the increment of the target traffic center area compared to the traffic core area, and obtaining the road length to be controlled and the number of vehicles to be controlled includes: A traffic center area with the smallest total length of central road sections is selected from the three-dimensional macro basic graph model as the traffic core area, and the total length of the core road sections of the traffic core area is obtained, and the section lengths of multiple central roads of the target traffic center area are summed to obtain the total length of the target road section, and the total length of the target road section is subtracted from the total length of the core road section to obtain the road length to be controlled; The target cumulative number of vehicles in the target traffic center area at the current time is obtained, and the target cumulative number of vehicles is subtracted from a preset critical cumulative number of vehicles to obtain the number of vehicles to be controlled.

7. The area boundary control method according to claim 1, characterized in that: The step of calculating the change durations of the traffic lights at the plurality of boundary intersections according to the number of controlled vehicles to obtain the green light adjustment durations corresponding to the plurality of green lights includes: S31, obtaining the green light durations corresponding to the plurality of boundary intersections in the current control cycle and the predicted number of vehicles expected to enter the target traffic center area in the next control cycle, and dividing the controlled number of vehicles by the predicted number of vehicles to obtain a control rate; S32, multiplying the control rate by any green light duration to obtain a green light adjustment amount for any boundary intersection, and adding the green light duration and the green light adjustment amount to obtain the green light adjustment duration; S33, repeat S31 to S32, process the green light durations of all boundary intersections, and obtain green light adjustment durations corresponding to multiple green lights.

8. The area boundary control method according to claim 7, characterized in that: After the step of adjusting the display duration of the green light at the corresponding boundary intersection according to the plurality of green light adjustment durations, the method further includes: According to the set prediction parameters, the green light adjustment duration and the number of roads to enter the target traffic center area are calculated respectively to obtain the predicted number of controlled vehicles, the predicted number of vehicles is subtracted from the predicted number of controlled vehicles to obtain the remaining number of vehicles, the remaining number of vehicles is divided by the preset induced compliance rate to obtain the number of induced vehicles, and the vehicles that are expected to enter the target traffic center area in the next control cycle are induced to roads outside the target traffic center area according to the induced number of vehicles.

9. A regional boundary control system based on traffic congestion index, characterized in that: include: A collection module is used to collect historical traffic data of the target traffic network according to time parameters, and obtain the lengths of sections corresponding to multiple roads and the traffic congestion index of each road in multiple different time periods; A clustering module is used to construct images of multiple roads and corresponding traffic congestion indexes according to multiple different time periods, obtain a road network topology map corresponding to each time period, and cluster the multiple road network topology maps by a spectral clustering algorithm to obtain traffic center areas of multiple time periods, wherein the traffic center area is composed of multiple central roads; A modeling module, for respectively obtaining the cumulative number of vehicles and the traffic completion rate corresponding to the traffic center area in multiple time periods, and constructing a three-dimensional macro basic graph model according to the multiple cumulative number of vehicles, the multiple traffic completion rates and the section lengths of the multiple central roads in each of the traffic center areas; The collection module is also used to collect the traffic data of the target traffic network at the current time to obtain the target traffic congestion index of each road; The clustering module is further used to construct an image of multiple roads and corresponding target traffic congestion indexes to obtain a target road network topology map, cluster the target road network topology map through a spectral clustering algorithm to obtain a target traffic center area, and the target traffic center area includes multiple boundary intersections with traffic lights; A control module is used to calculate the number of vehicles in the target traffic center area based on the three-dimensional macro basic graph model through a sliding mode variable structure control algorithm to obtain the number of controlled vehicles, and calculate the change duration of the traffic lights at the multiple boundary intersections according to the number of controlled vehicles to obtain the green light adjustment durations corresponding to the multiple green lights, and adjust the display durations of the green lights at the corresponding boundary intersections according to the multiple green light adjustment durations.

10. The area boundary control system according to claim 9, characterized in that: In the clustering module, images of multiple roads and corresponding traffic congestion indexes are constructed according to multiple different time periods to obtain a road network topology corresponding to each time period, including: The similarity between the traffic congestion indexes in any period is calculated by the similarity function to obtain the congestion similarity corresponding to multiple roads in any period. The similarity function is: Among them, w ij is the congestion similarity between the ith road and the jth road, x i is the traffic congestion index of the ith road, x j is the traffic congestion index of the jth road, σ 2 is the variance of the traffic congestion index, ‖·‖2 is the second norm; Taking the multiple roads as multiple road nodes, taking the congestion similarities corresponding to the multiple roads as weight values ​​of the multiple congestion edges, and connecting the multiple congestion edges with the corresponding road nodes according to the weight values ​​to construct a road network topology graph; In this process, multiple roads and corresponding traffic congestion indexes at multiple different time periods are processed to obtain the road network topology corresponding to each time period.

Images