Automatic working method and system of solar street lamp and storage medium

Abstract

The invention relates to the technical field of solar street lamp control, in particular to an automatic working method and system of a solar street lamp and a storage medium. Firstly, the illumination monitoring period of the solar street lamp is obtained; secondly, monitoring environmental parameters of the environment where the solar street lamp is located in real time in the illumination monitoring period; thirdly, judging whether a lighting switch of the solar street lamp needs to be turned on or not according to the environmental parameters; then, at the end of the illumination monitoring period, obtaining the residual electric quantity of the solar street lamp and the monitoring period parameter of the solar street lamp in the next illumination monitoring period; and finally, according to the residual electric quantity and the monitoring period parameter, judging whether the solar street lamp is lack of power in the next illumination monitoring period. According to the method, the solar street lamp can be controlled by combining environmental factors around the solar street lamp, and the working efficiency of the solar street lamp is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of solar street lamp control, and in particular to an automatic working method, system and storage medium of a solar street lamp. Background Art

[0002] As the world pays more attention to renewable energy, solar energy, as a clean and sustainable form of energy, is increasingly widely used. In urban and rural road lighting systems, traditional street lamps mostly rely on power grids, which are not only expensive to install and maintain, but also face problems such as energy waste and environmental pollution. In contrast, solar street lamps, with their low-carbon, environmentally friendly, energy-saving and high-efficiency characteristics, are gradually replacing traditional electric street lamps and becoming a new lighting solution.

[0003] At present, most solar street lights on the market adopt fixed working modes, usually through light-controlled switches to achieve automatic switching. However, this simple control method cannot adapt to different environments and usage requirements. In the case of unstable lighting conditions or large pedestrian flow at night, the fixed mode may lead to insufficient lighting or waste of electricity.

[0004] To this end, an automatic working method, system and storage medium of a solar street lamp are proposed. Summary of the invention

[0005] The object of the present invention is to provide an automatic working method, system and storage medium for a solar street light. First, a lighting monitoring cycle of the solar street light is obtained; second, during the lighting monitoring cycle, environmental parameters of the environment in which the solar street light is located are monitored in real time; third, whether the solar street light needs to turn on the lighting switch is judged based on the environmental parameters; then, at the end of the lighting monitoring cycle, the remaining power of the solar street light and the monitoring cycle parameters of the solar street light in the next lighting monitoring cycle are obtained; finally, based on the remaining power and the monitoring cycle parameters, whether the solar street light will be short of power in the next lighting monitoring cycle is judged.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An automatic working method of a solar street lamp, comprising:

[0008] Acquire a lighting monitoring cycle of a solar street lamp; and monitor environmental parameters of an environment in which the solar street lamp is located in real time during the lighting monitoring cycle.

[0009] Furthermore, the environmental parameters include sunlight illumination, rainfall intensity and visibility of the environment in which the solar street light is located.

[0010] It is determined whether the solar street lamp needs to turn on the lighting switch according to the environmental parameters.

[0011] Further, according to the sunlight illumination in the environmental parameters, it is judged whether the solar street lamp needs to turn on the lighting switch; when the lighting switch of the solar street lamp is in the off state, if [T dq -t1,T dq ] If the sunlight illumination in the time period is less than the set illumination threshold, it is judged that T dq The lighting switch needs to be turned on at the moment; where t1 represents the set first time threshold; otherwise, it is judged that T dq There is no need to turn on the lighting switch at all times;

[0012] When the lighting switch of the solar street lamp is in the on state, if [T dq -t2,T dq ] If the sunlight illumination in the time period is not less than the set illumination threshold, it is judged that T dq There is no need to turn on the lighting switch at this moment; wherein t2 represents the set second time threshold; otherwise, it is determined that T dq The lighting switch needs to be turned on at all times.

[0013] Furthermore, after determining whether the solar street lamp needs to turn on the lighting switch, the method further includes:

[0014] When it is determined that the solar street lamp does not need to turn on the lighting switch, continue to obtain the environmental parameters of the environment in which the solar street lamp is located; when it is determined that the solar street lamp needs to turn on the lighting switch, obtain the initial lighting brightness of the solar street lamp according to the obtained environmental parameters; after the solar street lamp turns on the lighting switch, obtain the audio data collected by the solar street lamp, the driving data within the illumination range of the solar street lamp and the environmental parameters in real time;

[0015] Identify the audio data to determine whether there is abnormal audio;

[0016] When there is no abnormal audio, the brightness of the solar street light is adjusted in real time according to the driving data and the environmental parameters; the driving data includes vehicle flow data and pedestrian flow data; the vehicle flow data includes the number of vehicles and the speed of each vehicle; the pedestrian flow data includes the number of pedestrians and the speed of each pedestrian;

[0017] When there is abnormal audio, the time when the abnormal audio occurs is obtained, recorded as T yc , adjust the brightness of the solar street light to a preset brightness threshold, and in [T yc ,T yc +t3] time period, maintain this brightness, t3 is the set third time threshold.

[0018] At the end of the lighting monitoring cycle, the remaining power of the solar street lamp and the monitoring cycle parameters of the solar street lamp in the next lighting monitoring cycle are obtained.

[0019] Furthermore, the monitoring cycle parameters include: monitoring cycle categories and weather parameters; the monitoring cycle categories include holidays and weekdays; the weather parameters include the interval between sunrise and sunset, sunshine duration, average light intensity, average temperature, rainfall time, rainfall, snowfall and maximum wind speed.

[0020] According to the remaining power and the monitoring cycle parameters, it is determined whether the solar street lamp will be short of power in the next lighting monitoring cycle.

[0021] Furthermore, the judgment process is:

[0022] According to the illumination duration and average illumination intensity in the monitoring cycle parameters, obtaining the illumination electric energy that the solar street lamp can store according to the light energy in the next illumination monitoring cycle;

[0023] According to the illumination electric energy and the remaining electric energy, the releasable electric energy of the solar street lamp in the next lighting monitoring cycle is obtained; the monitoring cycle parameters of the solar street lamp in the historical lighting monitoring cycle are obtained, and a historical monitoring cycle parameter set is constructed; the monitoring cycle parameters of the solar street lamp in the next lighting monitoring cycle are compared with the historical monitoring cycle parameter set to obtain a predicted value of the electric energy demand in the next lighting monitoring cycle;

[0024] When the power demand prediction value is not greater than the releasable power, it indicates that the solar street lamp will not be short of power in the next lighting monitoring cycle; otherwise, it is determined that the solar street lamp will be short of power in the next lighting monitoring cycle, and based on the power demand prediction value and the releasable power, the power shortage amount is obtained and a power shortage warning is issued.

[0025] Furthermore, the process of obtaining the power demand forecast value includes:

[0026] Clustering the data in the historical monitoring cycle parameter set to obtain multiple monitoring cycle parameter clusters;

[0027] Each of the monitoring cycle parameter clusters contains a plurality of monitoring cycle parameters and corresponding real values ​​of power demand in a historical lighting monitoring cycle; using each of the monitoring cycle parameter clusters to train a power demand prediction model, X trained power demand prediction models are obtained, where X is equal to the number of the monitoring cycle parameter clusters;

[0028] Calculating the cluster center point of each monitoring period parameter cluster;

[0029] Calculate the similarity between the monitoring cycle parameters of the next lighting monitoring cycle and each of the cluster center points, and obtain the maximum similarity; use the power demand prediction model corresponding to the monitoring cycle parameter clustering cluster where the cluster center point corresponding to the maximum similarity is located as the power demand prediction model corresponding to the next lighting monitoring cycle;

[0030] The monitoring cycle parameters of the next lighting monitoring cycle are input into the corresponding power demand prediction model to obtain the power demand prediction value of the next lighting monitoring cycle.

[0031] An automatic working system of a solar street lamp, comprising:

[0032] Lighting monitoring cycle acquisition unit: used to obtain the lighting monitoring cycle of the solar street light;

[0033] Environmental parameter acquisition unit: used for real-time monitoring of environmental parameters of the environment in which the solar street lamp is located during the lighting monitoring cycle;

[0034] Lighting switch control unit: used to determine whether the solar street lamp needs to turn on the lighting switch according to the environmental parameters;

[0035] A future monitoring cycle parameter acquisition unit: used to acquire the remaining power of the solar street lamp and the monitoring cycle parameters of the solar street lamp in the next lighting monitoring cycle at the end of the lighting monitoring cycle;

[0036] A power shortage detection unit is used to determine whether the solar street lamp will be short of power in the next lighting monitoring cycle according to the remaining power and the monitoring cycle parameters.

[0037] Furthermore, the lighting switch control unit comprises:

[0038] According to the sunlight illumination in the environmental parameters, determining whether the solar street lamp needs to turn on the lighting switch;

[0039] When the lighting switch of the solar street lamp is in the off state, if [T dq -t1,T dq ] If the sunlight illumination in the time period is less than the set illumination threshold, it is judged that T dq The lighting switch needs to be turned on at the moment; where t1 represents the set first time threshold; otherwise, it is judged that T dq There is no need to turn on the lighting switch at all times;

[0040] When the lighting switch of the solar street lamp is in the on state, if [T dq -t2,T dq ] If the sunlight illumination in the time period is not less than the set illumination threshold, it is judged that T dqThere is no need to turn on the lighting switch at this moment; wherein t2 represents the set second time threshold; otherwise, it is determined that T dq The lighting switch needs to be turned on at all times.

[0041] Furthermore, the power failure detection unit comprises:

[0042] According to the illumination duration and average illumination intensity in the monitoring cycle parameters, obtaining the illumination electric energy that the solar street lamp can store according to the light energy in the next illumination monitoring cycle;

[0043] According to the illumination electric energy and the remaining electric energy, the releasable electric energy of the solar street lamp in the next lighting monitoring cycle is obtained; the monitoring cycle parameters of the solar street lamp in the historical lighting monitoring cycle are obtained, and a historical monitoring cycle parameter set is constructed; the monitoring cycle parameters of the solar street lamp in the next lighting monitoring cycle are compared with the historical monitoring cycle parameter set to obtain a predicted value of the electric energy demand in the next lighting monitoring cycle;

[0044] When the power demand prediction value is not greater than the releasable power, it indicates that the solar street lamp will not be short of power in the next lighting monitoring cycle; otherwise, it is determined that the solar street lamp will be short of power in the next lighting monitoring cycle, and based on the power demand prediction value and the releasable power, the power shortage amount is obtained and a power shortage warning is issued.

[0045] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the automatic working method of the solar street lamp described above are implemented.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] 1. During the lighting monitoring cycle, when the present invention determines that the solar street light needs to turn on the lighting switch, the initial lighting brightness of the solar street light is obtained according to the environmental parameters, and the audio data around the solar street light is identified; after identifying that there is no abnormal audio, the brightness of the solar street light is adjusted in real time according to the driving data and environmental parameters; otherwise, the brightness of the solar street light is directly adjusted to the preset brightness threshold. This method can timely adjust the brightness of the solar street light according to the surrounding flow of people, vehicle flow and abnormal conditions, thereby improving the working efficiency of the solar street light.

[0048] 2. At the end of the lighting monitoring cycle, the present invention determines the amount of electricity that can be released by the solar street lamp in the next lighting monitoring cycle based on the monitoring cycle parameters in the next lighting monitoring cycle and the remaining electricity of the current solar street lamp; at the same time, the power demand forecast value in the next lighting monitoring cycle is obtained, and whether the solar street lamp will be short of electricity in the next lighting monitoring cycle is determined based on the amount of electricity that can be released and the power demand forecast value. This method can accurately obtain the energy storage situation of the solar street lamp in the next lighting monitoring cycle, and when it is determined that there will be a power shortage, the power shortage is obtained and a power shortage warning is issued, so as to ensure the normal lighting of the solar street lamp in advance and improve the working efficiency of the solar street lamp.

[0049] 3. The present invention clusters the data in the historical monitoring cycle parameter set, and trains a corresponding power demand prediction model for each cluster cluster; when predicting the power demand of the next lighting monitoring cycle, the monitoring cycle parameters of the next lighting monitoring cycle and the similarity of each cluster center point are input into the corresponding power demand prediction model to obtain the power demand prediction value of the next lighting monitoring cycle. This method combines the data of the next lighting monitoring cycle for clustering and then prediction, and can accurately obtain the power demand prediction value of the next lighting monitoring cycle, providing a data basis for power shortage judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flow chart of an automatic working method of a solar street light provided by an embodiment of the present invention;

[0051] Figure 2 A structural diagram of an automatic working system of a solar street light provided by an embodiment of the present invention;

[0052] Figure 3 A power failure determination flow chart provided by an embodiment of the present invention;

[0053] Figure 4 A flow chart for obtaining a power demand forecast value provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] 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.

[0055] As the world pays more attention to renewable energy, solar energy, as a clean and sustainable form of energy, is increasingly widely used. In urban and rural road lighting systems, traditional street lamps mostly rely on power grids, which are not only expensive to install and maintain, but also face problems such as energy waste and environmental pollution. In contrast, solar street lamps, with their low-carbon, environmentally friendly, energy-saving and high-efficiency characteristics, are gradually replacing traditional electric street lamps and becoming a new lighting solution.

[0056] At present, most solar street lights on the market adopt fixed working modes, usually through light-controlled switches to achieve automatic switching. However, this simple control method cannot adapt to different environments and usage requirements. In the case of unstable lighting conditions or large pedestrian flow at night, the fixed mode may lead to insufficient lighting or waste of electricity.

[0057] To this end, the present invention provides an automatic working method for a solar street lamp. This method is applied to an automatic working system of a solar street lamp. For specific method flow charts and system structure diagrams, refer to Figure 1 and Figure 2 .

[0058] Embodiment 1

[0059] Reference Figure 1 S10 in the embodiment is applied to a lighting monitoring cycle acquisition unit of an automatic working system of a solar street lamp.

[0060] Furthermore, this embodiment obtains the lighting monitoring period of the solar street lamps in Road A. The lighting monitoring period of the solar street lamps in Road A is from 6:00 am every day to 6:00 am the next day.

[0061] Reference Figure 1 S20 in the embodiment is applied to an environmental parameter acquisition unit of an automatic working system of a solar street lamp.

[0062] Furthermore, the environmental parameters include daylight illumination, rainfall intensity and visibility of the environment in which the solar street light is located; the daylight illumination of the environment is obtained based on the light intensity sensor installed on the solar street light; the rainfall intensity and the visibility are obtained based on real-time weather.

[0063] This step of the present embodiment obtains the environmental parameters around the solar street light, and the environmental parameters can provide a data basis for later determining whether the solar street light needs to turn on the lighting switch and calculating the initial lighting brightness.

[0064] Reference Figure 1 The S30 in the embodiment is applied to a lighting switch control unit of an automatic working system of a solar street lamp.

[0065] Furthermore, during the lighting monitoring cycle, it is determined whether the solar street lamp needs to turn on the lighting switch according to the sunlight illumination in the environmental parameter;

[0066] When the lighting switch of the solar street lamp is in the off state, if [T dq -t1,T dq ] If the sunlight illumination in the time period is less than the set illumination threshold, it is judged that T dq The lighting switch needs to be turned on at the moment; where t1 represents the set first time threshold; otherwise, it is judged that T dq The lighting switch does not need to be turned on at all times; the illumination threshold can be set to 15lux and 16lux, etc.; in this embodiment, the first time threshold is set to 30 seconds, which can also be modified according to actual applications;

[0067] When the lighting switch of the solar street lamp is in the on state, if [T dq -t2,T dq ] If the sunlight illumination in the time period is not less than the set illumination threshold, it is judged that T dq If the lighting switch does not need to be turned on at any time, the lighting switch of the solar street lamp is turned off; wherein t2 represents the set second time threshold; otherwise, it is determined that T dq The lighting switch needs to be turned on at all times; in this embodiment, the first time threshold is set to 2 minutes, which can also be modified according to actual applications.

[0068] This step of the present embodiment determines whether the solar street lamp needs to turn on the lighting switch according to the sunlight illumination in the environmental parameters obtained in the continuous time period. Compared with the traditional fixed time control of the lighting switch of the solar street lamp, this method can flexibly turn on and off the lighting switch according to the real-time environment, thereby improving the lighting efficiency of the solar street lamp.

[0069] Furthermore, after judging whether the solar street lamp needs to turn on the lighting switch according to the environmental parameters, the method further includes:

[0070] When it is determined that the solar street lamp does not need to turn on the lighting switch, continue to obtain the environmental parameters of the environment in which the solar street lamp is located; when it is determined that the solar street lamp needs to turn on the lighting switch, obtain the initial lighting brightness of the solar street lamp based on the environmental parameters, and the specific process includes: obtaining the lighting brightness corresponding to the daylight illumination in the environmental parameters in the lighting brightness database, recorded as the first lighting brightness; the lighting brightness database is obtained in advance; the lighting brightness database contains lighting brightness data and daylight illumination data; the initial lighting brightness of the solar street lamp is calculated based on the first lighting brightness and the environmental parameters, and the calculation formula is:

[0071]

[0072] Wherein, csld represents the initial lighting brightness; zmld gzd represents the first lighting brightness; jyqd represents the rainfall intensity; njd represents the visibility; α1 and α2 represent the rainfall intensity coefficient and visibility coefficient respectively; α1 and α2 are obtained based on experience; min{} represents the function of taking the minimum value; exp() is an exponential function with a natural constant as the base; zmld max Indicates the maximum lighting brightness set for the solar street light;

[0073] After the solar street light turns on the lighting switch, the audio data collected by the solar street light, the driving data within the illumination interval of the solar street light and the environmental parameters are obtained in real time; the audio data is identified to determine whether there is abnormal audio; the abnormal audio includes impact sound, screaming sound and sudden braking sound, etc.;

[0074] When there is no abnormal audio, the brightness of the solar street light is adjusted in real time according to the driving data and the environmental parameters; the driving data includes vehicle flow data and pedestrian flow data; the vehicle flow data includes the number of vehicles and the speed of each vehicle; the vehicles include motor vehicles and non-motor vehicles; the pedestrian flow data includes the number of pedestrians and the speed of each pedestrian; the adjustment formula is:

[0075]

[0076] Among them, LD represents the brightness of the solar street light after real-time adjustment, sl xr Expressed as the number of pedestrians; sd xr Expressed as the average speed of all pedestrians; sl cl Expressed as the number of vehicles; sd cl It is represented by the average speed of all vehicles; α1, α2, α3 and α4 represent the rainfall intensity coefficient, visibility coefficient, pedestrian influence coefficient and vehicle influence coefficient respectively; the values ​​of α1 and α2 are the same as α1 and α2 in the initial lighting brightness calculation formula; α3 and α4 are obtained based on experience;

[0077] When there is abnormal audio, the time when the abnormal audio occurs is obtained, recorded as T yc , adjust the brightness of the solar street light to a preset brightness threshold, and in [T yc ,T yc +t3] time period, maintain this brightness, t3 is the set third time threshold; t3 can be set to 15 minutes, 30 minutes, etc.

[0078] In this step of the present embodiment, during the lighting monitoring cycle, when it is determined that the solar street light needs to turn on the lighting switch, the initial lighting brightness of the solar street light is obtained according to the environmental parameters, and the audio data around the solar street light is identified; after identifying that there is no abnormal audio, the brightness of the solar street light is adjusted in real time according to the driving data and environmental parameters; otherwise, the brightness of the solar street light is directly adjusted to the preset brightness threshold. This method can timely adjust the brightness of the solar street light according to the surrounding pedestrian flow, vehicle flow and abnormal conditions, thereby improving the working efficiency of the solar street light.

[0079] Reference Figure 1 S40 in the embodiment is applied to a future monitoring cycle parameter acquisition unit of an automatic working system of a solar street lamp.

[0080] Furthermore, the monitoring cycle parameters include: monitoring cycle categories and weather parameters; the monitoring cycle categories include holidays and weekdays; the weather parameters include the interval between sunrise and sunset, sunshine duration, average light intensity, average temperature, rainfall time, rainfall, snowfall and maximum wind speed.

[0081] In this step of this embodiment, the pedestrian and vehicle traffic on the road will be different on holidays and weekdays, and weather parameters will also affect the pedestrian and vehicle traffic on the road and the sunlight illumination of the environment. The monitoring cycle parameters obtained in this step can provide a data basis for subsequent power demand prediction.

[0082] Reference Figure 1 S50 in the embodiment is applied to a power failure detection unit of an automatic working system of a solar street lamp.

[0083] Further, refer to Figure 3 , the power failure judgment process is:

[0084] According to the illumination duration and average illumination intensity in the monitoring cycle parameters, the illumination electric energy that the solar street lamp can store according to the light energy in the next illumination monitoring cycle is obtained; according to the illumination electric energy and the remaining power, the releasable power of the solar street lamp in the next illumination monitoring cycle is obtained; the calculation formula is:

[0085] ksfdl=min{gzdn+sydl,zddl}-zdaq;

[0086] Among them, ksfdl represents the amount of electricity that can be released by the solar street light in the next lighting monitoring cycle; gzdn represents the light energy that can be stored according to light energy in the next lighting monitoring cycle; sydl represents the remaining electricity of the solar street light at the end of the current lighting monitoring cycle; zddl represents the maximum amount of electricity that can be stored by the solar street light; zdaq represents the set minimum safe electricity; min{} represents the function of taking the minimum value;

[0087] Obtain monitoring cycle parameters of the solar street lamp in a historical lighting monitoring cycle and construct a historical monitoring cycle parameter set; compare the monitoring cycle parameters of the solar street lamp in a next lighting monitoring cycle with the historical monitoring cycle parameter set to obtain a predicted value of power demand in the next lighting monitoring cycle;

[0088] Further, refer to Figure 4 , the process of obtaining the power demand forecast value includes:

[0089] Clustering the data in the historical monitoring cycle parameter set to obtain multiple monitoring cycle parameter clusters;

[0090] Each of the monitoring cycle parameter clusters contains a plurality of monitoring cycle parameters in a historical lighting monitoring cycle and the corresponding real values ​​of power demand; the number of monitoring cycle parameters contained in each of the monitoring cycle parameter clusters is greater than the set minimum value; the minimum value is obtained based on historical experience; each monitoring cycle parameter corresponds to a monitoring cycle category and weather parameters in a lighting monitoring cycle;

[0091] Using each of the monitoring cycle parameter clusters to train a power demand forecasting model, obtaining X trained power demand forecasting models, where X is equal to the number of the monitoring cycle parameter clusters;

[0092] The power demand forecasting model is constructed based on a feedforward neural network, and RMSprop is used to optimize the parameters of the power demand forecasting model; the training process of each power demand forecasting model includes:

[0093] Step 1: Randomly initialize the weights and biases of the electricity demand forecasting model;

[0094] Step 2: taking the monitoring period parameters in each of the monitoring period parameter clusters as input and the power demand forecast value as output;

[0095] Step 3: Calculate the power demand loss function value of the power demand prediction model according to the power demand prediction value and the corresponding power demand actual value;

[0096] Step 4: when the power demand loss function value converges, the trained power demand forecasting model is obtained according to the weight and bias; otherwise, the weight and bias of the power demand forecasting model are optimized by using RMSprop, and the process returns to step 2;

[0097] Furthermore, the calculation formula of the power demand loss function value is:

[0098]

[0099] Among them, sshs i It is represented as the power demand loss function value of the i-th power demand forecasting model; N i It is represented by the number of monitoring cycle parameters in the i-th monitoring cycle parameter cluster; It is represented as the jth electricity demand forecast value output by the i-th electricity demand forecast model; It is represented by the actual value of the power demand corresponding to the predicted value of the power demand.

[0100] Further, calculating the cluster center point of each monitoring period parameter cluster;

[0101] Calculate the similarity between the monitoring cycle parameters of the next lighting monitoring cycle and each of the cluster center points, and obtain the maximum similarity; use the power demand prediction model corresponding to the monitoring cycle parameter clustering cluster where the cluster center point corresponding to the maximum similarity is located as the power demand prediction model corresponding to the next lighting monitoring cycle;

[0102] The monitoring cycle parameters of the next lighting monitoring cycle are input into the corresponding power demand prediction model to obtain the power demand prediction value of the next lighting monitoring cycle.

[0103] Furthermore, this embodiment collects monitoring cycle parameters of solar street lights 1 and 2 in road A during 700 historical lighting monitoring cycles, performs clustering, and trains multiple electricity demand prediction models based on the clustered data. This embodiment collects monitoring cycle parameters of solar street lights 1 and 2 in road A during five different lighting monitoring cycles; and obtains power demand prediction values ​​in different lighting monitoring cycles through multiple prediction methods, and obtains the power demand prediction error between the power demand prediction value and the actual power demand value, and the calculation result is:

[0104]

[0105] Among them, ydwc represents the electricity consumption forecast error; dlxq yc Expressed as the predicted value of power demand; dlxq zs It is the actual value of power demand.

[0106] Furthermore, the effectiveness of the power demand prediction method in this embodiment is verified by the power consumption prediction error; refer to Table 1 and Table 2 for specific results.

[0107] Table 1 Solar street light 1 power demand forecast results

[0108] Lighting monitoring cycle number Method 1 Method 2 Method 3 Method 4 1 94.56％ 91.48％ 86.49％ 82.35％ 2 93.87％ 90.75％ 85.40％ 81.46％ 3 94.27％ 91.07％ 86.25％ 81.83％ 4 93.47％ 91.30％ 85.15％ 80.75％ 5 94.18％ 90.67％ 85.75％ 81.90％

[0109] Table 2 Solar street light 2 power demand forecast results

[0110] Lighting monitoring cycle number Method 1 Method 2 Method 3 Method 4 1 93.75％ 90.87％ 85.49％ 81.39％ 2 94.08％ 91.23％ 85.20％ 80.82％ 3 93.26％ 91.15％ 85.94％ 81.53％ 4 94.56％ 90.95％ 86.17％ 81.72％ 5 93.24％ 90.51％ 85.62％ 81.16％

[0111] Furthermore, the method 1 in Table 1 and Table 2 is provided in this embodiment, which first performs clustering and then uses the power demand prediction model for prediction; the method 2 replaces the power demand prediction model with a feedforward neural network model on the basis of method 1; the method 3 does not perform clustering on the basis of method 1, directly trains the power demand prediction model through the monitoring cycle parameters in the historical lighting monitoring cycle, and uses the trained power demand prediction model for prediction; the method 4 replaces the power demand prediction model with a feedforward neural network model on the basis of method 3. It can be seen from Table 1 and Table 2 that the method adopted in this embodiment can effectively improve the accuracy of power demand prediction.

[0112] This step of the present embodiment clusters the data in the historical monitoring cycle parameter set, and trains a corresponding power demand prediction model for each cluster cluster; when predicting the power demand of the next lighting monitoring cycle, the monitoring cycle parameters of the next lighting monitoring cycle and the similarity of each cluster center point are input into the corresponding power demand prediction model to obtain the power demand prediction value of the next lighting monitoring cycle. This method combines the data of the next lighting monitoring cycle for clustering and then prediction, and can accurately obtain the power demand prediction value of the next lighting monitoring cycle, providing a data basis for power shortage judgment.

[0113] Furthermore, when the power demand prediction value is not greater than the releasable power, it indicates that the solar street lamp will not be short of power in the next lighting monitoring cycle; otherwise, it is determined that the solar street lamp will be short of power in the next lighting monitoring cycle, and based on the power demand prediction value and the releasable power, the power shortage amount is obtained and a power shortage warning is issued.

[0114] At the end of the lighting monitoring cycle, this step of the embodiment determines the amount of electricity that can be released by the solar street lamp in the next lighting monitoring cycle based on the monitoring cycle parameters in the next lighting monitoring cycle and the remaining electricity of the current solar street lamp; at the same time, the predicted value of electricity demand in the next lighting monitoring cycle is obtained, and whether the solar street lamp will be short of electricity in the next lighting monitoring cycle is determined based on the amount of electricity that can be released and the predicted value of electricity demand. This method can accurately obtain the energy storage situation of the solar street lamp in the next lighting monitoring cycle, and when it is determined that there will be a power shortage, the power shortage is obtained and a power shortage warning is issued, so as to ensure the normal lighting of the solar street lamp in advance and improve the working efficiency of the solar street lamp.

[0115] Embodiment 2

[0116] In the first embodiment, the method of the present invention is combined with the system to realize the automatic operation of the solar street lamp; in the embodiment of the present application, the method of the present invention will be described again, and the specific implementation process includes:

[0117] Acquire a lighting monitoring cycle of a solar street lamp; and monitor environmental parameters of an environment in which the solar street lamp is located in real time during the lighting monitoring cycle.

[0118] Furthermore, the environmental parameters include sunlight illumination, rainfall intensity and visibility of the environment in which the solar street light is located.

[0119] It is determined whether the solar street lamp needs to turn on the lighting switch according to the environmental parameters.

[0120] Further, according to the sunlight illumination in the environmental parameters, it is judged whether the solar street lamp needs to turn on the lighting switch; when the lighting switch of the solar street lamp is in the off state, if [T dq -t1,T dq ] If the sunlight illumination in the time period is less than the set illumination threshold, it is judged that T dq The lighting switch needs to be turned on at the moment; where t1 represents the set first time threshold; otherwise, it is determined that T dq There is no need to turn on the lighting switch at all times;

[0121] When the lighting switch of the solar street lamp is in the on state, if [T dq -t2,T dq ] If the sunlight illumination in the time period is not less than the set illumination threshold, it is judged that T dq There is no need to turn on the lighting switch at this moment; wherein t2 represents the set second time threshold; otherwise, it is determined that T dq The lighting switch needs to be turned on at all times.

[0122] Furthermore, after determining whether the solar street lamp needs to turn on the lighting switch, the method further includes:

[0123] When it is determined that the solar street lamp does not need to turn on the lighting switch, continue to obtain environmental parameters of the environment in which the solar street lamp is located; when it is determined that the solar street lamp needs to turn on the lighting switch, obtain the initial lighting brightness of the solar street lamp according to the environmental parameters;

[0124] After the solar street lamp turns on the lighting switch, the audio data collected by the solar street lamp, the driving data within the illumination interval of the solar street lamp and the environmental parameters are obtained in real time;

[0125] Identify the audio data to determine whether there is abnormal audio;

[0126] When there is no abnormal audio, the brightness of the solar street light is adjusted in real time according to the driving data and the environmental parameters; the driving data includes vehicle flow data and pedestrian flow data; the vehicle flow data includes the number of vehicles and the speed of each vehicle; the pedestrian flow data includes the number of pedestrians and the speed of each pedestrian;

[0127] When there is abnormal audio, the time when the abnormal audio occurs is obtained, recorded as T yc , adjust the brightness of the solar street light to a preset brightness threshold, and in [T yc ,T yc +t3] time period, maintain this brightness, t3 is the set third time threshold.

[0128] At the end of the lighting monitoring cycle, the remaining power of the solar street lamp and the monitoring cycle parameters of the solar street lamp in the next lighting monitoring cycle are obtained.

[0129] Furthermore, the monitoring cycle parameters include: monitoring cycle categories and weather parameters; the monitoring cycle categories include holidays and weekdays; the weather parameters include the interval between sunrise and sunset, sunshine duration, average light intensity, average temperature, rainfall time, rainfall, snowfall and maximum wind speed.

[0130] According to the remaining power and the monitoring cycle parameters, it is determined whether the solar street lamp will be short of power in the next lighting monitoring cycle.

[0131] Furthermore, the judgment process is:

[0132] According to the illumination duration and average illumination intensity in the monitoring cycle parameters, obtaining the illumination electric energy that the solar street lamp can store according to the light energy in the next illumination monitoring cycle;

[0133] According to the illumination electric energy and the remaining electric energy, the releasable electric energy of the solar street lamp in the next lighting monitoring cycle is obtained; the monitoring cycle parameters of the solar street lamp in the historical lighting monitoring cycle are obtained, and a historical monitoring cycle parameter set is constructed; the monitoring cycle parameters of the solar street lamp in the next lighting monitoring cycle are compared with the historical monitoring cycle parameter set to obtain a predicted value of the electric energy demand in the next lighting monitoring cycle;

[0134] When the power demand prediction value is not greater than the releasable power, it indicates that the solar street lamp will not be short of power in the next lighting monitoring cycle; otherwise, it is determined that the solar street lamp will be short of power in the next lighting monitoring cycle, and based on the power demand prediction value and the releasable power, the power shortage amount is obtained and a power shortage warning is issued.

[0135] Furthermore, the process of obtaining the power demand forecast value includes:

[0136] Clustering the data in the historical monitoring cycle parameter set to obtain multiple monitoring cycle parameter clusters;

[0137] Each of the monitoring cycle parameter clusters contains a plurality of monitoring cycle parameters and corresponding real values ​​of power demand in a historical lighting monitoring cycle; using each of the monitoring cycle parameter clusters to train a power demand prediction model, X trained power demand prediction models are obtained, where X is equal to the number of the monitoring cycle parameter clusters;

[0138] Calculating the cluster center point of each monitoring period parameter cluster;

[0139] Calculate the similarity between the monitoring cycle parameters of the next lighting monitoring cycle and each of the cluster center points, and obtain the maximum similarity; use the power demand prediction model corresponding to the monitoring cycle parameter clustering cluster where the cluster center point corresponding to the maximum similarity is located as the power demand prediction model corresponding to the next lighting monitoring cycle;

[0140] The monitoring cycle parameters of the next lighting monitoring cycle are input into the corresponding power demand prediction model to obtain the power demand prediction value of the next lighting monitoring cycle.

[0141] In this embodiment, when it is determined that the solar street lamp needs to turn on the lighting switch during the lighting monitoring cycle, the initial lighting brightness of the solar street lamp is obtained according to the environmental parameters, and the audio data around the solar street lamp is identified; after identifying that there is no abnormal audio, the brightness of the solar street lamp is adjusted in real time according to the driving data and environmental parameters; otherwise, the brightness of the solar street lamp is directly adjusted to the preset brightness threshold. This method can timely adjust the brightness of the solar street lamp according to the surrounding flow of people, vehicle flow and abnormal conditions, thereby improving the working efficiency of the solar street lamp. At the end of the lighting monitoring cycle, this embodiment determines the amount of electricity that can be released by the solar street lamp in the next lighting monitoring cycle according to the monitoring cycle parameters in the next lighting monitoring cycle and the remaining power of the current solar street lamp; at the same time, the power demand prediction value in the next lighting monitoring cycle is obtained, and it is determined whether the solar street lamp will be short of power in the next lighting monitoring cycle according to the amount of electricity that can be released and the power demand prediction value. This method can accurately obtain the energy storage situation of the solar street lamp in the next lighting monitoring cycle, and when it is determined that there will be a power shortage, the power shortage is obtained and a power shortage warning is issued, so as to ensure the normal lighting of the solar street lamp in advance and improve the working efficiency of the solar street lamp. This embodiment clusters the data in the historical monitoring cycle parameter set, and trains a corresponding power demand prediction model for each cluster cluster; when predicting the power demand of the next lighting monitoring cycle, the monitoring cycle parameters of the next lighting monitoring cycle and the similarity of each cluster center point are input into the corresponding power demand prediction model to obtain the power demand prediction value of the next lighting monitoring cycle. This method combines the data of the next lighting monitoring cycle for clustering and then prediction, and can accurately obtain the power demand prediction value of the next lighting monitoring cycle, providing a data basis for power shortage judgment.

[0142] Embodiment 3

[0143] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute an automatic operation method of a solar street light as described in any of the above embodiments.

[0144] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An automatic working method of a solar street lamp, characterized in that: include: Get the lighting monitoring cycle of solar street lights; During the lighting monitoring cycle, real-time monitoring of environmental parameters of the environment in which the solar street lamp is located; Determining whether the solar street lamp needs to turn on the lighting switch according to the environmental parameters; At the end of the lighting monitoring cycle, obtaining the remaining power of the solar street lamp and the monitoring cycle parameters of the solar street lamp in the next lighting monitoring cycle; According to the remaining power and the monitoring cycle parameters, it is determined whether the solar street lamp will be short of power in the next lighting monitoring cycle. The determination process is as follows: According to the illumination duration and average illumination intensity in the monitoring cycle parameters, obtaining the illumination electric energy that the solar street lamp can store according to the light energy in the next illumination monitoring cycle; Obtaining the releasable power of the solar street lamp according to the illumination power and the remaining power; Acquire monitoring cycle parameters of the solar street lamp in a historical lighting monitoring cycle, and construct a historical monitoring cycle parameter set; Compare the monitoring cycle parameters of the solar street lamp in the next lighting monitoring cycle with the historical monitoring cycle parameter set to obtain a predicted value of power demand in the next lighting monitoring cycle; When the power demand forecast value is not greater than the releasable power, it indicates that the solar street lamp will not be short of power in the next lighting monitoring cycle; Otherwise, it is determined that the solar street lamp will be short of power in the next lighting monitoring cycle, and based on the power demand prediction value and the releasable power, the power shortage amount is obtained and a power shortage warning is issued.

2. The automatic working method of a solar street lamp according to claim 1, characterized in that: The environmental parameters include sunlight illumination, rainfall intensity and visibility of the environment in which the solar street light is located.

3. The automatic working method of a solar street lamp according to claim 1, characterized in that: Judging whether the solar street lamp needs to turn on the lighting switch according to the environmental parameters includes: According to the sunlight illumination in the environmental parameter, determining whether the solar street lamp needs to turn on the lighting switch; When the lighting switch of the solar street lamp is in the off state, if [T dq -t1,T dq ] If the sunlight illumination in the time period is less than the set illumination threshold, it is judged that T dq The lighting switch needs to be turned on at the moment; where t1 represents the set first time threshold; otherwise, it is judged that T dq There is no need to turn on the lighting switch at all times; When the lighting switch of the solar street lamp is in the on state, if [T dq -t2,T dq ] If the sunlight illumination in the time period is not less than the set illumination threshold, it is judged that T dq There is no need to turn on the lighting switch at this moment; wherein t2 represents the set second time threshold; otherwise, it is determined that T dq The lighting switch needs to be turned on at all times.

4. The automatic working method of a solar street light according to claim 1, characterized in that: After judging whether the solar street lamp needs to turn on the lighting switch according to the environmental parameters, the method further includes: When it is determined that the solar street lamp does not need to turn on the lighting switch, continue to obtain environmental parameters of the environment in which the solar street lamp is located; when it is determined that the solar street lamp needs to turn on the lighting switch, obtain the initial lighting brightness of the solar street lamp according to the obtained environmental parameters; After the solar street lamp turns on the lighting switch, the audio data collected by the solar street lamp, the driving data within the illumination interval of the solar street lamp and the environmental parameters are obtained in real time; Identify the audio data to determine whether there is abnormal audio; When there is no abnormal audio, the brightness of the solar street light is adjusted in real time according to the driving data and the environmental parameters; the driving data includes vehicle flow data and pedestrian flow data; the vehicle flow data includes the number of vehicles and the speed of each vehicle; the pedestrian flow data includes the number of pedestrians and the speed of each pedestrian; When there is abnormal audio, the time when the abnormal audio occurs is obtained, recorded as T yc , adjust the brightness of the solar street light to a preset brightness threshold, and in [T yc ,T yc +t3] time period, maintain this brightness, t3 is the set third time threshold.

5. The automatic working method of a solar street light according to claim 1, characterized in that: The monitoring cycle parameters include: monitoring cycle category and weather parameters; the monitoring cycle category includes holidays and weekdays; the weather parameters include sunrise and sunset interval, sunshine duration, average sunshine intensity, average temperature, rainfall time, rainfall, snowfall and maximum wind speed.

6. The automatic working method of a solar street light according to claim 1, characterized in that: The process of obtaining the power demand forecast value includes: Obtain each monitoring cycle parameter in the historical monitoring cycle parameter set; Clustering the data in the historical monitoring cycle parameter set to obtain multiple monitoring cycle parameter clusters; Each of the monitoring cycle parameter clusters contains a plurality of monitoring cycle parameters in a historical lighting monitoring cycle and corresponding actual values ​​of power demand; Using each of the monitoring cycle parameter clusters to train a power demand forecasting model, obtaining X trained power demand forecasting models, where X is equal to the number of the monitoring cycle parameter clusters; Calculating the cluster center point of each monitoring period parameter cluster; Calculate the similarity between the monitoring cycle parameters of the next lighting monitoring cycle and each of the cluster center points, and obtain the maximum similarity; use the power demand prediction model corresponding to the monitoring cycle parameter clustering cluster where the cluster center point corresponding to the maximum similarity is located as the power demand prediction model corresponding to the next lighting monitoring cycle; The monitoring cycle parameters of the next lighting monitoring cycle are input into the corresponding power demand prediction model to obtain the power demand prediction value of the next lighting monitoring cycle.

7. An automatic working system of a solar street light, characterized in that: include: Lighting monitoring cycle acquisition unit: used to obtain the lighting monitoring cycle of the solar street light; Environmental parameter acquisition unit: used for real-time monitoring of environmental parameters of the environment in which the solar street lamp is located during the lighting monitoring cycle; Lighting switch control unit: used to determine whether the solar street lamp needs to turn on the lighting switch according to the environmental parameters; A future monitoring cycle parameter acquisition unit: used to acquire the remaining power of the solar street lamp and the monitoring cycle parameters of the solar street lamp in the next lighting monitoring cycle at the end of the lighting monitoring cycle; A power shortage detection unit is used to determine whether the solar street lamp will be short of power in the next lighting monitoring cycle according to the remaining power and the monitoring cycle parameters.

8. The automatic working system of a solar street light according to claim 7, characterized in that: The lighting switch control unit comprises: According to the sunlight illumination in the environmental parameter, determining whether the solar street lamp needs to turn on the lighting switch; When the lighting switch of the solar street lamp is in the off state, if [T dq -t1,T dq ] If the sunlight illumination in the time period is less than the set illumination threshold, it is judged that T dq The lighting switch needs to be turned on at the moment; where t1 represents the set first time threshold; otherwise, it is judged that T dq There is no need to turn on the lighting switch at all times; When the lighting switch of the solar street lamp is in the on state, if [T dq -t2,T dq ] If the sunlight illumination in the time period is not less than the set illumination threshold, it is judged that T dq There is no need to turn on the lighting switch at this moment; wherein t2 represents the set second time threshold; otherwise, it is determined that T dq The lighting switch needs to be turned on at all times.

9. The automatic working system of a solar street light according to claim 7, characterized in that: The power shortage detection unit comprises: obtaining the illumination electric energy that can be stored according to the light energy of the solar street lamp in the next illumination monitoring cycle according to the illumination duration and the average illumination intensity in the monitoring cycle parameters; Obtaining the releasable power of the solar street lamp according to the illumination power and the remaining power; Acquire monitoring cycle parameters of the solar street lamp in a historical lighting monitoring cycle, and construct a historical monitoring cycle parameter set; Compare the monitoring cycle parameters of the solar street lamp in the next lighting monitoring cycle with the historical monitoring cycle parameter set to obtain a predicted value of power demand in the next lighting monitoring cycle; When the power demand prediction value is not greater than the releasable power, it indicates that the solar street lamp will not be short of power in the next lighting monitoring cycle; otherwise, it is determined that the solar street lamp will be short of power in the next lighting monitoring cycle, and based on the power demand prediction value and the releasable power, the power shortage amount is obtained and a power shortage warning is issued.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images