Traffic signal lamp control method based on multi-source heterogeneous data

Abstract

The invention provides a traffic signal lamp control method based on multi-source heterogeneous data, which can be applied to the technical field of traffic signal control. The traffic signal lamp control method based on the multi-source heterogeneous data comprises the following steps: acquiring historical traffic information of a plurality of intersections in a historical period; inputting the historical traffic information into a prediction model to obtain respective predicted traffic parameters of a plurality of traffic flow phases of the current intersection in a future period and signal phase information of a plurality of traffic lights; updating the duration of a green light signal in the traffic control model based on the predicted traffic parameter and the signal phase information until the queue length in the future period reaches a target value, and obtaining the target green light duration of the green light signal and the target period duration of the future period, the traffic control model is constructed based on the queue length and congestion density of a plurality of traffic lights of a plurality of traffic flow phases in a future period; and controlling various traffic lights according to the target green light duration and the target period duration.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traffic signal control, and more particularly to a traffic signal lamp control method based on multi-source heterogeneous data. BACKGROUND

[0002] Multi-source heterogeneous traffic data of intersections collected through various sensors has been widely applied to traffic signal control. Multi-source heterogeneous traffic data increases the diversity of traffic information of intersections, which can analyze the traffic conditions of the intersections from multiple aspects, and is beneficial to the control of traffic signal lamps.

[0003] However, the traffic operation of the intersection is also affected by the external environment (such as the conflict of vehicle flow of other intersections), so the control accuracy of the traffic signal lamp is low, which easily causes traffic congestion and safety accidents, and reduces the traffic efficiency of the intersection. SUMMARY

[0004] In view of the above problems, the present application provides a traffic signal lamp control method based on multi-source heterogeneous data.

[0005] According to a first aspect of the present application, a traffic signal lamp control method based on multi-source heterogeneous data is provided, comprising: obtaining historical traffic information of a plurality of intersections in a historical period, wherein the plurality of intersections include a current intersection and an upstream intersection of the current intersection; inputting the historical traffic information into a prediction model to obtain predicted traffic parameters of a plurality of vehicle flow phases of the current intersection in a future period and signal phase information of a plurality of traffic signal lamps, wherein the plurality of vehicle flow phases represent directions in which vehicles can travel in the current intersection; updating a length of a green signal in a traffic control model based on the predicted traffic parameters and the signal phase information until a queue length in the future period reaches a target value, to obtain a target green signal length of the green signal and a target cycle length of the future period, wherein the plurality of traffic signal lamps include the green signal, the queue length represents a number of vehicles waiting to pass through the current intersection, and the traffic control model is constructed based on queue lengths and congestion densities of the plurality of traffic signal lamps in the future period for the plurality of vehicle flow phases; and controlling the plurality of traffic signal lamps according to the target green signal length and the target cycle length.

[0006] According to an embodiment of the present application, the predicted traffic parameters include a predicted arrival rate, a predicted saturation release rate, and a predicted congestion density, the predicted arrival rate represents a number of vehicles traveling to the current intersection within a preset time, and the signal phase information includes a signal phase sequence and a phase loss length.

[0007] According to an embodiment of the present application, the history period comprises a current period, the future period comprises a next period of the current period, and the traffic control model is constructed based on the following manners: determining a shock wave speed based on a predicted arrival rate, a predicted saturated release rate and a predicted jam density of the next period; constructing a sub-model of a queue length of each of the multiple traffic signals based on the shock wave speed, the queue length at the end of the current period and a duration of the green signal, so as to determine the queue length of each of the multiple traffic signals of the current intersection in the next period; determining a first target duration and a second target duration in the next period based on a signal phase sequence, a phase loss duration and the duration of the green signal; constructing a sub-model of a jam density of the current intersection based on the first target duration, the second target duration and the queue length of each of the multiple traffic signals in the next period, so as to determine the jam density of the current intersection in the next period; and constructing the traffic control model of the current intersection according to the sub-model of the queue length of each of the multiple traffic signals and the sub-model of the jam density.

[0008] According to an embodiment of the present application, the signal phase sequence is a first red phase, a green phase, a yellow phase and a second red phase, and the signal phase information further comprises a first red phase duration and a second red phase duration; the sub-model of the queue length of each of the multiple traffic signals is constructed based on the shock wave speed, the queue length at the end of the current period and the duration of the green signal, comprising: determining a queue length of the first red phase based on the shock wave speed and the first red phase duration, and constructing a sub-model of a cumulative queue length of the first red phase based on a sum of the queue length of the first red phase and the queue length at the end of the current period, so as to determine the cumulative queue length of the first red phase of the current intersection in the next period; determining a passing length of the green phase based on the predicted saturated release rate, the predicted jam density and the duration of the green signal, and constructing a sub-model of a residual queue length of the green phase based on a sum of the cumulative queue length of the first red phase and the passing length of the green phase, so as to determine the residual queue length of the green phase of the current intersection in the next period; and determining a queue length of the second red phase based on the shock wave speed and the second red phase duration, and constructing a sub-model of a cumulative queue length of the second red phase based on a sum of the queue length of the second red phase and the residual queue length of the green phase, so as to determine the cumulative queue length of the second red phase of the current intersection in the next period.

[0009] According to an embodiment of the present application, the first target duration and the second target duration in the next period are determined based on the signal phase sequence, the phase loss duration and the duration of the green signal, comprising: determining the first target duration before the green phase starts and the second target duration after the green phase ends in the next period according to the signal phase sequence, the first red phase duration, the duration of the green signal, a yellow phase duration and a second red phase duration, and the yellow phase duration being the phase loss duration.

[0010] According to an embodiment of the present application, the sub-model of the congestion density of the current intersection is constructed based on the first target time length, the second target time length and the queue length of each traffic signal in the next cycle, including: determining the first congestion parameter of the first red light phase based on the first target time length, the queue length at the end of the current cycle and the queuing length of the first red light phase; determining the second congestion parameter of the second red light phase based on the second target time length, the remaining queuing length of the green light phase and the queuing length of the second red light phase; and constructing the sub-model of the congestion density based on the first congestion parameter, the second congestion parameter and the predicted congestion density.

[0011] According to an embodiment of the present application, the time length of the green light signal in the traffic control model is updated based on the predicted traffic parameters and the signal phase information until the queue length in the future cycle reaches the target value, to obtain the target green light time length of the green light signal and the target cycle time length of the future cycle, including: inputting the predicted traffic parameters and the signal phase information into the traffic control model, and updating the time length of the green light signal in the traffic control model based on the constraint condition that the congestion density in the traffic control model is less than or equal to the critical density, until the cumulative queuing length of the second red light phase in the continuous multiple preset cycles in the future cycle reaches the target value, to obtain the target green light time length; and determining the target cycle time length according to the target green light time length, the phase loss time length, the first red light phase time length and the second red light phase time length.

[0012] According to an embodiment of the present application, the prediction model includes a forget gate, an input gate, an output gate and a memory unit, and the prediction model is obtained by training in the following manner: inputting traffic training information of a plurality of training intersections in a training cycle into an initial prediction model to obtain an initial prediction value of a current training intersection, the initial prediction value including initial traffic parameters and initial signal phase information, the plurality of training intersections including the current training intersection and an upstream training intersection of the current training intersection; updating model parameters of the initial prediction model based on an error between the initial prediction value and a true value until the error meets a preset condition to obtain the prediction model, the true value including true traffic parameters and true signal phase information of the current training intersection.

[0013] According to an embodiment of the present application, the model parameters include weights and biases of the forget gate, the input gate, the output gate and the memory unit; and the model parameters of the initial prediction model are updated based on an error between the initial prediction value and the true value until the error meets a preset condition to obtain the prediction model, including: determining a gradient of the tth model parameter according to the tth model parameter, a step length coefficient in a gradient descent algorithm and the tth error, t being an integer greater than or equal to 1; and updating the tth model parameter according to the tth model parameter, the gradient and the step length coefficient to obtain a t+1th model parameter updated in the t+1th time.

[0014] According to an embodiment of the present application, the historical traffic information comprises: historical driving speeds of vehicles passing through multiple intersections collected via inductive coils, historical traffic volumes of the multiple intersections collected via vehicle-mounted locators, and historical queue lengths of the multiple intersections collected via roadside cameras.

[0015] A second aspect of the present application provides a traffic signal control device based on multi-source heterogeneous data, comprising: an acquisition module configured to acquire historical traffic information of multiple intersections in a historical period, wherein the multiple intersections comprise a current intersection and an upstream intersection of the current intersection; an input module configured to input the historical traffic information into a prediction model to obtain predicted traffic parameters of multiple traffic phases of the current intersection in a future period and signal phase information of multiple traffic signals, wherein the multiple traffic phases represent directions in which vehicles can travel in the current intersection; an update module configured to update a length of a green signal in a traffic control model based on the predicted traffic parameters and the signal phase information until a queue length in the future period reaches a target value, to obtain a target green signal length of the green signal and a target cycle length of the future period, wherein the multiple traffic signals comprise the green signal, the queue length represents a number of vehicles waiting to pass through the current intersection, and the traffic control model is constructed based on queue lengths and congestion densities of the multiple traffic signals in the future period for the multiple traffic phases; and a control module configured to control the multiple traffic signals according to the target green signal length and the target cycle length.

[0016] A third aspect of the present application provides an electronic device, comprising: one or more processors; and a memory configured to store one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement steps of the method.

[0017] A fourth aspect of the present application further provides a computer-readable storage medium having stored thereon a computer program or instructions, wherein the computer program or instructions are executed by a processor to implement steps of the method.

[0018] A fifth aspect of the present application further provides a computer program product comprising a computer program or instructions, wherein the computer program or instructions are executed by a processor to implement steps of the method.

[0019] According to the embodiment of the present application, by inputting the historical traffic information of the current intersection and the upstream intersection in the plurality of intersections into the prediction model, the prediction traffic parameters and signal phase information of the plurality of traffic phases of the current intersection in the future period can be accurately obtained due to the consideration of the influence of the upstream intersection on the current intersection. Since the traffic control model is constructed based on the queue length and congestion density of the plurality of traffic signals in the future period of the plurality of traffic phases, the queue length and congestion density in the traffic control model can accurately reflect the dynamic traffic conditions of the intersection. Therefore, the length of the green light signal in the traffic control model is updated based on the prediction traffic parameters and signal phase information until the queue length in the future period reaches the target value, and the target green light length and the target cycle length of the future period are obtained, realizing high-precision traffic flow prediction and signal timing optimization according to the dynamic traffic conditions of the intersection. The plurality of traffic signals are controlled according to the target green light length and the target cycle length to ensure that the vehicles can efficiently pass through the current intersection and improve the traffic efficiency of the current intersection. BRIEF DESCRIPTION OF DRAWINGS

[0020] The above and other objects, features and advantages of the present application will become more apparent from the following description of embodiments of the present application taken in conjunction with the accompanying drawings, in which:

[0021] Figure 1 A scenario diagram of the application of the traffic signal control method based on multi-source heterogeneous data according to the embodiment of the present application is shown;

[0022] Figure 2 A flowchart of the traffic signal control method based on multi-source heterogeneous data according to the embodiment of the present application is shown;

[0023] Figure 3 A traffic flow heat map of the current intersection at different time periods according to the embodiment of the present application is shown;

[0024] Figure 4 A prediction result of the current intersection according to the embodiment of the present application is shown;

[0025] Figure 5A A simulation experiment result for signal timing according to the embodiment of the present application is shown;

[0026] Figure 5B A structural block diagram of the traffic signal control system based on multi-source heterogeneous data according to the embodiment of the present application is shown;

[0027] Figure 6 A structural block diagram of the traffic signal control device based on multi-source heterogeneous data according to the embodiment of the present application is shown;

[0028] Figure 7A block diagram of an electronic device suitable for implementing a traffic signal control method based on multi-source heterogeneous data according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0029] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. It is to be understood, however, that these descriptions are merely exemplary and are intended to illustrate the scope of the present application, not to limit it. In the following detailed description of the embodiments of the present application, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to one skilled in the art that the embodiments of the present application can be practiced without these specific details. In other instances, well-known structures and functions have been omitted or simplified in order not to obscure the concepts of the present application.

[0030] The terms used herein are merely used to describe specific embodiments, and are not intended to limit the present application. The terms "include" and "have" and the like used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0031] All terms used herein, including technical and scientific terms, have the same meanings as those generally understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of the present specification, and should not be interpreted in an idealized or excessively formal manner.

[0032] In the case of using expressions similar to "at least one of A, B, and C, etc.", it should generally be interpreted to include at least one of the items, but not limited to the items (e.g., "a system having at least one of A, B, and C" should include a system having A alone, a system having B alone, a system having C alone, a system having A and B together, a system having A and C together, a system having B and C together, and / or a system having A, B, and C together, etc.).

[0033] Traffic signal control using multi-source heterogeneous data collected via roadside cameras, vehicle-mounted sensors, ground coils, and other environmental monitoring devices has been widely used in traffic signal control, but the length of the traffic signal is often affected by sudden events, which can cause traffic congestion and safety accidents.

[0034] In one implementation, a centralized signal timing control method requires massive real-time traffic information and high-performance computing resources, and has high requirements for data types and quantities and computing performance, so it is not suitable for real-time control of large-scale traffic networks, and it is more difficult to accurately control the length of the traffic light signal to complete efficient passage of vehicles at the intersection.

[0035] In another implementation, the distributed signal timing control method is applied to the roadside controller and the Internet of Vehicles technology, the data of multiple intersections in a region can be shared in real time, which is more suitable for the coordinated optimization of multiple intersections, and it is difficult to guarantee the local optimization of single intersection traffic, the control precision of traffic signal is low, and the traffic efficiency of intersection is reduced.

[0036] Therefore, an embodiment of the present application provides a traffic signal lamp control method based on multi-source heterogeneous data, comprising: obtaining historical traffic information of multiple intersections in a historical period, wherein the multiple intersections include a current intersection and an upstream intersection of the current intersection; inputting the historical traffic information into a prediction model to obtain prediction traffic parameters of multiple traffic phases of the current intersection in a future period and signal phase information of multiple traffic signal lamps, wherein the multiple traffic phases represent directions in which vehicles can travel in the current intersection; updating a duration of a green signal in a traffic control model based on the prediction traffic parameters and the signal phase information until a queue length in the future period reaches a target value, to obtain a target green signal duration of the green signal and a target period duration of the future period, wherein the multiple traffic signal lamps include the green signal, the queue length represents a number of vehicles waiting to pass through the current intersection, and the traffic control model is constructed based on queue lengths and congestion densities of the multiple traffic signal lamps in the future period for the multiple traffic phases; and controlling the multiple traffic signal lamps according to the target green signal duration and the target period duration.

[0037] Figure 1 An application scenario diagram of the traffic signal lamp control method based on multi-source heterogeneous data according to an embodiment of the present application is shown.

[0038] As shown in Figure 1 The application scenario 100 according to the embodiment can include a vehicle 110, a traffic light 120 at an upstream intersection, and a traffic light 130 at a current intersection. A driver will drive the vehicle through the upstream intersection according to the indication of the traffic light 120 at the upstream intersection. After passing through the upstream intersection, the current intersection has multiple traffic phases, such as a left-turn phase, a straight-ahead phase, and a right-turn phase. The driver will pass through the current intersection according to the indication of the traffic light 130 at the current intersection. The traffic light 130 at the current intersection can include a red light, a green light, and a yellow light. The traffic light 130 at the current intersection can have multiple signal phases, for example, a green light phase when the green light is on, a yellow light phase when the yellow light is on, and a red light phase when the red light is on.

[0039] For example, when the traffic light 130 at the current intersection displays a green light, the vehicle 110 can straight pass along the lane direction, and if the green light phase allows right turn, the vehicle can turn to the right lane. It should be noted that the traffic light 130 at the current intersection can set a left straight green light, and when the left straight green light is on, the vehicle 110 can turn to the left lane.

[0040] For example, when the traffic light 130 at the current intersection displays a red light, the straight or left-turn vehicle needs to wait behind the stop line, and the right-turn vehicle can turn slowly. When the traffic light 130 at the current intersection displays a yellow light, the vehicle (such as a straight vehicle or a left-turn vehicle) that has entered the current intersection beyond the stop line needs to continue to complete the passage, and the vehicle that has not crossed the stop line needs to slow down and stop behind the stop line.

[0041] A roadside camera can be installed on the traffic light 130 at the current intersection to collect the queue length of the vehicle waiting for passage at the current intersection. A ground inductive coil is arranged on the road between the upstream intersection and the current intersection to collect the driving speed of the vehicle passing through the current intersection. A vehicle-mounted locator can be installed on the vehicle 110 and other driving vehicles to collect the traffic volume of the current intersection. It should be noted that the traffic volume can also be collected by the ground inductive coil.

[0042] It should be noted that, Figure 1 The number of vehicles 110 in the current intersection is only illustrative. In actual situations, the number of vehicles can be multiple, and different vehicles can have different driving directions. The traffic light 130 at the current intersection can set a left straight green light as needed, which is not limited herein.

[0043] Figure 2 A flowchart of a traffic signal control method based on multi-source heterogeneous data according to an embodiment of the present application is shown.

[0044] As shown in Figure 2 The traffic signal control method based on multi-source heterogeneous data of the embodiment includes operations S210-S240.

[0045] In operation S210, historical traffic information of a plurality of intersections in a historical period is obtained, wherein the plurality of intersections include a current intersection and an upstream intersection of the current intersection.

[0046] According to an embodiment of the present application, the plurality of intersections can include the current intersection, a plurality of upstream intersections of the current intersection. For example, as shown in Figure 1 The upstream intersection of the current intersection is a “T” intersection. The upstream intersection of the “T” intersection can include two “X” intersections (X1 and X2). Figure 1The upstream intersection of the current intersection can include one "T" intersection and two "X" intersections (not shown). Therefore, the upstream intersection of the current intersection can include one "T" intersection and two "X" intersections.

[0047] According to an embodiment of the present application, the history period can be a period adjacent to a future period. For example, the current period is the 5th period, the history period can be the 1st-5th period, and the future period can be the 6th period.

[0048] For example, the history period can include a plurality of history sub-periods, and the future period can also include a plurality of future sub-periods. The current period is the 5th sub-period, the history period can be the 1st-5th sub-period, and the future period can be the 6th-7th sub-period.

[0049] It should be noted that the period is determined according to the signal type of the traffic light, for example, the length of the period can be the length of time after the traffic light flashes according to the indication of each signal.

[0050] According to an embodiment of the present application, the history traffic information can include history traffic passing information of the current intersection and history traffic passing information of a plurality of upstream intersections. For example, the history traffic passing information can include the length of time of each signal in the traffic light, the vehicle speed, the number of vehicles after each signal ends, the congestion length of time of the intersection, etc.

[0051] In operation S220, the history traffic information is input into the prediction model to obtain the prediction traffic parameters of each of a plurality of traffic phases of the current intersection in the future period and the signal phase information of a plurality of traffic signals.

[0052] According to an embodiment of the present application, the plurality of traffic phases can include straight, left turn, right turn, etc. Meanwhile, the plurality of traffic phases are not limited to straight, left turn, and right turn, and can be set according to the actual intersection situation to have a plurality of left turn phases and a plurality of right turn phases.

[0053] According to an embodiment of the present application, the prediction model can be a machine learning algorithm, for example, a support vector machine algorithm, a random forest algorithm, and a neural network algorithm, etc. For example, the history traffic information of the plurality of traffic phases of the current intersection and the history traffic information of the plurality of traffic phases of the upstream intersection are feature processed according to the time information to obtain traffic state features. The traffic state features are input into the prediction model to obtain the prediction traffic parameters of each of the plurality of traffic phases of the current intersection in the future period and the signal phase information of the plurality of traffic signals.

[0054] According to an embodiment of the present application, the prediction traffic parameters can represent the passing state of the current intersection in the future period.

[0055] According to an embodiment of the present application, the signal phase is determined according to multiple signals of the traffic signal light. The signal phase information can be information of the multiple traffic signal lights. For example, the multiple signals of the traffic signal light can include a green light signal. For example, the signal phase information of the multiple traffic signal lights can include a flashing sequence of the multiple traffic signal lights and a flashing duration, etc.

[0056] In operation S230, a duration of a green light signal in the traffic control model is updated based on the predicted traffic parameter and the signal phase information until a queue length in a future period reaches a target value, to obtain a target green light duration of the green light signal and a target period duration of the future period, wherein the multiple traffic signal lights include the green light, the queue length represents a number of vehicles waiting to pass through the current intersection, and the traffic control model is constructed based on the queue length and the congestion density of the multiple traffic phases in the multiple traffic signal lights in the future period.

[0057] According to an embodiment of the present application, the congestion density is used to describe a critical index of the traffic flow from “smooth” to “congestion”. The value range of the congestion density is greater than the critical density and less than the jam density. The critical density can be a critical point of the highest efficiency of the intersection. The jam density can be a density when the vehicles at the intersection are completely stopped.

[0058] According to an embodiment of the present application, since the queue length and the congestion density of the multiple traffic phases in the multiple traffic signals in the future period can accurately reflect the dynamic traffic situation of the intersection, the traffic control model is constructed based on the queue length and the congestion density of the multiple traffic phases in the multiple traffic signals in the future period.

[0059] According to an embodiment of the present application, the target value can make the cumulative delay in the future period reach a minimum value. For example, after updating the duration of the green light signal in the traffic control model multiple times, multiple queue lengths are obtained. The target value can be the minimum value in the multiple queue lengths.

[0060] In operation S240, the multiple traffic signal lights are controlled according to the target green light duration and the target period duration.

[0061] According to an embodiment of the present application, the green light in the multiple traffic signal lights flashes according to the target green light duration. The duration after the multiple traffic signal lights flash in turn is the target period duration.

[0062] For example, a trigger discrete optimization algorithm of n-order phase can be used to realize the global optimization (such as the minimum delay and the maximum traffic volume) of the intersection traffic efficiency by dynamically adjusting the duration of the green light signal of each traffic phase in the traffic control model.

[0063] According to the embodiment of the present application, by inputting the historical traffic information of the current intersection and the upstream intersection in the multiple intersections into the prediction model, the prediction traffic parameters and signal phase information of the multiple traffic phases of the current intersection in the future period can be accurately obtained, since the influence of the upstream intersection on the current intersection is considered. Since the traffic control model is constructed based on the queue length and congestion density of the multiple traffic signals in the future period of the multiple traffic phases, the queue length and congestion density in the traffic control model can accurately reflect the dynamic traffic conditions of the intersection. Therefore, the duration of the green light signal in the traffic control model is updated based on the prediction traffic parameters and signal phase information, until the queue length in the future period reaches the target value, the target green light duration and the target cycle duration of the future period are obtained, the high-precision traffic flow prediction is realized, and the signal timing optimization is performed according to the dynamic traffic conditions of the intersection. The multiple traffic signals are controlled according to the target green light duration and the target cycle duration, so as to ensure that the vehicles can efficiently pass through the current intersection and improve the traffic efficiency of the current intersection.

[0064] According to the embodiment of the present application, the historical traffic information includes the historical driving speed of the vehicles passing through the multiple intersections collected by the ground inductive coil, the historical traffic volume of the multiple intersections collected by the vehicle-mounted locator, and the historical queue length of the multiple intersections collected by the roadside camera.

[0065] According to the embodiment of the present application, the ground inductive coil can be installed at the current intersection and the upstream intersection, so as to obtain the historical driving speed of the vehicles at the intersection. The roadside camera can be installed beside the road of the current intersection and the upstream intersection, so as to collect the historical queue length of the current intersection and the upstream intersection.

[0066] It should be noted that in the technical solution of the present application, the traffic information involved is information and data authorized by the driver or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the related data comply with relevant laws, regulations and standards, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for the driver to choose authorization or refusal.

[0067] According to the embodiment of the present application, the traffic state features under the multi-source heterogeneous data are determined based on the historical driving speed, the historical traffic volume and the historical queue length of the vehicles of the multiple intersections.

[0068] Based on the vehicle-mounted locator, the current intersection's historical traffic volume at the current time and the previous time is obtained. The historical traffic volume of the upstream intersection at the current time and the previous time is obtained by using a time series analysis algorithm. The historical traffic volume data, the historical traffic volume, and the historical queue length are fused to form a traffic state feature under multi-source monitoring, which has real-time and robustness. The traffic state feature is input into the prediction model as an input sequence.

[0069] In an embodiment, the prediction model can include an intersection control agent, a plurality of sub-area control agents, and a network control agent, and each of the plurality of sub-areas (such as the plurality of sub-areas including the current intersection and the plurality of upstream intersections) corresponds to a sub-area control agent.

[0070] The intersection control agent is used to collect multi-source heterogeneous information. At the intersection, various types of sensors are deployed to collect data such as traffic, speed, queue length, etc. in real time, and these heterogeneous data are cleaned, converted, and noise and redundancy are removed to preliminarily fuse into usable traffic state features.

[0071] The sub-area control agent is responsible for summarizing and coordinating in the sub-area. The sub-area control agent collects the traffic state features of each intersection in the region, and compares and analyzes the traffic states of different intersections. According to the traffic demand and the overall situation, the control strategies of each intersection are coordinated and optimized to ensure the order of traffic in the sub-area.

[0072] The network control agent comprehensively forms a multi-source heterogeneous data fusion control model at the network level. The network control agent integrates the information of all sub-areas to evaluate the traffic situation from a global perspective. Based on the evaluation result, the control strategies of each sub-area are uniformly adjusted and optimized.

[0073] The agent has autonomous decision-making ability and can work cooperatively. Based on the intersection control agent, multi-source heterogeneous information such as traffic, speed, queue length, etc. is collected locally, cleaned, converted, and preliminarily fused. Based on the regional traffic features, the sub-area control agent is established to collect intersection information, compare different states, and then further summarize and coordinate. According to the information of the network sub-area, the network control agent is constructed to globally adjust and optimize, forming a multi-source heterogeneous data fusion control model.

[0074] In another embodiment, the historical traffic volume of the upstream intersection based on the vehicle-mounted locator is shown in the following formula (1):

[0075] (1);

[0076] is the historical traffic volume of the intersection (upstream intersection) at the time, is Intersection No. Historical traffic flow at any given time yes Intersection No. Historical traffic flow at any given time It is an integer greater than 1. For integers greater than 2, from 1 to A moment is a period of time within a historical cycle.

[0077] The historical traffic flow at the current intersection is obtained based on the vehicle locator, as shown in the following formula (2):

[0078] (2);

[0079] yes Intersection (current intersection) No. Historical traffic flow at any given time yes Intersection No. Historical traffic flow at any given time yes Intersection No. Historical traffic flow at any given moment.

[0080] Historical traffic flow data, historical traffic volume, and historical queue length are fused together to form traffic state characteristics under multi-source monitoring, possessing real-time performance and robustness. These traffic state characteristics are then used as input sequences into the prediction model.

[0081] The prediction model can be a long short-term memory network, while the traffic control model can be constructed from the queue lengths and congestion densities of various traffic lights in future cycles for different traffic flow phases. The queue lengths and congestion densities are derived from traffic flow wave theory. Therefore, combining long short-term memory networks and traffic flow wave models provides clear numerical definitions and enables end-to-end joint optimization of traffic flow prediction and signal timing.

[0082] According to an embodiment of the present invention, the predicted traffic parameters include the predicted arrival rate, the predicted saturation release rate, and the predicted congestion density. The predicted arrival rate represents the number of vehicles approaching the current intersection within a preset time. The signal phase information includes the signal phase sequence and the phase loss duration.

[0083] According to an embodiment of the present invention, the predicted saturation release rate characterizes the first target (maximum) number of vehicles under the continuous traffic flow condition during the duration of the green light signal.

[0084] According to an embodiment of the present invention, congestion density characterizes the second target (maximum) number of vehicles that the current intersection can accommodate when vehicles are stopped at the current intersection.

[0085] According to an embodiment of the present application, the signal phase sequence can be a sequence in which a plurality of traffic signal lights are sequentially flashed. For example, the plurality of traffic signal lights include a red light, a green light and a yellow light, and are sequentially flashed in the order of the green light, the yellow light and the red light, and the signal phase sequence can be a red light phase, a green light phase and a yellow light phase.

[0086] According to an embodiment of the present application, the phase loss duration can be a duration of the yellow light phase.

[0087] According to an embodiment of the present application, the history period includes a current period, the future period includes a next period of the current period, and the traffic control model is constructed based on the following manner: determining a shock wave speed based on a predicted arrival rate, a predicted saturated release rate and a predicted jam density of the next period; constructing a sub-model of a queue length of each of the plurality of traffic signal lights based on the shock wave speed, the queue length at the end of the current period and a duration of the green light signal, so as to determine the queue length of each of the plurality of traffic signal lights of the current intersection in the next period; determining a first target duration and a second target duration in the next period based on the signal phase sequence, the phase loss duration and the duration of the green light signal; constructing a sub-model of a jam density of the current intersection based on the first target duration, the second target duration and the queue length of each of the plurality of traffic signal lights in the next period, so as to determine the jam density of the current intersection in the next period; and constructing the traffic control model of the current intersection according to the sub-model of the queue length of each of the plurality of traffic signal lights and the sub-model of the jam density.

[0088] According to an embodiment of the present application, the shock wave speed is determined according to the following formula (3):

[0089] (3);

[0090] k represents the next period, represents the arrival rate, is the predicted arrival rate of the traffic phase p in the next period. represents the saturated release rate, is the predicted saturated release rate of the traffic phase p of the current intersection in the duration of the green light signal. represents the jam density, is the predicted jam density of the traffic phase p in the next period.

[0091] According to an embodiment of the present application, the sub-model of the queue length of each of the plurality of traffic signal lights is constructed based on the shock wave speed, the queue length at the end of the current period and the duration of the green light signal by the motion wave theory. For example, the queue length of each of the plurality of traffic signal lights can be dynamically established according to the number of vehicles passing through different signal phase durations.

[0092] According to the embodiment of the present application, since the traffic control model of the current intersection is constructed by using the sub-models of the queue length of each traffic signal and the sub-model of the congestion density, the traffic control model can accurately reflect the dynamic traffic condition of the intersection.

[0093] According to the embodiment of the present application, the signal phase sequence is a first red light phase, a green light phase, a yellow light phase and a second red light phase, and the signal phase information further comprises a first red light phase duration and a second red light phase duration; based on the shock wave speed, the queue length at the end of the current cycle and the duration of the green light signal, the sub-models of the queue length of each traffic signal are constructed, including: based on the shock wave speed and the first red light phase duration, the queue length of the first red light phase is determined, and based on the sum of the queue length at the end of the current cycle and the queue length of the first red light phase, the sub-model of the cumulative queue length of the first red light phase is constructed, so as to determine the cumulative queue length of the first red light phase of the current intersection in the next cycle; based on the predicted saturation release rate, the predicted congestion density and the duration of the green light signal, the traffic length of the green light phase is determined, and based on the sum of the cumulative queue length of the first red light phase and the traffic length of the green light phase, the sub-model of the residual queue length of the green light phase is constructed, so as to determine the residual queue length of the green light phase of the current intersection in the next cycle; based on the shock wave speed and the second red light phase duration, the queue length of the second red light phase is determined, and based on the sum of the queue length of the second red light phase and the residual queue length of the green light phase, the sub-model of the cumulative queue length of the second red light phase is constructed, so as to determine the cumulative queue length of the second red light phase of the current intersection in the next cycle.

[0094] According to the embodiment of the present application, the sub-model of the queue length at the end of the current cycle is shown in formula (4), the sub-model of the cumulative queue length of the first red light phase is shown in formula (5), the sub-model of the residual queue length of the green light phase is shown in formula (6), and the sub-model of the cumulative queue length of the second red light phase is shown in formula (7).

[0095] (4);

[0096] The queue length at the end of the current cycle is the queue length at the end of the previous cycle of the current cycle .

[0097] (5);

[0098] is the cumulative queue length of the first red light phase, is the first red light phase duration. (i.e. the first red light phase duration the product of the shock wave speed is the queue length of the first red light phase.

[0099] (6);

[0100] is the remaining queue length of the green light phase, is the duration of the green light signal, is the length of the green light phase.

[0101] (7);

[0102] is the cumulative queue length of the second red light phase, is the duration of the second red light phase, is the queue length of the second red light phase.

[0103] According to the embodiment of the present application, based on the signal phase sequence, the phase loss duration and the duration of the green light signal, the first target duration and the second target duration in the next cycle are determined, comprising: according to the signal phase sequence, the first red light phase duration, the duration of the green light signal, the yellow light phase duration and the second red light phase duration, the first target duration before the start of the green light phase and the second target duration after the end of the green light phase in the next cycle are determined, and the yellow light phase duration is the phase loss duration.

[0104] According to the embodiment of the present application, the first red light phase duration, the duration of the green light signal, the yellow light phase duration (the phase loss duration) and the signal phase sequence in the next cycle are predicted, and the first target duration before the start of the green light phase and the second target duration after the end of the green light phase in the next cycle can be determined.

[0105] According to the embodiment of the present application, based on the first target duration, the second target duration and the queue length of each traffic signal in the next cycle, a sub-model of the congestion density of the current intersection is constructed, comprising: based on the first target duration, the queue length at the end of the current cycle and the queue length of the first red light phase, a first congestion parameter of the first red light phase is determined; based on the second target duration, the remaining queue length of the green light phase and the queue length of the second red light phase, a second congestion parameter of the second red light phase is determined; based on the first congestion parameter, the second congestion parameter and the predicted congestion density, a sub-model of the congestion density is constructed.

[0106] According to the embodiment of the present application, the sub-model of the congestion density is shown in formula (8):

[0107] (8);

[0108] , i.e. is the queue length of the first red phase in the next cycle k, is the queue length of the second red phase in the next cycle k. The first congestion parameter is , is the first target duration in the next cycle k. The second congestion parameter is , is the second target duration in the next cycle k. N represents the number of cycles in the future cycle obtained by prediction. P represents the number of traffic phases of the current intersection.

[0109] is the traffic phase the congestion metric in the next cycle (k). represents the congestion density of the future cycle.

[0110] According to an embodiment of the present application, the duration of the green signal in the traffic control model is updated based on the predicted traffic parameters and signal phase information until the queue length in the future cycle reaches the target value, to obtain the target green signal duration and the target cycle duration in the future cycle, including: inputting the predicted traffic parameters and signal phase information into the traffic control model, and updating the duration of the green signal in the traffic control model based on the constraint condition that the congestion density in the traffic control model is less than or equal to the critical density, until the cumulative queue length of the second red phase in the future cycle reaches the target value in a plurality of preset cycles, to obtain the target green signal duration; determining the target cycle duration according to the target green signal duration, the phase loss duration, the first red phase duration and the second red phase duration.

[0111] Given the predicted arrival rate, the predicted saturation release rate, the predicted congestion density, the signal phase sequence, and the phase loss duration (yellow) of each traffic phase, the current cycle length , the duration of the green signal of each phase is determined. Since the objective function (formula (4) to formula (8)) is linear with respect to , a linear programming is obtained, and and are solved, which are the optimal cycle length and green signal allocation duration. Then the green duration, yellow duration and red duration in the cycle length are arranged in the time axis, triggered according to the phase, to ensure that the "first red duration + green duration + phase loss duration + second red duration = cycle duration". After each execution of the rolling cycle control is completed, new data is read again for the next round of optimal traffic flow control.

[0112] The queue growth rate is determined by using the motion wave theory, and a globally optimal traffic control model of the motion wave theory (formula (4) to formula (7) and a flow density graph (formula (8)) is established. The dynamic programming method is used to determine the green light allocation rule. Then, the congestion density in the phase critical state is calculated, and the optimal cycle length and the time length of the green light signal of each phase are solved, so as to realize the optimal traffic flow passing.

[0113] According to an embodiment of the present application, the time length of the green light signal in the traffic control model is updated based on the constraint condition that the congestion density in the traffic control model is less than or equal to the critical density, until the cumulative queue length of the second red light phase reaches a minimum value (cumulative delay minimization) in the next N preset periods in the future cycle, so as to trigger the solving of the target green light time length by formula (4) to formula (8), and realize the optimal traffic flow passing of the current intersection, thereby realizing the passing efficiency of multiple intersections in the region.

[0114] According to an embodiment of the present application, the prediction model includes a forgetting gate, an input gate, an output gate and a memory unit, and the prediction model is obtained by training in the following manner: inputting traffic training information of a plurality of training intersections in a training period into an initial prediction model to obtain an initial prediction value of a current training intersection, the initial prediction value including initial traffic parameters and initial signal phase information, the plurality of training intersections including the current training intersection and an upstream training intersection of the current training intersection; updating model parameters of the initial prediction model based on an error between the initial prediction value and a true value until the error meets a preset condition, to obtain the prediction model, the true value including true traffic parameters and true signal phase information of the current training intersection.

[0115] According to an embodiment of the present application, the initial prediction model can be a pre-trained long short-term memory network, and the long short-term memory network including the forgetting gate, the input gate, the output gate and the memory unit is established according to the following formula:

[0116] (9);

[0117] The traffic state feature input into the long short-term memory network is, is the hidden state feature obtained by the last update, is the forgetting gate, is the input gate, is the output gate, is the memory unit, is the reserved state feature output by the memory unit in the last update process, is the reserved state feature output by the memory unit in the current update process, is the hidden state feature obtained by the current update, ​is an activation function, usually sigmoid function, tanh is hyperbolic tangent activation function. are weights of the forget gate, the input gate, the output gate and the memory cell respectively, are biases of the forget gate, the input gate, the output gate and the memory cell respectively.

[0118] According to the embodiment of the present application, in the training phase of the prediction model, the gradient descent method is used to optimize the parameters of the long short-term memory network, so that the error between the initial prediction value and the true value converges (or reaches a minimum value). The preset condition can be that the error between the initial prediction value and the true value converges (or reaches a minimum value). The error formula is as follows:

[0119] (10);

[0120] According to the embodiment of the present application, the model parameters include the weights and biases of the forget gate, the input gate, the output gate and the memory cell respectively; the model parameters of the initial prediction model are updated based on the error between the initial prediction value and the true value until the error meets the preset condition, to obtain the prediction model, including: determining the gradient of the t-th model parameter according to the t-th model parameter updated for the t-th time, the step coefficient in the gradient descent algorithm and the t-th error, t is an integer greater than or equal to 1; updating the t-th model parameter according to the t-th model parameter, the gradient and the step coefficient, to obtain the t+1-th model parameter updated for the t+1-th time.

[0121] The weights and biases of the forget gate, the input gate, the output gate and the memory cell are updated according to the following formula.

[0122] (11);

[0123] is the weight of the long short-term memory network in the t-th update, is the weight of the long short-term memory network in the t+1-th update, is the step coefficient, which controls the amplitude of each parameter update in the negative gradient direction. is the gradient of . is the gradient of . is the bias of the long short-term memory network in the t-th update, is the bias of the long short-term memory network in the t+1-th update, is the gradient of .

[0124] ​​In the implementation of model training, a long short-term memory network including a forgetting gate, an input gate, an output gate, and a memory cell is established. The gating mechanism is an important link to ensure the stability of the model, but it is impractical to manually adjust the parameters in the training stage of the model. Therefore, the gradient descent method is used to optimize the weights and biases of the long short-term memory network to realize the convergence (or reach a minimum value) of the error between the initial prediction value and the true value. The model optimization process stores the parameters of the weights, biases, and gate states in the updating process of the long short-term memory network around the current error function.

[0125] For example, the region where the current intersection is located is modeled and calibrated in a simulation environment of VISSIM (Verkehr In Städten - Simulation, urban traffic simulation system). The region can include 5 entrance lanes and 13 movements, mainly straight and left turn two phase movements.

[0126] The traffic flow dataset can be the whole year traffic data of the region in the historical year. The traffic data can include the number of vehicles passing through the intersection, the speed, the vehicle type, and other indicators in each period. To realize efficient and accurate data collection, the traffic simulation software combines the actual traffic data to construct an automated data collection and preprocessing process, and eliminates outliers and missing values to ensure the continuity and reliability of the dataset.

[0127] Figure 3 A traffic flow heat map of the current intersection at different periods is shown according to an embodiment of the application.

[0128] As shown in Figure 3 , the traffic flow heat of two months at different periods intuitively reflects the vehicle distribution characteristics of the current intersection at different periods, and reveals that the vehicle distribution of the current intersection presents nonlinear fluctuations.

[0129] Figure 4 A prediction result at the current intersection is shown according to an embodiment of the application.

[0130] As shown in Figure 4 , the data of July and August in the historical year are used as the training set, and the data of September is used for model testing and verification. The solid line 3 is the true data, and the dashed line is the predicted data. Figure 4 The error between the predicted data and the true data of the traffic flow in the prediction result in September is small, which verifies the robustness of the training and testing results based on the long short-term memory network, indicates that the model prediction trend is highly consistent with the actual traffic flow trend, and proves the effectiveness and reliability of the long short-term memory network.

[0131] Figure 5A ​Simulation results for signal timing according to embodiments of the application are shown.

[0132] As shown in Figure 5A , the statistical data set of 4000 cycles is used for prediction, the signal timing parameters obtained by solving the five models are input into the simulation environment, for each test method, 30 simulation experiments are performed respectively, and each simulation experiment takes 4900 seconds. Figure 5A The time distribution of the average travel delay under the five traffic signal control methods is shown. The abscissa represents the average travel delay of the vehicle, and the ordinate represents the frequency of different delay times. In Figure 5A , the model in the middle performs best in traffic signal control, and the average travel delay is mainly concentrated in the lower interval (about 40-55s), the distribution range is narrow and the fluctuation is small, which indicates that the vehicle passes more smoothly and the delay is less. In contrast, the traditional Webster model and Maxband model perform poorly in terms of delay, with generally higher average travel delay and wider distribution range, and Webster model and Maxband model are difficult to effectively alleviate traffic congestion during peak hours. The fuzzy model and MDAE (Multi-Objective Dynamic Signal Timin) model perform in the middle in terms of delay control, although they are improved compared with Webster model and Maxband model, but the overall performance is still inferior to the proposed model.

[0133] Figure 5B A structural block diagram of a traffic signal lamp control system based on multi-source heterogeneous data according to embodiments of the application is shown.

[0134] As shown in Figure 5B , the traffic signal lamp control system based on multi-source heterogeneous data 500 includes a data collector 510, a feature extractor 520, a processor 530, a memory 540, and a signal control device 550.

[0135] The data collector 510 is configured to collect multi-source heterogeneous traffic data in real time from roadside sensors, vehicle-mounted sensors, ground coils, and historical databases. The collected data is transmitted to the feature extractor 520.

[0136] The feature extractor 520 is configured to denoise, fill missing values, and detect outliers for the raw data output by the data collector, calculate and output traffic state features, and transmit the output traffic state feature vector to the processor 530.

[0137] The processor 530 is coupled to the feature extractor 520, and the processor 530 is configured to train and online predict the historical traffic state feature sequence and transmit it to the memory 540.

[0138] The memory 540 is coupled to the processor 530, and is configured to store the historical traffic data, model parameters and weights, training samples, prediction results and optimization intermediate quantities required for system operation. The memory 540 is also configured to store the traffic state features output by the feature extractor 520.

[0139] The signal control device 550 is configured to receive the optimal timing plan generated by the processor, so as to drive the traffic signal lights to switch according to the set timing. The signal control device can be selected from a traffic controller device, a traffic signal light, etc. There can be multiple signal control devices.

[0140] Figure 6 A structural block diagram of a traffic signal light control device based on multi-source heterogeneous data according to an embodiment of the present application is shown.

[0141] As shown in Figure 6 The traffic signal light control device 600 based on multi-source heterogeneous data according to the embodiment includes an acquisition module 610, an input module 620, an update module 630 and a control module 640.

[0142] The acquisition module 610 is configured to acquire historical traffic information of a plurality of intersections in a historical period, wherein the plurality of intersections include a current intersection and an upstream intersection of the current intersection. In an embodiment, the acquisition module 610 can be configured to perform the operation S210 described above, and details are not repeated here.

[0143] The input module 620 is configured to input the historical traffic information into a prediction model to obtain prediction traffic parameters of a plurality of vehicle flow phases of the current intersection in a future period and signal phase information of a plurality of traffic signal lights, wherein the plurality of vehicle flow phases represent directions in which vehicles can travel in the current intersection. In an embodiment, the input module 620 can be configured to perform the operation S220 described above, and details are not repeated here.

[0144] The update module 630 is configured to update a duration of a green signal in a traffic control model based on the prediction traffic parameters and the signal phase information until a queue length in the future period reaches a target value, to obtain a target green signal duration of the green signal and a target period duration of the future period, wherein the plurality of traffic signal lights include the green signal, the queue length represents a number of vehicles waiting to pass through the current intersection, and the traffic control model is constructed based on queue lengths and congestion densities of the plurality of vehicle flow phases in the future period. In an embodiment, the update module 630 can be configured to perform the operation S230 described above, and details are not repeated here.

[0145] The control module 640 is configured to control the plurality of traffic signal lights according to the target green light duration and the target cycle duration. In an embodiment, the control module 640 can be configured to perform the operation S240 described above, and details are not repeated here.

[0146] According to an embodiment of the present application, the predicted traffic parameters include a predicted arrival rate, a predicted saturated release rate and a predicted jam density, the predicted arrival rate representing a number of vehicles arriving at the current intersection within a preset time, and the signal phase information includes a signal phase sequence and a phase loss duration.

[0147] According to an embodiment of the present application, the history cycle includes a current cycle, the future cycle includes a next cycle of the current cycle, and the traffic control model is constructed based on: determining a shock wave speed based on the predicted arrival rate, the predicted saturated release rate and the predicted jam density of the next cycle; constructing a sub-model of the queue length of each of the plurality of traffic signal lights based on the shock wave speed, the queue length at the end of the current cycle and the duration of the green light signal, so as to determine the queue length of each of the plurality of traffic signal lights of the current intersection in the next cycle; determining a first target duration and a second target duration in the next cycle based on the signal phase sequence, the phase loss duration and the duration of the green light signal; constructing a sub-model of the jam density of the current intersection based on the first target duration, the second target duration and the queue length of each of the plurality of traffic signal lights in the next cycle, so as to determine the jam density of the current intersection in the next cycle; and constructing the traffic control model of the current intersection according to the sub-model of the queue length of each of the plurality of traffic signal lights and the sub-model of the jam density.

[0148] According to an embodiment of the present application, the signal phase sequence is a first red light phase, a green light phase, a yellow light phase and a second red light phase, and the signal phase information further comprises a first red light phase duration and a second red light phase duration; based on the shock wave speed, the queue length at the end of the current period and the duration of the green light signal, a sub-model of the queue length of each of the plurality of traffic signals in the next period is constructed, including: based on the shock wave speed and the first red light phase duration, the queue length of the first red light phase is determined, and based on the sum of the queue length at the end of the current period and the queue length of the first red light phase, a sub-model of the cumulative queue length of the first red light phase is constructed, so as to determine the cumulative queue length of the first red light phase of the current intersection in the next period; based on the predicted saturation release rate, the predicted jam density and the duration of the green light signal, the passing length of the green light phase is determined, and based on the sum of the cumulative queue length of the first red light phase and the passing length of the green light phase, a sub-model of the residual queue length of the green light phase is constructed, so as to determine the residual queue length of the green light phase of the current intersection in the next period; based on the shock wave speed and the second red light phase duration, the queue length of the second red light phase is determined, and based on the sum of the queue length of the second red light phase and the residual queue length of the green light phase, a sub-model of the cumulative queue length of the second red light phase is constructed, so as to determine the cumulative queue length of the second red light phase of the current intersection in the next period.

[0149] According to an embodiment of the present application, based on the signal phase sequence, the phase loss duration and the duration of the green light signal, the first target duration and the second target duration in the next period are determined, including: based on the signal phase sequence, the first red light phase duration, the duration of the green light signal, the yellow light phase duration and the second red light phase duration, the first target duration before the start of the green light phase and the second target duration after the end of the green light phase in the next period are determined, and the yellow light phase duration is the phase loss duration.

[0150] According to an embodiment of the present application, based on the first target duration, the second target duration and the queue length of each of the plurality of traffic signals in the next period, a sub-model of the jam density of the current intersection is constructed, including: based on the first target duration, the queue length at the end of the current period and the queue length of the first red light phase, a first jam parameter of the first red light phase is determined; based on the second target duration, the residual queue length of the green light phase and the queue length of the second red light phase, a second jam parameter of the second red light phase is determined; based on the first jam parameter, the second jam parameter and the predicted jam density, a sub-model of the jam density is constructed.

[0151] According to an embodiment of the present invention, the update module 630 includes an update submodule and a determination submodule. The update submodule is used to input predicted traffic parameters and signal phase information into the traffic control model, and based on the constraint that the congestion density in the traffic control model is less than or equal to the critical density, update the duration of the green light signal in the traffic control model until the cumulative queue length of the second red light phase in multiple consecutive preset cycles in the future cycle reaches the target value, thereby obtaining the target green light duration; the determination submodule is used to determine the target cycle duration based on the target green light duration, the phase loss duration, the duration of the first red light phase, and the duration of the second red light phase.

[0152] According to an embodiment of the present invention, the prediction model includes a forget gate, an input gate, an output gate, and a memory unit. The prediction model is trained in the following manner: traffic training information of multiple training intersections during the training period is input into the initial prediction model to obtain the initial prediction value of the current training intersection. The initial prediction value includes initial traffic parameters and initial signal phase information. The multiple training intersections include the current training intersection and its upstream training intersection. The model parameters of the initial prediction model are updated based on the error between the initial prediction value and the true value until the error meets a preset condition to obtain the prediction model. The true value includes the true traffic parameters and true signal phase information of the current training intersection.

[0153] According to an embodiment of the present invention, the model parameters include the weights and biases of the forget gate, input gate, output gate, and memory unit, respectively; the model parameters of the initial prediction model are updated based on the error between the initial predicted value and the true value until the error meets a preset condition to obtain the prediction model, including: determining the gradient of the t-th model parameter according to the t-th updated model parameter, the step size coefficient in the gradient descent algorithm, and the t-th error, where t is an integer greater than or equal to 1; updating the t-th model parameter according to the t-th model parameter, the gradient, and the step size coefficient to obtain the t+1-th updated model parameter.

[0154] According to an embodiment of the present invention, historical traffic information includes: historical driving speeds of vehicles passing through multiple intersections collected via inductive loop detectors, historical traffic flow at multiple intersections collected via vehicle-mounted locators, and historical queue lengths at multiple intersections collected via roadside cameras.

[0155] According to an embodiment of the present application, any of the modules of the obtaining module 610, the inputting module 620, the updating module 630 and the controlling module 640 can be combined in one module, or any of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of the modules can be combined with at least part of the functions of the other modules, and implemented in one module. According to an embodiment of the present application, at least one of the obtaining module 610, the inputting module 620, the updating module 630 and the controlling module 640 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system in package, an application specific integrated circuit (ASIC), or any other reasonable manner of integrating or packaging a circuit, etc. or implemented by hardware or firmware, or implemented in any one of software, hardware and firmware or in a proper combination of any of them. Alternatively, at least one of the obtaining module 610, the inputting module 620, the updating module 630 and the controlling module 640 can be at least partially implemented as a computer program module which, when executed, can perform the corresponding functions.

[0156] Figure 7 A block diagram of an electronic device suitable for implementing the traffic signal control method based on multi-source heterogeneous data according to an embodiment of the present application is shown.

[0157] As shown in Figure 7 The electronic device 700 according to an embodiment of the present application includes a processor 530 which can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 702 or loaded from a storage portion 708 into a random access memory (RAM) 703. The processor 530 can include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special purpose microprocessor (e.g., an application specific integrated circuit (ASIC)), etc. The processor 530 can also include an on-board memory for cache use. The processor 530 can include a single processing unit or multiple processing units for executing different actions of the method processes according to embodiments of the present application.

[0158] In the RAM 703, various programs and data required for the operation of the electronic device 700 are stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other via the bus 704. The processor 530 performs various operations of the method flow according to the embodiments of the present application by executing the programs in the ROM 702 and / or the RAM 703. It should be noted that the programs can also be stored in one or more memories other than the ROM 702 and the RAM 703. The processor 530 can also perform various operations of the method flow according to the embodiments of the present application by executing the programs stored in the one or more memories.

[0159] According to the embodiments of the present application, the electronic device 700 can further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device 700 can further include one or more of the following components connected to the input / output (I / O) interface 705: an input part 706 including a keyboard, a mouse, etc.; an output part 707 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage part 708 including a hard disk, etc.; and a communication part 709 including a network interface card such as a LAN card, a modem, etc. The communication part 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as necessary. A removable recording medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 710 as necessary, so that a computer program read out therefrom is installed in the storage part 708 as necessary.

[0160] The present application also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments; or can exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, when the one or more programs are executed, the method according to the embodiments of the present application is implemented.

[0161] According to an embodiment of the present application, the computer readable storage medium can be a non-transitory computer readable storage medium, for example, can include but not limited to: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present application, the computer readable storage medium can include one or more memories of the ROM 702 and / or the RAM 703 described above and / or one or more memories other than the ROM 702 and the RAM 703.

[0162] Embodiments of the present application also include a computer program product, which includes a computer program containing program codes for executing the method shown in the flow chart. When the computer program product is run in a computer system, the program codes are used to make the computer system implement the traffic signal control method based on multi-source heterogeneous data provided by the embodiments of the present application.

[0163] The above functions defined in the system / device of the embodiments of the present application are performed when the computer program is executed by the processor 530. According to an embodiment of the present application, the system, device, module, unit, etc. described above can be implemented by computer program modules.

[0164] In one embodiment, the computer program can rely on tangible storage media such as optical storage media, magnetic storage media, etc. In another embodiment, the computer program can also be transmitted, distributed, and downloaded in the form of signals on network media, and be downloaded and installed through the communication part 709, and / or installed from the detachable medium 711. The program codes contained in the computer program can be transmitted by any appropriate network media, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

[0165] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the detachable medium 711. When the computer program is executed by the processor 530, the above functions defined in the system of the embodiments of the present application are performed. According to an embodiment of the present application, the system, device, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0166] According to embodiments of the present application, program code for implementing the computer programs provided by embodiments of the present application can be written in any combination of one or more programming languages, and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. The programming language can include, but is not limited to, Java, C++, python, "C" language, or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the remote computing device, or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0167] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0168] Those skilled in the art will appreciate that the features recited in the various embodiments of the present application can be combined and / or integrated in a variety of ways, even if such combinations or integrations are not expressly noted in the present application. In particular, the features recited in the various embodiments of the present application can be combined and / or integrated in a variety of ways without departing from the spirit and scope of the present application. All such combinations and / or integrations are within the scope of the present application.

[0169] The embodiments of the present application described above are merely intended to illustrate the present application. These embodiments are merely for illustrative purposes, and are not intended to limit the scope of the present application. Although the above describes each embodiment separately, this does not mean that the measures in each embodiment cannot be used advantageously in combination. Numerous alternatives and modifications of embodiments of the present application can be made by those skilled in the art without departing from the scope of the present application, and all such alternatives and modifications are to be included within the scope of the present application.

Claims

1. A traffic signal control method based on multi-source heterogeneous data, characterized in that, The method includes: Obtain historical traffic information for multiple intersections within a historical period, wherein the multiple intersections include the current intersection and the upstream intersection of the current intersection; The historical traffic information is input into the prediction model to obtain the predicted traffic parameters of each of the multiple traffic flow phases at the current intersection in the future cycle and the signal phase information of multiple traffic lights, wherein the multiple traffic flow phases represent the directions in which vehicles can travel at the current intersection. The duration of the green light signal in the traffic control model is updated based on the predicted traffic parameters and the signal phase information until the queue length in the future cycle reaches the target value, thereby obtaining the target green light duration and the target cycle duration of the future cycle. The various traffic lights include green lights, the queue length represents the number of vehicles waiting to pass through the current intersection, and the traffic control model is constructed based on the queue length and congestion density of the various traffic lights in the future cycle for each of the various traffic flow phases. The various traffic lights are controlled according to the target green light duration and the target cycle duration.

2. The method according to claim 1, characterized in that, The predicted traffic parameters include predicted arrival rate, predicted saturation release rate, and predicted congestion density. The predicted arrival rate represents the number of vehicles approaching the current intersection within a preset time. The signal phase information includes signal phase sequence and phase loss duration.

3. The method according to claim 2, characterized in that, The historical period includes the current period, and the future period includes the period following the current period. The traffic control model is constructed based on the following: The shock wave velocity is determined based on the predicted arrival rate, the predicted saturation release rate, and the predicted congestion density for the next cycle. Based on the shock wave velocity, the queue length at the end of the current cycle, and the duration of the green light signal, a sub-model of the queue length of each of the various traffic lights is constructed to determine the queue length of each of the various traffic lights at the current intersection in the next cycle. Based on the signal phase sequence, the phase loss duration, and the duration of the green light signal, the first target duration and the second target duration in the next cycle are determined. Based on the first target duration, the second target duration, and the queue lengths of the various traffic lights in the next cycle, a sub-model of the congestion density of the current intersection is constructed to determine the congestion density of the current intersection in the next cycle. Based on the sub-models of the queue lengths of the various traffic lights and the sub-model of the congestion density, the traffic control model of the current intersection is constructed.

4. The method according to claim 3, characterized in that, The signal phase sequence is the first red light phase, the green light phase, the yellow light phase, and the second red light phase. The signal phase information also includes the duration of the first red light phase and the duration of the second red light phase. The sub-models for constructing the queue lengths of the various traffic lights, based on the shock wave velocity, the queue length at the end of the current cycle, and the duration of the green light signal, include: Based on the shock wave velocity and the duration of the first red light phase, the queue length of the first red light phase is determined, and a sub-model of the cumulative queue length of the first red light phase is constructed according to the sum of the queue length of the first red light phase and the queue length at the end of the current cycle, so as to determine the cumulative queue length of the first red light phase of the current intersection in the next cycle. Based on the predicted saturation release rate, the predicted congestion density, and the duration of the green light signal, the passage length of the green light phase is determined, and a sub-model of the remaining queue length of the green light phase is constructed according to the cumulative queue length of the first red light phase and the passage length of the green light phase, so as to determine the remaining queue length of the green light phase of the current intersection in the next cycle. Based on the shock wave velocity and the duration of the second red light phase, the queue length of the second red light phase is determined, and a sub-model of the cumulative queue length of the second red light phase is constructed according to the sum of the queue length of the second red light phase and the remaining queue length of the green light phase, so as to determine the cumulative queue length of the second red light phase of the current intersection in the next cycle.

5. The method according to claim 4, characterized in that, The step of determining the first target duration and the second target duration in the next cycle based on the signal phase sequence, the phase loss duration, and the duration of the green light signal includes: Based on the signal phase sequence, the duration of the first red light phase, the duration of the green light signal, the duration of the yellow light phase, and the duration of the second red light phase, the first target duration before the start of the green light phase and the second target duration after the end of the green light phase are determined in the next cycle, and the duration of the yellow light phase is the phase loss duration.

6. The method according to claim 4, characterized in that, The sub-model for constructing the congestion density of the current intersection based on the first target duration, the second target duration, and the queue lengths of the various traffic lights in the next cycle includes: Based on the first target duration, the queue length at the end of the current cycle, and the queue length of the first red light phase, the first congestion parameter of the first red light phase is determined; Based on the second target duration, the remaining queue length of the green light phase, and the queue length of the second red light phase, the second congestion parameter of the second red light phase is determined. Based on the first congestion parameter, the second congestion parameter, and the predicted congestion density, a sub-model of the congestion density is constructed.

7. The method according to any one of claims 4 to 6, characterized in that, The process of updating the green light signal duration in the traffic control model based on the predicted traffic parameters and the signal phase information until the queue length in the future cycle reaches the target value, thereby obtaining the target green light duration and the target cycle duration of the future cycle, includes: The predicted traffic parameters and the signal phase information are input into the traffic control model. Based on the constraint that the congestion density in the traffic control model is less than or equal to the critical density, the duration of the green light signal in the traffic control model is updated until the cumulative queue length of the second red light phase in multiple consecutive preset cycles in the future cycle reaches the target value, and the target green light duration is obtained. The target cycle duration is determined based on the target green light duration, the phase loss duration, the first red light phase duration, and the second red light phase duration.

8. The method according to claim 1, characterized in that, The prediction model includes a forget gate, an input gate, an output gate, and a memory unit, and is trained in the following manner: Traffic training information from multiple training intersections during the training period is input into the initial prediction model to obtain the initial prediction value of the current training intersection. The initial prediction value includes initial traffic parameters and initial signal phase information. The multiple training intersections include the current training intersection and the upstream training intersection of the current training intersection. The model parameters of the initial prediction model are updated based on the error between the initial predicted value and the actual value until the error meets a preset condition, thereby obtaining the prediction model. The actual value includes the actual traffic parameters and actual signal phase information of the current training intersection.

9. The method according to claim 8, characterized in that, The model parameters include the weights and biases of the forget gate, the input gate, the output gate, and the memory unit, respectively. The step of updating the model parameters of the initial prediction model based on the error between the initial predicted value and the true value until the error meets a preset condition, thereby obtaining the prediction model, includes: The gradient of the t-th model parameter is determined based on the t-th updated model parameter, the step size coefficient in the gradient descent algorithm, and the t-th error, where t is an integer greater than or equal to 1; The t-th model parameters are updated based on the t-th model parameters, the gradient, and the step size coefficient to obtain the (t+1)-th updated model parameters.

10. The method according to claim 1, characterized in that, The historical traffic information includes: the historical driving speed of vehicles passing through the multiple intersections collected by inductive loop detectors, the historical traffic flow of the multiple intersections collected by vehicle locators, and the historical queue length of the multiple intersections collected by roadside cameras.

Images