A Brightness Intelligent Control Method Based on Photovoltaic Street Lights

Abstract

The present invention discloses a brightness intelligent control method based on photovoltaic street lamps, which belongs to the technical field of street lamp control, and specifically comprises: obtaining the ambient light illumination and road vehicle flow of the road section in real time, if there is the first time that the ambient light illumination is less than or equal to a preset threshold value, inputting the current ambient light illumination and road vehicle flow into a pre-dimming network model, and obtaining the initial brightness of the street lamp of the road section when it is turned on; presetting an observation period H, obtaining the road information of the road section within the observation period in real time, and calculating the road resistance coefficient of the road section within any monitoring period, generating a curve Y(t) of the change of the road resistance coefficient over time, calculating the change coefficient K, determining the road vehicle flow according to the change coefficient, and adjusting the brightness of the road lamp according to the road vehicle flow and the ambient light illumination. The present invention avoids frequent changes in the dimming level of the street lamp brightness, reduces energy waste, and avoids the problem of glare or visual discomfort.

Description

Technical Field

[0001] The present invention relates to the technical field of street lamp control, and in particular to a brightness intelligent control method based on photovoltaic street lamps. Background Art

[0002] Photovoltaic street lights are mainly composed of solar cell modules, controllers, batteries, LED light sources, lamp poles and lamp housings. Among them, the solar cell module is the core part, which converts solar energy into electrical energy; the controller is responsible for controlling the charging and discharging of the battery to protect the battery from overcharging and over-discharging; the battery is used to store the electrical energy converted by the solar panel during the day so as to supply power at night; the LED light source is a light source with the characteristics of high efficiency and energy saving. During the day, the solar panel absorbs sunlight and converts it into electrical energy, which is stored in the battery through the controller. At night, when the light intensity drops to a certain level, the controller will automatically detect and issue instructions to enable the battery to start supplying power to the LED light source, thereby realizing the lighting function. Photovoltaic street lights do not require laying cables, AC power supply, and electricity bills. They have the characteristics of good stability, long life, and high luminous efficiency.

[0003] At present, the existing technology implements the strategy of "lights on when cars come" street lamp dimming according to real-time traffic flow. By monitoring the traffic flow in real time, the light brightness can be adjusted to the lowest level when there are no vehicles passing, thereby greatly reducing energy consumption. However, when the traffic flow is stable and high, the street lamps are dimmed according to this strategy due to changes in real-time traffic flow, which will cause the dimming level of the street lamps to change frequently, wasting energy. At the same time, the driver may find it difficult to adapt to the rapid changes in brightness in a short period of time, causing glare or visual discomfort, leading to certain safety hazards. Summary of the invention

[0004] The purpose of the present invention is to provide a method for intelligently controlling the brightness of photovoltaic street lamps to solve the following technical problems:

[0005] At present, the existing technology implements the strategy of "lights on when cars come" street lamp dimming according to real-time traffic flow. By monitoring the traffic flow in real time, the light brightness can be adjusted to the lowest level when there are no vehicles passing, thereby greatly reducing energy consumption. However, when the traffic flow is stable and high, the street lamps are dimmed according to this strategy due to changes in real-time traffic flow, which will cause the dimming level of the street lamps to change frequently, wasting energy. At the same time, the driver may find it difficult to adapt to the rapid changes in brightness in a short period of time, causing glare or visual discomfort, leading to certain safety hazards.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A method for intelligently controlling brightness of a photovoltaic street lamp, characterized in that it comprises the following steps:

[0008] S1, select a target road and obtain all the road intersections of the target road, and divide the target road into several road segments with adjacent intersections as dividing points; select any road segment and obtain the ambient light illumination and road traffic volume of the road segment in real time, if there is a first time when the ambient light illumination is less than or equal to a preset threshold, then input the current ambient light illumination and road traffic volume into a pre-trained dimming network model to obtain a dimming level, and use the brightness L0 corresponding to the dimming level as the initial brightness of the street light on the road segment;

[0009] S2, preset an observation period H, divide the observation period evenly into n monitoring periods, obtain the road information of the road section in the observation period in real time, and calculate the road resistance coefficient of the road section in any monitoring period, with time as the horizontal coordinate and the road resistance coefficient as the vertical coordinate, to generate a curve Y(t) of the change of the road resistance coefficient over time, wherein the road information includes the maximum speed limit of the road, the number of lanes, the road length, the road curvature and the traffic volume;

[0010] S3, obtaining the starting point, the end point, the peak point and the valley point in the variable curve Y'(t) and taking them as feature points, calculating the slope k between adjacent feature points, according to the calculation formula The coefficient of variation K is calculated. If K is greater than or equal to a preset threshold, the maximum traffic flow of the road section during the observation period is calculated, and the current ambient light illumination and the maximum traffic flow are input into a pre-trained dimming network model to obtain a dimming level, and the brightness L' corresponding to the dimming level is used as the brightness of the street lamp on the road; if K is less than the preset threshold, the current traffic flow and ambient light illumination of the road are obtained, and the current ambient light illumination and traffic flow are input into a pre-trained dimming network model to obtain a dimming level, and the brightness L' corresponding to the dimming level is used as the brightness of the street lamp on the road.

[0011] As a further solution of the present invention: in S1, the process of obtaining the dimming network model is:

[0012] Acquire training set data, wherein the training set data includes a sample set; generate a back propagation network model and set training parameters; normalize the training set data; and train the back propagation network model using the sample set to obtain the trained dimming network model.

[0013] As a further solution of the present invention: in S2, the calculation process of the road resistance coefficient is:

[0014] S11, obtain the road information of the road section, obtain the maximum length of the vehicle body and mark it as I, set the safe distance between each vehicle as z, determine the buffer section in the road section and obtain the buffer section length S, calculate the maximum total number of vehicles that the non-buffer section can accommodate at the same time, record it as the vehicle capacity, and mark it as Gmax, where:

[0015] ;

[0016] Where M is the number of lanes in the road section;

[0017] S12, obtaining the number of all vehicles Gc that have exited the buffer section of the road section in the current monitoring period, obtaining the total time T1 of any vehicle passing through the road and the time T2 of the vehicle staying in the buffer section, and then calculating the traffic speed V according to the total vehicle time and the stay time, the length S of the buffer section and the total length L of the road, and calculating the road resistance coefficient Y of the road section according to the traffic speed, the road vehicle capacity and the road vehicle flow;

[0018] ;

[0019] ;

[0020] ;

[0021] Among them, Gd is the current vehicle flow of the road section, and R is the curvature of the road.

[0022] As a further solution of the present invention: the specific process of determining the buffer section is:

[0023] The maximum speed limit v of the road section is obtained, the time t consumed when the initial speed v is decelerated to 0 with a preset acceleration a is obtained, and the distance S traveled by the vehicle in the process of decelerating to stopping is calculated, and the first road intersection point is selected along the opposite direction of the road travel, and the road intersection point is used as the starting point to select a section of length S from the road section and mark it as a buffer section.

[0024] As a further solution of the present invention: S3 also includes correcting the next observation period H according to the variation coefficient.

[0025] As a further solution of the present invention: the specific process of correction is:

[0026] ;

[0027] Among them, K 标 is the preset coefficient of variation threshold.

[0028] As a further solution of the present invention: S3 also includes that if the slope k of the first adjacent feature point is greater than or equal to a preset threshold, the observation period ends in advance, the current traffic flow and ambient light illumination of the road are obtained, the current ambient light illumination and traffic flow are input into a pre-trained dimming network model to obtain a dimming level, and the corresponding brightness L' of the dimming level is used as the brightness of the road lamp.

[0029] As a further solution of the present invention: when the observation period ends early, the observation duration that ends early is obtained and marked as h, and H=h is set, and S2 and S3 are repeated.

[0030] Beneficial effects of the present invention:

[0031] In the actual solution of the present invention, when the detected ambient light illumination is less than the preset threshold, it means that the street light needs to be turned on. By obtaining the ambient light illumination and traffic volume of the road in real time, and combining with the pre-trained dimming network model, the brightness of the street light can be adjusted intelligently. At the same time, after detecting that the road traffic volume has changed, it will not directly trigger the brightness change of the street light, but set the monitoring period T, and observe the road resistance change rate of the road within the monitoring period T. It can be understood that the road resistance change rate reflects the change of traffic flow or vehicle speed over time. For example, within a period of time, if the traffic flow increases sharply or the vehicle speed drops sharply, the road resistance change rate will be higher, indicating that the traffic conditions of the road section have become more congested and the travel speed has slowed down. On the contrary, when the vehicle speed increases or the traffic volume decreases, the road resistance change rate is low, indicating that the road is unobstructed. The change coefficient is calculated based on the road resistance change rate. It can be understood that the larger the change coefficient, the more drastic the traffic change. If the dimming of this strategy is performed due to the changes in real-time traffic flow, the dimming level of the street lamp brightness will change frequently, wasting energy while the driver may find it difficult to adapt to the rapid change of brightness in a short time, causing glare or visual discomfort and causing certain safety hazards. Therefore, the present invention uses the maximum traffic volume as the standard to adjust the brightness of the street lamp on the road; the smaller the change coefficient, the more stable the traffic change, so the present invention uses the latest collected traffic volume as the standard to adjust the brightness of the street lamp on the road. The present invention monitors the change of the road resistance coefficient over time according to dynamic change factors such as traffic flow fluctuations and traffic congestion, and adjusts the street lamp brightness adaptively, avoiding frequent changes in the dimming level of the street lamp brightness, reducing energy waste and avoiding the problem of glare or visual discomfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention will be further described below in conjunction with the accompanying drawings.

[0033] Figure 1 It is a schematic flow chart of a brightness intelligent control method based on photovoltaic street lamps of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] See also Figure 1 As shown, the present invention is a brightness intelligent control method based on photovoltaic street lamps, S1, select a target road and obtain all road intersections of the target road, and divide the target road into several road segments with adjacent intersections as dividing points; select any road segment and obtain the ambient light illumination and road vehicle flow of the road segment in real time, if there is a first ambient light illumination that is less than or equal to a preset threshold, then input the current ambient light illumination and road vehicle flow into a pre-trained dimming network model to obtain a dimming level, and use the brightness L0 corresponding to the dimming level as the initial brightness of the street lamp of the road segment;

[0036] S2, preset an observation period H, divide the observation period evenly into n monitoring periods, obtain the road information of the road section in the observation period in real time, and calculate the road resistance coefficient of the road section in any monitoring period, with time as the horizontal coordinate and the road resistance coefficient as the vertical coordinate, to generate a curve Y(t) of the change of the road resistance coefficient over time, wherein the road information includes the maximum speed limit of the road, the number of lanes, the road length, the road curvature and the traffic volume;

[0037] S3, obtaining the starting point, the end point, the peak point and the valley point in the variable curve Y'(t) and taking them as feature points, calculating the slope k between adjacent feature points, according to the calculation formula The coefficient of variation K is calculated. If K is greater than or equal to a preset threshold, the maximum traffic flow of the road section during the observation period is calculated, and the current ambient light illumination and the maximum traffic flow are input into a pre-trained dimming network model to obtain a dimming level, and the brightness L' corresponding to the dimming level is used as the brightness of the street lamp on the road; if K is less than the preset threshold, the current traffic flow and ambient light illumination of the road are obtained, and the current ambient light illumination and traffic flow are input into a pre-trained dimming network model to obtain a dimming level, and the brightness L' corresponding to the dimming level is used as the brightness of the street lamp on the road.

[0038] In the actual solution of the present invention, when the detected ambient light illumination is less than the preset threshold, it means that the street light needs to be turned on. By obtaining the ambient light illumination and traffic volume of the road in real time, and combining with the pre-trained dimming network model, the brightness of the street light can be adjusted intelligently. At the same time, after detecting that the road traffic volume has changed, it will not directly trigger the brightness change of the street light, but set the monitoring period T, and observe the road resistance change rate of the road within the monitoring period T. It can be understood that the road resistance change rate reflects the change of traffic flow or vehicle speed over time. For example, within a period of time, if the traffic flow increases sharply or the vehicle speed drops sharply, the road resistance change rate will be higher, indicating that the traffic conditions of the road section have become more congested and the travel speed has slowed down. On the contrary, when the vehicle speed increases or the traffic volume decreases, the road resistance change rate is low, indicating that the road is unobstructed. The change coefficient is calculated based on the road resistance change rate. It can be understood that the larger the change coefficient, the more drastic the traffic change. If the dimming of this strategy is performed due to the changes in real-time traffic flow, the dimming level of the street lamp brightness will change frequently, wasting energy while the driver may find it difficult to adapt to the rapid change of brightness in a short time, causing glare or visual discomfort and causing certain safety hazards. Therefore, the present invention uses the maximum traffic volume as the standard to adjust the brightness of the street lamp on the road; the smaller the change coefficient, the more stable the traffic change, so the present invention uses the latest collected traffic volume as the standard to adjust the brightness of the street lamp on the road. The present invention monitors the change of the road resistance coefficient over time according to dynamic change factors such as traffic flow fluctuations and traffic congestion, and adjusts the street lamp brightness adaptively, avoiding frequent changes in the dimming level of the street lamp brightness, reducing energy waste while avoiding the problem of glare or visual discomfort.

[0039] As a further solution of the present invention: in S1, the process of obtaining the dimming network model is:

[0040] Acquire training set data, wherein the training set data includes a sample set; generate a back propagation network model and set training parameters; normalize the training set data; and train the back propagation network model using the sample set to obtain the trained dimming network model.

[0041] As a further solution of the present invention: in S2, the calculation process of the road resistance coefficient is:

[0042] S11, obtain the road information of the road section, set the safe distance between each vehicle as z, obtain the maximum length of the vehicle body and mark it as I, determine the buffer section in the road section and obtain the length of the buffer section S; calculate the maximum total number of vehicles that the non-buffer section can accommodate at the same time, record it as the vehicle capacity, and mark it as Gmax, where:

[0043] Gmax=(LS) / (z+I)*m;

[0044] S12, obtaining the number of all vehicles Gc that have exited the buffer section of the road section in the current monitoring period, obtaining the total time T1 of any vehicle passing through the road and the time T2 of the vehicle staying in the buffer section, and then calculating the traffic speed V according to the total vehicle time and the stay time, the length S of the buffer section and the total length L of the road, and calculating the road resistance coefficient Y of the road section according to the traffic speed, the road vehicle capacity and the road vehicle flow;

[0045] ;

[0046] ;

[0047] ;

[0048] Among them, Gd is the current vehicle flow of the road section, and R is the curvature of the road.

[0049] The present invention evaluates congestion by combining vehicle capacity and traffic speed. Traffic capacity refers to the maximum number of vehicles that a road can carry within a period of time, while traffic speed refers to the maximum speed at which vehicles pass through the road. When the traffic volume exceeds the vehicle capacity, the traffic speed will decrease, leading to congestion. It can be understood that traffic lights on the road will affect the speed of road vehicles. Therefore, a buffer section is set and the total time T1 for any outgoing vehicle to pass through the road section and the time T2 for the vehicle to stay in the buffer section are obtained. The driving time of the vehicle on the regular section is calculated, thereby obtaining the maximum value of the driving time of several vehicles on the regular section. The actual driving speed of the vehicle on the current road is calculated based on the maximum time, and the actual congestion coefficient of the road is calculated based on the obtained road traffic volume, vehicle capacity and traffic speed.

[0050] As a further solution of the present invention: the specific process of determining the buffer section is:

[0051] The maximum speed limit v of the road section is obtained, the time t consumed when the initial speed v is decelerated to 0 with a preset acceleration a is obtained, and the distance S traveled by the vehicle in the process of decelerating to stopping is calculated, and the first road intersection point is selected along the opposite direction of the road travel, and the road intersection point is used as the starting point to select a section of length S from the road section and mark it as a buffer section.

[0052] As a further solution of the present invention: S3 also includes correcting the next observation period H according to the variation coefficient.

[0053] By adjusting the next observation period H according to the variation coefficient K, it is possible to adaptively respond to real-time changing traffic conditions and environmental conditions. Usually, traffic flow, road conditions and other influencing factors (such as weather, holidays or traffic density during specific periods) will fluctuate over time. By correcting the observation period, the time dimension of monitoring can be adjusted more flexibly to avoid information lag or excessive concentration caused by fixed periods. When the variation coefficient K is large, it means that the traffic flow fluctuates greatly, so the next observation period H can be shortened to provide more frequent adjustments; during relatively stable traffic periods: when the variation coefficient K is small, it means that the traffic state is relatively stable, and the observation period can be extended to reduce the consumption of computing resources and unnecessary frequent adjustments. By correcting the observation period according to the variation coefficient, the impact of traffic flow fluctuations on street lamp brightness can be captured more accurately, especially during periods of drastic or irregular traffic changes. For unstable traffic flow, shortening the observation period can help the system respond to changes more promptly and adjust the brightness. During relatively stable traffic periods, extending the period can reduce unnecessary adjustments and avoid the system burden caused by excessive adjustments.

[0054] As a further solution of the present invention: the specific process of correction is:

[0055] ;

[0056] Among them, K 标 is the preset change coefficient threshold, and β is the preset correction coefficient.

[0057] As a further solution of the present invention: S3 also includes that if the slope k of the first adjacent feature point is greater than or equal to a preset threshold, the observation period ends in advance, the current traffic flow and ambient light illumination of the road are obtained, the current ambient light illumination and traffic flow are input into a pre-trained dimming network model to obtain a dimming level, and the corresponding brightness L' of the dimming level is used as the brightness of the road lamp.

[0058] As a further solution of the present invention: when the observation period ends early, the observation duration that ends early is obtained and marked as h, and H=h is set, and S2 and S3 are repeated.

[0059] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A brightness intelligent control method based on photovoltaic street lamps, characterized in that: The following steps are involved: S1, selecting a target road and obtaining all road intersections of the target road, dividing the target road into a number of road segments using adjacent intersections as segmentation points; Select any road section and obtain the ambient light illumination and road traffic volume of the road section in real time. If there is a first time when the ambient light illumination is less than or equal to the preset threshold, input the current ambient light illumination and road traffic volume into the pre-trained dimming network model to obtain the dimming level, and use the brightness L0 corresponding to the dimming level as the initial brightness of the street light on the road section; S2, preset an observation period H, divide the observation period evenly into n monitoring periods, obtain the road information of the road section in the observation period in real time, and calculate the road resistance coefficient of the road section in any monitoring period, with time as the horizontal coordinate and the road resistance coefficient as the vertical coordinate, to generate a curve Y(t) of the change of the road resistance coefficient over time, wherein the road information includes the maximum speed limit of the road, the number of lanes, the road length, the road curvature and the traffic volume; S3, obtain the starting point, end point, peak point and valley point in the change curve Y'(t) and use them as feature points, calculate the slope k between adjacent feature points, and use the calculation formula The coefficient of variation K is calculated, where h is the observation duration within the observation period. If K is greater than or equal to a preset threshold, the maximum traffic flow of the road section within the observation period is calculated, and the current ambient light illumination and the maximum traffic flow are input into a pre-trained dimming network model to obtain a dimming level, and the brightness L' corresponding to the dimming level is used as the brightness of the street lamp on the road; if K is less than the preset threshold, the current traffic flow and ambient light illumination of the road are obtained, and the current ambient light illumination and traffic flow are input into a pre-trained dimming network model to obtain a dimming level, and the brightness L' corresponding to the dimming level is used as the brightness of the street lamp on the road; The calculation process of the road resistance coefficient is: S11, obtain the road information of the road section, set the safe distance between each vehicle as z, obtain the maximum length of the vehicle body and mark it as I, determine the buffer section in the road section and obtain the length of the buffer section S; calculate the maximum total number of vehicles that the non-buffer section can accommodate at the same time, record it as the vehicle capacity, and mark it as Gmax, where: Gmax = (LS) / (z+I)*m; S12, obtaining the number of all vehicles Gc that have exited the buffer section of the road section in the current monitoring period, obtaining the total time T1 of any vehicle passing through the road and the time T2 of the vehicle staying in the buffer section, and then calculating the traffic speed V according to the total vehicle time and the stay time, the length S of the buffer section and the total length L of the road section, and calculating the road resistance coefficient Y of the road section according to the traffic speed, the road vehicle capacity and the road vehicle flow; Among them, Gd is the current vehicle flow of the road section, and R is the curvature of the road.

2. According to claim 1, a method for intelligent brightness control based on photovoltaic street lamps is characterized in that: In S1, the process of obtaining the dimming network model is as follows: Acquire training set data, wherein the training set data includes a sample set; generate a back propagation network model and set training parameters; normalize the training set data; and train the back propagation network model using the sample set to obtain the trained dimming network model.

3. According to claim 1, a method for intelligent brightness control based on photovoltaic street lamps is characterized in that: The specific process of determining the buffer section is as follows: The maximum speed limit v of the road section is obtained, the time t consumed when the initial speed v is decelerated to 0 with a preset acceleration a is obtained, and the distance S traveled by the vehicle in the process of decelerating to stopping is calculated, and the first road intersection point is selected along the opposite direction of the road travel, and the road intersection point is used as the starting point to select a section of length S from the road section and mark it as a buffer section.

4. The method for intelligent brightness control based on photovoltaic street lamps according to claim 1 is characterized in that: The S3 also includes correcting the next observation period H according to the variation coefficient.

5. The method for intelligent brightness control based on photovoltaic street lamps according to claim 4 is characterized in that: The specific process of correction is: Among them, K 标 is the preset change coefficient threshold, and β is the preset correction coefficient.

6. The method for intelligent brightness control based on photovoltaic street lamps according to claim 1, characterized in that: The S3 also includes that if the slope k of the first adjacent feature point is greater than or equal to a preset threshold, the observation period ends in advance, the current traffic flow and ambient light illumination of the road are obtained, the current ambient light illumination and traffic flow are input into a pre-trained dimming network model to obtain a dimming level, and the corresponding brightness L' of the dimming level is used as the brightness of the road lamp.

7. The method for intelligent brightness control based on photovoltaic street lamps according to claim 6 is characterized in that: The method also includes obtaining the observation duration that ends early and marking it as h when the observation cycle ends early, setting H=h, and repeating S2 and S3.

Images