Intelligent road system based on traffic flow dynamic change and illumination adjustment method

Abstract

The invention discloses an intelligent road system and an illumination adjustment method based on traffic flow dynamic change, and the system comprises a first analysis module which is used for obtaining dynamic data of a target road region, generating real-time traffic flow characteristic parameters, building a first illumination adjustment model based on the real-time traffic flow characteristic parameters, and obtaining a dynamic illumination prediction value; the second analysis module is used for acquiring static data of a target road area, generating road basic characteristic parameters, and constructing a second illumination adjustment model based on the road basic characteristic parameters to obtain a reference illumination predicted value; and the fusion module is used for fusing the dynamic illumination predicted value and the reference illumination predicted value, generating a comprehensive illumination control value and driving a street lamp controller to execute brightness adjustment operation. Illumination can be adjusted in time according to real-time traffic changes, the brightness is dynamically adjusted according to actual requirements, energy consumption waste is avoided, and intelligentization and reliability of the system are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent traffic control, and particularly to a smart road system and a lighting adjustment method based on dynamic changes in vehicle flow. Background Art

[0002] With the rapid development of smart cities and intelligent transportation systems, road lighting control technology has gradually evolved from traditional time-based control to dynamic perception and adaptive adjustment. Existing technologies mostly focus on data-driven in a single dimension and lack collaborative modeling of dynamic traffic scenarios and static infrastructure characteristics. At the system architecture level, the mainstream solutions still adopt a simplified control logic of "dynamic prediction + fixed threshold", which is difficult to cope with the non-linear impact of complex traffic events (such as accidents and extreme weather) on lighting requirements and has limitations in safety assurance.

[0003] Most systems only rely on vehicle flow or time series data and fail to integrate multi-modal features such as vehicle speed, resulting in insufficient environmental adaptability and generally lacking a response mechanism for abnormal events. Summary of the Invention

[0004] In view of the problems existing in the existing smart road system and lighting adjustment method based on dynamic changes in vehicle flow, the present invention is proposed. Therefore, the problem to be solved by the present invention is how to provide a smart road system and a lighting adjustment method and system based on dynamic changes in vehicle flow.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a smart road system based on dynamic changes in vehicle flow, which includes a first analysis module for obtaining dynamic data of a target road area, generating real-time vehicle flow characteristic parameters, constructing a first lighting adjustment model based on the real-time vehicle flow characteristic parameters, and obtaining a dynamic lighting prediction value;

[0007] The first lighting adjustment model extracts spatial features of real-time vehicle flow based on a convolutional neural network CNN and outputs a preliminary brightness prediction value;

[0008] The preliminary brightness prediction value is corrected for visibility according to the ratio of the weather visibility to the reference visibility threshold to obtain a corrected brightness prediction value;

[0009] A vehicle speed influence factor is introduced, and a dynamic weight coefficient is generated in combination with a traffic accident sign to dynamically adjust the corrected brightness prediction value to obtain a dynamic lighting prediction value;

[0010] A second analysis module for obtaining static data of the target road area, generating road basic characteristic parameters, constructing a second lighting adjustment model based on the road basic characteristic parameters, and obtaining a reference lighting prediction value;

[0011] The second lighting adjustment model calculates the basic lighting requirements based on the total road length and the number of lanes in the target road area;

[0012] The basic lighting requirements are corrected according to the street lamp distribution density and the rated power of a single lamp in the target road area to generate corrected reference lighting requirements;

[0013] The lane type weight is introduced to the corrected reference lighting requirements to generate a reference lighting prediction value;

[0014] The fusion module is used to fuse the dynamic lighting prediction value and the reference lighting prediction value to generate a comprehensive lighting control value, and drive the street lamp controller to perform the brightness adjustment operation.

[0015] As a preferred solution of the intelligent road system based on the dynamic changes of vehicle flow according to the present invention, wherein: the dynamic data includes the real-time vehicle flow, the average vehicle speed, the weather visibility, and the traffic accident signs in the target road area; the static data includes the total road length, the number of lanes, the street lamp distribution density, the rated power of a single lamp, and the reference visibility threshold.

[0016] As a preferred solution of the intelligent road system based on the dynamic changes of vehicle flow according to the present invention, wherein: the first lighting adjustment model is used to output the dynamic lighting prediction value of the target road area; the preliminary brightness prediction value is represented by the following formula:

[0017]

[0018] Wherein, is the preliminary brightness prediction value, σ is the Sigmoid activation function, Q t-k is the real-time vehicle flow at the tk moment in the target road area, K represents the length of the time window, that is, the number of historical vehicle flow data points used to calculate the brightness prediction at the current moment; k is the summation index variable, representing the traversal from the 1st to the Kth historical time point, w k is the CNN convolution kernel weight, and b is the bias term;

[0019] The corrected brightness prediction value is represented by the following formula:

[0020]

[0021] In the formula, is the corrected brightness prediction value, W t is the weather visibility at the t moment in the target road area, W ref is the reference visibility threshold in the target road area;

[0022] The dynamic lighting prediction value is represented by the following formula:

[0023]

[0024] In the formula, is the dynamic lighting prediction value, and β t is the dynamic lighting weight coefficient, and A t is the traffic accident sign at time t in the target road area, and α v is the vehicle speed influence factor, and V t is the average vehicle speed at time t in the target road area, and V max is the maximum allowable vehicle speed in the target road area.

[0025] As a preferred solution of the intelligent road system based on vehicle flow dynamic changes according to the present invention, wherein: the second lighting adjustment model is used to output the reference lighting prediction value of the target road area;

[0026] The basic lighting requirement is expressed by the following formula:

[0027]

[0028] wherein, I 1 is the basic lighting requirement, L is the total length of the road in the target road area, N is the number of lanes in the target road area, and P max is the rated power of a single lamp;

[0029] The corrected reference lighting requirement is expressed by the following formula:

[0030]

[0031] wherein, I 2 is the corrected reference lighting requirement, ρ is the street lamp distribution density, and ρ opt is the optimal distribution density;

[0032] The reference lighting prediction value is expressed by the following formula:

[0033]

[0034] E t = E e + E n

[0035] γ e + γ n = 1

[0036] wherein, I base is the reference lighting prediction value, γ e is the emergency lane weight, γ n is the normal lane weight, E t is the historical lighting energy consumption of all lanes, and E e is the historical lighting energy consumption of the emergency lanen is the historical lighting energy consumption of the ordinary lane.

[0037] As a preferred solution of the intelligent road system based on vehicle dynamic changes according to the present invention, when fusing the dynamic lighting prediction value and the reference lighting prediction value, an adaptive weight allocation strategy is adopted, specifically:

[0038] Generate a dynamic fusion weight according to the ratio of the real-time traffic volume to the historical peak traffic volume, so as to calculate the comprehensive lighting control value. The calculation formula is:

[0039]

[0040] where ∈ is a tiny constant to prevent the denominator from being zero; Q t is the real-time traffic volume, Q p is the historical peak traffic volume, I f is the comprehensive lighting control value, η t is the fusion weight.

[0041] As a preferred solution of the intelligent road system based on vehicle dynamic changes according to the present invention, the brightness adjustment operation includes:

[0042] Dynamically adjust the lighting response threshold according to the real-time traffic index. The formula is:

[0043]

[0044] where Q t is the real-time traffic volume at time t in the target road area, V t is the average vehicle speed at time t in the target road area, I p is the lighting response threshold, T i is the real-time traffic index, T r is the reference traffic index;

[0045] Preset the maximum brightness threshold I max and the minimum brightness threshold I min ;

[0046] The system monitors the comprehensive lighting control value in real time. When the comprehensive lighting control value exceeds the lighting response threshold, trigger the lighting response and perform the brightness adjustment operation in the target road area;

[0047] If the duration for which the comprehensive lighting control value exceeds the preset maximum brightness threshold is greater than 10 seconds, immediately adjust the street lamp brightness to the maximum brightness;

[0048] If the duration is less than 10 seconds, gradually increase the brightness to the maximum brightness at a rate of 10% per second;

[0049] When the comprehensive lighting control value is lower than the preset minimum brightness threshold, the low-brightness maintenance mode is activated, and the lighting brightness is directly locked at the minimum brightness and maintained.

[0050] Set the safety visibility threshold according to the meteorological department's standards. When the real-time visibility is lower than the safety visibility threshold, trigger the emergency lighting protocol, immediately interrupt the current brightness control logic, force all street lights to switch to the maximum brightness mode, synchronously activate the stroboscopic warning function, and push the road conditions information to the navigation platform.

[0051] In a second aspect, the present invention provides a smart road lighting adjustment method based on dynamic traffic changes, which includes: obtaining the dynamic data of the target road area, generating real-time traffic flow characteristic parameters, constructing a first lighting adjustment model based on the real-time traffic flow characteristic parameters, and obtaining a dynamic lighting prediction value.

[0052] Obtain the static data of the target road area, generate road basic characteristic parameters, construct a second lighting adjustment model based on the road basic characteristic parameters, and obtain a reference lighting prediction value.

[0053] Fuse the dynamic lighting prediction value and the reference lighting prediction value to generate a comprehensive lighting control value, and drive the street light controller to perform a brightness adjustment operation.

[0054] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the processor executes the computer program, it implements the steps of the smart road lighting adjustment method based on dynamic traffic changes.

[0055] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by a processor, it implements the steps of the smart road lighting adjustment method based on dynamic traffic changes.

[0056] The beneficial effects of the present invention are as follows: it can adjust the lighting in a timely manner according to real-time traffic changes, ensure sufficient light is provided at critical moments, dynamically adjust the brightness according to actual needs, avoid unnecessary energy consumption waste, realize the intelligence and reliability of the system, and can not only meet the basic lighting requirements but also take into account traffic fluctuations, with strong adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0058] Figure 1It is a structural diagram of a smart road system based on dynamic changes in vehicle flow. Specific implementation manners

[0059] To make the above objects, features, and advantages of the present invention more understandable, the following will describe the specific implementation manners of the present invention in detail with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0060] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0061] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is separate or selectively mutually exclusive with other embodiments.

[0062] Refer to Figure 1 , which is the first embodiment of the present invention. This embodiment provides a smart road system based on dynamic changes in vehicle flow, including:

[0063] A first analysis module for obtaining dynamic data of a target road area, generating real-time traffic flow characteristic parameters, constructing a first lighting adjustment model based on the real-time traffic flow characteristic parameters, and obtaining a dynamic lighting prediction value;

[0064] Divide the real-time traffic flow data of the target road area into historical window data with a length of K according to the time series to form an input matrix [Q t-k , Q t-k+1 , …, Q t-1 ;

[0065] Perform spatial feature extraction on the input matrix through a pre-trained convolutional neural network (CNN). The CNN includes a convolutional layer, a pooling layer, and a fully connected layer, and outputs a hidden feature vector;

[0066] Input the hidden feature vector into the Sigmoid activation function for normalization to generate a preliminary brightness prediction value reflecting the basic demand of the spatio-temporal distribution of traffic flow for brightness. The preliminary brightness prediction value is represented by the following formula:

[0067]

[0068] Among them, is the preliminary brightness prediction value, σ is the Sigmoid activation function, and Q t-k is the real-time traffic flow at time tk in the target road area, K represents the length of the time window, that is, the number of historical traffic flow data points used to calculate the brightness prediction at the current moment; k is the summation index variable, indicating the traversal from the 1st to the Kth historical time point, and w k is the weight of the CNN convolution kernel, and b is the bias term;

[0069] Obtain the real-time weather visibility data W t , and compare it with the preset reference visibility threshold W ref to calculate the corrected brightness prediction value Realize the brightness adjustment based on visibility adaption. The corrected brightness prediction value is expressed by the following formula:

[0070]

[0071] In the formula, is the corrected brightness prediction value, W t is the weather visibility at time t in the target road area, and W ref is the reference visibility threshold of the target road area;

[0072] According to the ratio of the real-time average vehicle speed V t to the maximum allowable vehicle speed V max of the road, calculate the vehicle speed impact factor α v , and the formula is:

[0073]

[0074] If the traffic accident sign A t = 1 (indicating an accident exists), then set the dynamic weight coefficient β t = 1.5 to enhance the lighting; otherwise, β t = α v , so that the weight decreases when the vehicle speed decreases;

[0075] Optimize the corrected brightness prediction value according to the dynamic weight coefficient to obtain the dynamic lighting prediction value Complete the responsive adjustment to abnormal events and vehicle speed changes. The formula for the dynamic lighting prediction value is:

[0076]

[0077] In the formula, is the dynamic lighting prediction value, β t is the dynamic weight coefficient, A t is the traffic accident sign at time t in the target road area, and α vis the vehicle speed impact factor, V t is the average vehicle speed at time t in the target road area, V max is the maximum allowable vehicle speed in the target road area;

[0078] The second analysis module is used to obtain the static data of the target road area, generate road basic characteristic parameters, construct a second lighting adjustment model based on the road basic characteristic parameters, and obtain a reference lighting prediction value;

[0079] The implementation process of the second lighting adjustment model includes the following steps:

[0080] Obtain the total road length L and the number of lanes N of the target road area, combine the two according to the proportional relationship, calculate the basic lighting demand, and generate the basic lighting demand I 1 , which is expressed by the following formula:

[0081]

[0082] where, I 1 is the basic lighting demand, L is the total road length of the target road area, in km, N is the number of lanes of the target road area, P max is the rated power of a single lamp;

[0083] Based on the difference between the street lamp distribution density (the number of street lamps per unit length) and the preset optimal distribution density, adjust the basic lighting demand, perform energy efficiency optimization and correction, which is expressed by the following formula:

[0084]

[0085] where, I 2 is the corrected reference lighting demand, ρ is the street lamp distribution density, ρ opt is the optimal distribution density, I base is the reference lighting prediction value;

[0086] If the actual distribution density ρ of the street lamps in the target road area is higher than the preset optimal distribution density ρ opt , it indicates that the street lamps are over-distributed, and the redundant energy consumption is reduced by reducing the demand value; if the actual distribution density ρ of the street lamps in the target road area is lower than the preset optimal distribution density ρ opt , then appropriately increase the demand value to make up for the insufficient coverage; combine the rated power of a single lamp, incorporate the power constraint into the correction process, and ensure that the corrected reference lighting demand meets the actual power supply capacity limit.

[0087] According to the lane types (such as emergency lanes, ordinary lanes) in the target road area, respectively count their historical lighting energy consumption ratios;

[0088] Assign weight coefficients to different lane types. The weight values are set based on the importance of lane functions and energy consumption characteristics. Integrate the corrected baseline lighting demand with the lane type weights to generate the final baseline lighting prediction value I base , which is used to reflect the differential impact of lane types on the overall lighting demand, and is expressed by the following formula:

[0089]

[0090] E t = E e + E n

[0091] γ e + γ n = 1

[0092] Among them, I base is the baseline lighting prediction value, γ e is the emergency lane weight, γ n is the normal lane weight, E t is the historical lighting energy consumption of all lanes, E e is the historical lighting energy consumption of the emergency lane, E n is the historical lighting energy consumption of the normal lane;

[0093] The fusion module is used to fuse the dynamic lighting prediction value and the baseline lighting prediction value to generate a comprehensive lighting control value and drive the street lamp controller to perform the brightness adjustment operation.

[0094] When fusing the dynamic lighting prediction value and the baseline lighting prediction value, an adaptive weight allocation strategy is adopted. The implementation process of the adaptive weight allocation strategy includes the following steps:

[0095] Obtain the real-time traffic flow and historical peak data. Collect the current traffic flow data of the target road area in real time, and retrieve the historical peak traffic flow (the highest traffic flow record in the past 30 days) of this area through the historical database;

[0096] Calculate the ratio of the real-time traffic flow to the historical peak traffic flow. To prevent the denominator from being zero, a small constant is introduced into the denominator to generate the fusion weight;

[0097] Multiply the fusion weight by the dynamic lighting prediction value to obtain the contribution value of the dynamic part, and multiply the remaining weight by the baseline lighting prediction value to obtain the contribution value of the baseline part;

[0098] Sum the two contribution values to generate a comprehensive lighting control value and complete the coordinated control of the lighting control signal,

[0099]

[0100] Among them, I fis the comprehensive lighting control value, and ∈ is a tiny constant to prevent the denominator from being zero; Q t is the real-time traffic flow, and Q p is the historical peak traffic flow, and η t is the fusion weight;

[0101] Dynamically adjust the lighting response threshold according to the real-time traffic index:

[0102]

[0103] where Q t is the real-time traffic flow at time t in the target road area, V t is the average vehicle speed at time t in the target road area, I p is the lighting response threshold, T i is the real-time traffic index, T r is the reference traffic index, which is set according to historical data.

[0104] The preset maximum brightness threshold I max is set according to the road grade, lighting standard and historical accident data;

[0105] The system monitors the comprehensive lighting control value I f in real time. When the comprehensive lighting control value I f exceeds the lighting response threshold I p , trigger the lighting response;

[0106] If the comprehensive lighting control value I f exceeds the preset maximum brightness threshold I max for more than 10 seconds, immediately adjust the street lamp brightness to the maximum brightness;

[0107] If the duration is less than 10 seconds, start the gradual adjustment algorithm to gradually increase the brightness to the maximum brightness threshold I max at a rate of 10% per second.

[0108] The preset minimum brightness threshold I min is set based on the energy-saving goal to ensure basic visibility;

[0109] When the comprehensive lighting control value I f is lower than the preset minimum brightness threshold I min , start the low-brightness maintenance mode and directly lock the lighting brightness at the minimum brightness.

[0110] The safety visibility threshold W safe is set according to the meteorological department's standard. When the real-time visibility W t is lower than the safety threshold W safe, triggering the emergency lighting protocol, immediately interrupting the current brightness control logic, forcing all street lights to switch to maximum brightness mode, synchronously starting the strobe alarm function to enhance the warning effect, and pushing traffic information to the navigation platform.

[0111] Sensor fault detection: If the visibility sensor has no data update for 3 consecutive minutes or the value is out of the reasonable range, it is judged as a fault. During the fault period, the visibility forced response module is suspended and the historical visibility data W is used by default. h Replace and mark abnormal status.

[0112] When rules conflict (such as forcing maximum brightness and energy-saving mode), they are executed according to the following priority: visibility safety > over-limit response > low-limit energy saving;

[0113] When the mandatory mode is triggered, an alarm message including the location, triggering reason and duration is sent to the traffic management center.

[0114] Furthermore, the present embodiment also provides an intelligent road lighting adjustment method based on dynamic changes in traffic flow, including: obtaining dynamic data of the target road area, generating real-time traffic flow characteristic parameters, constructing a first lighting adjustment model based on the real-time traffic flow characteristic parameters, and obtaining a dynamic lighting prediction value; obtaining static data of the target road area, generating basic road characteristic parameters, constructing a second lighting adjustment model based on the basic road characteristic parameters, and obtaining a benchmark lighting prediction value; fusing the dynamic lighting prediction value with the benchmark lighting prediction value to generate a comprehensive lighting control value, and driving the street lamp controller to perform a brightness adjustment operation.

[0115] This embodiment also provides a computer device, which is applicable to the case of a smart road system and a lighting adjustment method based on dynamic changes in traffic flow, and includes: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement all or part of the steps of the method described in the embodiment of the present invention as proposed in the above embodiment.

[0116] This embodiment also provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the method in any optional implementation manner of the above embodiment. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (abbreviated as SRAM), electrically erasable programmable read-only memory (abbreviated as EEPROM), erasable programmable read-only memory (abbreviated as EPROM), programmable read-only memory (abbreviated as PROM), read-only memory (abbreviated as ROM), magnetic memory, flash memory, a magnetic disk or an optical disc.

[0117] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. For technical details not described in detail in this embodiment, reference can be made to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0118] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. Intelligent road system based on dynamic changes of traffic flow, characterized by: include, A first analysis module is used to obtain dynamic data of a target road area, generate real-time traffic flow characteristic parameters, build a first lighting adjustment model based on the real-time traffic flow characteristic parameters, and obtain a dynamic lighting prediction value; The first lighting adjustment model extracts spatial features of real-time vehicle flow based on a convolutional neural network (CNN) and outputs a preliminary brightness prediction value; According to the ratio of weather visibility to the reference visibility threshold, the preliminary brightness forecast value is corrected for visibility to obtain a corrected brightness forecast value; The vehicle speed influencing factor is introduced, and the dynamic weight coefficient is generated in combination with the traffic accident sign, and the corrected brightness prediction value is dynamically adjusted to obtain the dynamic lighting prediction value; A second analysis module is used to obtain static data of the target road area, generate basic road characteristic parameters, construct a second lighting adjustment model based on the basic road characteristic parameters, and obtain a reference lighting prediction value; The second lighting adjustment model calculates the basic lighting demand based on the total road length and the number of lanes in the target road area; The basic lighting demand is corrected according to the street lamp distribution density and the rated power of a single lamp in the target road area to generate a corrected benchmark lighting demand; Introduce lane type weights to modify benchmark lighting requirements and generate benchmark lighting prediction values; The fusion module is used to fuse the dynamic lighting prediction value with the reference lighting prediction value to generate a comprehensive lighting control value and drive the street lamp controller to perform brightness adjustment operations.

2. The intelligent road system based on dynamic changes of traffic flow as claimed in claim 1, characterized in that: The dynamic data includes the real-time traffic volume, average vehicle speed, weather visibility, and traffic accident signs in the target road area; the static data includes the total length of the road, the number of lanes, the street light distribution density, the rated power of a single lamp, and the benchmark visibility threshold.

3. The intelligent road system based on dynamic changes of traffic flow as claimed in claim 2, characterized in that: The first lighting adjustment model is used to output a dynamic lighting prediction value of the target road area; the preliminary brightness prediction value is expressed by the following formula: in, is the initial brightness prediction value, σ is the Sigmoid activation function, Q t-k is the real-time traffic flow in the target road area at time tk, K represents the length of the time window, that is, the number of historical traffic flow data points used to calculate the brightness prediction at the current time; k is the summation index variable, indicating the traversal from the 1st to the Kth historical time point, w k is the CNN convolution kernel weight, b is the bias term; The modified brightness prediction value is expressed by the following formula: In the formula, To correct the brightness prediction value, W t is the weather visibility of the target road area at time t, W ref is the benchmark visibility threshold of the target road area; The dynamic lighting prediction value is expressed by the following formula: In the formula, is the dynamic lighting prediction value, β t is the dynamic lighting weight coefficient, A t is the traffic accident sign of the target road area at time t, α v is the vehicle speed influencing factor, V t is the average vehicle speed in the target road area at time t, V max is the maximum allowed speed in the target road area.

4. The intelligent road system based on dynamic changes of traffic flow as claimed in claim 3, characterized in that: The second lighting adjustment model is used to output a reference lighting prediction value for a target road area; The basic lighting requirement is expressed by the following formula: Among them, I1 is the basic lighting demand, L is the total length of the target road area, N is the number of lanes in the target road area, P max Rated power of a single lamp; The modified baseline lighting requirement is expressed by the following formula: Where I2 is the modified baseline lighting demand, ρ is the street lamp distribution density, and ρ opt is the optimal distribution density; The reference lighting prediction value is expressed by the following formula: AND t =And e +E n c e +g n =1 Among them, I base is the baseline lighting prediction value, γ e is the emergency lane weight, γ n is the weight of the common lane, E t is the historical lighting energy consumption of all lanes, E e is the historical lighting energy consumption of the emergency lane, E n Historical lighting energy consumption for common lanes.

5. The intelligent road system based on dynamic changes of traffic flow as claimed in claim 4, characterized in that: When fusing the dynamic lighting prediction value with the reference lighting prediction value, an adaptive weight allocation strategy is adopted, specifically: The dynamic fusion weight is generated according to the ratio of real-time traffic flow to historical peak traffic flow, so as to calculate the comprehensive lighting control value. The calculation formula is: Among them, ∈ is a small constant to prevent the denominator from being zero; Q t is the real-time traffic flow, Q p is the historical peak traffic volume, I f is the comprehensive lighting control value, η t is the fusion weight.

6. The intelligent road system based on dynamic changes of traffic flow as claimed in claim 5, characterized in that: The brightness adjustment operation includes: The lighting response threshold is dynamically adjusted according to the real-time traffic index. The formula is: Among them, Q t is the real-time traffic flow in the target road area at time t, V t is the average vehicle speed in the target road area at time t, I p is the lighting response threshold, T i is the real-time traffic index, T r For reference traffic index; Preset maximum brightness threshold I max and minimum brightness threshold I min ; The system monitors the comprehensive lighting control value in real time. When the comprehensive lighting control value exceeds the lighting response threshold, the lighting response is triggered to adjust the brightness of the target road area. If the duration of the integrated lighting control value exceeding the preset maximum brightness threshold is greater than 10 seconds, the street light brightness is immediately adjusted to the maximum brightness; If the duration is less than 10 seconds, gradually increase the brightness to the maximum brightness at a rate of 10% per second; When the comprehensive lighting control value is lower than the preset minimum brightness threshold, the low brightness maintenance mode is activated to directly lock the lighting brightness to the minimum brightness and maintain it; The safety visibility threshold is set according to the standards of the meteorological department. When the real-time visibility is lower than the safety visibility threshold, the emergency lighting protocol is triggered, the current brightness control logic is immediately interrupted, all street lights are forced to switch to the maximum brightness mode, the strobe alarm function is started synchronously, and the road condition information is pushed to the navigation platform.

7. A method for adjusting intelligent road lighting based on dynamic changes in traffic flow, based on the intelligent road system based on dynamic changes in traffic flow as claimed in any one of claims 1 to 6, characterized in that: include, Acquire dynamic data of a target road area, generate real-time traffic flow characteristic parameters, construct a first lighting adjustment model based on the real-time traffic flow characteristic parameters, and obtain a dynamic lighting prediction value; Obtaining static data of a target road area, generating basic road characteristic parameters, constructing a second lighting adjustment model based on the basic road characteristic parameters, and obtaining a reference lighting prediction value; The dynamic lighting prediction value and the reference lighting prediction value are integrated to generate a comprehensive lighting control value, and the street lamp controller is driven to perform a brightness adjustment operation.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent road lighting adjustment method based on dynamic changes in traffic flow as described in claim 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the intelligent road lighting adjustment method based on dynamic changes in traffic flow as described in claim 7 are implemented.

Images