Traffic signal coordination control method, device, equipment and storage medium

Abstract

The invention discloses a traffic signal coordination control method and device, equipment and a storage medium. All intersections of a road in a preset area are divided to obtain a plurality of target sub-areas; acquiring an average congestion index of the target sub-region in the current period and a predicted congestion index of the target sub-region in the next period, and acquiring an average intersection distance of the target sub-region; and according to the average congestion index of the target sub-area in the current period, the predicted congestion index and the average intersection distance, performing coordination control on traffic signals of each intersection in the target sub-area. According to the embodiment of the invention, the traffic signal is controlled by dividing the preset area into the sub-areas and comprehensively considering the average congestion index, the predicted congestion index and the average intersection distance for each sub-area, so that the traffic pressure is effectively relieved, and the traffic efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of transportation. Specifically, it relates to a traffic signal coordination control method, device, equipment and storage medium. Background Art

[0002] In recent years, the urban traffic flow in China has increased sharply, and phenomena such as traffic congestion, traffic accidents, and traffic violations have become more and more serious, seriously affecting people's quality of life. Traffic signal lights are an important means of traffic management. How to use the reasonable control of signal lights to improve the road passing rate is the key to alleviating traffic congestion and reducing traffic accidents.

[0003] The existing technology mainly controls traffic signals according to the real-time traffic flow information of each intersection, considering incomplete parameters and unable to effectively relieve traffic pressure. Summary of the Invention

[0004] Based on this, the present invention provides a traffic signal coordination control method, device, equipment and storage medium, which can divide a preset area into sub-areas, and for each sub-area, comprehensively consider the average congestion index, predicted congestion index and average intersection spacing to control traffic signals and effectively relieve traffic pressure.

[0005] To achieve the above object, an embodiment of the present invention provides a traffic signal coordination control method, including:

[0006] Dividing all intersections on the roads in the preset area to obtain a number of target sub-areas;

[0007] Obtaining the average congestion index of the target sub-area in the current cycle and the predicted congestion index of the next cycle;

[0008] Obtaining the average intersection spacing of the target sub-area;

[0009] Coordinating and controlling the traffic signals of each intersection in the target sub-area according to the average congestion index, the predicted congestion index and the average intersection spacing of the target sub-area in the current cycle.

[0010] As an improvement of the above solution, it further includes: subtracting the average congestion index of the target sub-area in the current cycle from the predicted congestion index of the target sub-area to obtain the average congestion change index of the target sub-area;

[0011] The coordinating and controlling the traffic signals of each intersection in the target sub-area according to the average congestion index, the predicted congestion index and the average intersection spacing of the target sub-area in the current cycle includes:

[0012] Determine the target coordinated control mode according to the first comparison result, the second comparison result, and the third comparison result based on the mapping relationship between the preset coordinated control mode and the comparison result;

[0013] Coordinately control the traffic signals at each intersection in the target sub-area according to the target coordinated control mode;

[0014] Among them, the first comparison result is the comparison result between the average congestion change index of the target sub-area and the preset change index threshold, the second comparison result is the comparison result between the predicted congestion index of the target sub-area and the preset congestion index threshold, and the third comparison result is the comparison result between the average intersection spacing of the target sub-area and the preset spacing threshold.

[0015] As an improvement to the above solution, the determining the target coordinated control mode according to the first comparison result, the second comparison result, and the third comparison result based on the mapping relationship between the preset coordinated control mode and the comparison result; and coordinately controlling the traffic signals at each intersection in the target sub-area according to the target coordinated control mode includes:

[0016] When the first condition is met, no adjustment of the traffic signal is made; where the first condition is that the average congestion change index of the target sub-area is less than or equal to the preset change index threshold and the average congestion index of the target sub-area in the current cycle is less than or equal to the congestion index threshold;

[0017] When the second condition is met, control the synchronous change of the linkage phase signal lights between adjacent intersections; where the second condition is that the first condition is not met and the average intersection spacing of the target sub-area is less than or equal to the preset first spacing threshold;

[0018] When the third condition is met, adopt the preset maximum green wave bandwidth control model to coordinately control the traffic signals in the target sub-area; where the third condition is that the first condition and the second condition are not met, the average intersection spacing of the target sub-area is less than or equal to the preset second spacing threshold, the first spacing threshold is greater than the second spacing threshold, and the average congestion index of the target sub-area in the current cycle is less than or equal to the preset congestion index threshold;

[0019] When none of the first condition, the second condition, and the third condition are met, use the preset stop delay control model to coordinately control the traffic signals in the target sub-area so that the weighted sum of the total number of stops and the delay time in the target sub-area is minimized.

[0020] As an improvement to the above solution, the dividing all intersections on the roads in the preset area to obtain several target sub-areas includes:

[0021] Obtain a number of current original sub - regions in the preset area;

[0022] Obtain the sub - region feature parameters of the original sub - regions; wherein, the sub - region feature parameters include the average congestion index of the current period, the average congestion change index, the congestion correlation degree of adjacent intersections, and the combined congestion correlation degree;

[0023] Taking the maximum combined congestion correlation degree of sub - regions and the minimum number of sub - regions in the preset area as the optimization objectives, based on the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, perform separation operations and merging operations on the original sub - regions according to the sub - region feature parameters to obtain a number of unions;

[0024] Update the original sub - regions according to the unions to obtain target sub - regions.

[0025] As an improvement of the above solution, the step of taking the maximum combined congestion correlation degree of sub - regions and the minimum number of sub - regions in the preset area as the optimization objectives, based on the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, and performing separation operations and merging operations on the original sub - regions according to the sub - region feature parameters to obtain a number of unions includes:

[0026] When the average congestion change index of the original sub - region is greater than the preset change index threshold, or the absolute value of the difference between the combined congestion correlation degrees of the original sub - region in the next period and the current period is greater than the preset first correlation degree threshold, perform a separation operation on the original sub - region to obtain a number of unions;

[0027] When there is a separated single intersection, perform a merging operation on the adjacent intersections whose congestion correlation degree is greater than the preset second correlation degree threshold to form a union;

[0028] Construct the target optimization function: max N (K S ·∑ M S m -K M ·M); where N represents the number of intersections in the preset area,.S m is the combined congestion correlation degree of the sub - region, M is the number of sub - regions in the preset area, K S is the preset total combined correlation degree proportion coefficient of the sub - region, K M is the preset sub - region number proportion coefficient;

[0029] Based on the target optimization function and the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, control each union to spread to adjacent other unions to update the unions.

[0030] As an improvement to the above solution, updating the original sub-region according to the coalition to obtain a target sub-region includes:

[0031] When the value of the target optimization function of the updated coalition is greater than the value of the target optimization function of the original sub-region, using the updated coalition as the target sub-region to replace the original sub-region;

[0032] When the value of the target optimization function of the updated coalition is less than or equal to the value of the target optimization function of the original sub-region, using the original sub-region as the target sub-region.

[0033] As an improvement to the above solution, the congestion correlation degree of adjacent intersections is obtained by the following method:

[0034] Calculating the traffic characteristic similarity of adjacent intersections in the first direction and the traffic characteristic similarity in the second direction according to the obtained traffic parameters;

[0035] Calculating the signal cycle similarity of adjacent intersections in the first direction and the signal cycle similarity in the second direction according to the preset cycle pre-timing of each intersection;

[0036] Calculating the one-way correlation degree of adjacent intersections in the first direction and the one-way correlation degree in the second direction according to the traffic characteristic similarity and the signal cycle similarity;

[0037] Adjusting the one-way correlation degree in the first direction according to a preset first congestion impact coefficient, and adjusting the one-way correlation degree in the second direction according to a preset second congestion impact coefficient; wherein, the first congestion impact coefficient and the second congestion impact coefficient are respectively positively correlated with the predicted value of the congestion condition of the adjacent intersection, the first congestion impact coefficient has a greater correlation with the downstream intersection in the first direction than with the upstream intersection in the first direction, and the second congestion impact coefficient has a greater correlation with the downstream intersection in the second direction than with the upstream intersection in the second direction;

[0038] When the first congestion impact coefficient of the adjacent intersection is greater than the second congestion impact coefficient, using the adjusted one-way correlation degree of the adjacent intersection in the first direction as the congestion correlation degree of the adjacent intersection;

[0039] When the first congestion impact coefficient of the adjacent intersection is less than the second congestion impact coefficient, using the adjusted one-way correlation degree of the adjacent intersection in the second direction as the congestion correlation degree of the adjacent intersection;

[0040] When the first congestion influence coefficient of the adjacent intersection is equal to the second congestion influence coefficient, the unidirectional correlation degrees of the adjusted first direction and the second direction are averaged to obtain the congestion correlation degree of the adjacent intersection.

[0041] As an improvement of the above solution, the combined congestion correlation degree is obtained in the following manner:

[0042] For each adjacent intersection, the unidirectional correlation degree of the first direction is adjusted according to a preset first congestion influence coefficient, the unidirectional correlation degree of the second direction is adjusted according to a preset second congestion influence coefficient, and the maximum unidirectional correlation degree is selected from the adjusted unidirectional correlation degrees as the traffic characteristic correlation degree of the adjacent intersection; wherein, the first congestion influence coefficient and the second congestion influence coefficient are respectively positively correlated with the predicted congestion condition value of the adjacent intersection, the first congestion influence coefficient has a greater correlation with the downstream intersection of the first direction than with the upstream intersection of the first direction, and the second congestion influence coefficient has a greater correlation with the downstream intersection of the second direction than with the upstream intersection of the second direction;

[0043] Select the minimum value from the obtained signal cycle similarities of all the adjacent intersections;

[0044] According to the traffic characteristic correlation degrees of all the adjacent intersections and the minimum signal cycle similarity, calculate the combined congestion correlation degree.

[0045] To achieve the above object, an embodiment of the present invention further provides a traffic signal coordination control device, including:

[0046] A sub-region division module, configured to divide all intersections of roads in a preset area to obtain a plurality of target sub-regions;

[0047] A congestion index acquisition module, configured to acquire the average congestion index of the target sub-region in the current cycle and the predicted congestion index of the next cycle;

[0048] An intersection spacing acquisition module, configured to acquire the average intersection spacing of the target sub-region;

[0049] A coordination control module, configured to coordinately control the traffic signals of each intersection in the target sub-region according to the average congestion index, the predicted congestion index, and the average intersection spacing of the target sub-region in the current cycle.

[0050] To achieve the above object, an embodiment of the present invention further provides a traffic signal coordination control device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the traffic signal coordination control method described in any of the above embodiments is implemented.

[0051] To achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. When the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the traffic signal coordination control method described in any of the above embodiments.

[0052] Compared with the prior art, for the traffic signal coordination control method, device, equipment, and storage medium disclosed in the embodiments of the present invention, first, all intersections on the roads in a preset area are divided to obtain several target sub-areas; then, the average congestion index of the target sub-areas in the current cycle and the predicted congestion index in the next cycle are obtained, and the average intersection spacing of the target sub-areas is obtained; finally, according to the average congestion index, the predicted congestion index, and the average intersection spacing of the target sub-areas in the current cycle, the traffic signals at each intersection in the target sub-areas are coordinated and controlled. It can be seen that by dividing the preset area into sub-areas and considering the average congestion index, predicted congestion index, and average intersection spacing for each sub-area, the embodiments of the present invention control the traffic signals, effectively relieve traffic pressure, and improve traffic efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To more clearly illustrate the technical solutions of the present invention, the drawings required for the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0054] Figure 1 is a flowchart of a traffic signal coordination control method provided by an embodiment of the present invention;

[0055] Figure 2 is a structural diagram of a traffic signal coordination control device provided by an embodiment of the present invention;

[0056] Figure 3 is a structural diagram of a traffic signal coordination control structure provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] See Figure 1 , which is a schematic flow chart of a traffic signal coordination control method provided by an embodiment of the present invention. Specifically, the traffic signal coordination control method includes steps S1 to S4:

[0059] S1. Divide all intersections on the roads in the preset area to obtain several target sub-areas;

[0060] S2. Obtain the average congestion index of the target sub-area in the current cycle and the predicted congestion index of the next cycle;

[0061] S3. Obtain the average intersection spacing of the target sub-area;

[0062] S4. Coordinate and control the traffic signals of each intersection in the target sub-area according to the average congestion index, the predicted congestion index, and the average intersection spacing of the target sub-area in the current cycle.

[0063] Specifically, the entire control area (preset area) is divided into sub-areas, and then the sub-areas are dynamically adjusted. The intersections within each sub-area are highly correlated and need to be coordinated for traffic signal control. The coordination control method needs to be differentiated according to the characteristics of each sub-area.

[0064] Exemplarily, according to the characteristics of the sub-area scheme and the change in the congestion degree within the sub-area, the traffic signals within each sub-area are coordinated and optimized for the next signal control cycle:

[0065] (1) Calculate the characteristic parameters of the sub-area

[0066] Obtain the current congestion index and the predicted congestion index of each intersection within the sub-area for comparison, and calculate the average congestion change index of the sub-area according to formulas (1) and (2)

[0067]

[0068]

[0069] Among them, m is the total number of lanes of all intersections within the sub-area; is the average congestion change index of the congestion state within the sub-area; PI ais the change index of the ath lane in the sub - area; is the congestion index of the ath lane in the current cycle; in the above formula, the average change index The larger it is, the more obvious the traffic deterioration trend is.

[0070] According to the predicted traffic parameters, calculate the average congestion index in the sub - area for the next cycle (predicted congestion index):

[0071]

[0072] where m is the total number of lanes of all intersections in the sub - area; is the predicted congestion index of the ath lane in the next cycle; According to the static road network relationship, calculate the average intersection spacing in the sub - area

[0073] where D i，j is the spacing between adjacent intersections, n represents the number of adjacent intersections, a and b represent two adjacent intersections, Q represents the set of intersections in the sub - area, and is calculated according to the static road network relationship.

[0074] (2) According to the sub - area characteristic parameters, coordinate and control the traffic signals at each intersection in the sub - area.

[0075] Compared with the prior art, the embodiment of the present invention divides the preset area into sub - areas, and for each sub - area, comprehensively considers the average congestion index, the predicted congestion index and the average intersection spacing, and controls the traffic signals, effectively relieving the traffic pressure and improving the traffic efficiency.

[0076] In one implementation, it further includes: subtracting the average congestion index of the target sub - area in the current cycle from the predicted congestion index of the target sub - area to obtain the average congestion change index of the target sub - area;

[0077] The coordinating and controlling the traffic signals at each intersection in the target sub - area according to the average congestion index, the predicted congestion index and the average intersection spacing of the target sub - area in the current cycle includes:

[0078] Based on the mapping relationship between the preset coordination control method and the comparison result, determine the target coordination control method according to the first comparison result, the second comparison result and the third comparison result;

[0079] Coordinately control the traffic signals at each intersection in the target sub - area according to the target coordination control method;

[0080] Among them, the first comparison result is the comparison result between the average congestion change index of the target sub-region and a preset change index threshold, the second comparison result is the comparison result between the predicted congestion index of the target sub-region and a preset congestion index threshold, and the third comparison result is the comparison result between the average intersection spacing of the target sub-region and a preset spacing threshold.

[0081] Specifically, the average congestion change index of the sub-region calculated according to formulas (1) and (2) is compared with the preset change index threshold, and the predicted congestion index in the sub-region in the next cycle is compared with the preset congestion index threshold, and the average intersection in the sub-region calculated according to formula (4) is compared with the preset spacing threshold to obtain the corresponding comparison result; based on the pre-set mapping relationship between the coordinated control method and the comparison result, the corresponding coordinated control method is selected for the community according to the current comparison result to control the traffic signal. In the embodiment of the present invention, different coordinated control methods are provided for different traffic states, and the control method is more flexible and can better meet the coordinated control requirements under different traffic states.

[0082] In one implementation manner, based on the pre-set mapping relationship between the coordinated control method and the comparison result, the target coordinated control method is determined according to the first comparison result, the second comparison result and the third comparison result; the traffic signals at each intersection in the target sub-region are coordinated and controlled according to the target coordinated control method, including:

[0083] When the first condition is satisfied, no adjustment of the traffic signal is performed; wherein, the first condition is that the average congestion change index of the target sub-region is less than or equal to the preset change index threshold and the average congestion index of the target sub-region in the current cycle is less than or equal to the congestion index threshold;

[0084] When the second condition is satisfied, the linked phase signal lights between adjacent intersections are controlled to change synchronously; wherein, the second condition is that the first condition is not satisfied and the average intersection spacing of the target sub-region is less than or equal to a preset first spacing threshold;

[0085] When the third condition is satisfied, a preset maximum green wave bandwidth control model is adopted to coordinate and control the traffic signals in the target sub-region; wherein, the third condition is that the first condition and the second condition are not satisfied, the average intersection spacing of the target sub-region is less than or equal to a preset second spacing threshold, the first spacing threshold is greater than the second spacing threshold, and the average congestion index of the target sub-region in the current cycle is less than or equal to the preset congestion index threshold;

[0086] When none of the first condition, the second condition, and the third condition is satisfied, a preset parking delay control model is used to coordinately control the traffic signals in the target sub - area, so as to minimize the weighted sum of the total number of stops and the delay time in the target sub - area.

[0087] Exemplarily, the traffic coordination control process in the sub - area includes: (1) calculating the characteristic parameters of the sub - area; (2) selecting a coordination control model according to the sub - area characteristic parameters, and the specific control logic is as follows:

[0088] ① When holds, no adjustment of traffic signals is made, and each intersection continues to use the current signal timing plan to avoid frequent signal adjustments and introduce unstable factors. T P1 is the change index threshold, is the congestion index threshold;

[0089] ② When the condition does not satisfy ① holds, a synchronous control mode is adopted, and the linked - phase signal lights between adjacent intersections change synchronously, allowing the vehicle flow to continuously pass through adjacent intersections and avoiding the deterioration of the traffic state due to vehicle flow blockage. is the first spacing threshold.

[0090] ③ When the condition does not satisfy ① and ② holds, a maximum green - wave bandwidth control model is adopted to coordinately control the signals, so that the vehicle flow can continuously obtain the right - of - way with green lights when passing through its adjacent intersections. is the second spacing threshold.

[0091] ④ When the conditions ①, ②, and ③ are not satisfied, a parking delay control model is used to conduct signal coordination in the sub - area to achieve the goal of minimizing the weighted sum of the total number of stops and the delay time in the sub - area.

[0092] It should be noted that the synchronous control mode means that the signal lights of two adjacent intersections adopt synchronous signals of both green lights and both red lights at the same time, or a traffic control mode with only a green - light time difference; for the green - wave coordinated control, the green - wave means the signal state in which the vehicle flow passes through each adjacent intersection and obtains continuous green lights, and the green - wave coordinated control is to connect multiple intersections in a certain way so that when the vehicle flow travels from the previous intersection to the next adjacent intersection, it just obtains the green - light signal; for the parking - delay coordinated control, it is a regional traffic benefit optimization control method with the goal of minimizing the weighted sum of the number of stops and the delay time.

[0093] This embodiment provides a regional control model selection mechanism based on "sub - area characteristic parameters", which meets the coordinated control requirements under different traffic states, has a more flexible control method, and can better meet the coordinated control requirements under different traffic states.

[0094] In one embodiment, dividing all intersections of roads in the preset area to obtain a number of target sub-areas includes:

[0095] Obtain a number of current original sub-areas in the preset area;

[0096] Obtain the sub-area characteristic parameters of the original sub-areas; wherein, the sub-area characteristic parameters include the average congestion index, average congestion change index, congestion correlation degree of adjacent intersections, and combined congestion correlation degree in the current cycle;

[0097] Taking the maximum combined congestion correlation degree of sub-areas and the minimum number of sub-areas in the preset area as the optimization objectives, based on the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, perform separation operations and merging operations on the original sub-areas according to the sub-area characteristic parameters to obtain a number of unions;

[0098] Update the original sub-areas according to the unions to obtain target sub-areas.

[0099] In one embodiment, taking the maximum combined congestion correlation degree of sub-areas and the minimum number of sub-areas in the preset area as the optimization objectives, based on the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, perform separation operations and merging operations on the original sub-areas according to the sub-area characteristic parameters to obtain a number of unions, including:

[0100] When the average congestion change index of the original sub-area is greater than the preset change index threshold, or the absolute value of the difference between the combined congestion correlation degrees of the original sub-area in the next cycle and the current cycle is greater than the preset first correlation degree threshold, perform a separation operation on the original sub-area to obtain a number of unions;

[0101] When there is a single separated intersection, merge the adjacent intersections with a congestion correlation degree greater than the preset second correlation degree threshold to form a union;

[0102] Construct the target optimization function: max N (K S ·∑ M S m -K M ·M); where N represents the number of intersections in the preset area,.S m is the combined congestion correlation degree of the sub-area, M is the number of sub-areas in the preset area, K S is the preset total combined correlation degree ratio coefficient of the sub-areas, K M is the preset sub-area number ratio coefficient;

[0103] Based on the objective optimization function and the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, control each union to spread to adjacent other unions to update the union.

[0104] In one implementation manner, the updating the original sub-region according to the union to obtain a target sub-region includes:

[0105] When the value of the objective optimization function of the updated union is greater than the value of the objective optimization function of the original sub-region, use the updated union as the target sub-region to replace the original sub-region;

[0106] When the value of the objective optimization function of the updated union is less than or equal to the value of the objective optimization function of the original sub-region, use the original sub-region as the target sub-region.

[0107] Specifically, the embodiment of the present invention details the process of dynamic partitioning of sub-regions. Sub-region partitioning is the basis of coordinated control. If the partitioning is unreasonable, it will affect the coordinated control effect. If the partitioning changes too frequently, it will cause instability of signal control. Therefore, it is necessary to adjust the sub-region partitioning situation timely and appropriately to adapt to the dynamically changing traffic environment. In the existing solutions, each intersection is regarded as an independent entity, and the separation and merging of sub-regions are determined according to the change of the correlation degree between two adjacent intersections, without considering the overall correlation degree property of multiple intersections and the change trend of the current traffic operation state. When the traffic condition of a certain intersection changes, this type of method is prone to cause frequent and large sub-region partitioning changes, increasing the instability of signal control. In the embodiment of the present invention, both the congestion correlation degree between adjacent intersections and the combined congestion correlation degree of multiple intersections are considered, multiple intersections are regarded as a union, and the partitioning is dynamically adjusted in units of the union, combining the current traffic congestion change trend, to adapt to traffic changes while ensuring the stability of control.

[0108] The specific steps of sub-region update are as follows:

[0109] (1) Calculate sub-region characteristic parameters.

[0110] According to the predicted traffic parameters and the pre-timing of a single intersection, the combined congestion correlation degree within the sub-region is predicted by formulas (14) and (15) in the current cycle

[0111] Compare the current average congestion index of each intersection within the sub-region with the predicted congestion index, and calculate the average congestion change index of the congestion state within the sub-region according to formulas (1) and (2)

[0112] (2) Perform sub-region separation according to the average congestion change index and the change of the combined congestion correlation degree.

[0113] When or (the first correlation threshold), a separation operation is performed on this sub - area. That is, when the worsening trend of traffic congestion in the sub - area exceeds a certain threshold, or when the change in the combined congestion correlation is large, the sub - area is separated; otherwise, the sub - area is not separated. When the traffic operation status is controllable, a certain degree of traffic condition fluctuation within the sub - area is allowed.

[0114] (3) Generate sub - area union blocks according to the congestion correlation of adjacent intersections.

[0115] After step (2), if there are separated single intersections, calculate the congestion correlation of each adjacent intersection according to formulas (11), (12), and (13). For adjacent intersections with a correlation greater than the threshold (the second correlation threshold), a merging operation is performed, and intersections with high correlation are bundled as much as possible to form a union. Together with the sub - area blocks that are not separated after step (2), several sub - area unions {Q 1 , Q 2 ,...} are obtained. Each union contains one or more intersections and participates in subsequent sub - area adjustments as a whole, which can not only improve the reliability of sub - area division but also achieve dimensionality reduction by block division and simplify the calculation.

[0116] (4) Generate the best merging plan by spreading the sub - area union blocks according to the sub - area division optimization model.

[0117] For a connectivity control area, the fewer the number of control sub - areas, the more beneficial it is to the overall coordination effect; the larger the sum of the combined congestion correlations of all control sub - areas, the better the coordination control effect within the sub - area. Suppose there are N intersections in the connectivity area, and the partition model of the overall area is defined as the weighted sum of the number of sub - areas and the total combined correlation. The target optimization function of the partition is:

[0118] max N (K S ·∑ M S m -K M ·M); (5)

[0119]

[0120] Among them, S m is the combined congestion correlation of the sub - area; M is the number of control sub - areas in this connectivity area; K S is the proportionality coefficient of the total combined correlation of the sub - area, taking an empirical value; K M is the proportionality coefficient of the number of sub - areas, taking an empirical value; Constraints for sub - area merging; I is the combined congestion correlation degree of the sub - area; is the threshold value of the combined congestion correlation degree within the sub - area (merging threshold);

[0121] For the sub - area union block set obtained in step (3), for each sub - block, it spreads to the adjacent sub - blocks around it and attempts to merge sub - block with sub - block. Calculate the combined congestion correlation degree according to formulas (14) and (15). Under the constraint conditions of formula (6), if the combined correlation degree value is less than the threshold then the two sub - blocks are not allowed to merge. If the combined congestion correlation degree value is greater than or equal to the threshold then the two sub - blocks are allowed to merge, which is one of the alternative solutions. Search for the partition plan with the optimal target optimization value in the overall area according to formula (5).

[0122] (5) Sub - area update.

[0123] Compare the optimal sub - area partition plan in step (4) with the original sub - area plan. If the target optimization value of the new plan is better than the current plan, then in the next signal control cycle, adopt the new sub - area plan to obtain several target sub - areas; otherwise, no sub - area adjustment is made.

[0124] In one implementation manner, the congestion correlation degree of adjacent intersections is obtained through the following method:

[0125] Calculate the traffic characteristic similarity in the first direction and the traffic characteristic similarity in the second direction of adjacent intersections according to the obtained traffic parameters;

[0126] Calculate the signal cycle similarity in the first direction and the signal cycle similarity in the second direction of the adjacent intersections according to the preset cycle pre - timing of each intersection;

[0127] Calculate the one - way correlation degree in the first direction and the one - way correlation degree in the second direction of the adjacent intersections according to the traffic characteristic similarity and the signal cycle similarity;

[0128] Adjust the one - way correlation degree in the first direction according to the preset first congestion influence coefficient, and adjust the one - way correlation degree in the second direction according to the preset second congestion influence coefficient; wherein, the first congestion influence coefficient and the second congestion influence coefficient are respectively positively correlated with the predicted congestion condition value of the adjacent intersections, the first congestion influence coefficient has a greater correlation with the downstream intersection in the first direction than with the upstream intersection in the first direction, and the second congestion influence coefficient has a greater correlation with the downstream intersection in the second direction than with the upstream intersection in the second direction;

[0129] When the first congestion influence coefficient of the adjacent intersection is greater than the second congestion influence coefficient, the one-way correlation degree of the adjacent intersection in the first direction after adjustment is used as the congestion correlation degree of the adjacent intersection;

[0130] When the first congestion influence coefficient of the adjacent intersection is less than the second congestion influence coefficient, the one-way correlation degree of the adjacent intersection in the second direction after adjustment is used as the congestion correlation degree of the adjacent intersection;

[0131] When the first congestion influence coefficient of the adjacent intersection is equal to the second congestion influence coefficient, the one-way correlation degrees of the adjusted first direction and the second direction are averaged to obtain the congestion correlation degree of the adjacent intersection.

[0132] In one implementation, the combined congestion correlation degree is obtained in the following manner:

[0133] For each adjacent intersection, the one-way correlation degree in the first direction is adjusted according to a preset first congestion influence coefficient, the one-way correlation degree in the second direction is adjusted according to a preset second congestion influence coefficient, and the maximum one-way correlation degree is selected from the adjusted one-way correlation degrees as the traffic characteristic correlation degree of the adjacent intersection; wherein, the first congestion influence coefficient and the second congestion influence coefficient are respectively positively correlated with the predicted congestion condition value of the adjacent intersection, the first congestion influence coefficient has a greater correlation with the downstream intersection in the first direction than with the upstream intersection in the first direction, and the second congestion influence coefficient has a greater correlation with the downstream intersection in the second direction than with the upstream intersection in the second direction;

[0134] Select the minimum value from the obtained signal cycle similarities of all the adjacent intersections;

[0135] Calculate the combined congestion correlation degree according to the traffic characteristic correlation degrees of all the adjacent intersections and the minimum signal cycle similarity.

[0136] Specifically, the main basis for controlling sub-region division is the traffic characteristic similarity between intersections and the consistency of coordinated control within the sub-region. In the existing intersection correlation degree models, only the distance between intersections, traffic flow, and signal cycle are considered. However, if a certain intersection is congested, the congestion condition will spread to the upstream, downstream, and adjacent intersections after a period of time. Therefore, the congestion condition of intersections is an important factor for judging whether adjacent intersections need coordinated control and is also the most fundamental purpose of coordinated control.

[0137] Therefore, based on the traditional "distance-flow-cycle" correlation model, a congestion impact coefficient is introduced, and factors such as section spacing, dynamic traffic flow, dynamic vehicle speed, congestion degree, intersection signal timing cycle, intersection signal phase, and downstream queue length are comprehensively considered to establish a congestion correlation model for adjacent intersections and a combined congestion correlation model for multiple intersections.

[0138] (1) Congestion correlation model for adjacent intersections.

[0139] Let I i，j be the correlation degree between adjacent intersections i and j, where i is the upstream intersection and j is the downstream intersection. Based on the classic Whitson model, the queue length and traffic flow dispersion coefficient are introduced to obtain the traffic characteristic similarity as follows:

[0140]

[0141] Among them, is the traffic characteristic similarity of the traffic flow from intersection i to j, and its value range is [0, 1]; f is the number of traffic flow branches from intersection i to intersection j. For example, if intersection i is a crossroads, then f is 3; p i->j is the number of phases in a cycle at intersection i that allow traffic flow to enter intersection j. For example, for a crossroads, a total of P phases are designed, and among them, there are two phases with traffic flow from i to j, then the number of such phases is 2; q max is the maximum branch traffic flow from intersection i to intersection j; q m is the traffic flow from intersection i to intersection j at phase e; β e is the traffic flow proportion coefficient from intersection i to j at phase e; P is the total number of phases at intersection i; is the total traffic flow from intersection i to j in all phases; d i，j is the distance between intersections i and j; l j is the queue length at intersection j; v is the average driving speed from intersection i to j; K T is the traffic characteristic correlation weight coefficient, taking an empirical value.

[0142] According to the pre-timing of the cycle of each intersection, the signal cycle similarity of adjacent intersections is obtained as follows:

[0143]

[0144] Among them, is the signal cycle characteristic correlation degree between intersections i and j, and its value range is [0, 1]; C i is the independent designed signal cycle of intersection i; C j is the independent designed signal cycle of intersection j; max(Ci , C j ) is the larger value in the independent design signal cycles of intersections i and j; min(C i , C j ) is the smaller value in the independent design signal cycles of intersections i and j; K C is the weight coefficient related to the signal cycle characteristics, taking an empirical value.

[0145] The correlation degree between adjacent intersections consists of the similarity of traffic characteristics and the similarity of signal cycles, and there is:

[0146]

[0147] I i，j = 0.5·(I i->j + I j->i ); (10)

[0148] Among them, I i->j is the correlation degree of the vehicle flow from intersection i -> intersection j; I j->i is the correlation degree of the vehicle flow from intersection j -> intersection i; I i，j is the correlation degree between adjacent intersections i and j;

[0149] The above formula (10) is the preliminary correlation degree model of adjacent intersections. In this model, factors such as intersection spacing, traffic volume, queue length, and signal cycle are integrated, but the changing trend of traffic state is not considered. In actual traffic, after a certain intersection becomes congested, it will spread to upstream, downstream, and adjacent intersections after a period of time, causing congestion even when the traffic volume at other intersections does not change significantly. Therefore, on the basis of the preliminary scheme, a traffic factor - congestion impact coefficient for compensating the correlation degree of adjacent intersections is proposed to explore the impact of traffic congestion status on adjacent intersections. Through analysis, the impact trend of the congestion status of intersections on the correlation degree shows a certain positive correlation, and there is:

[0150]

[0151] Among them,

[0152] - is the congestion impact coefficient from intersection i -> j;

[0153] I i->j ′ - is the congestion correlation degree of the vehicle flow from intersection i -> intersection j;

[0154] Upon further analysis, it is found that the congestion states of the upstream intersection and the downstream intersection do not exactly match the slopes of the curves of the influence on the correlation degree. It shows that the congestion of the downstream intersection has a greater impact on the correlation degree, and there is a certain lag between the changing trends of the congestion states of the intersections and the changing trends of the correlation degree. Based on this, the predicted congestion level is used to compensate for the lag in the change of the correlation degree, and different weighting factors are selected for the congestion conditions of the upstream and downstream intersections, as follows:

[0155]

[0156] Among them,

[0157] α i - is the proportionality coefficient of the congestion condition of the upstream intersection i, taking an empirical value;

[0158] α j - is the proportionality coefficient of the congestion condition of the downstream intersection j, with α i +α j =1, and α j >α i . Considering that in practice, if the traffic flow state of the downstream intersection is good, it can "digest" a certain amount of traffic flow and relieve the congestion of the upstream intersection without significantly affecting its own congestion condition; on the contrary, if the congestion condition of the downstream intersection is serious, it will greatly affect the traffic flow state of the upstream. Therefore, the downstream intersection is relatively insensitive to the congestion degree of the upstream intersection, while the upstream intersection is relatively sensitive to the congestion degree of the downstream intersection. Therefore, the downstream congestion proportionality coefficient α j takes a relatively large value.

[0159] J i - is the predicted value of the congestion condition of intersection i (predicted congestion index), which is quantified by the predicted congestion level. The 4 congestion levels are converted into a compensation coefficient in the range of [1.0, 2.0] through linear mapping, as follows where J Li is the predicted congestion level of intersection i, obtained through prediction. The predicted congestion level can form a feedforward compensation for the lag in the influence on the correlation degree in formula (12).

[0160] J j - is the predicted value of the congestion condition of intersection j.

[0161] Finally, in calculating the correlation degree of different traffic flow directions, instead of using the average value method, the calculated value in the congestion direction is more preferably selected to obtain the congestion correlation degree model of adjacent intersections, as follows:

[0162]

[0163] Among them,

[0164] I j->i ′ - is the congestion correlation degree of the traffic flow from intersection j to intersection i;

[0165] I i，j ′ - is the congestion correlation degree between adjacent intersections i and j;

[0166] In the above formula, the higher the congestion level of the intersection, the greater the compensation for the correlation degree. The more serious the congestion in a certain traffic direction, the more inclined to use the correlation degree in that direction for subsequent analysis.

[0167] (2) Multi - intersection combined congestion correlation degree model

[0168] In the existing technical solutions, only the correlation degree of adjacent intersections is analyzed, and there is little analysis of the combined correlation degree of multiple intersections. However, the same control sub - area contains multiple intersections, and there must be a certain correlation degree between multiple intersections to achieve good coordinated control. But in the case of congestion, the congested sections should be regarded as the same sub - area for coordinated control to clear the traffic in time. As the number of intersections increases, the correlation degree of traffic characteristics in the sub - area gradually weakens, and the correlation degree of signal cycle characteristics increases. Therefore, in the embodiments of the present invention, first, the "congestion influence coefficient" is used to compensate the traffic characteristics of each adjacent intersection, then the combined traffic characteristics of multiple intersections are calculated, and finally, for the multi - intersection combined congestion correlation degree model, there is:

[0169] Let S h be the combined correlation degree of a group of associated intersections {1, 2,..., h}, which contains h intersections and g pairs of associated intersections. A combined congestion correlation degree model for a group of intersections is established:

[0170]

[0171]

[0172] Among them,

[0173] - is the traffic characteristic correlation degree based on congestion compensation between adjacent intersections i and j in the sub - area.

[0174] - is the list of traffic characteristic correlation degrees between adjacent intersections in the sub - area, with a total of g pairs of associated intersections, that is, there are g values in the list.

[0175] Π - product operator.

[0176] - intersection group I (1，2，...，h) The total cycle characteristic correlation degree, taking the minimum value of the cycle correlation degrees between pairwise intersections.

[0177] - Intersection Group I (1，2，...，h) The overall traffic characteristic correlation degree is compensated by adding a quantization coefficient of the congestion level to the traffic characteristic correlation degree.

[0178] Furthermore, the prediction of traffic parameters and the single intersection pre-timing (the cycle pre-timing of the intersection) are determined as follows:

[0179] By using the monitoring videos installed at the intersections and through deep learning object detection technology and multi-object tracking technology, the traffic parameters of each lane within the cycle are obtained in real time, including: traffic flow, average vehicle speed, queue length, and congestion level. The congestion level includes 4 levels, namely, smooth traffic (Level 1), slightly congested traffic (Level 2), moderately congested traffic (Level 3), and severely congested traffic (Level 4).

[0180] The traffic parameter prediction takes 5 minutes as a cycle, that is, Δt p = 5 (mmin). Based on the traffic parameters of the current cycle, the traffic parameters of the previous cycle, the traffic parameters of the same time period of the previous day, the traffic parameters of the same time period of the previous week, holiday events, and the current weather, a deep learning spatio-temporal graph convolutional network model is used to predict the traffic parameters of the next cycle. Through this method, the predicted values of traffic flow, vehicle speed, queue length, and congestion level of each lane of each intersection in the region for the next 5 minutes are obtained.

[0181] The signal control takes 15 minutes as a cycle, that is, Δt s = 15 (mmin). The traffic parameters referred to in the next signal control cycle are calculated by averaging the parameters of 3 traffic cycles, and there are:

[0182]

[0183] Among them,

[0184] - are the traffic parameters of the next signal control cycle;

[0185] - are the traffic parameters of the past traffic cycle;

[0186] - are the traffic parameters of the current traffic cycle;

[0187] - are the predicted parameters of the future traffic cycle;

[0188] According to the Webster delay model, the signal pre-timing design of the next signal control cycle is carried out for each intersection, and the pre-timed signal cycle C of each intersection is obtained:

[0189]

[0190] Among them,

[0191] L - is the total lost time of the signal light cycle (including the front lost time, the rear lost time of each green light time, the all - red time of the phase, etc.);

[0192] Y 0 - is the sum of the traffic flow ratios (designed traffic flow / designed saturation flow rate) of the key lanes of each key phase.

[0193] Compared with the prior art, in the embodiment of the present invention, first, all intersections of the roads in the preset area are divided to obtain several target sub - areas; then, the average congestion index of the target sub - area in the current cycle and the predicted congestion index of the next cycle are obtained, and the average intersection spacing of the target sub - area is obtained; finally, according to the average congestion index, the predicted congestion index and the average intersection spacing of the target sub - area in the current cycle, the traffic signals of each intersection in the target sub - area are coordinately controlled. Thus, it can be seen that in the embodiment of the present invention, by dividing the preset area into sub - areas and for each sub - area, comprehensively considering the average congestion index, the predicted congestion index and the average intersection spacing, the traffic signals are controlled, effectively relieving the traffic pressure and improving the traffic efficiency.

[0194] See Figure 2 , the embodiment of the present invention also provides a traffic signal coordination control device, including:

[0195] A sub - area division module 11, configured to divide all intersections of the roads in the preset area to obtain several target sub - areas;

[0196] A congestion index acquisition module 12, configured to obtain the average congestion index of the target sub - area in the current cycle and the predicted congestion index of the next cycle;

[0197] An intersection spacing acquisition module 13, configured to obtain the average intersection spacing of the target sub - area;

[0198] A coordination control module 14, configured to coordinately control the traffic signals of each intersection in the target sub - area according to the average congestion index, the predicted congestion index and the average intersection spacing of the target sub - area in the current cycle.

[0199] In an implementation manner, the coordination control module is specifically configured to:

[0200] Subtract the average congestion index of the target sub - area in the current cycle from the predicted congestion index of the target sub - area to obtain the average congestion change index of the target sub - area;

[0201] Determine the target coordinated control mode according to the mapping relationship between the preset coordinated control mode and the comparison result, based on the first comparison result, the second comparison result, and the third comparison result;

[0202] Coordinately control the traffic signals at each intersection in the target sub - area according to the target coordinated control mode;

[0203] Among them, the first comparison result is the comparison result between the average congestion change index of the target sub - area and the preset change index threshold, the second comparison result is the comparison result between the predicted congestion index of the target sub - area and the preset congestion index threshold, and the third comparison result is the comparison result between the average intersection spacing of the target sub - area and the preset spacing threshold.

[0204] In one implementation, the determining the target coordinated control mode according to the mapping relationship between the preset coordinated control mode and the comparison result, based on the first comparison result, the second comparison result, and the third comparison result; and coordinately controlling the traffic signals at each intersection in the target sub - area according to the target coordinated control mode includes:

[0205] When the first condition is met, no adjustment of the traffic signal is made; where the first condition is that the average congestion change index of the target sub - area is less than or equal to the preset change index threshold and the average congestion index of the target sub - area in the current cycle is less than or equal to the congestion index threshold;

[0206] When the second condition is met, control the synchronous change of the linkage phase signal lights between adjacent intersections; where the second condition is that the first condition is not met and the average intersection spacing of the target sub - area is less than or equal to the preset first spacing threshold;

[0207] When the third condition is met, adopt the preset maximum green - wave bandwidth control model to coordinately control the traffic signals in the target sub - area; where the third condition is that the first condition and the second condition are not met, the average intersection spacing of the target sub - area is less than or equal to the preset second spacing threshold, the first spacing threshold is greater than the second spacing threshold, and the average congestion index of the target sub - area in the current cycle is less than or equal to the preset congestion index threshold;

[0208] When none of the first condition, the second condition, and the third condition are met, use the preset stop - delay control model to coordinately control the traffic signals in the target sub - area so that the weighted sum of the total number of stops and the delay time in the target sub - area is minimized.

[0209] In one implementation, the sub - area division module is specifically the same as:

[0210] Obtain several current original sub - areas in the preset area;

[0211] Obtain the sub-region feature parameters of the original sub-region; wherein, the sub-region feature parameters include the average congestion index, average congestion change index, congestion correlation degree of adjacent intersections, and combined congestion correlation degree of the current period.

[0212] Taking the maximum combined congestion correlation degree of sub-regions and the minimum number of sub-regions within the preset area as the optimization objectives, based on the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, perform separation and merging operations on the original sub-regions according to the sub-region feature parameters to obtain a number of unions.

[0213] Update the original sub-regions according to the unions to obtain target sub-regions.

[0214] In one implementation, the step of taking the maximum combined congestion correlation degree of sub-regions and the minimum number of sub-regions within the preset area as the optimization objectives, based on the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, and performing separation and merging operations on the original sub-regions according to the sub-region feature parameters to obtain a number of unions includes:

[0215] When the average congestion change index of the original sub-region is greater than the preset change index threshold, or the absolute value of the difference between the combined congestion correlation degrees of the original sub-region in the next period and the current period is greater than the preset first correlation degree threshold, perform a separation operation on the original sub-region to obtain a number of unions.

[0216] When there is a single separated intersection, perform a merging operation on the adjacent intersections whose congestion correlation degree is greater than the preset second correlation degree threshold to form a union.

[0217] Construct a target optimization function: max N (K S ·∑ M S m -K M ·M); where N represents the number of intersections within the preset area, S m is the combined congestion correlation degree of the sub-region, M is the number of sub-regions within the preset area, K S is the preset total combined correlation degree proportion coefficient of the sub-region, and K M is the preset sub-region number proportion coefficient.

[0218] Based on the target optimization function and the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, control each union to spread to adjacent other unions to update the unions.

[0219] In one implementation, updating the original sub-region according to the coalition to obtain a target sub-region includes:

[0220] When the value of the target optimization function of the updated coalition is greater than the value of the target optimization function of the original sub-region, using the updated coalition as the target sub-region to replace the original sub-region;

[0221] When the value of the target optimization function of the updated coalition is less than or equal to the value of the target optimization function of the original sub-region, using the original sub-region as the target sub-region.

[0222] In one implementation, the congestion correlation degree of adjacent intersections is obtained in the following manner:

[0223] Calculating the traffic characteristic similarity of adjacent intersections in the first direction and the traffic characteristic similarity in the second direction according to the obtained traffic parameters;

[0224] Calculating the signal cycle similarity of adjacent intersections in the first direction and the signal cycle similarity in the second direction according to the pre-set cycle pre-timing of each intersection;

[0225] Calculating the one-way correlation degree of adjacent intersections in the first direction and the one-way correlation degree in the second direction according to the traffic characteristic similarity and the signal cycle similarity;

[0226] Adjusting the one-way correlation degree of the first direction according to a pre-set first congestion influence coefficient, and adjusting the one-way correlation degree of the second direction according to a pre-set second congestion influence coefficient; wherein, the first congestion influence coefficient and the second congestion influence coefficient are respectively positively correlated with the predicted value of the congestion condition of the adjacent intersection, the first congestion influence coefficient has a greater correlation with the downstream intersection in the first direction than with the upstream intersection in the first direction, and the second congestion influence coefficient has a greater correlation with the downstream intersection in the second direction than with the upstream intersection in the second direction;

[0227] When the first congestion influence coefficient of the adjacent intersection is greater than the second congestion influence coefficient, using the adjusted one-way correlation degree of the adjacent intersection in the first direction as the congestion correlation degree of the adjacent intersection;

[0228] When the first congestion influence coefficient of the adjacent intersection is less than the second congestion influence coefficient, using the adjusted one-way correlation degree of the adjacent intersection in the second direction as the congestion correlation degree of the adjacent intersection;

[0229] When the first congestion influence coefficient of the adjacent intersection is equal to the second congestion influence coefficient, the average calculation is performed on the one-way correlation degrees of the adjusted first direction and the second direction to obtain the congestion correlation degree of the adjacent intersection.

[0230] In one implementation manner, the combined congestion correlation degree is obtained through the following steps:

[0231] For each adjacent intersection, the one-way correlation degree of the first direction is adjusted according to a preset first congestion influence coefficient, the one-way correlation degree of the second direction is adjusted according to a preset second congestion influence coefficient, and the maximum one-way correlation degree is selected from the adjusted one-way correlation degrees as the traffic characteristic correlation degree of the adjacent intersection; wherein, the first congestion influence coefficient and the second congestion influence coefficient are respectively in a positive correlation with the predicted congestion condition value of the adjacent intersection, the first congestion influence coefficient has a greater correlation with the downstream intersection of the first direction than with the upstream intersection of the first direction, and the second congestion influence coefficient has a greater correlation with the downstream intersection of the second direction than with the upstream intersection of the second direction;

[0232] The minimum value is selected from the obtained signal cycle similarities of all the adjacent intersections;

[0233] The combined congestion correlation degree is calculated according to the traffic characteristic correlation degrees of all the adjacent intersections and the minimum signal cycle similarity.

[0234] It should be noted that the working process of the specific traffic signal coordination control device may refer to the working process of the traffic signal coordination control method in the above embodiment, which will not be elaborated here.

[0235] Compared with the prior art, the traffic signal coordination control device disclosed in the embodiment of the present invention first divides all intersections on the roads in a preset area to obtain several target sub-areas; then, obtains the average congestion index of the target sub-areas in the current cycle and the predicted congestion index in the next cycle, and obtains the average intersection spacing of the target sub-areas; finally, coordinates and controls the traffic signals of each intersection in the target sub-areas according to the average congestion index, the predicted congestion index and the average intersection spacing of the target sub-areas in the current cycle. It can be seen that the embodiment of the present invention effectively alleviates traffic pressure and improves traffic efficiency by dividing the preset area into sub-areas and comprehensively considering the average congestion index, the predicted congestion index and the average intersection spacing for each sub-area to control the traffic signals.

[0236] See Figure 3, an embodiment of the present invention further provides a traffic signal coordination control device, including a processor 21, a memory 22, and a computer program stored in the memory and configured to be executed by the processor 21. When the processor 21 executes the computer program, the steps in the traffic signal coordination control method embodiment as described above are implemented, such as Figure 1 the steps S1 to S4 described in; or, when the processor 21 executes the computer program, the functions of each module in the above device embodiments are implemented.

[0237] Exemplarily, the computer program can be divided into one or more modules. The one or more modules are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of completing specific functions, and this instruction segment is used to describe the execution process of the computer program in the traffic signal coordination control device. For example, the computer program can be divided into multiple modules, and the specific functions of each module are as follows:

[0238] The sub-region division module 11 is used to divide all intersections on the roads in the preset area to obtain several target sub-regions;

[0239] The congestion index acquisition module 12 is used to acquire the average congestion index of the target sub-region in the current cycle and the predicted congestion index of the next cycle;

[0240] The intersection spacing acquisition module 13 is used to acquire the average intersection spacing of the target sub-region;

[0241] The coordination control module 14 is used to coordinately control the traffic signals of each intersection in the target sub-region according to the average congestion index, the predicted congestion index, and the average intersection spacing of the target sub-region in the current cycle.

[0242] The specific working processes of each module can refer to the working process of the traffic signal coordination control device described in the above embodiments, and will not be elaborated here.

[0243] The traffic signal coordination control device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The traffic signal coordination control device can include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art can understand that the traffic signal coordination control device can further include input / output devices, network access devices, a bus, etc.

[0244] The processor 21 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor 21 is the control center of the traffic signal coordination control device and connects all parts of the entire traffic signal coordination control device through various interfaces and lines.

[0245] The memory 22 can be used to store the computer programs and / or modules. The processor 21 realizes various functions of the traffic signal coordination control device by running or executing the computer programs and / or modules stored in the memory 22 and by calling the data stored in the memory 22. The memory 22 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function (such as an image playback function, etc.); the data storage area may store data created according to the use of the mobile phone, etc. In addition, the memory 22 may include high-speed random access memory and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0246] Among them, if the modules integrated in the traffic signal coordinated control device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0247] The above is the preferred implementation manner of the present invention. It should be noted that for those of ordinary skill in the art of this technology, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A traffic signal coordination control method, characterized in that, it includes: Dividing all intersections on the roads within a preset area to obtain several target sub-areas; Obtaining the average congestion index of the target sub-areas in the current cycle and the predicted congestion index of the next cycle; Obtaining the average intersection spacing of the target sub-areas; Coordinating and controlling the traffic signals of each intersection within the target sub-areas according to the average congestion index, the predicted congestion index and the average intersection spacing of the target sub-areas in the current cycle.

2. The traffic signal coordination control method according to claim 1, characterized in that, it further includes: Subtracting the average congestion index of the target sub-areas in the current cycle from the predicted congestion index of the target sub-areas to obtain the average congestion change index of the target sub-areas; The coordinating and controlling the traffic signals of each intersection within the target sub-areas according to the average congestion index, the predicted congestion index and the average intersection spacing of the target sub-areas in the current cycle includes: Based on the mapping relationship between the preset coordination control method and the comparison result, determining the target coordination control method according to the first comparison result, the second comparison result and the third comparison result; Coordinating and controlling the traffic signals of each intersection within the target sub-areas according to the target coordination control method; wherein, the first comparison result is the comparison result between the average congestion change index of the target sub-areas and the preset change index threshold, the second comparison result is the comparison result between the predicted congestion index of the target sub-areas and the preset congestion index threshold, and the third comparison result is the comparison result between the average intersection spacing of the target sub-areas and the preset spacing threshold.

3. The traffic signal coordination control method according to claim 2, characterized in that, The determining the target coordination control method based on the mapping relationship between the preset coordination control method and the comparison result, and according to the first comparison result, the second comparison result and the third comparison result; The coordinating and controlling the traffic signals of each intersection within the target sub-areas according to the target coordination control method includes: When the first condition is met, no adjustment of the traffic signal is made; wherein, the first condition is that the average congestion change index of the target sub-areas is less than or equal to the preset change index threshold and the average congestion index of the target sub-areas in the current cycle is less than or equal to the congestion index threshold; When the second condition is met, controlling the synchronous change of the linkage phase signal lights between adjacent intersections; wherein, the second condition is that the first condition is not met and the average intersection spacing of the target sub-areas is less than or equal to the preset first spacing threshold; When the third condition is met, adopting the preset maximum green wave bandwidth control model to coordinate and control the traffic signals within the target sub-areas; wherein, the third condition is that the first condition and the second condition are not met, the average intersection spacing of the target sub-areas is less than or equal to the preset second spacing threshold, the first spacing threshold is greater than the second spacing threshold, and the average congestion index of the target sub-areas in the current cycle is less than or equal to the preset congestion index threshold; When none of the first condition, the second condition, and the third condition is satisfied, a preset parking delay control model is used to coordinately control the traffic signals in the target sub - area so as to minimize the weighted sum of the total number of stops and the delay time in the target sub - area.

4. The traffic signal coordination control method according to any one of claims 1 to 3, characterized in that the dividing of all intersections on the roads in the preset area to obtain a plurality of target sub - areas includes: obtaining a plurality of current original sub - areas in the preset area; obtaining the sub - area characteristic parameters of the original sub - areas; wherein, the sub - area characteristic parameters include the average congestion index, the average congestion change index, the congestion correlation degree between adjacent intersections, and the combined congestion correlation degree in the current cycle; taking the maximum combined congestion correlation degree of the sub - areas and the minimum number of sub - areas in the preset area as the optimization objectives, and based on the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, performing separation operations and merging operations on the original sub - areas according to the sub - area characteristic parameters to obtain a plurality of unions; updating the original sub - areas according to the unions to obtain the target sub - areas.

5. The traffic signal coordination control method according to claim 4, characterized in that the taking the maximum combined congestion correlation degree of the sub - areas and the minimum number of sub - areas in the preset area as the optimization objectives, and based on the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, performing separation operations and merging operations on the original sub - areas according to the sub - area characteristic parameters to obtain a plurality of unions includes: when the average congestion change index of the original sub - area is greater than a preset change index threshold, or the absolute value of the difference between the combined congestion correlation degrees of the original sub - area in the next cycle and the current cycle is greater than a preset first correlation degree threshold, performing a separation operation on the original sub - area to obtain a plurality of unions; when there is a separated single intersection, merging the adjacent intersections with the congestion correlation degree greater than a preset second correlation degree threshold to form a union; Construct the objective optimization function: max N (K S ·∑ M S m -K M ·M); where N represents the number of intersections in the preset area, S m is the combined congestion correlation degree of the sub-areas, M is the number of sub-areas in the preset area, K S is the preset total combined correlation degree proportionality coefficient of the sub-areas, K M is the preset proportionality coefficient of the number of sub-areas; based on the target optimization function and the constraint condition that the combined congestion correlation degree of the union is greater than or equal to the merging threshold, controlling each union to spread to other adjacent unions to update the union.

6. The traffic signal coordination control method according to claim 5, characterized in that the updating the original sub - areas according to the unions to obtain the target sub - areas includes: when the value of the target optimization function of the updated union is greater than the value of the target optimization function of the original sub - area, using the updated union as the target sub - area to replace the original sub - area; when the value of the target optimization function of the updated union is less than or equal to the value of the target optimization function of the original sub - area, using the original sub - area as the target sub - area.

7. The traffic signal coordination control method according to claim 4, characterized in that the congestion correlation degree between adjacent intersections is obtained by the following method: calculating the traffic characteristic similarity in the first direction and the traffic characteristic similarity in the second direction between adjacent intersections according to the obtained traffic parameters; Calculate the signal cycle similarity in the first direction and the signal cycle similarity in the second direction of the adjacent intersections according to the pre-set cycle pre-timing of each of the intersections. Calculate the one-way correlation degree in the first direction and the one-way correlation degree in the second direction of the adjacent intersections according to the traffic characteristic similarity and the signal cycle similarity. Adjust the one-way correlation degree in the first direction according to a pre-set first congestion influence coefficient, and adjust the one-way correlation degree in the second direction according to a pre-set second congestion influence coefficient; wherein, the first congestion influence coefficient and the second congestion influence coefficient are respectively positively correlated with the predicted value of the congestion condition of the adjacent intersections, the first congestion influence coefficient has a greater correlation with the downstream intersection in the first direction than with the upstream intersection in the first direction, and the second congestion influence coefficient has a greater correlation with the downstream intersection in the second direction than with the upstream intersection in the second direction. When the first congestion influence coefficient of the adjacent intersection is greater than the second congestion influence coefficient, use the adjusted one-way correlation degree in the first direction of the adjacent intersection as the congestion correlation degree of the adjacent intersection. When the first congestion influence coefficient of the adjacent intersection is less than the second congestion influence coefficient, use the adjusted one-way correlation degree in the second direction of the adjacent intersection as the congestion correlation degree of the adjacent intersection. When the first congestion influence coefficient of the adjacent intersection is equal to the second congestion influence coefficient, average the adjusted one-way correlation degrees in the first direction and the second direction to obtain the congestion correlation degree of the adjacent intersection.

8. The traffic signal coordination control method according to claim 4, characterized in that, the combined congestion correlation degree is obtained by the following method: For each of the adjacent intersections, adjust the one-way correlation degree in the first direction according to a pre-set first congestion influence coefficient, adjust the one-way correlation degree in the second direction according to a pre-set second congestion influence coefficient, and select the maximum one-way correlation degree from the adjusted one-way correlation degrees as the traffic characteristic correlation degree of the adjacent intersection; wherein, the first congestion influence coefficient and the second congestion influence coefficient are respectively positively correlated with the predicted value of the congestion condition of the adjacent intersections, the first congestion influence coefficient has a greater correlation with the downstream intersection in the first direction than with the upstream intersection in the first direction, and the second congestion influence coefficient has a greater correlation with the downstream intersection in the second direction than with the upstream intersection in the second direction. Select the minimum value from the obtained signal cycle similarities of all the adjacent intersections. Calculate the combined congestion correlation degree according to the traffic characteristic correlation degrees of all the adjacent intersections and the minimum signal cycle similarity.

9. A traffic signal coordination control device, characterized in that, comprising: A sub-region division module for dividing all intersections on the roads in a preset area to obtain a number of target sub-regions. The congestion index acquisition module is used to obtain the average congestion index of the target sub-region in the current cycle and the predicted congestion index of the next cycle; The intersection spacing acquisition module is used to obtain the average intersection spacing of the target sub-region; The coordinated control module is used to coordinately control the traffic signals of each intersection in the target sub-region according to the average congestion index, the predicted congestion index and the average intersection spacing of the target sub-region in the current cycle.

10. A traffic signal coordinated control device, characterized in that, it includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the traffic signal coordinated control method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, the computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the traffic signal coordinated control providing method according to any one of claims 1 to 8.

Images