Smart street lighting system, street lighting intelligent control device and control method thereof

Abstract

The present invention provides a smart street lamp lighting system, a street lamp lighting intelligent control device and a control method thereof. The smart street lamp lighting control system of the present invention includes: a street lamp lighting intelligent control device, an Internet of Things and multiple street lamps. The street lamp lighting intelligent control device controls and obtains the status of multiple street lamps and the corresponding street lamp surrounding environment illumination information through an Internet of Things platform. The street lamp lighting intelligent control device calculates the fitness of each control scheme based on the street lamp status information and environmental illumination information and combines the street lamp geographical location information and road section importance information. Finally, according to the size of the fitness, the switch light control scheme with the largest fitness is selected to control the switching of each street lamp. The present invention can adaptively generate the preferred switch light control scheme by setting the fitness function to ensure the order and rationality of street lamp control, reduce the energy consumption of street lamps and extend the service life of street lamps.

Description

Technical Field

[0001] The present invention relates to the field of smart lighting, and in particular to a smart street lighting system, a street lighting intelligent control device and a control method thereof. Background Art

[0002] With the improvement of people's living standards and the rapid development of cities, the requirements for road lighting are getting higher and higher. At present, road lighting not only needs to meet functional lighting and ensure road safety, but also needs to achieve scientific energy saving.

[0003] Traditional streetlight control relies on a timer, typically switching on at a fixed time each evening and off at a fixed time each morning. This fixed-time control method is insensitive to changes in natural light intensity, influenced by seasons and weather. This can result in streetlights being switched off when natural light is low, leaving people without illumination, and remaining on when natural light is high, resulting in energy waste.

[0004] With the development of intelligent sensing technology, streetlights are now able to detect ambient light intensity, enabling energy conservation. By sensing ambient light intensity, streetlights automatically adjust their on / off settings. For streetlights equipped with dimming capabilities, they can also reduce brightness or operating time to minimize energy consumption.

[0005] To further conserve energy, smart lighting also uses a midnight lighting system. This means that in the latter part of the night, when pedestrian and vehicle traffic is low and brightness doesn't need to be high, alternate streetlights are lit, or two rows of streetlights are lit in a staggered pattern to conserve energy. This method is efficient, intelligent, and advanced, but existing smart lighting control systems also have the following problems:

[0006] 1. The alternate lighting method is relatively fixed and requires manual setting of rules, which has poor flexibility.

[0007] 2. Poor adaptability: The lighting strategy cannot be adjusted adaptively based on the streetlight status. For example, if some streetlights are damaged and cannot be turned on, the alternate lighting strategy cannot be adjusted in time until they are repaired. This ultimately results in insufficient lighting in the area, affecting driving and pedestrian safety.

[0008] 3. The special characteristics of intersections and road sections are not taken into account, and the importance of all street lights is assumed to be the same. However, in fact, at some key intersections or key terrain locations, such as accident-prone areas, more brightness is needed to ensure road safety, but the alternate lighting method ignores this special characteristic.

[0009] 4. It fails to consider streetlight usage. A streetlight's lifespan is closely tied to usage. Although streetlights initially have the same initial lifespan, over time, some lights last longer, while others last shorter. This is especially true when some lights are updated or reinstalled for maintenance, where their lifespan begins anew. The alternate-lighting method ignores the changing properties of the streetlights themselves.

[0010] In summary, existing intelligent lighting control systems are unable to be flexible and adaptable at the same time, and are unable to ensure lighting brightness, pedestrian and vehicle safety, and save energy as much as possible. Summary of the Invention

[0011] The present invention provides a smart street lamp lighting system, a street lamp lighting intelligent control device and a control method thereof. The smart street lamp lighting control system of the present invention includes: a street lamp lighting intelligent control device, an Internet of Things and multiple street lamps. The street lamp lighting intelligent control device controls and obtains the status of multiple street lamps and the corresponding street lamp surrounding environment illumination information through an Internet of Things platform. The street lamp lighting intelligent control device controls the switch status of each street lamp based on the street lamp status information and environmental illumination information and combines the street lamp geographical location information and road section importance information, outputs the street lamp control result, and the street lamp is lit or extinguished according to the street lamp control result.

[0012] The present invention is implemented through the following technical solutions, first providing a street lighting intelligent control method, which includes:

[0013] S10: Generate K initialization schemes based on the number N of street lamps in binary coding and combined with the online status information set and the fault status information set as K individuals of the population to complete the initialization of the street lamp population. Any individual in the population can be expressed as

[0014] S20.A: Calculate the fitness of each population based on the number of streetlights, the minimum number of lights on, and the fitness function for the number of lights on.

[0015] S20.B: Calculate the lighting uniformity fitness of each individual in the population based on the street light location information set, the lighting uniformity fitness function, and the lighting control scheme represented by each individual in the population;

[0016] S20.C: Calculate the usage duration fitness of each population individual based on the lighting control scheme represented by each population individual, the usage duration information of the corresponding street light, and the duration fitness function;

[0017] S20.D: Calculate the importance fitness of each individual in the population based on the importance set of streetlight locations, the importance fitness function, and the lighting control scheme represented by each individual in the population;

[0018] S30: normalizing each fitness function according to the fitness of the number of lights on, the fitness of the uniformity of lights on, the fitness of the duration of use, and the fitness of importance of each population individual, and summing the normalized fitness functions to obtain a comprehensive fitness function;

[0019] S40: Calculating the comprehensive fitness of each population individual according to the comprehensive fitness function;

[0020] S50: If there is a population individual whose comprehensive fitness is greater than the fitness of a preset individual, a light on / off control scheme is generated based on the representation of the population individual with the largest fitness.

[0021] Furthermore, the fitness function of the number of lights on is:

[0022] f1=-x 2 +Nx+c

[0023]

[0024] c=M 2 -NM

[0025] Among them, N is the total number of street lights, M is the minimum number of lights on, is the lighting status of the i-th streetlight of the K-th individual in the population.

[0026] Furthermore, the process of constructing the lighting uniformity fitness function is as follows:

[0027] When all street lights are on the same road, N street lights can be divided into N / 2 grids. Data is constructed based on these N / 2 grids:

[0028]

[0029] Among them L j is the number of lights on in the first j grids. At this time, the fitness function for the uniformity of lights on is:

[0030]

[0031] Where Var(L) is the variance of the grid data L;

[0032] When street lamps are located on different roads, the position of each street lamp is taken as a coordinate point, all coordinate points are obtained, and a polygon is formed;

[0033] Select the coordinate points of the bright spot lamp, and the polygon forms a scatter diagram of points enclosing the space;

[0034] Calculating a Voronoi diagram based on the scatter diagram to obtain an area set A of Voronoi polygons;

[0035] Solve the variance Var(A) and mean E(A) of the area set A. At this time, the lighting uniformity fitness function is:

[0036]

[0037] Where E(A) is the mean of the area set A of the Voronoi polygons, and Var(A) is the variance of the area set A of the Voronoi polygons.

[0038] Furthermore, the duration fitness function is:

[0039]

[0040] Among them, T i is the usage time of the i-th street light, is the lighting status of the i-th streetlight of the K-th individual in the population.

[0041] Furthermore, the importance fitness function is:

[0042]

[0043] Among them, G i is the importance of the i-th street light, is the lighting status of the i-th streetlight of the K-th individual in the population.

[0044] Furthermore, the normalization formula of each fitness function is as follows:

[0045]

[0046] in, are the maximum and minimum values ​​of the i-th fitness function respectively.

[0047] Furthermore, after step S40, the method further includes:

[0048] S51: If the fitness of all population individuals is less than the fitness of a preset individual, the population individuals are updated according to the genetic algorithm to obtain a new generation of population individuals, and steps S20.A, S20.B, S20.C, and S20.D are re-executed.

[0049] Furthermore, before step S51, the method further includes:

[0050] S51.a: Is the number of iterations greater than a preset threshold? If not, execute step S51. If so, generate a light on / off control solution using the representation of the preset individual.

[0051] On the other hand, the present invention also provides a street lighting intelligent control device, which includes:

[0052] Population initialization module: It is used to generate K initialization schemes as K individuals of the population based on the number of street lights N in binary coding and combined with the online status information set and the fault status information set to complete the initialization of the street light population. Any individual in the population can be expressed as

[0053] Light quantity fitness calculation module: used to calculate the light quantity fitness of each population individual according to the number of street lights, the minimum number of lights on and the light quantity fitness function;

[0054] Lighting uniformity fitness calculation module: used to calculate the lighting uniformity fitness of each population individual based on the geographical location information set of a road lamp, the lighting uniformity fitness function and the lighting control scheme represented by each population individual;

[0055] Usage time fitness calculation module: used to calculate the usage time fitness of each population individual based on the lighting control scheme represented by each population individual, the usage time information of the corresponding street lamp and the time fitness function;

[0056] Importance fitness calculation module: used to calculate the importance fitness of each population individual based on the importance set of street lamp positions, the importance fitness function, and the lighting control scheme represented by each population individual;

[0057] Comprehensive fitness function construction module: used to normalize each fitness function according to the fitness of the number of lights on, the fitness of the uniformity of lights on, the fitness of the duration of use, and the fitness of importance of each population individual, and sum the normalized fitness functions to obtain the comprehensive fitness function;

[0058] Comprehensive fitness calculation module: used to calculate the comprehensive fitness of each population individual according to the comprehensive fitness function;

[0059] Light switch control scheme generation module: used to generate a light switch control scheme based on the representation of the population individual with the largest fitness if the comprehensive fitness of the population individual is greater than the fitness of a preset individual.

[0060] On the other hand, the present invention further provides a smart street lighting control system, comprising any of the above-mentioned street lighting intelligent control devices, an Internet of Things platform, and a plurality of street lights;

[0061] The IoT platform controls and obtains the status of multiple street lamps and the illumination information of the surrounding environment of the corresponding street lamps, and exchanges data with the street lamp lighting intelligent control device, which is used to generate a street lamp switch control plan;

[0062] In summary, the advantages of the present invention over the prior art are as follows:

[0063] 1. The present invention comprehensively considers various factors such as street lamp usage, street lamp status, information about the road section where the street lamp is located, etc., to achieve a comprehensive design of street lamp lighting and achieve higher energy saving.

[0064] 2. The present invention distinguishes the importance of road sections, so that the street lights on important sections can better ensure the lighting brightness for pedestrians and vehicles, thereby improving safety.

[0065] 3. The present invention takes the properties of the street lamp itself into consideration and increases the service life of the entire street lamp system.

[0066] 4. Compared with the traditional fixed mode, this solution is more intelligent and more adaptable.

[0067] For better understanding and implementation, the present invention is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 is a schematic diagram of an exemplary smart street lighting control system provided by the present invention;

[0069] Figure 2 This is a structural block diagram of the intelligent street lighting control device provided by the present invention;

[0070] Figure 3 for Figure 2 Flowchart of the control method of the intelligent control device for street lighting shown;

[0071] Figure 4 This is a schematic diagram of the streetlight area division by the lighting uniformity fitness calculation module when the streetlight intelligent control device of the present invention controls the streetlights of a road;

[0072] Figure 5 This is a schematic diagram of the streetlight area division by the lighting uniformity fitness calculation module when the streetlight intelligent control device of the present invention controls streetlights on multiple roads;

[0073] Figure 6 This is a flow chart of a control method of a street lighting intelligent control device according to another embodiment of the present invention;

[0074] Figure 7 Schematic diagram of an exemplary mutation process of the present invention. DETAILED DESCRIPTION

[0075] The smart street lamp lighting control system of the present invention includes: a street lamp lighting intelligent control device, an Internet of Things, and multiple street lamps. The street lamp lighting intelligent control device controls and obtains the status of multiple street lamps and the corresponding street lamp surrounding environment illumination information through an Internet of Things platform. The street lamp lighting intelligent control device controls the switch status of each street lamp based on the street lamp status information and environmental illumination information and combines the street lamp geographical location information and road section importance information, and outputs the street lamp control results.

[0076] See also Figure 1 In the present invention, the Internet of Things platform is connected to N street lamps, where the online status information set of the street lamps is recorded as S, S = {S1, S2, ..., S i ,…,S N}, the online state is divided into online and offline, represented by 1 and 0 respectively; the fault state information set of the street lamp is recorded as W, W = {W1, W2, ..., W i ,…,W N}, the status is divided into normal and fault, represented by 1 and 0 respectively; the working time of the street light is recorded as T, in hours. The working time information set of all street lights is recorded as T = {T1, T2, ..., T i ,…,T N}, the location importance set of street lights is denoted as G, which can be provided by the street light management department and the traffic management department. G={G1,G2,…,G i ,…,G N When the street light senses the ambient light intensity, if the illumination is less than a certain value, it meets the conditions for turning on the light at night.

[0077] See also Figure 2 In the smart street lighting system of the present invention, the street lighting intelligent control device generates control results based on the above-mentioned multiple parameter sets, and ultimately controls which street lights are turned on and which are not. Specifically, the street lighting intelligent control device includes a population initialization module 10, a light quantity fitness calculation module 20.A, a light uniformity fitness calculation module 20.B, a usage duration fitness calculation module 20.C, an importance fitness calculation module 20.D, a comprehensive fitness function construction module 30, a comprehensive fitness calculation module 40, and a light on / off control scheme generation module 50. Please refer to Figure 3 ,The execution steps of each module of the street lighting intelligent control device are as follows:

[0078] The population initialization module 10 is used to execute step S10: generate K initialization schemes as K individuals of the population in a binary coding manner according to the number of street lamps N combined with the online status information set and the fault status information set to complete the initialization of the street lamp population. Any individual in the population can be represented as

[0079] Each individual in the population represents a lighting control scheme. Since the lighting state of each street light is on or off, it is associated with binary through coding, with 0 representing off and 1 representing on; then a lighting control scheme is in is the lighting status of the i-th streetlight of the K-th individual; however, not all streetlights are in use or in good condition. In order to eliminate the influence of offline and faulty streetlights on the lighting control scheme, the lighting control needs to exclude offline streetlights and faulty streetlights. Therefore, the lighting control scheme is combined with the online status information set and the fault status information set. That is, for any street light, whether it is turned on or off depends not only on the lighting control scheme but also on its own online status and fault status. At this time, the population individual OF k This is the actual initialization scheme that indicates whether the street light is on or not.

[0080] The light quantity fitness calculation module 20.A is configured to execute step S20.A: calculating the light quantity fitness of each population individual according to the number of street lights, the minimum number of lights on, and the light quantity fitness function;

[0081] The fitness function is the primary metric for measuring the quality of an individual. Based on the size of the fitness function, individuals are selected based on their survival of the fittest. This study examines the number of lights on a streetlight system, their uniformity, their usage time, and the importance of their location, providing a corresponding fitness function.

[0082] Specifically, the fitness function of the number of lights is as follows:

[0083] f1=-x 2 +Nx+c

[0084]

[0085] c=M 2 -NM

[0086] Among them, N is the total number of street lights, M is the minimum number of lights on, is the lighting status of the i-th streetlight of the K-th individual in the population.

[0087] The lighting uniformity fitness calculation module 20.B is configured to execute step S20.B: calculating the lighting uniformity fitness of each individual in the population based on the location information set of the street lights, the lighting uniformity fitness function, and the lighting control scheme represented by each individual in the population;

[0088] The streetlight deployment methods are different in different road sections. For different streetlight deployment methods, the present invention adopts different methods to calculate the lighting uniformity fitness function. Specifically, if the system controls the streetlights of a road, such as Figure 4 As shown, arbitrarily set the beginning and end of a road, and divide the grids along the road direction with two street lamps on both sides of the road as a group. If the street lamps are arranged symmetrically, then N street lamps can be divided into N / 2 grids. Data is constructed based on these N / 2 grids. Among them L j is the number of lights on in the first j grids. Calculate the variance of L to get Var(L). The smaller the variance, the more uniform the distribution. At this time, the fitness function for the uniformity of lights is:

[0089]

[0090] Where Var(L) is the variance of the grid data.

[0091] If the system controls multiple street lights, the Voronoi diagram method will be used to measure the uniformity. Figure 5 First, consider the position of each streetlight as a coordinate point. Obtain all coordinate points and form a polygon. The edge of the polygon is at a certain distance from the coordinate point. This distance is set to half the distance between the two lamps. At this time, for an individual K in the population, when the lighting control scheme represented by this individual is used to light up, not all lamps will light up. Select the coordinate points of the bright lamps and form a scatter diagram of the points in the enclosed space with the above polygon. For this scatter diagram, calculate the Voronoi (Voronoi) diagram to obtain the area set A of the Voronoi polygon. Calculate the variance of A to obtain Var(A) and the mean E(A), and then calculate the coefficient of variation. The smaller the coefficient of variation, the more uniform the size and shape of the Voronoi polygons are, and thus the more uniform the point distribution is. The fitness function for lighting uniformity is:

[0092]

[0093] Where E(A) is the mean of the area set A of the Voronoi polygons, and Var(A) is the variance of the area set A of the Voronoi polygons.

[0094] The usage time fitness calculation module 20.C is used to execute step S20.C: calculating the usage time fitness of each population individual according to the lighting control scheme represented by each population individual, the usage time information of the corresponding street lamp, and the time fitness function;

[0095] To ensure the service life of the entire street light system, it is generally necessary to light the street lights evenly. In particular, some newly replaced street lights need to be used as much as possible. Therefore, the fitness function of the usage time is constructed as follows:

[0096]

[0097] Among them, T i is the usage time of the i-th street light, is the lighting status of the i-th streetlight of the K-th individual in the population.

[0098] At this time, if the i-th street lamp is used for a longer time, its fitness will be lower, so compared with other street lamps, the feasibility of it being selected to turn on will be smaller.

[0099] The importance fitness calculation module 20.D is configured to execute step S20.D: calculating the importance fitness of each individual in the population based on the street lamp location importance set, the importance fitness function, and the lighting control scheme represented by each individual in the population;

[0100] In some key locations, streetlights should be selected and turned on with a higher probability, such as corners and intersections. Places like these have a high probability of turning on lights, so it is necessary to assign corresponding importance levels based on the location of the streetlights. This invention uses the location importance set G of the streetlights to represent the importance of each streetlight, and constructs the importance fitness function based on the location importance set:

[0101]

[0102] Among them, G i is the importance of the i-th street light, is the lighting status of the i-th streetlight of the K-th individual in the population.

[0103] The comprehensive fitness function construction module 30 is used to execute step S30: normalize each fitness function according to the fitness of the number of lights on, the fitness of the uniformity of lights on, the fitness of the duration of use, and the fitness of importance of each population individual, and sum the normalized fitness functions to obtain a comprehensive fitness function;

[0104] The four fitness functions above have different dimensionality issues due to different measurement standards. To achieve a unified measurement, we must first address the dimensionality issue. For a population of K, that is, K individuals, we first perform normalization using min-max normalization. For any fitness function, the normalization process is as follows:

[0105]

[0106] in, are the maximum and minimum values ​​of the i-th fitness function respectively.

[0107] Therefore, the final comprehensive fitness function is:

[0108] in, is the normalized fitness of any fitness function.

[0109] The comprehensive fitness calculation module 40 is used to execute step S40: calculating the comprehensive fitness of each population individual according to the comprehensive fitness function.

[0110] The normalized comprehensive fitness function is only It is related, that is, it is only related to each switch state in each individual. By substituting each value in the individual into the comprehensive fitness function and summing them up, we can get the fitness of each individual K, that is, the fitness set.

[0111] The light switching control scheme generating module 50 is configured to execute step S50: if there is a population individual whose comprehensive fitness is greater than the fitness of a preset individual, then generating a light switching control scheme based on the representation of the population individual with the greatest fitness.

[0112] As a universal street light control scheme, the alternate lighting scheme itself has certain feasibility. Substitute the lighting control scheme into the comprehensive fitness function to calculate its fitness, which is used as a threshold fitness. When the fitness of an individual in the population is greater than the fitness, it means that there is a street light control scheme that is better than the alternate lighting scheme in the generated population. At this time, the OF of the individual with the largest fitness is used. k , as the final street light control solution and issue switch instructions to complete the street light switch control.

[0113] The present invention comprehensively considers multiple factors such as street lamp usage, street lamp status, information about the road section where the street lamp is located, etc., to achieve a comprehensive design of street lamp lighting, achieve higher energy saving and distinguish the importance of road sections, so that street lamps on important road sections can better ensure the lighting brightness for pedestrians and vehicles, and improve safety.

[0114] However, the above scheme still has some shortcomings. First, if this system controls N street lights, there will be 2N power solutions for turning the street lights on and off. If the fitness of each solution is calculated for this exponential growth control scheme, then when N exceeds a certain value, the amount of calculation is very large, and the efficiency of generating light-on solutions is low. However, if only K individuals of the population are randomly generated for evaluation, it is very likely that none of the K individuals will be as good as the method of turning on every other light, which will make the control scheme invalid. Based on the above problems, please refer to Figure 6 In another embodiment, the present invention further comprises after step S40:

[0115] S51: If the fitness of all population individuals is less than the fitness of a preset individual, the population individuals are updated according to the genetic algorithm to obtain a new generation of population individuals, and steps S20.A, S20.B, S20.C, and S20.D are re-executed.

[0116] Genetic algorithms update offspring through selection, crossover, and mutation. The selection steps are as follows:

[0117] 1) Obtain the comprehensive fitness of each individual in the population. The higher the comprehensive fitness value, the greater the individual advantage.

[0118] 2) Calculate the total comprehensive fitness and add up the comprehensive fitness of all individuals to get the total.

[0119] 3) Calculate the selection probability of each individual, which is equal to the individual fitness value divided by the total fitness.

[0120] 4) Construct a cumulative probability distribution and add up the selection probability of each individual to get an interval.

[0121] 5) Generate a random number between 0 and 1, and select the corresponding individual as the parent based on which interval the random number falls.

[0122] After the individual selection is completed, crossover is required. This invention adopts the simplest single-point crossover, but can also support other crossover operators. In single-point crossover, a crossover point is randomly set in the individual to divide the individual gene into two parts. The offspring is generated by two parents. After the crossover, the individuals need to be bitwise ANDed with the online state and the fault state, that is,

[0123] Similarly, the present invention adopts the simplest basic bit mutation, and can also support other mutation operators. In the basic bit mutation of the present invention, the mutation probability is related to the characteristics of the basic bit. For the i-th gene of an individual, the first M bits and the last M bits of the position are counted. If there are more positions with the same code as the i-th gene, the mutation probability is increased. Figure 7 , assuming M = 1, if there are more identical codes on both sides of the mutation bit, the mutation probability will be increased, while if there are no identical codes on both sides of the mutation bit in the figure below, the mutation probability will be reduced. This ensures the uniformity of individual codes. After mutation, each individual needs to be bitwise ANDed with the online state and fault state, that is,

[0124] Through the above steps, K new offspring population individuals are generated, that is, new lighting control schemes. The fitness of the K lighting control schemes is then repeatedly calculated. When the stopping criterion is met, that is, the number of iterations exceeds a preset threshold, or the comprehensive fitness of a lighting control scheme is higher than that of the every other lighting scheme, then the genetic update can be stopped and the final control result can be output.

[0125] The present invention uses a genetic algorithm and a set fitness function to adaptively generate an optimal switch light control scheme to ensure orderly and reasonable street light control. Compared with the existing technology, it has the following advantages:

[0126] 1. The present invention comprehensively considers various factors such as street lamp usage, street lamp status, information about the road section where the street lamp is located, etc., to achieve a comprehensive design of street lamp lighting and achieve higher energy saving.

[0127] 2. The present invention distinguishes the importance of road sections, so that the street lights on important sections can better ensure the lighting brightness for pedestrians and vehicles, thereby improving safety.

[0128] 3. The present invention takes the properties of the street lamp itself into consideration and increases the service life of the entire street lamp system.

[0129] 4. Compared with the traditional fixed mode, this solution is more intelligent and more adaptable.

[0130] Finally, it should be noted that the smart street lamp lighting system, street lamp lighting intelligent control device and control method thereof disclosed in the embodiments of the present invention are only preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A street lighting intelligent control method, characterized by: S10: Generate K initialization schemes based on the number N of street lamps in binary coding and combined with the online status information set and the fault status information set as K individuals of the population to complete the initialization of the street lamp population. Any individual in the population can be expressed as S20.A: Calculate the fitness of each population based on the number of streetlights, the minimum number of lights on, and the fitness function for the number of lights on. S20.B: Calculate the lighting uniformity fitness of each individual in the population based on the street light location information set, the lighting uniformity fitness function, and the lighting control scheme represented by each individual in the population; S20.C: Calculate the usage duration fitness of each population individual based on the lighting control scheme represented by each population individual, the usage duration information of the corresponding street light, and the duration fitness function; S20.D: Calculate the importance fitness of each individual in the population based on the importance set of streetlight locations, the importance fitness function, and the lighting control scheme represented by each individual in the population; S30: normalizing each fitness function according to the fitness of the number of lights on, the fitness of the uniformity of lights on, the fitness of the duration of use, and the fitness of importance of each population individual, and summing the normalized fitness functions to obtain a comprehensive fitness function; S40: Calculating the comprehensive fitness of each population individual according to the comprehensive fitness function; S50: If there is a population individual whose comprehensive fitness is greater than the fitness of a preset individual, a light on / off control scheme is generated based on the representation of the population individual with the largest fitness.

2. The intelligent control method for street lighting according to claim 1, characterized in that: The fitness function of the number of lights on is: f1=-x 2 +Nx+c c=M 2 -NM Among them, N is the total number of street lights, M is the minimum number of lights on, is the lighting status of the i-th streetlight of the K-th individual in the population.

3. The intelligent control method for street lighting according to claim 2, characterized in that: The construction process of the lighting uniformity fitness function is as follows: When all street lights are on the same road, N street lights can be divided into N / 2 grids. Data is constructed based on these N / 2 grids: Among them L j is the number of lights on in the first j grids. At this time, the fitness function for the uniformity of lights on is: Where Var(L) is the variance of the grid data L; When street lamps are located on different roads, the position of each street lamp is taken as a coordinate point, all coordinate points are obtained, and a polygon is formed; Select the coordinate points of the bright spot lamp, and the polygon forms a scatter diagram of points enclosing the space; Calculating a Voronoi diagram based on the scatter diagram to obtain an area set A of Voronoi polygons; Solve the variance Var(A) and mean E(A) of the area set A. At this time, the lighting uniformity fitness function is: Where E(A) is the mean of the area set A of the Voronoi polygons, and Var(A) is the variance of the area set A of the Voronoi polygons.

4. The intelligent control method for street lighting according to claim 3, characterized in that: The duration fitness function is: Among them, T i is the usage time of the i-th street light, is the lighting status of the i-th streetlight of the K-th individual in the population.

5. The intelligent control method for street lighting according to claim 4, characterized in that: The importance fitness function is: Among them, G i is the importance of the i-th street light, is the lighting status of the i-th streetlight of the K-th individual in the population.

6. The intelligent control method for street lighting according to claim 5, characterized in that: The normalization formula of each fitness function is as follows: in, are the maximum and minimum values ​​of the i-th fitness function respectively.

7. The intelligent control method for street lighting according to any one of claims 1 to 6, characterized in that: After step S40, the method further includes: S51: If the fitness of all population individuals is less than the fitness of a preset individual, the population individuals are updated according to the genetic algorithm to obtain a new generation of population individuals, and steps S20.A, S20.B, S20.C, and S20.D are re-executed.

8. The intelligent control method for street lighting according to claim 7, characterized in that: Before step S51, the method further includes: S51.a: Is the number of iterations greater than a preset threshold? If not, execute step S51. If so, generate a light on / off control solution using the representation of the preset individual.

9. An intelligent control device for street lighting, characterized in that: include: Population initialization module: It is used to generate K initialization schemes as K individuals of the population based on the number of street lights N in binary coding and combined with the online status information set and the fault status information set to complete the initialization of the street light population. Any individual in the population can be expressed as Light quantity fitness calculation module: used to calculate the light quantity fitness of each population individual according to the number of street lights, the minimum number of lights on and the light quantity fitness function; Lighting uniformity fitness calculation module: used to calculate the lighting uniformity fitness of each population individual based on the geographical location information set of a road lamp, the lighting uniformity fitness function and the lighting control scheme represented by each population individual; Usage time fitness calculation module: used to calculate the usage time fitness of each population individual based on the lighting control scheme represented by each population individual, the usage time information of the corresponding street lamp and the time fitness function; Importance fitness calculation module: used to calculate the importance fitness of each population individual based on the importance set of street lamp positions, the importance fitness function, and the lighting control scheme represented by each population individual; Comprehensive fitness function construction module: used to normalize each fitness function according to the fitness of the number of lights on, the fitness of the uniformity of lights on, the fitness of the duration of use, and the fitness of importance of each population individual, and sum the normalized fitness functions to obtain the comprehensive fitness function; Comprehensive fitness calculation module: used to calculate the comprehensive fitness of each population individual according to the comprehensive fitness function; Light switch control scheme generation module: used to generate a light switch control scheme based on the representation of the population individual with the largest fitness if the comprehensive fitness of the population individual is greater than the fitness of a preset individual.

10. A smart street lighting control system, characterized in that: include: The intelligent street lighting control device, Internet of Things platform, and multiple street lamps according to claim 9: The Internet of Things platform controls and obtains the status of multiple street lamps and the illumination information of the surrounding environment of the corresponding street lamps and exchanges data with the street lamp lighting intelligent control device, and the street lamp lighting intelligent control device is used to generate a street lamp switch control plan.

Images