A method and device for dynamically adjusting green wave band

Abstract

The present invention relates to the field of computer technology, and proposes a method and device for dynamically adjusting a green wave band, the method comprising: determining a periodic signal control parameter of a green wave band, and calculating the minimum and maximum green light durations in the direction of the green wave band based on the periodic signal control parameter; in response to reaching the minimum green light duration within the period, extending the green wave band by a preset time, and predicting the first and second parking delay durations caused by maintaining and switching green lights at all intersections in the direction of the green wave band; in response to the first and second parking delay durations meeting a first preset condition, returning to the step of extending the green wave band by a preset time until the maximum green light duration is reached within the period. This scheme can realize the adjustment of the green wave scheme within the period, adapt to the microscopic changes in traffic demand, cooperate with the periodic signal control parameters of each intersection, dynamically adjust the green light duration in the direction of the green wave band, and effectively avoid the waste of time and space resources at the intersection.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for dynamically adjusting a green wave band. Background Art

[0002] The green wave belt is on a designated traffic route. After the speed of the road section is specified, the signal controller is required to make corresponding adjustments to the starting time of the green lights at each intersection passed by the traffic flow according to the distance of the road section. By controlling the signal lights on the main line in linkage, it can ensure that the traffic flow encounters the "green light" when it reaches each intersection, so that vehicles can pass through this traffic route without stopping or with a reduced frequency of stopping.

[0003] The existing green wave control method generates a signal control plan for each traffic light based on offline historical traffic data and optimization models. It is not adaptable to real-time traffic data. The optimization model is established based on certain assumptions, but the actual traffic conditions are often more complicated. It is difficult to strictly follow these assumptions, which can easily lead to large deviations in the generated signal control plan. Once the signal control plan is generated, it needs to be executed according to a fixed cycle during operation, which makes it difficult to flexibly respond to the dynamic optimization and adjustment of the key control parameters of each traffic light.

[0004] Based on this, the existing green wave control methods need to be improved urgently. Summary of the invention

[0005] In view of the existing green wave control method, a periodic signal control plan for each traffic light is generated based on offline historical traffic data and an optimization model. However, the method has the problems of poor adaptability to real-time traffic data, large deviation of the actually generated signal control plan, and difficulty in flexibly and dynamically adjusting key control parameters due to the execution of the generated signal control plan at a fixed period. The present invention proposes a method and device for dynamically adjusting the green wave band.

[0006] Based on the above objectives, one aspect of the present invention provides a method for dynamically adjusting a green band, comprising: Determine the periodic signal control parameters of the green wave band, and calculate the minimum and maximum green light durations in the direction of the green wave band based on the periodic signal control parameters; In response to reaching the minimum green light duration within the cycle, the green wave band is extended by a preset time, and the first and second parking delay durations caused by maintaining and switching green lights at all intersections in the direction of the green wave band are predicted; In response to the first and second parking delay durations meeting the first preset condition, returning to the step of extending the green wave band by a preset time until the maximum green light duration is reached within the cycle.

[0007] In some embodiments, the first preset condition includes: The first parking delay duration is less than the second parking delay duration, or the value by which the first parking delay duration exceeds the second parking delay duration is less than or equal to a preset excess threshold.

[0008] In some embodiments, the method further comprises: In response to the first and second parking delay durations not meeting the first preset condition, the green lights of all intersections in the direction of the green wave band are switched to red lights.

[0009] In some embodiments, before the step of extending the green wave band for a preset time, the step includes: The phase offsets between all intersections on the green wave band are kept unchanged based on the periodic signal control parameters.

[0010] In some embodiments, the step of predicting the first and second parking delay durations caused by maintaining and switching green lights at all intersections in the green wave band direction includes: Starting from when the minimum green light duration is reached within the cycle, real-time traffic data of all intersections on the green wave band is obtained and input into the estimation model; The estimation model is used to predict the first and second parking delay durations caused by maintaining and switching green lights at all intersections after the green wave band is extended for a preset time.

[0011] In some embodiments, the step of calculating the minimum and maximum green light durations in the green wave band direction based on the green wave band comprises: Determine the green light timings corresponding to all intersections in the green wave band direction based on the periodic signal control parameters; The corresponding green light duration lower limits are calculated based on the green light timings corresponding to all the intersections and the corresponding pedestrian crossing times, and the maximum value of the green light duration lower limits corresponding to all the intersections is used as the minimum green light duration in the green wave band direction.

[0012] In some embodiments, the step of calculating the lower limits of the green light durations corresponding to all intersections in the green wave band direction based on the green light timings corresponding to all intersections and the pedestrian crossing times corresponding to all intersections in the green wave band direction includes: The product of the green light timing corresponding to all the intersections and the preset downward adjustment ratio is calculated, and the product is compared with the corresponding pedestrian crossing time, and the larger of the two is used as the lower limit of the green light time corresponding to all the intersections.

[0013] In some embodiments, the step of calculating the minimum and maximum green light durations in the direction of the green wave band based on the green wave band further includes: The corresponding green light duration upper limits are calculated based on the green light timings corresponding to all the intersections and the longest waiting times in the corresponding branch directions, and the minimum value of the green light duration upper limits corresponding to all the intersections is used as the maximum green light duration in the green wave band direction.

[0014] In some embodiments, the step of calculating the upper limits of the green light durations corresponding to all intersections based on the green light timings corresponding to all intersections and the maximum waiting times in the branch directions corresponding to all intersections includes: The product of the green light timing corresponding to all the intersections and the preset upward adjustment ratio is calculated, and the product is compared with the longest waiting time in the corresponding branch direction, and the smaller of the two is used as the upper limit of the green light duration corresponding to all the intersections.

[0015] Another aspect of an embodiment of the present invention provides an electronic device, comprising at least one processor; and a memory, wherein the memory stores computer instructions that can be executed on the processor, and when the instructions are executed by the processor, the steps of the above-mentioned method for dynamic adjustment of the green wave band are implemented.

[0016] The present invention has at least the following beneficial effects: A method for dynamically adjusting a green wave band of the present invention, based on determining a periodic signal control parameter, calculates the maximum green light duration and the minimum green light duration in the green wave band direction according to the periodic signal control parameter, and extends the green light in the green wave band direction by a preset time as a whole starting from the minimum green light duration in the period, predicts that all intersections in the green wave band direction will keep green lights and switch green lights (switching green lights to other signal lights) in the green wave band direction respectively corresponding to the first parking delay duration and the second parking delay duration, if both meet the first preset condition, then returns to the step of extending the green light in the green wave band direction by a preset time as a whole, and continues to extend the green light in the green wave band direction by a preset time as a whole, until the maximum green light duration is reached in the period. In the period, the green light duration in the green wave band direction is extended, and the maximum green light duration determined in the green wave band direction can be reached, and it can be coordinated with the periodic signal control parameter to dynamically adjust the green light duration in the green wave band direction, better adapt to the microscopic changes in real-time traffic conditions, and effectively avoid the waste of time and space resources at intersections.

[0017] In addition, the electronic device of the present invention also has at least the above beneficial effects, which will not be described in detail. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A flow chart of a method for dynamically adjusting a green band provided by a first embodiment of the present invention; Figure 2 A schematic diagram of variables for period-level green band optimization provided by another embodiment of the present invention; Figure 3 A schematic diagram of vehicle positions at an intersection provided for a first embodiment of the present invention; Figure 4 Another flow chart of a method for dynamically adjusting a green band provided by another embodiment of the present invention; Figure 5 A schematic structural diagram of an electronic device provided in accordance with another embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following describes embodiments of the present invention. However, it should be understood that the disclosed embodiments are merely examples and other embodiments can take various alternative forms.

[0021] Furthermore, it should be noted that the terms "includes," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that includes a series of elements includes not only those elements, but may also include elements not explicitly listed or inherent to these processes, methods, articles, or apparatuses.

[0022] One or more embodiments of the present application will be described below with reference to the accompanying drawings.

[0023] Based on the above objectives, a first aspect of an embodiment of the present invention provides an embodiment of a method for dynamically adjusting a green band. Figure 1 FIG. 1 is a flow chart of a method for dynamically adjusting a green band provided by an embodiment of the present invention. Figure 1 As shown, including: S1. Determine the periodic signal control parameters of the green wave band, and calculate the minimum and maximum green light durations in the direction of the green wave band based on the periodic signal control parameters; Specifically, the periodic signal control parameters refer to the signal control parameters of all intersections in the green wave direction, including the signal period, green light duration, and green light phase offset corresponding to all intersections. The periodic signal control parameters are obtained by solving the optimization model established according to the optimization objectives and constraints of the green wave.

[0024] Specifically, the minimum and maximum green light durations in the green wave band direction refer to the maximum value of the green light duration and the minimum value of the green light duration in the entire green wave band direction. In other words, on the basis that the periodic signal control parameters have been determined, no matter how the green light duration in the green wave band direction is extended or shortened, it must be within the range of the minimum and maximum green light durations. The calculation process of the maximum green light duration and the minimum green light duration is as follows: According to the periodic signal control parameters, the green light timing, green light phase offset and signal cycle corresponding to all intersections in the green wave band direction can be obtained, and the green light phase offset between all intersections remains unchanged. Based on the green light timing corresponding to all intersections in the green wave band direction, the corresponding green light duration upper limit (based on the periodic signal control parameters, the upper limit of the green light duration of a certain intersection in the green wave band direction) and the green light duration lower limit (based on the periodic signal control parameters, the lower limit of the green light duration of a certain intersection in the green wave band direction) are calculated. Based on the upper limits of the green light duration corresponding to all intersections in the green wave band direction, the maximum green light duration in the green wave band direction is determined. Specifically, the minimum value of the upper limits of the green light duration corresponding to all intersections in the green wave band direction is used as the maximum green light duration in the green wave band direction; based on the lower limits of the green light duration corresponding to all intersections in the green wave band direction, the minimum green light duration in the green wave band direction is determined. Specifically, the minimum value of the lower limits of the green light duration corresponding to all intersections in the green wave band direction is used as the minimum green light duration in the green wave band direction.

[0025] Among them, for a certain intersection, determining the upper and lower limits of the green light duration in the green wave band direction involves a more specific calculation process, as follows: based on the product of the green light timing corresponding to all intersections in the green wave band direction and the preset downward adjustment ratio, determine the corresponding green light duration downward adjustment value; based on the larger of the corresponding green light duration downward adjustment value and the corresponding pedestrian crossing time, determine the corresponding green light duration lower limit. Based on the product of the green light timing corresponding to all intersections in the green wave band direction and the preset upward adjustment ratio, determine the corresponding green light duration upward adjustment value; based on the smaller of the corresponding green light duration upward adjustment value and the longest waiting time in the corresponding branch direction, determine the corresponding green light duration upper limit.

[0026] In a specific example, a specific process of determining the periodic signal control parameter is also given. Figure 2 As shown, Figure 2The diagram shows a variable diagram of green band periodic optimization provided by another embodiment of the present invention. The optimization goal of the green band is to maximize the bandwidth of the green band, and the constraints include green band bandwidth balance, green light phase offsets of all intersections in the direction of the green band not exceeding an integer period, and green light duration of all intersections not less than the minimum green light duration in the direction of the green band, and the queued vehicles can be cleared within the target time. Figure 3 As shown in the figure, the green wave formed on the main road generally involves multiple continuous intersections. For example, intersection i and intersection i+1 are continuous intersections. The direction from intersection i to intersection i+1 is determined as the downward direction of the green wave, and vice versa. Obtain the traffic data of all intersections in the direction of the green wave within a period of time, such as obtaining the traffic data of all intersections in the time period [t, t+1], including: the downward flow V corresponding to all intersections i , the traffic in the upstream direction ; Saturation flow rate in the downstream direction , the saturation flow rate in the upward direction ; Saturated headway time hi, the corresponding calculation formula is Si=1 / hi; Downlink green wave bandwidth , Green wave bandwidth in the uplink direction The unit of green wave bandwidth is cycle; the uplink and downlink ratio corresponding to green wave bandwidth is ; Maximum constraint C corresponding to the cycle time max and the minimum constraint C min ; Downstream intervention variables corresponding to all intersections and upward intervening variables , whose unit is also cycle; downlink travel time and travel time on the uplink section ; Green light duration in the direction of the green wave band , which is the solution variable; downlink queue clearing time and uplink queue clearing time Combined with the optimization objectives and constraints of the green wave belt, a mixed integer optimization model is constructed, as shown in the following formula 1-10: (Formula 1) (Formula 2) (Formula 3) (Formula 4) (Formula 5) (Formula 6) (Formula 7) (Formula 8) (Formula 9) (Formula 10) Among them, i represents the i-th intersection in the direction of the green wave belt, m i Indicates integer multiples of period; represents the phase difference of intersection i, which is the solution variable; z represents the signal frequency, which is the inverse of the period and is also the solution variable. By solving the solution variables in the above formulas 1-10, the signal period C=1 / z of the periodic signal control parameter of the green wave band is obtained, and the green light timing g corresponding to all intersections in the green wave band direction is i =Cr i , the green light phase offsets corresponding to all intersections in the green wave direction It can be understood that the periodic signal control parameters of the green band at least include the parameters calculated above.

[0027] Generate the periodic signal control parameters of the green wave band according to the signal cycle C (for example, every 15 minutes) and send them to the traffic lights at all intersections in the direction of the green wave band. Based on the periodic signal control parameters, all intersections in the direction of the green wave band can obtain the corresponding green light timing. The green light timing obtained at different intersections will be different. For example, the green light timing obtained by intersection i in the direction of the green wave band is 30s, and the green light timing obtained by intersection i+1 in the direction of the green wave band is 40s. The periodic signal control parameters provide periodic control of signals for all intersections in the direction of the green wave band, meet the macro changes in traffic demand, and provide a reference benchmark for extending the green light duration in the direction of the green wave band, which is conducive to the subsequent extension of the green light duration within the green wave band cycle based on the periodic signal control parameters.

[0028] S2, in response to reaching the minimum green light duration within the cycle, extending the green wave band by a preset time, and predicting the first and second parking delay durations caused by maintaining and switching green lights at all intersections in the direction of the green wave band; Specifically, the preset time is determined according to the parking delay duration caused by switching different signal states at all intersections in the green wave band direction. In other words, after all intersections in the green wave band direction are extended by the preset time, the corresponding green light duration needs to be within the range of the minimum and maximum green light durations, and does not exceed the maximum green light duration. Based on actual experience, the preset time is generally 3s. It is understandable that the preset time for each overall extension in the green wave band direction can be changed, such as the preset time for the next extension is a certain proportion of the preset time for the current extension, or the preset time for each extension is a multiple of a fixed value, or the preset time for each extension remains unchanged, etc.

[0029] For a specific example, see Figure 4 , please refer to Figure 1-4 , Figure 4 Another flow chart of the method for dynamic adjustment of the green wave band provided by another embodiment of the present invention, based on the periodic signal control parameters, the signals of all intersections in the direction of the green wave band are periodically changed, and the phase offset between each intersection is kept unchanged. In one cycle, the green light duration of all intersections in the direction of the green wave band is monitored. When a green light duration reaches the minimum green light duration, at this time, based on the preset time determined above, the green lights of all intersections in the direction of the green wave band are extended by the preset time as a whole (the green light duration of the green wave band is extended within the cycle), and it is predicted that the green lights of all intersections will continue to remain green or switch to green to generate an overall parking delay duration in the direction of the green wave band, that is, the first parking delay duration generated by maintaining the green light or the second parking delay duration generated by switching the green light (for example, switching to a red light). If the relationship between the first parking delay time and the second parking delay time meets the first preset condition, the green light is maintained to continue to extend the preset time, and the above prediction is repeated to continue to extend the preset time and then maintain the green light or switch to the red light to generate the parking delay time until the maximum green light duration is reached; otherwise, the green light is switched, such as switching the green light to a red light, indicating that the extension of the green light duration within the cycle has ended. In this way, the green light duration in the direction of the green wave band is dynamically extended within the cycle according to the actual traffic conditions, and the green light duration in the direction of the green wave band is extended to the greatest extent, meeting the micro changes in traffic demand. Combining the scheme of dynamically extending the green light duration of the green wave band within the cycle with the periodic signal control parameters of the green wave band can realize the dynamic adjustment of the green light duration of the green wave band, meeting the macro and micro changes in traffic demand.

[0030] In another specific example, the specific process of parking delay duration prediction is also given, as follows: the parking delay duration is predicted by a pre-trained prediction model. Based on the periodic signal control parameters, the phase offset between all intersections is kept unchanged, and the minimum green light duration g is achieved within the period. min Start timing, record it as time t, and extend the green lights of all intersections in the direction of the green wave band by the preset time t step , extend the preset time t step The corresponding time is t+t step , starting from time t, obtain [t, t+t step ] time period, including but not limited to the vehicle speed, the lane in which it is located and the number and length of vehicles in the queue, the distance between the vehicle and the stop line ahead, the remaining green light duration and red light duration of the downstream intersection in the direction of the vehicle, etc. step] The real-time traffic data of all intersections in the green wave direction during the time period are input into the prediction model, and the prediction model is used to predict the extension of t step After that, all intersections (on the basis of keeping the phase difference shift unchanged) correspond to the first stop delay time delay1 generated by keeping the green light in the green wave band direction, and the second stop delay time delay2 generated by switching the green light (for example, switching to red light) in the green wave band direction. If delay1 and delay2 do not meet the first preset condition, then extend t step Then, all intersections in the green wave band direction will switch to green lights (switch the green lights, for example, to red lights), that is, continue to extend the green light duration within the exit cycle; if delay1 and delay2 meet the first preset condition, then extend t step Then keep all intersections in the green wave direction green and continue to extend the preset time t step , get [t, t+2t step The real-time traffic data of all intersections in the green wave direction during the time period are input into the prediction model, and the prediction model is used to predict the extension of 2t step After that, all intersections (on the basis of keeping the phase difference shift unchanged) keep the first stop delay time delay11 caused by the green light, and the second stop delay time delay21 caused by switching the green light (for example, switching to a red light). According to the above judgment process, continue to judge whether delay11 and delay21 meet the first preset condition, so as to further judge whether to extend the 2t step After that, all intersections will keep green lights (then continue to extend the preset time t step Until the maximum green light duration g is reached within the cycle max ) or switch to extend the green light duration during the red light exit cycle.

[0031] The estimation model is used to predict the first and second parking delays caused by keeping or switching the green light at all intersections in the green wave direction after the preset time is extended. It can accurately predict the impact of keeping or switching the green light on the green wave belt as a whole after the preset time is extended, so as to make an accurate judgment on whether to keep the green wave or switch the green light to exit. This cycle is repeated to extend the green light duration in the green wave direction, and the maximum green light duration can reach g max , making full use of the space-time resources of all intersections and dynamically adjusting the green wave belt in the main line direction.

[0032] S3. In response to the first and second parking delay durations meeting the first preset condition, return to the step of extending the green wave band by a preset time until the maximum green light duration is reached within the cycle.

[0033] Specifically, the first preset condition means that the first parking delay duration is less than the second parking delay duration, or the value by which the first parking delay duration exceeds the second parking delay duration is less than or equal to a preset excess threshold. Herein, the preset excess threshold is determined by the first parking delay duration and a preset ratio value. Further specifically, the preset excess threshold is the product value of the first parking delay duration and the preset ratio value. The preset ratio value, such as 0.1, 0.2, etc., is determined according to the actual situation.

[0034] In a specific example, please continue to refer to Figure 1-4 , based on the optimization objective of the green wave band (such as maximizing the bandwidth of the green wave band) and the constraint conditions (such as the balance of the green wave bandwidth, the green light phase offset of all intersections in the green wave band direction not exceeding an integer cycle, the green light duration of all intersections not less than the minimum green light duration in the green wave band direction, and the queuing vehicles can be cleared within the target time), a mixed-integer optimization model is constructed, and its solution is obtained to get the periodic signal control parameters of the green wave band, including the signal cycle, green light duration, and green light phase offset corresponding to each intersection respectively. Among them, the construction and specific solution process of the mixed-integer optimization model are as described above and will not be elaborated further.

[0035] Based on the determined periodic signal control parameters, determine the maximum green light duration g max and the minimum green light duration g min , and its specific determination process is as described above and will not be elaborated further.

[0036] (1) During the cycle, monitor the green light duration of all intersections in the green wave band direction. When one green light duration reaches the minimum green light duration g min , record it as time t, and start timing from this moment. Extend the green lights of all intersections in the green wave band direction by a preset time t step , and predict the first parking delay duration delay1 generated by keeping the green lights of all intersections in the green wave band direction after extending for t step (while keeping the phase difference offset unchanged), and the second parking delay duration delay2 generated by switching to red lights in the green wave band direction. Among them, the specific process of predicting the parking delay duration through the prediction model is as described above and will not be elaborated further.

[0037] (2) If delay1 < delay2, it means that the delay generated by keeping the green lights of all intersections in the green wave band direction after extending for t step is smaller, then continue to keep the green lights on after extending for t step ; If delay1 > delay2, calculate (delay1 - delay2) / delay1 and compare it with the preset ratio value opt-thd (such as 0.1). If (delay1 - delay2) / delay1 is greater than opt-thd, it means that the delay caused by switching to red light in the green wave band direction can be reduced by at least opt-thd. Then, on the basis of keeping the phase offset between all intersections unchanged, extend all intersections by t step Then switch to red light and exit to continue extending by t step , and enter the next cycle. Otherwise, extend by t step Then continue to keep the green light on. Among them, delay1 * opt-thd represents the preset excess threshold. In other words, if delay1 - delay2 < delay1 * opt-thd, extend all intersections on the green wave band by t step Then continue to keep the green light on. Otherwise, extend all intersections by t step Then switch to red light and exit to continue extending by t step .

[0038] Repeat the above steps (1)-(2) until the green light duration in the green wave band direction reaches the maximum green light duration g within the cycle max End.

[0039] Dynamically adjust the green wave band within the cycle, which maximally extends the green light duration in the green wave band direction and can reach the maximum green light duration g determined in the green wave band direction at most max , adapts to the microscopic changes in traffic demand, and cooperates with the periodic signal control parameters to effectively avoid the problem of waste of intersection space-time resources.

[0040] According to several embodiments of the present invention, the method for dynamically adjusting the green wave band further includes: in response to the first and second stop delay durations not meeting the first preset condition, switching the green lights of all intersections in the green wave band direction to red lights.

[0041] In a specific example, please continue to refer to Figure 1-4 , construct a mixed integer optimization model based on the optimization objectives and constraints of the green wave band, solve it to obtain the periodic signal control parameters of the green wave band, including the signal cycle, green light duration, and green light phase offset corresponding to each intersection, etc. Based on the determined periodic signal control parameters, calculate the maximum green light duration g max and the minimum green light duration g min , and the specific calculation process is as described above and will not be elaborated here.

[0042] During the cycle, monitor the green light duration of all intersections in the green wave direction. When a green light duration reaches the minimum green light duration g min , recorded as time t, the green lights of all intersections in the green wave band direction are extended by the preset time t step , predicting the extension of t step Afterwards, all intersections (on the basis of keeping the phase difference offset unchanged) maintain the first stop delay time delay1 caused by the green light in the green wave band direction, and switch to the second stop delay time delay2 caused by the red light in the green wave band direction.

[0043] If delay1>delay2, calculate (delay1-delay2) / delay1 and compare it with the preset ratio value opt-thd (for example, 0.1). If (delay1-delay2) / delay1>opt-thd, that is, delay1-delay2>delay1*opt-thd, it means that the delay caused by switching to red light in the green waveband direction can at least reduce the delay above opt-thd. Then, on the basis of keeping the phase offset between all intersections unchanged, extend all intersections by t step After that, the light turns red and you exit to extend the time step , enter the next cycle.

[0044] Quantify the extension of t step After that, all intersections maintain green lights or switch to red lights, and the overall impact on the parking delay duration in the direction of the green wave belt is used to determine whether to extend the green light duration in the direction of the green wave belt within the cycle, so as to maximize the use of the space-time resources of all intersections on the green wave belt and reduce the waste of space-time resources.

[0045] According to some embodiments of the present invention, before the step of extending the green wave band for a preset time, the method includes: keeping the phase offsets between all intersections on the green wave band unchanged based on the periodic signal control parameters.

[0046] Specifically, based on the optimization objectives of the green wave band (such as maximizing the bandwidth of the green wave band) and constraints (such as green wave bandwidth balance, the green light phase offset of all intersections in the direction of the green wave band does not exceed an integer period, the green light duration of all intersections is not less than the minimum green light duration in the direction of the green wave band, and the queued vehicles can be cleared within the target time), a mixed integer optimization model is constructed and solved to obtain the periodic signal control parameters of the green wave band, including the signal cycle, green light duration and green light phase offset corresponding to all intersections. After determining the periodic signal control parameters, the phase offset between all intersections is kept unchanged. Based on this, all intersections are extended by the corresponding preset time t step, which ensures that the green light duration in the direction of the green wave band is extended within the cycle without changing the phase relationship between all intersections. That is, the signal control parameters of all intersections will not be changed at the macro level, but will be adjusted according to the actual traffic conditions at the micro level, which can adapt to the dynamic changes of traffic flow.

[0047] According to some embodiments of the present invention, the step of predicting the first and second stop delay durations caused by maintaining and switching green lights at all intersections in the direction of the green wave band includes: starting from reaching the minimum green light duration within the cycle, obtaining real-time traffic data of all intersections on the green wave band and inputting it into the estimation model; predicting through the estimation model the first and second stop delay durations caused by maintaining and switching green lights at all intersections after extending the green wave band for a preset time.

[0048] Specifically, the parking delay duration is predicted by a pre-trained prediction model. The prediction function is obtained by training historical traffic data, and the training process is as follows: the speed of the target vehicle at the previous moment, the lane it is in and the number of vehicles in the queue and the length of the queue, the distance between the target vehicle and the stop line ahead, and the remaining green light duration and red light duration of the downstream intersection in the direction of the target vehicle are used as historical traffic data. The prediction function is , represents the parking delay time of the target vehicle j passing the downstream intersection i of the road section at the previous time t, represents the lane where the target vehicle j was located at the last moment t, represents the distance between the target vehicle j and the stop line ahead at the last moment t, represents the speed of target vehicle j at the last moment t, represents the number of queued vehicles in the lane where the target vehicle j is located at the previous moment t, represents the queue length of the lane where the target vehicle j is located at the last moment t, Indicates the remaining green light duration of the downstream intersection in the direction of target vehicle j at the previous time t, Indicates the duration of the red light at the downstream intersection in the direction of travel of the target vehicle. Input the above parameters into the estimation function to calculate the parking delay duration corresponding to the target vehicle j passing through its downstream intersection i at the current time t+1. Input historical traffic data into the estimation function, calculate the parking delay duration corresponding to the target vehicle passing through its downstream intersection at the current time through the estimation function, and perform multiple rounds of training on the estimation function through an integrated learning algorithm (such as xgboost), and use the estimation function determined by the final round of training as the estimation model. The estimation model obtained by pre-training is used to predict the parking delay duration caused by maintaining a green light or switching to a red light after extending the preset time, so that the prediction result is more accurate and more in line with the dynamic changes of actual traffic data.

[0049] According to some embodiments of the present invention, the step of calculating the minimum and maximum green light durations in the green wave band direction based thereon includes: determining the green light timings corresponding to all intersections in the green wave band direction based on the periodic signal control parameters; calculating the corresponding lower limits of the green light durations based on the green light timings corresponding to all intersections and the corresponding pedestrian crossing durations, and taking the maximum value of the lower limits of the green light durations corresponding to all intersections as the minimum green light duration in the green wave band direction. The step of calculating the corresponding lower limits of the green light durations based on the green light timings corresponding to all intersections in the green wave band direction and the corresponding pedestrian crossing durations includes: calculating the product of the green light timings corresponding to all intersections and the preset downward adjustment ratio, comparing it with the corresponding pedestrian crossing duration, and taking the larger of the two as the lower limits of the green light durations corresponding to all intersections.

[0050] For details, please continue to refer to Figure 1-4 According to the periodic signal control parameters of the determined green wave band, the signal period, green light duration, and green light phase offset corresponding to all intersections can be obtained. In the green wave band direction, first determine the lower limit of the green light duration corresponding to all intersections g min,i , which is based on the corresponding green light timing g i and the corresponding pedestrian crossing time Specifically, calculate the green light timing g corresponding to all intersections i The product of the preset down-adjustment ratio flr (generally 0.7 according to experience) determines the corresponding down-adjustment value of the green light duration. , lower the green light duration corresponding to all intersections and the corresponding pedestrian crossing duration Compare them and take the larger one as the lower limit of the green light duration g min,i , Then, the lower limit of the green light duration corresponding to all intersections is g. min,i The maximum value in the green wave band direction is taken as the minimum green light duration g min , .

[0051] According to some embodiments of the present invention, the step of calculating the minimum and maximum green light durations in the direction of the green wave band based on the step further includes: calculating the upper limits of the corresponding green light durations based on the green light timings corresponding to all intersections and the longest waiting time in the corresponding branch directions, and taking the minimum value of the upper limits of the green light durations corresponding to all intersections as the maximum green light duration in the green wave band direction. The step of calculating the upper limits of the corresponding green light durations based on the green light timings corresponding to all intersections and the maximum waiting time in the corresponding branch directions includes: calculating the product of the green light timings corresponding to all intersections and the preset upward adjustment ratio, comparing it with the longest waiting time in the corresponding branch direction, and taking the smaller of the two as the upper limits of the green light durations corresponding to all intersections.

[0052] For details, please continue to refer to Figure 1-4 According to the periodic signal control parameters of the determined green wave band, the signal period, green light duration, and green light phase offset corresponding to all intersections can be obtained. In the green wave band direction, first determine the upper limit of the green light duration corresponding to all intersections g max,i , which is based on the corresponding green light timing g i And the longest waiting time in the corresponding branch direction (generally 120s according to experience) t_wait i Specifically, calculate the green light timing g corresponding to all intersections i The product of the preset upward adjustment ratio fur (generally 1.3 according to experience) determines the corresponding green light duration increase value. , adjust the green light duration corresponding to all intersections to the maximum waiting time in the corresponding branch direction (which is generally 120s according to experience) t_wait i Compare the two and take the smaller one as the upper limit of the green light duration. , . Then the upper limit of green light duration corresponding to all intersections is calculated. The minimum value in the green wave direction is taken as the maximum green light duration , .

[0053] In addition, the present invention also provides a specific process for preprocessing the traffic data of each intersection, please continue to refer to Figure 4 , historical traffic data or real-time traffic data can be preprocessed to obtain data that meets the requirements of subsequent calculations. The details are as follows: Obtain high-precision map data, roadside perception vehicle data, and signal light control data for traffic arterial sections. It can be understood that the historical or real-time traffic data collected at each intersection is collected from at least the above three types of data. Process the high-precision map data to obtain lane data with turn signs, the topological relationship of upstream and downstream intersections on traffic arterial sections, and the distance between consecutive intersections on traffic arterial sections; collect sub-second roadside perception vehicle data from roadside perception equipment, for example, the corresponding collection frequency is 10hz, including vehicle position, shape contour, instantaneous speed, heading angle and other data; obtain the second-level signal control data of traffic lights at each intersection, and the corresponding collection frequency is 1hz, which includes data such as the signal light status control of each intersection.

[0054] Furthermore, the roadside perception vehicle data in the three types of preprocessed data is associated with the lane information in the high-precision map data to determine the relative position relationship between the vehicle and the lane. The specific process of counting the parking delay time at the intersection corresponding to the vehicle passing through and the length of the vehicle queue at each intersection is as follows: The vehicle's parking status is confirmed based on the speed judgment conditions corresponding to parking. Based on the sub-second historical perception of vehicle trajectory data, the instantaneous speed is defined as a parking state when it is less than the speed threshold Vstop. According to experience, Vstop is generally 0.1m / s. When the cumulative parking time of the vehicle in the import lane of a certain intersection exceeds the time threshold Tstop, the vehicle is considered to have stopped at the intersection. According to experience, Tstop is generally 3s. After that, the cumulative parking time corresponding to the vehicle passing through the intersection is further counted as the parking delay duration of the vehicle passing through the intersection.

[0055] Based on the relative position relationship, the corresponding queue length when the vehicle stops is confirmed. According to the sub-second historical perception vehicle trajectory data, if it is judged that the instantaneous speed on a lane at a certain moment in the intersection is less than Vstop, the vehicles with a distance of no more than 3m from the end of the stop line are defined as vehicles queuing at the intersection, and the distance from the rear of the queued vehicle to the stop line is used as the queue length. In this way, it can be determined whether the vehicle at the intersection is in a parked state. If it is in a parked state, the parking delay time of the vehicle passing through and the key data such as the length of the vehicle queue at the intersection can be further calculated. Based on this, data preparation is carried out for calculating periodic signal control parameters and the process of dynamically adjusting the green wave band within the period.

[0056] According to another aspect of the present invention, an electronic device is provided. The electronic device may be a server. Figure 5As shown. The electronic device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the method for dynamic adjustment of the green wave band described above is implemented.

[0057] Finally, it should be noted that a person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program of the method for setting system parameters can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium of the program can be a disk, an optical disk, a read-only storage memory (ROM) or a random access memory (RAM), etc. The above-mentioned computer program embodiment can achieve the same or similar effect as any of the above-mentioned method embodiments corresponding thereto.

[0058] In addition, the method disclosed in the embodiment of the present invention can also be implemented as a computer program executed by a processor, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the above functions defined in the method disclosed in the embodiment of the present invention are performed.

[0059] In addition, the above method steps and system units may also be implemented using a controller and a computer-readable storage medium for storing a computer program that enables the controller to implement the above steps or unit functions.

[0060] It will also be appreciated by those skilled in the art that various exemplary logic blocks, modules, circuits and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, a general description has been given to the functions of various schematic components, blocks, modules, circuits and steps. Whether this function is implemented as software or hardware depends on specific applications and the design constraints imposed on the entire system. Those skilled in the art can implement the function in various ways for each specific application, but this implementation decision should not be interpreted as causing a departure from the disclosed scope of the embodiments of the present invention.

[0061] In one or more exemplary designs, the functions may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored on or transmitted through a computer-readable medium as one or more instructions or codes. Computer-readable media include computer storage media and communication media, which include any media that facilitate the transfer of computer programs from one location to another. The storage medium may be any available medium that can be accessed by a general or special-purpose computer. As an example and not by way of limitation, the computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, or any other medium that can be used to carry or store the required program code in the form of instructions or data structures and can be accessed by a general or special-purpose computer or a general or special-purpose processor. In addition, any connection may be appropriately referred to as a computer-readable medium. For example, if a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves are used to send software from a website, server, or other remote source, the above-mentioned coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are all included in the definition of the medium. As used herein, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, Blu-ray disc, etc., where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0062] The above are exemplary embodiments disclosed in the present invention, but it should be noted that various changes and modifications may be made without departing from the scope disclosed in the embodiments of the present invention as defined in the claims. The functions, steps and / or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any particular order. In addition, although the elements disclosed in the embodiments of the present invention may be described or required in individual form, they may also be understood as multiple unless explicitly limited to the singular.

[0063] It should be understood that, as used herein, the singular forms "a", "an" are intended to include the plural forms as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations including one or more of the associated listed items.

[0064] The serial numbers of the embodiments disclosed in the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0065] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0066] A person skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the above embodiments of the present invention, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims

1. A method for dynamically adjusting a green band, characterized in that: include: Determine the periodic signal control parameters of the green wave band, and calculate the minimum and maximum green light durations in the direction of the green wave band based on the periodic signal control parameters; In response to reaching the minimum green light duration within the cycle, the green wave band is extended by a preset time, and the first and second parking delay durations caused by maintaining and switching green lights at all intersections in the direction of the green wave band are predicted; In response to the first and second parking delay durations meeting the first preset condition, returning to the step of extending the green wave band by a preset time until the maximum green light duration is reached within the cycle.

2. The method for dynamic adjustment of green band according to claim 1, characterized in that: The first preset condition includes: The first parking delay duration is less than the second parking delay duration, or the value by which the first parking delay duration exceeds the second parking delay duration is less than or equal to a preset excess threshold.

3. The method for dynamic adjustment of green band according to claim 1, characterized in that: The method further comprises: In response to the first and second parking delay durations not meeting the first preset condition, the green lights of all intersections in the direction of the green wave band are switched to red lights.

4. The method for dynamic adjustment of green band according to claim 1, characterized in that: Before the step of extending the green wave band for a preset time, the method includes: The phase offsets between all intersections on the green wave band are kept unchanged based on the periodic signal control parameters.

5. The method for dynamic adjustment of green band according to claim 1, characterized in that: The step of predicting the first and second stop delay durations caused by maintaining and switching green lights at all intersections in the green wave band direction includes: Starting from when the minimum green light duration is reached within the cycle, real-time traffic data of all intersections on the green wave band is obtained and input into the estimation model; The estimation model is used to predict the first and second parking delay durations caused by maintaining and switching green lights at all intersections after the green wave band is extended for a preset time.

6. The method for dynamic adjustment of green band according to claim 1, characterized in that: The step of calculating the minimum and maximum green light durations in the green wave band direction based on the green wave band comprises: Determine the green light timings corresponding to all intersections in the green wave band direction based on the periodic signal control parameters; The corresponding green light duration lower limits are calculated based on the green light timings corresponding to all the intersections and the corresponding pedestrian crossing times, and the maximum value of the green light duration lower limits corresponding to all the intersections is used as the minimum green light duration in the green wave band direction.

7. The method for dynamic adjustment of green band according to claim 6, characterized in that: The step of calculating the lower limits of the green light durations respectively corresponding to all intersections in the green wave band direction based on the green light timings respectively corresponding to all intersections and the pedestrian crossing durations respectively corresponding to all intersections in the green wave band direction comprises: The product of the green light timing corresponding to all the intersections and the preset downward adjustment ratio is calculated, and the product is compared with the corresponding pedestrian crossing time, and the larger of the two is used as the lower limit of the green light time corresponding to all the intersections.

8. The method for dynamic adjustment of green band according to claim 6, characterized in that: The step of calculating the minimum and maximum green light durations in the direction of the green wave band based on the green wave band also includes: The corresponding green light duration upper limits are calculated based on the green light timings corresponding to all the intersections and the longest waiting times in the corresponding branch directions, and the minimum value of the green light duration upper limits corresponding to all the intersections is used as the maximum green light duration in the green wave band direction.

9. The method for dynamic adjustment of green band according to claim 8, characterized in that: The step of calculating the upper limits of the green light durations respectively corresponding to all the intersections based on the green light timings respectively corresponding to all the intersections and the maximum waiting times respectively corresponding to the branch road directions comprises: The product of the green light timing corresponding to all the intersections and the preset upward adjustment ratio is calculated, and the product is compared with the longest waiting time in the corresponding branch direction, and the smaller of the two is used as the upper limit of the green light duration corresponding to all the intersections.

10. An electronic device, characterized in that: include: at least one processor; and a memory storing computer instructions executable on the processor, wherein the instructions, when executed by the processor, implement the steps of the method for dynamic adjustment of the green band as described in any one of claims 1 to 9.

Images