Intelligent control method and system of solar street lamp

Abstract

The application discloses an intelligent control method and system for solar street lamps, and particularly relates to the technical field of intelligent control; the method comprises the following steps: collecting photovoltaic power generation data and battery charging and discharging data of a solar street lamp node, analyzing spatial difference characteristics of photovoltaic power generation capacity of the solar street lamp node and time fluctuation characteristics of a battery energy storage state, and outputting the spatial difference characteristic data and the time fluctuation characteristic data; evaluating power generation uneven distribution characteristics caused by dynamic shielding and energy storage state mutation characteristics respectively, and outputting power generation spatial unevenness evaluation data and energy storage time mutation evaluation data; constructing a local energy link imbalance prediction model, outputting energy link imbalance prediction data of the solar street lamp node, dynamically adjusting power distribution and brightness control strategies of the solar street lamp, and realizing intelligent sensing and regulation of energy link instability under local shielding, so that the stability and energy saving of an overall lighting system of a solar street lamp group are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent control, more particularly, the present application relates to an intelligent control method and system for solar street lamps. BACKGROUND

[0002] As a new type of lighting facility widely used in urban roads, parks and public places, solar street lamps use solar energy for self-generation and energy storage for use at night or under insufficient sunlight conditions.

[0003] In actual operation, buildings, trees and other facilities in the environment of solar street lamps often cause dynamic shading, resulting in temporal and spatial non-uniformity of solar power generation capacity and energy storage state of the street lamp nodes. The local energy link imbalance caused by dynamic shading not only reduces the overall lighting stability of the solar street lamp group, but also causes the energy supply status of each street lamp node to fluctuate with time and locally mutate irregularly due to differences in location, shading time and angle, thereby affecting the reliability and stability of overall lighting. SUMMARY

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide an intelligent control method and system for solar street lamps to solve the problems raised in the background art.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0006] An intelligent control method for solar street lamps, comprising the following steps:

[0007] S1: Collecting photovoltaic power generation data and battery charge and discharge data of each solar street lamp node in a solar street lamp group, and preprocessing to output real-time power generation and energy storage state data;

[0008] S2: Based on the real-time power generation and energy storage state data, analyzing the spatial difference characteristics of photovoltaic power generation capacity, and outputting spatial difference characteristic data;

[0009] S3: Based on the real-time power generation and energy storage state data, analyzing the temporal fluctuation characteristics of the battery energy storage state, and outputting temporal fluctuation characteristic data;

[0010] S4: Based on the spatial difference characteristic data, evaluating the uneven distribution characteristics of power generation caused by dynamic shading, and outputting power generation spatial unevenness evaluation data;

[0011] S5: Based on the temporal fluctuation characteristic data, identifying the battery energy storage state mutation characteristics caused by temporary shading, and outputting energy storage temporal mutation evaluation data;

[0012] S6: constructing a local energy link imbalance prediction model based on the power generation space imbalance evaluation data and the energy storage time mutation evaluation data, and outputting energy link imbalance prediction data;

[0013] S7: dynamically adjusting the power distribution and brightness control strategy of the solar street lamp based on the energy link imbalance prediction data.

[0014] In a preferred embodiment, S1, specifically:

[0015] Collecting photovoltaic power generation data and battery charging and discharging data of each solar street lamp node in the solar street lamp group;

[0016] Based on the geographical position information of each solar street lamp node and the time series information of data collection, the photovoltaic power generation data and battery charging and discharging data are denoised, missing value processed and outlier processed, and the real-time power generation and energy storage state data of the solar street lamp node is output.

[0017] In a preferred embodiment, S2, specifically:

[0018] Griding the real-time power generation and energy storage state data of the solar street lamp node according to the geographical coordinates;

[0019] Calculating the average power value, power variance value and power range value of photovoltaic power generation for each space grid to form spatial statistical indicators;

[0020] Based on the spatial statistical indicators, a spatial difference analysis model is constructed, and the regional difference distribution of photovoltaic power generation capacity is identified through the Euclidean distance clustering algorithm to generate spatial clustering labels;

[0021] Outputting the spatial difference feature data of the solar street lamp node according to the spatial clustering labels.

[0022] In a preferred embodiment, S3, specifically:

[0023] Based on the real-time power generation and energy storage state data of the solar street lamp node, the battery charging and discharging data of each solar street lamp node is statistically segmented;

[0024] In each time period, the change trend of the remaining battery capacity of the solar street lamp node battery, the fluctuation amplitude of the charging current and the discharging current, and the range value of the charging voltage and the discharging voltage are calculated to form the time series fluctuation characteristic indicators of each solar street lamp node;

[0025] Normalizing the time series fluctuation characteristic indicators of each solar street lamp node to output the time fluctuation characteristic data of the solar street lamp node.

[0026] In a preferred embodiment, S4, specifically:

[0027] The photovoltaic power generation difference value is obtained by performing difference operation on the photovoltaic power generation average power value of each spatial grid in the spatial difference characteristic data of the solar street lamp node and the photovoltaic power generation average power value of the adjacent spatial grid;

[0028] A preset shielding difference threshold is set, a target spatial grid with a photovoltaic power generation difference value greater than the preset shielding difference threshold is extracted, and is identified;

[0029] The solar street lamp node number contained in the target spatial grid is counted, and the power generation imbalance degree index is calculated in combination with the corresponding photovoltaic power generation difference value;

[0030] The solar street lamp node number, target spatial grid identification and power generation imbalance degree index are summarized, and the power generation spatial imbalance evaluation data of the solar street lamp node is output.

[0031] In one preferred embodiment, S5, specifically:

[0032] A fluctuation threshold of battery energy storage state mutation is set;

[0033] The time node at which the battery energy storage state mutates is determined by performing fluctuation threshold judgment on the time fluctuation characteristic data of the solar street lamp node;

[0034] The solar street lamp node number at which the energy storage state mutates, and the mutation frequency and mutation amplitude of each corresponding solar street lamp node are counted;

[0035] The solar street lamp node number, the time node at which the battery energy storage state mutates, the mutation frequency and the mutation amplitude are summarized, and the energy storage time mutation evaluation data of the solar street lamp node is output.

[0036] In one preferred embodiment, S6, specifically:

[0037] The power generation spatial imbalance evaluation data and the energy storage time mutation evaluation data are aligned and fused according to the solar street lamp node number to form the imbalance feature vector of each solar street lamp node;

[0038] A regression prediction function of the local energy link imbalance prediction model is established with the imbalance feature vector as the independent variable and the energy link imbalance prediction value as the dependent variable;

[0039] According to the regression prediction function and the future prediction time period, the energy link imbalance prediction value of each solar street lamp node is calculated;

[0040] Based on the solar street lamp node number, the prediction time period and the energy link imbalance prediction value, the energy link imbalance prediction data of the solar street lamp node is output.

[0041] In a preferred embodiment, S7, specifically:

[0042] According to the energy link imbalance prediction value of each solar street lamp node in the energy link imbalance prediction data, the power distribution adjustment rule and the brightness control level rule are preset;

[0043] The energy link imbalance prediction value of each solar street lamp node is compared with the power distribution adjustment rule and the brightness control level rule respectively, and the target power distribution value and the target brightness level of each solar street lamp node in the prediction time period are determined;

[0044] Based on the target power distribution value and the target brightness level of each solar street lamp node, the power distribution and the brightness control strategy of the solar street lamp node are dynamically adjusted.

[0045] In another aspect, the present application provides a kind of intelligent control system of solar street lamp, comprising:

[0046] Data acquisition module: the photovoltaic power generation data and battery charge-discharge data of each solar street lamp node in solar street lamp group are collected and pretreated, and real-time power generation and energy storage state data are outputted;

[0047] Spatial analysis module: based on real-time power generation and energy storage state data, the spatial difference characteristics of photovoltaic power generation capacity are analyzed, and spatial difference characteristic data are outputted;

[0048] Time analysis module: based on real-time power generation and energy storage state data, the time fluctuation characteristics of battery energy storage state are analyzed, and time fluctuation characteristic data are outputted;

[0049] Power generation evaluation module: based on spatial difference characteristic data, the power generation imbalance distribution characteristics caused by dynamic shading are evaluated, and power generation spatial imbalance evaluation data are outputted;

[0050] Energy storage evaluation module: based on time fluctuation characteristic data, the battery energy storage state mutation characteristics caused by temporary shading are identified, and energy storage time mutation evaluation data are outputted;

[0051] Imbalance prediction module: according to power generation spatial imbalance evaluation data and energy storage time mutation evaluation data, local energy link imbalance prediction model is constructed, and energy link imbalance prediction data are outputted;

[0052] Strategy adjustment module: based on energy link imbalance prediction data, the power distribution and brightness control strategy of solar street lamp are dynamically adjusted.

[0053] The technical effects and advantages of the intelligent control method and system of solar street lamp of the present application are:

[0054] The photovoltaic power generation and battery charging and discharging data of each street lamp node are preprocessed, so that the accuracy and integrity of the input data are improved; the spatial difference feature analysis can reveal the regional distribution law of the photovoltaic capacity of each node in the group, and provide a quantitative basis for identifying the uneven power generation phenomenon caused by dynamic shading; the time fluctuation feature analysis can capture the sudden change of the battery energy storage state, and provide a sensitive index for detecting the energy storage mutation caused by temporary shading; the local energy link imbalance prediction model constructed based on the spatial difference feature data and the time fluctuation feature data can predict the energy supply and demand imbalance degree of each node in the future period in advance, realize the change from passive response to active warning; and the power distribution and brightness control strategy is dynamically adjusted according to the prediction result, so that the overall lighting quality can be ensured while the electric energy is saved to the maximum, and the operation stability and reliability of the solar street lamp group in the complex shading environment are improved. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 FIG. 1 is a schematic diagram of an intelligent control method of a solar street lamp according to the present application;

[0056] Figure 2 FIG. 2 is a structural schematic diagram of an intelligent control system of a solar street lamp according to the present application. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0058] Embodiment 1

[0059] Figure 1 The present application provides an intelligent control method of a solar street lamp, which comprises the following steps:

[0060] S1: collecting photovoltaic power generation data and battery charging and discharging data of each solar street lamp node in a solar street lamp group, and pre-processing, outputting real-time power generation and energy storage state data;

[0061] S2: based on the real-time power generation and energy storage state data, analyzing the spatial difference feature of the photovoltaic power generation capacity, and outputting spatial difference feature data;

[0062] S3: based on the real-time power generation and energy storage state data, analyzing the time fluctuation feature of the battery energy storage state, and outputting time fluctuation feature data;

[0063] S4: Based on the spatial difference feature data, the uneven distribution characteristics of power generation caused by dynamic occlusion are evaluated, and power generation spatial imbalance evaluation data are output;

[0064] S5: Based on the time fluctuation feature data, the battery energy storage state mutation characteristics caused by temporary occlusion are identified, and energy storage time mutation evaluation data are output;

[0065] S6: According to the power generation spatial imbalance evaluation data and the energy storage time mutation evaluation data, a local energy link imbalance prediction model is constructed, and energy link imbalance prediction data are output;

[0066] S7: Based on the energy link imbalance prediction data, the power distribution and brightness control strategy of the solar street lamp is dynamically adjusted.

[0067] S1: Collect and preprocess the photovoltaic power generation data and battery charge and discharge data of each solar street lamp node in the solar street lamp group, and output real-time power generation and energy storage state data, including:

[0068] Collect and preprocess the photovoltaic power generation data and battery charge and discharge data of each solar street lamp node in the solar street lamp group, and output real-time power generation and energy storage state data, including:

[0069] The solar street lamp group is a whole set of multiple solar street lamp nodes deployed on both sides of a certain area or road, for example, 50 solar street lamp nodes distributed on both sides of a city park or street form a solar street lamp group. Each solar street lamp node includes at least one solar panel, at least one battery pack, at least one LED lamp, and corresponding data acquisition and control devices. Photovoltaic power generation data are real-time output voltage, current and power electrical parameter data of solar panels in actual operation, for example, the real-time output voltage of a solar panel on a certain solar street lamp node is 12 volts, the current is 3 amperes, and the corresponding power is 36 watts. Battery charge and discharge data are real-time electrical parameter data generated by the battery pack during actual operation, including real-time charging voltage, real-time discharging voltage, real-time charging current, real-time discharging current and real-time remaining battery capacity, for example, the real-time charging voltage of a battery in a certain solar street lamp node is 12.5 volts, the real-time discharging voltage is 12 volts, the real-time charging current is 1.2 amperes, the real-time discharging current is 1.0 amperes, and the real-time remaining battery capacity is 85%. During data collection, photovoltaic power generation data and battery charge and discharge data of each solar street lamp node are acquired in real time through sensors, and the position information of each data collection point is stored in the form of geographic coordinates, for example, the longitude and latitude coordinates of each solar street lamp node are determined by GPS positioning equipment, and the data collection frequency can be set to record data every 1 minute, that is, the time series information of data collection is accurate to the minute level.

[0070] Based on the geographical position information of each solar street lamp node and the time series information of data collection, the photovoltaic power generation data and the battery charging and discharging data are denoised, missing value processed and outlier processed, and the real-time power generation and energy storage state data of the solar street lamp node are outputted.

[0071] The denoising processing refers to processing the high-frequency noise signal in the data by using the median filtering method or the moving average method to eliminate the random fluctuations in the data; the missing value processing is to repair the missing data caused by sensor communication failure or temporary network interruption in the data collection process, for example, if a node lacks current data in a specific time period in the continuous data collection process, linear interpolation is performed on the data before and after the time to supplement the missing data; the outlier processing is to identify and eliminate error data points deviating from the actual running state, for example, the normal range of the output power of the solar cell panel under actual running conditions is between 30 and 40 watts, if the output power of a solar street lamp node suddenly appears 200 watts, it is determined as an outlier, the outlier is eliminated and restored to a reasonable data range by interpolation method. After the above denoising, missing value processing and outlier processing, the data set reflecting the current actual running state of the solar street lamp node is obtained, that is, the real-time power generation and energy storage state data. The real-time power generation and energy storage state data includes the geographical coordinate information of the node, the time series information and the processed real-time photovoltaic power generation data and real-time battery charging and discharging data, for example, the output data form is: the solar street lamp node numbered 001, the actual real-time output voltage at a specific date and time (for example, May 25, 2025, 14:30) is 12 volts, the real-time output current is 3 amperes, the real-time output power is 36 watts, the real-time charging voltage is 12.5 volts, the real-time discharging voltage is 12 volts, the real-time charging current is 1.2 amperes, the real-time discharging current is 1.0 amperes, the real-time remaining battery capacity is 85%, the geographical position is 30.567 degrees north latitude and 104.067 degrees east longitude.

[0072] S2: Based on the real-time power generation and energy storage state data, analyze the spatial difference characteristics of the photovoltaic power generation capacity, and output the spatial difference characteristic data, including:

[0073] The real-time power generation and energy storage state data of the solar street lamp node is grid spatially divided according to the geographical coordinates;

[0074] The geographical position data of each solar street lamp node in the solar street lamp group is divided into a plurality of continuous spatial grids according to certain rules, each spatial grid corresponds to a specific geographical position range, for example, the longitude and latitude range of 50 solar street lamp nodes arranged in a city park is divided into grids, that is, a spatial grid is established every 0.001 degrees of longitude and latitude, the solar street lamp nodes within the range of north latitude 30.567 degrees to north latitude 30.568 degrees and east longitude 104.067 degrees to east longitude 104.068 degrees are classified into the same spatial grid, and other solar street lamp nodes are classified into adjacent or other spatial grids, and each spatial grid contains one or more solar street lamp nodes. The data result of spatial grid division is that the real-time power generation and energy storage state data of each solar street lamp node is identified and classified by spatial position, and each spatial grid has unique spatial position identification information.

[0075] The average photovoltaic power value, the power generation power variance value and the power generation power range value of each spatial grid are calculated to form spatial statistical indicators.

[0076] Based on the divided spatial grid, the photovoltaic power generation data in the real-time power generation and energy storage state data of the solar street lamp nodes contained in each spatial grid is statistically calculated, including calculating the average photovoltaic power value, the power generation power variance value and the power generation power range value. The average photovoltaic power value refers to the average value of the real-time output power data of all solar street lamp nodes in the spatial grid in the same time period, for example, the spatial grid contains 5 solar street lamp nodes, the real-time output power is 34 watts, 35 watts, 36 watts, 33 watts and 32 watts respectively, then the sum of the above 5 powers is divided by 5 to get the average photovoltaic power value of 34 watts; the power generation power variance value is the variance of the real-time output power data of the solar street lamp nodes in the spatial grid, which is used to reflect the dispersion degree between the real-time power outputs of different solar street lamp nodes in the spatial grid, for example, based on the real-time output power data of 5 solar street lamp nodes, the sum of the squares of the differences between each node and the average value is calculated, and then divided by the number 5 to get the power generation power variance value; the power generation power range value is the difference between the maximum and minimum values of the real-time output power data of the solar street lamp nodes in the spatial grid, for example, the maximum value of the real-time output power of the 5 nodes is 36 watts, and the minimum value is 32 watts, then the power generation power range value is 4 watts. The above data together constitute the spatial statistical indicators of each spatial grid, through calculation, each spatial grid obtains the corresponding average photovoltaic power value, power generation power variance value and power generation power range value.

[0077] Based on the spatial statistical index, a spatial difference analysis model is constructed, and the regional difference distribution of the photovoltaic power generation capacity is identified by using the Euclidean distance clustering algorithm to generate a spatial clustering label.

[0078] The spatial statistical index of each spatial grid obtained, i.e., the average power value, the power variance value and the power range value of photovoltaic power generation, jointly constitutes a feature data vector. Based on the feature data vector, a spatial difference analysis model is constructed. The Euclidean distance clustering algorithm is used to calculate the feature data vector to determine the similarity and difference between the spatial grids. The Euclidean distance clustering algorithm specifically calculates the Euclidean distance between the feature data vectors of any two spatial grids. For example, the spatial statistical index of spatial grid A is an average power of 34 watts, a power variance of 0.8, and a power range of 4 watts, and the spatial statistical index of spatial grid B is an average power of 30 watts, a power variance of 2.5, and a power range of 7 watts. Then, the Euclidean distance between grid A and grid B is calculated. Then, the spatial grids with a Euclidean distance less than a set threshold are divided into the same class by the Euclidean distance clustering algorithm, and the spatial grids with a Euclidean distance greater than the set threshold are divided into different classes. A larger Euclidean distance indicates a larger difference between the spatial grids, and a smaller Euclidean distance indicates a smaller difference between the spatial grids. Through the above calculation, for example, 50 spatial grids are divided into different classes, such as class A representing a region with high power generation capacity, class B representing a region with medium power generation capacity, and class C representing a region with low power generation capacity. Each spatial grid is assigned a spatial clustering label representing the class to which it belongs, reflecting the regional difference distribution characteristics between the spatial grids.

[0079] According to the spatial clustering label, the spatial difference feature data of the solar street lamp node is outputted;

[0080] After the clustering analysis is completed, each spatial grid has a spatial clustering label, which identifies the regional difference class of the solar street lamp node. For example, the spatial grid labels of the solar street lamp nodes numbered 001 to 005 in the spatial grid are all class A, and the output spatial difference feature data is the corresponding relationship between the node number and the class A label. Similarly, other solar street lamp nodes can be assigned to class B or class C, and the corresponding relationship between the node number and the corresponding spatial clustering label is outputted. The output data is, for example, the spatial difference feature data of solar street lamp nodes numbered 001, 002, 003, 004, and 005 is "class A", the spatial difference feature data of nodes numbered 006, 007, 008, 009, and 010 is "class B", and so on. The output of the spatial difference feature data of all solar street lamp nodes is completed.

[0081] S3: Based on the real-time power generation and energy storage state data, the fluctuation characteristics of the battery energy storage state in time are analyzed, and the time fluctuation feature data is outputted, including:

[0082] Based on the real-time power generation and energy storage state data of the solar street lamp node, the battery charging and discharging data of each solar street lamp node is segmented and counted;

[0083] For each solar street lamp node in the solar street lamp group, the battery charging and discharging data contained in the real-time power generation and energy storage state data is continuously divided according to a fixed time length, and the divided time period data is counted, calculated and analyzed respectively; for example, if the data collection frequency is to record data once every minute, the battery charging and discharging data within 24 hours can be divided into 1 hour as a statistical time period, and 24 continuous and same length time periods are obtained; each time period data includes real-time charging voltage, discharging voltage, charging current, discharging current and remaining battery capacity and other electrical parameters; for example, the data of the solar street lamp node numbered 001 in the time period from 0:00 to 1:00 on a certain day, that is, all the charging voltage, discharging voltage, charging current, discharging current and remaining battery capacity data recorded during 0:00 to 1:00 are taken as a statistical unit, the data from 1:00 to 2:00 is taken as the next statistical unit, and so on, the data of 24 hours in a day is continuously divided into 24 statistical units, so as to calculate and analyze each time unit respectively.

[0084] In each time period, the change trend of the remaining battery capacity of the solar street lamp node battery, the fluctuation amplitude of the charging current and the discharging current, and the range value of the charging voltage and the discharging voltage are calculated to form the time series fluctuation characteristic index of each solar street lamp node;

[0085] For the data in each time period, the trend of the remaining battery capacity of the solar street lamp node battery is analyzed, and the direction and rate of the change of the remaining battery capacity in the time period are calculated by linear trend fitting method. For example, the real-time remaining battery capacity of a certain solar street lamp node from 0 minutes to 60 minutes in an hour is 85%, 84.8%, 84.6%, 84.3% and a series of data, and the capacity decrease rate is about 0.0117% per minute through linear trend calculation, indicating that the overall trend of the battery in the time period is continuous capacity decrease; the fluctuation amplitude of the charging current and the discharging current is calculated respectively, that is, the difference between the maximum and minimum values of the charging current and the discharging current in each time period is calculated, for example, the real-time charging current of a certain solar street lamp node in the same time period changes between 1.2 ampere and 1.5 ampere, and the charging current fluctuation amplitude is 0.3 ampere, and the discharging current changes from 0.8 ampere to 1.0 ampere in the same period, and the discharging current fluctuation amplitude is 0.2 ampere; at the same time, the range of the real-time charging voltage and the real-time discharging voltage of the battery in each time period is calculated, that is, the difference between the maximum and minimum values of the real-time voltage data, for example, the maximum value of the real-time charging voltage of the battery in the same time period is 12.5 volts, and the minimum value is 12.2 volts, and the charging voltage range is 0.3 volts, and the maximum value of the real-time data of the discharging voltage is 12.0 volts, and the minimum value is 11.8 volts, and the discharging voltage range is 0.2 volts. The above data after calculation constitutes the time series fluctuation characteristic index of each solar street lamp node in the time period.

[0086] The time series fluctuation characteristic index of each solar street lamp node is normalized to output the time fluctuation characteristic data of the solar street lamp node.

[0087] The normalization calculation method is: first, the maximum and minimum values of the corresponding characteristic index of all solar street lamp nodes in all time periods are counted, for example, if the maximum value of the battery capacity change trend index of all solar street lamp nodes in 24 time periods of a day is 0.02% per minute, and the minimum value is 0.005% per minute, the capacity change trend index of a certain solar street lamp node is 0.0117% per minute, and the normalization calculation is carried out: (0.0117%-0.005%) / (0.02%-0.005%) is about 0.4467; similarly, the same normalization calculation is carried out for the charging current fluctuation amplitude, the discharging current fluctuation amplitude, the charging voltage range and the discharging voltage range, and all the characteristic indexes are unified to 0 to 1.

[0088] After the normalization processing is completed, time fluctuation characteristic data in a unified numerical range is generated for each solar street lamp node, including normalized values of battery capacity change trend, charging current and discharging current fluctuation amplitude, charging voltage and discharging voltage range value and other indicators. For example, the time fluctuation characteristic data output is as follows: the solar street lamp node numbered 001 has a normalized battery capacity change trend index of 0.4467, a charging current fluctuation amplitude index of 0.3, a discharging current fluctuation amplitude index of 0.2, a charging voltage range value index of 0.25, and a discharging voltage range value index of 0.2 during the period from 0:00 to 1:00 on May 25, 2025, and all the normalized characteristic index data calculated for each solar street lamp node in each time period is listed.

[0089] S4: Based on the spatial difference characteristic data, the uneven distribution characteristics of power generation caused by dynamic occlusion are evaluated, and power generation spatial unevenness evaluation data is output, including:

[0090] The photovoltaic power generation difference value is obtained by performing difference operation on the photovoltaic power generation average power value of each spatial grid and the photovoltaic power generation average power value of the adjacent spatial grid in the spatial difference characteristic data of the solar street lamp node.

[0091] Based on the spatial difference characteristic data of the solar street lamp node, the photovoltaic power generation average power of all spatial grids in the solar street lamp group is compared and calculated, and the power difference value between each spatial grid and the adjacent spatial grid is obtained; for example, the photovoltaic power generation average power value in the spatial range of grid A in a certain solar street lamp group is 35 watts, and the photovoltaic power generation average power value of adjacent grid B is 32 watts, then the power difference value between grid A and grid B is calculated by difference operation, which is 35 watts minus 32 watts, and the difference value is 3 watts; if there is another adjacent grid C on the other side of grid B, and the photovoltaic power generation average power value in the spatial range of grid C is 34 watts, then the difference value between grid B and grid C is calculated by difference operation, which is 34 watts minus 32 watts, and the difference value is 2 watts; the photovoltaic power generation difference value between all spatial grids and adjacent spatial grids in the entire solar street lamp group range is obtained by performing difference calculation on the photovoltaic power generation average power value of each spatial grid and all adjacent spatial grids in the above manner.

[0092] A preset occlusion difference threshold is set, and target spatial grids with a photovoltaic power generation difference value greater than the preset occlusion difference threshold are extracted and identified.

[0093] After obtaining the difference value of photovoltaic power generation between the space grids, a shielding difference threshold value is set in advance to determine whether the power difference value between the space grids exceeds the normal photovoltaic power generation difference range, for example, the shielding difference threshold value is set to 2.5 watts, the power difference value between the space grid A and the space grid B is 3 watts, which exceeds the preset shielding difference threshold value 2.5 watts, so the space grid A and the space grid B are marked as target space grids, and are identified as having a photovoltaic power generation imbalance condition; the difference value between the adjacent space grid B and the space grid C is 2 watts, which does not exceed the shielding difference threshold value 2.5 watts, and is not marked as a target space grid; in this way, a set of target space grid set with a photovoltaic power generation imbalance condition can be obtained; for example, the photovoltaic power generation difference values of the three space grids A1, A2 and A3 in a certain area are 3.5 watts, 4 watts and 3.2 watts respectively, all of which are greater than the shielding difference threshold value 2.5 watts, so the space grids A1, A2 and A3 are all identified as target space grids.

[0094] The solar street lamp node numbers contained in the target space grids are counted, and the power generation imbalance degree index is calculated in combination with the corresponding photovoltaic power generation difference value.

[0095] The solar street lamp nodes contained in each target space grid are numbered and counted, for example, the solar street lamp node numbers contained in the space grid A1 are 001, 002 and 003, the solar street lamp node numbers contained in the space grid A2 are 004, 005 and 006, and the solar street lamp node numbers contained in the space grid A3 are 007, 008 and 009; based on the corresponding photovoltaic power generation difference value of each target space grid, the power generation imbalance degree index is calculated, which is a quantitative index reflecting the imbalance degree of photovoltaic power generation of the space grid, for example, the power generation imbalance degree index = photovoltaic power generation difference value / average photovoltaic power value in the space grid; taking the space grid A1 as an example, the photovoltaic power generation difference value of the space grid A1 is 3.5 watts, and the average photovoltaic power value in the space grid is 35 watts, so the power generation imbalance degree index is calculated to be 0.1; similarly, for the space grid A2, the photovoltaic power generation difference value is 4 watts, and the average power value in the space grid is 32 watts, so the power generation imbalance degree index is 0.125, and the power generation imbalance degree index of the space grid A3 is calculated in a similar manner; in this way, the power generation imbalance degree index of all target space grids is calculated, and the contained node numbers are counted correspondingly, which are used to evaluate the power generation imbalance of each solar street lamp node.

[0096] The solar street lamp node numbers, target space grid identification and power generation imbalance degree index are summarized, and the power generation space imbalance evaluation data of the solar street lamp nodes are outputted.

[0097] After the generation imbalance index is calculated, the generation imbalance index of all target space grids, the node numbers of all solar street lamps contained, and the spatial position identification of the target space grid itself are uniformly integrated into the generation space imbalance evaluation data of the solar street lamp node. For example, the output format of the generation space imbalance evaluation data is: the solar street lamp node numbers 001, 002, and 003 are contained in the space grid A1, and the generation imbalance index is 0.1; the solar street lamp node numbers 004, 005, and 006 are contained in the space grid A2, and the generation imbalance index is 0.125; the solar street lamp node numbers 007, 008, and 009 are contained in the space grid A3, and the generation imbalance index is 0.114; and so on. The spatial position identification, node number, and corresponding generation imbalance index of all target space grids are listed. The generation space imbalance evaluation data reflects the imbalance condition of each region in the overall range of the solar street lamp group.

[0098] S5: Based on the time fluctuation characteristic data, the battery energy storage state mutation characteristics caused by temporary shielding are identified, and the energy storage time mutation evaluation data is output, including:

[0099] The fluctuation threshold of battery energy storage state mutation is set;

[0100] According to the stability requirement of the battery energy storage state in the actual operation process of the solar street lamp node, the fluctuation threshold is set to determine whether the battery energy storage state has a mutation condition. The fluctuation threshold of the battery energy storage state mutation includes the threshold for the change trend of the remaining battery capacity, the threshold for the fluctuation amplitude of the charging current, the threshold for the fluctuation amplitude of the discharging current, and the threshold for the charging voltage and discharging voltage range. For example, in the actual application scenario, according to the long-term observation data of the battery performance, it is determined that the normal change trend rate of the remaining battery capacity per minute is 0.005% to 0.02%, and the fluctuation threshold of the change trend of the remaining battery capacity is set to 0.025% per minute. When the change trend of the remaining battery capacity exceeds 0.025% per minute, it is determined to be a mutation. The fluctuation amplitude of the charging current and the discharging current generally changes within a range of less than 0.5 ampere, and the fluctuation amplitude threshold is set to 0.6 ampere. The charging voltage and discharging voltage range generally does not exceed 0.5 volt in the actual battery normal charging and discharging process, and the voltage range threshold is set to 0.6 volt. In the setting process, the above fluctuation thresholds are set according to long-term data observation and actual demand analysis, and are applicable to the battery performance analysis and state mutation monitoring of all solar street lamp nodes in the solar street lamp group.

[0101] The time fluctuation characteristic data of the solar street lamp node is subjected to fluctuation threshold judgment to determine the time node at which the battery energy storage state has a mutation;

[0102] Based on the set fluctuation threshold of battery energy storage state mutation, the time series fluctuation characteristic indexes calculated from the battery charge and discharge data of each statistical time period of the solar street lamp nodes are compared and judged item by item to determine whether the energy storage state mutation occurs. For each statistical time period of each solar street lamp node, it is judged whether the change trend value of the remaining battery capacity exceeds the set fluctuation threshold, for example, the change trend value of the remaining battery capacity of the solar street lamp node numbered 001 is 0.027% per minute in the statistical time period from 10:00 to 11:00 on May 25, 2025, which exceeds the set fluctuation threshold of 0.025%, so it is determined that the energy storage state mutation occurs. It is judged whether the fluctuation amplitude of the charging current and the discharging current exceeds the set fluctuation threshold, for example, the fluctuation amplitude of the charging current of the solar street lamp node numbered 002 is 0.65 amperes in the statistical time period from 11:00 to 12:00 on the same day, which exceeds the set fluctuation threshold of 0.6 amperes, so it is determined that the energy storage state mutation exists. It is judged whether the range value of the charging voltage and the discharging voltage exceeds the set fluctuation threshold, for example, the range value of the charging voltage of the solar street lamp node numbered 003 is 0.7 volts in the statistical time period from 13:00 to 14:00 on the same day, which exceeds the fluctuation threshold of 0.6 volts, so it is determined that the energy storage state mutation occurs in the node numbered 003. By judging each fluctuation index of all solar street lamp nodes in each statistical time period, all time nodes of the battery energy storage state mutation are determined.

[0103] The number of solar street lamp nodes that occur energy storage state mutation and the mutation times and mutation amplitudes of each corresponding solar street lamp node are counted.

[0104] After determining the time node of the sudden change of the battery energy storage state, the number of each solar street lamp node with a sudden change in energy storage state is counted, as well as the total number of sudden changes in energy storage state of each solar street lamp node within a certain statistical period and the amplitude corresponding to each sudden change; for example, for the solar street lamp node numbered 001, after counting, in the 24 statistical time periods of May 25, 2025, a total of 3 times of sudden change in the trend of residual battery capacity occurred, which occurred at 10:00-11:00, 14:00-15:00 and 17:00-18:00, and the amplitude of each sudden change was 0.027%, 0.03% and 0.026% respectively; the solar street lamp node numbered 002, in the same day statistical period, a total of 2 times of sudden change in the amplitude of charging current fluctuation occurred, which occurred at 11:00-12:00 and 16:00-17:00, and the sudden change amplitudes were 0.65 amperes and 0.68 amperes respectively; the solar street lamp node numbered 003, in the whole day statistical period, a total of 1 time of sudden change in the charging voltage range value occurred, which occurred in the 13:00-14:00 statistical time period, and the sudden change amplitude was 0.7 volts. Through the above statistical process, the number of sudden changes in energy storage state and the amplitude of each sudden change of all solar street lamp nodes are recorded, which provides a basis for dynamic management of energy storage state.

[0105] The solar street lamp node number, the time node of the sudden change of the battery energy storage state, the number of sudden changes and the amplitude of sudden changes are summarized, and the energy storage time mutation evaluation data of the solar street lamp node is output.

[0106] After completing the counting of all the number of sudden changes and amplitudes, the number of all solar street lamp nodes with a sudden change in energy storage state, the time node of the sudden change of the energy storage state, the number of sudden changes and the amplitude of sudden changes are summarized and integrated into the energy storage time mutation evaluation data; for example, the output format of the energy storage time mutation evaluation data is: the solar street lamp node numbered 001, on May 25, 2025, 3 times of sudden change in energy storage state occurred at 10:00-11:00, 14:00-15:00 and 17:00-18:00 respectively, and the amplitudes of the sudden changes were 0.027%, 0.03% and 0.026% respectively; the solar street lamp node numbered 002, on May 25, 2025, 2 times of sudden change in the amplitude of charging current fluctuation occurred at 11:00-12:00 and 16:00-17:00 respectively, and the amplitudes of the sudden changes were 0.65 amperes and 0.68 amperes respectively; the solar street lamp node numbered 003, on May 25, 2025, 1 time of sudden change in the charging voltage range value occurred at 13:00-14:00, and the sudden change amplitude was 0.7 volts.

[0107] S6: According to the power generation space imbalance evaluation data and the energy storage time mutation evaluation data, a local energy link imbalance prediction model is constructed, and energy link imbalance prediction data is output, including:

[0108] The power generation space imbalance evaluation data and the energy storage time mutation evaluation data are aligned and fused according to the solar street lamp node number to form an imbalance feature vector of each solar street lamp node;

[0109] The solar street lamp node numbers in the power generation space imbalance evaluation data are sorted and recorded, and the corresponding energy storage time mutation evaluation data is retrieved by taking the solar street lamp node number as an index. For example, the solar street lamp node numbered 001 in the solar street lamp group records a photovoltaic power generation imbalance degree index of 0.1 in the power generation space imbalance evaluation data and belongs to the spatial grid A1, and records that the energy storage state mutation occurred in the time period of 10:00-11:00, 14:00-15:00 and 17:00-18:00 on May 25, 2025 in the energy storage time mutation evaluation data, with a total of 3 mutation times, and each mutation amplitude is 0.027%, 0.03% and 0.026% respectively. After data alignment and fusion, the imbalance feature vector of the solar street lamp node numbered 001 includes the photovoltaic power generation imbalance degree index 0.1, the time node of the energy storage state mutation (10:00-11:00, 14:00-15:00, 17:00-18:00), the mutation times 3 and the mutation amplitudes (0.027%, 0.03%, 0.026%), which completely expresses the overall imbalance characteristics of the solar street lamp node numbered 001 in the spatial and time dimensions.

[0110] A regression prediction function of the local energy link imbalance prediction model is established by taking the imbalance feature vector as the independent variable and the energy link imbalance prediction value as the dependent variable;

[0111] The local energy link imbalance prediction model takes the imbalance feature vector of each solar street lamp node as the input variable, and takes the energy link imbalance prediction value of the solar street lamp node as the output variable. The quantitative relationship between the feature vector and the energy link imbalance prediction value is determined by regression analysis method. The specific definition of the energy link imbalance prediction value is: the quantitative description of the energy supply imbalance condition caused by the insufficient photovoltaic power generation capacity or the unstable battery energy storage state of the solar street lamp node in the future prediction time period; the calculation method is: the spatial imbalance degree index and the energy storage state mutation frequency and amplitude are combined by weighting to determine the comprehensive index for quantifying the future imbalance degree of the energy link of the solar street lamp node, i.e. the energy link imbalance prediction value; the weight can be fitted and determined based on the historical operation data of the solar street lamp group. For example, in the actual operation data analysis, it is found that the influence weight of the photovoltaic power generation imbalance degree index on the future imbalance prediction is 0.6, the influence weight of the energy storage state mutation frequency is 0.25, and the influence weight of the energy storage mutation amplitude is 0.15. The comprehensive index calculated by the above combination method is the energy link imbalance prediction value.

[0112] The regression prediction function of the local energy link imbalance prediction model is constructed in a linear regression or nonlinear regression manner, for example, a multiple linear regression method is used to establish the linear relationship between each feature parameter of the imbalance feature vector of the solar street lamp node and the energy link imbalance prediction value. The regression function form is: energy link imbalance prediction value = weight coefficient 1 x power generation imbalance degree index + weight coefficient 2 x energy storage state mutation frequency + weight coefficient 3 x energy storage mutation amplitude + constant term. The weight coefficients 1, 2 and 3 are obtained by least square method data fitting calculation. For example, assuming that the weight coefficients of the No. 001 solar street lamp node after historical data fitting are 0.6, 0.25 and 0.15 respectively, and the constant term is 0.01, the energy link imbalance prediction value of the future specific time period can be accurately predicted by using the regression prediction function.

[0113] According to the regression prediction function and the future prediction time period, the energy link imbalance prediction value of each solar street lamp node is calculated;

[0114] Taking the No. 001 solar street lamp node as an example, the imbalance feature vector of the future prediction time period May 26, 2025, 10:00-11:00 is input, including the photovoltaic power generation imbalance degree index 0.1, the predicted energy storage state mutation frequency 1 times, and the energy storage mutation amplitude 0.028%. The energy link imbalance prediction value calculated by the regression prediction function is 0.320042. The energy link imbalance prediction value of each solar street lamp node is calculated by the above method.

[0115] Based on the solar street lamp node number, the predicted time period and the energy link imbalance prediction value, the energy link imbalance prediction data of the solar street lamp node is outputted;

[0116] Each solar street lamp node number, the predicted time period parameter and the corresponding energy link imbalance prediction value are integrated to form the energy link imbalance prediction data of the solar street lamp node; for example, the output form of the energy link imbalance prediction data is: the solar street lamp node number 001, the energy link imbalance prediction value from 10:00 to 11:00 on May 26, 2025 is 0.320042, and so on, the energy link imbalance prediction data of all solar street lamp nodes in the future predicted time period of the solar street lamp group is listed, and the future energy link running state of each solar street lamp node is expressed.

[0117] S7: Based on the energy link imbalance prediction data, the power distribution and brightness control strategy of the solar street lamp is dynamically adjusted, including:

[0118] According to the energy link imbalance prediction value of each solar street lamp node in the energy link imbalance prediction data, the power distribution adjustment rule and the brightness control level rule are preset;

[0119] The energy link imbalance prediction value is the degree of energy supply imbalance that the solar street lamp node may have due to insufficient photovoltaic power generation capacity or unstable battery energy storage state in a future specific time period. The greater the energy link imbalance prediction value of each solar street lamp node, the more serious the energy supply imbalance condition that the solar street lamp node faces in the future prediction period, and the more tense the predicted energy supply; the smaller the energy link imbalance prediction value of each solar street lamp node, the more stable the energy link condition in the prediction future period, and the more sufficient the energy supply margin. The power distribution adjustment rule is defined as an adjustment rule for determining the distribution between the battery energy storage power and the photovoltaic power generation power of the solar street lamp node based on the energy link imbalance prediction value, which is manifested as different power adjustment strategies corresponding to different imbalance prediction value intervals; the brightness control level rule is defined as a standard for determining the output brightness level of the LED lamp of the solar street lamp node based on the energy link imbalance prediction value. According to historical data analysis and experience, the energy link imbalance prediction value of the solar street lamp node is divided into multiple intervals, and corresponding power distribution adjustment rules and brightness control level rules are set in each interval. For example, the energy link imbalance prediction value range of 0 to 1 in the solar street lamp group is divided: when the energy link imbalance prediction value is less than 0.2, it is determined that the future energy link state of the solar street lamp node is basically stable, at this time the preset power distribution adjustment rule is that the power distribution ratio of the solar cell panel and the battery remains the default value, for example, the photovoltaic power generation power accounts for 60%, and the battery output power accounts for 40%; at this time, the brightness control level rule is set to the normal state brightness of the lamp, that is, 100% of the rated power. When the energy link imbalance prediction value is greater than or equal to 0.2 and less than 0.5, it is determined that the future energy link of the solar street lamp node has a mild imbalance risk, at this time the power distribution adjustment rule is set to appropriately reduce the output power ratio of the battery, for example, adjusting the solar cell panel to provide power to account for 70%, and the battery to provide power to account for 30%; at the same time, the brightness control level rule is set to 90% of the rated power. When the energy link imbalance prediction value is greater than or equal to 0.5 and less than 0.8, it is determined that the future energy link of the solar street lamp node has a moderate imbalance risk, at this time the power distribution adjustment rule is set to reduce the output power ratio of the battery, for example, adjusting the solar cell panel to provide power to account for 80%, and the battery to provide power to account for 20%; at the same time, the brightness control level rule is set to 75% of the rated power. When the energy link imbalance prediction value is greater than or equal to 0.8, it is determined that the future energy link of the solar street lamp node has a serious imbalance risk, at this time the power distribution adjustment rule is set to reduce the output power of the battery to the maximum extent, adjusting the solar cell panel to provide power to account for 90%, and the battery to provide power to account for 10%; at the same time, the brightness control level rule is set to 60% of the rated power.The above numerical values and rule intervals are predetermined reference standards. In actual application, the rule intervals and power adjustment ratios can be flexibly set and adjusted according to specific solar street lamp group positions, node densities, historical energy supply and demand imbalance conditions and other factors.

[0120] The energy link imbalance prediction value of each solar street lamp node is compared with the power distribution adjustment rule and the brightness control level rule respectively to determine the target power distribution value and the target brightness level of each solar street lamp node in the prediction time period.

[0121] Taking the solar street lamp node numbered 001 as an example, assuming that the energy link imbalance prediction value of the solar street lamp node in the prediction time period from 10:00 to 11:00 on May 26, 2025 is calculated as 0.320042, then according to the pre-set power distribution adjustment rule and brightness control level rule, since 0.320042 is in the interval greater than or equal to 0.2 and less than 0.5, according to the corresponding rule, the target power distribution value of the solar street lamp node in the time period is 70% of the total power of the photovoltaic power generation power and 30% of the total power of the battery output power, and at the same time the target brightness level is determined as 90% of the rated power of the solar street lamp node lamp. Similarly, the target power distribution value and the target brightness level of all nodes of the solar street lamp group are calculated respectively, and the determined target power distribution value and the target brightness level are recorded and stored for specific control and adjustment of the solar street lamp node.

[0122] Based on the target power distribution value and the target brightness level of each solar street lamp node, the power distribution and brightness control strategy of the solar street lamp node is dynamically adjusted.

[0123] The power distribution instruction is sent to the data acquisition and control device inside the solar street lamp node according to the target power distribution value in real time, and the output power ratio between the battery and the solar panel in the node is adjusted in real time through the control device; at the same time, the power output level of the LED lamp in the node is adjusted in real time according to the target brightness level, so that the actual output brightness of the lamp matches the target brightness level. For example, taking the solar street lamp node numbered 001 as an example, the control device receives the instruction that the target power distribution value is 70% for the solar panel and 30% for the battery from 10:00 to 11:00 on May 26, 2025, and then controls the battery output current and voltage in real time, adjusts the power output to 30%, and the solar panel output power is adjusted to 70% accordingly; at the same time, the LED lamp driving circuit output current and voltage are controlled in real time, and the actual brightness of the lamp is adjusted to the target brightness level, that is, the rated power of 90%, for example, if the rated power of the LED lamp is 30 watts, the actual output brightness is adjusted to 27 watts. Through real-time dynamic adjustment, intelligent power management and brightness control of the solar street lamp node are comprehensively realized, and the energy supply balance and lighting quality of the solar street lamp group as a whole are ensured.

[0124] Embodiment 2

[0125] The difference between the embodiment 2 and the embodiment 1 of the present application is that the embodiment 2 introduces an intelligent control system of a solar street lamp.

[0126] Figure 2 The structural schematic diagram of the intelligent control system of the solar street lamp is given, and the intelligent control system of the solar street lamp comprises:

[0127] The data acquisition module: acquires the photovoltaic power generation data and battery charging and discharging data of each solar street lamp node in the solar street lamp group, and pre-processes, and outputs real-time power generation and energy storage state data;

[0128] The spatial analysis module: based on the real-time power generation and energy storage state data, analyzes the spatial difference characteristics of the photovoltaic power generation capacity, and outputs spatial difference characteristic data;

[0129] The time analysis module: based on the real-time power generation and energy storage state data, analyzes the time fluctuation characteristics of the battery energy storage state, and outputs time fluctuation characteristic data;

[0130] The power generation evaluation module: based on the spatial difference characteristic data, evaluates the power generation uneven distribution characteristics caused by dynamic shading, and outputs power generation spatial unevenness evaluation data;

[0131] The energy storage evaluation module: based on the time fluctuation characteristic data, identifies the battery energy storage state mutation characteristics caused by temporary shading, and outputs energy storage time mutation evaluation data;

[0132] imbalance prediction module: according to the power generation space imbalance evaluation data and the energy storage time mutation evaluation data, a local energy link imbalance prediction model is constructed, and energy link imbalance prediction data is output;

[0133] strategy adjustment module: based on the energy link imbalance prediction data, the power distribution and brightness control strategy of the solar street lamp is dynamically adjusted.

[0134] The above formulas are all dimensionless numerical calculations, the formulas are obtained by software simulation of a large amount of data to obtain a formula of the nearest real situation, and the preset parameters and threshold values in the formula are set by the person skilled in the art according to the actual situation.

[0135] The above embodiments can be realized wholly or partially by software, hardware, firmware or any other combination. When realized by software, the above embodiments can be realized in the form of a computer program product wholly or partially. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another by wired (for example, infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center and the like containing one or more available medium sets. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), optical medium (for example, DVD) or semiconductor medium. The semiconductor medium can be a solid state disk.

[0136] Those skilled in the art can realize that the modules and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0137] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-described system, device and module can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0138] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the division of the above-described device embodiment is merely an example, and the division of the modules can be different, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or modules, and can be in electrical, mechanical or other forms.

[0139] The modules illustrated as separated components can or can not be physically separated, and the components illustrated as modules can or can not be physical modules, and can be located in one place, or can be distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0140] In addition, each functional module in the various embodiments of the present application can be integrated into a processing module, or each module can exist physically, or two or more modules can be integrated into one module.

[0141] If the functions are realized in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0142] The above description is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0143] Finally: the above only for the preferred embodiments of the present application, and not for limiting the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application, should be included in the scope of protection of the present application.

Claims

1. A method for intelligent control of a solar street light, characterized in that, Comprise the following steps: S1: Collect photovoltaic power generation data and battery charging and discharging data of each solar street lamp node in the solar street lamp group, and pretreat, output real-time power generation and energy storage state data; S2: Based on the real-time power generation and energy storage state data, analyze the spatial difference characteristics of the photovoltaic power generation capacity, and output the spatial difference characteristic data; S3: Based on the real-time power generation and energy storage state data, analyze the fluctuation characteristics of the battery energy storage state in time, and output the time fluctuation characteristic data; S4: Based on the spatial difference characteristic data, evaluate the uneven distribution characteristics of power generation caused by dynamic shading, and output the uneven distribution evaluation data of power generation; S5: Based on the time fluctuation characteristic data, identify the battery energy storage state mutation characteristics caused by temporary shading, and output the energy storage time mutation evaluation data; Set the fluctuation threshold of battery energy storage state mutation; Determine the time node of battery energy storage state mutation by judging the time fluctuation characteristic data of the solar street lamp node according to the fluctuation threshold; Statistical energy storage state mutation of solar street lamp node number and each corresponding solar street lamp node mutation frequency and mutation amplitude; Summarize the solar street lamp node number, the time node of battery energy storage state mutation, the mutation frequency and the mutation amplitude, and output the energy storage time mutation evaluation data of the solar street lamp node; S6: According to the uneven distribution evaluation data of power generation and the energy storage time mutation evaluation data, construct a local energy link imbalance prediction model, and output the energy link imbalance prediction data; Align and fuse the uneven distribution evaluation data of power generation and the energy storage time mutation evaluation data according to the solar street lamp node number, form the imbalance feature vector of each solar street lamp node; Take the imbalance feature vector as the independent variable and the energy link imbalance prediction value as the dependent variable to establish the regression prediction function of the local energy link imbalance prediction model; According to the regression prediction function and the future prediction time period, calculate the energy link imbalance prediction value of each solar street lamp node; Based on the solar street lamp node number, the prediction time period and the energy link imbalance prediction value, output the energy link imbalance prediction data of the solar street lamp node; S7: Based on the energy link imbalance prediction data, dynamically adjust the power distribution and brightness control strategy of the solar street lamp; According to the energy link imbalance prediction value of each solar street lamp node in the energy link imbalance prediction data, set the power distribution adjustment rule and the brightness control level rule in advance; Compare the energy link imbalance prediction value of each solar street lamp node with the power distribution adjustment rule and the brightness control level rule respectively, determine the target power distribution value and the target brightness level of each solar street lamp node in the prediction time period; Based on the target power distribution value and the target brightness level of each solar street lamp node, dynamically adjust the power distribution and brightness control strategy of the solar street lamp node. 2.The intelligent control method of the solar street lamp according to claim 1, characterized in that, S1, specifically: Collect photovoltaic power generation data and battery charging and discharging data of each solar street lamp node in the solar street lamp group; Based on the geographical position information of each solar street lamp node and the time series information of data collection, the photovoltaic power generation data and the battery charging and discharging data are denoised, missing value processed and outlier processed, and the real-time power generation and energy storage state data of the solar street lamp node are output. 3.The intelligent control method of the solar street lamp according to claim 2, characterized in that, S2, specifically: The real-time power generation and energy storage state data of the solar street lamp node are spatially divided according to the geographical coordinates; The average power value, power variance value and power range value of photovoltaic power generation are calculated for each spatial grid to form spatial statistical indicators; Based on the spatial statistical indicators, a spatial difference analysis model is constructed, and the regional difference distribution of photovoltaic power generation capacity is identified through the Euclidean distance clustering algorithm to generate spatial clustering labels; According to the spatial clustering labels, the spatial difference feature data of the solar street lamp node is output. 4.The intelligent control method of the solar street lamp according to claim 3, characterized in that, S3, specifically: Based on the real-time power generation and energy storage state data of the solar street lamp node, the battery charging and discharging data of each solar street lamp node is segmented and counted; In each time period, the change trend of the remaining battery capacity, the fluctuation amplitude of the charging and discharging current, and the range value of the charging and discharging voltage of the solar street lamp node battery are calculated to form the time series fluctuation feature indicators of each solar street lamp node; The time series fluctuation feature indicators of each solar street lamp node are normalized to output the time fluctuation feature data of the solar street lamp node.

5. The intelligent control method of the solar street lamp according to claim 4, characterized in that, S4, specifically: The average power value of photovoltaic power generation of each spatial grid in the spatial difference feature data of the solar street lamp node and the average power value of photovoltaic power generation of the adjacent spatial grid are difference operated to obtain the photovoltaic power generation difference value; A preset shading difference threshold is set, the target spatial grid with a photovoltaic power generation difference value greater than the preset shading difference threshold is extracted and identified; The solar street lamp node number contained in the target spatial grid is counted, and the corresponding photovoltaic power generation difference value is combined to calculate the power generation imbalance index; The solar street lamp node number, target spatial grid identification and power generation imbalance index are summarized to output the power generation spatial imbalance evaluation data of the solar street lamp node.

6. An intelligent control system of a solar street lamp, used for implementing the intelligent control method of a solar street lamp according to any one of claims 1-5, characterized in that, It includes: A data collection module: collects photovoltaic power generation data and battery charging and discharging data of each solar street lamp node in a solar street lamp group, and pre-processes the data to output real-time power generation and energy storage state data; A spatial analysis module: based on the real-time power generation and energy storage state data, analyzes the difference features of photovoltaic power generation in space, and outputs spatial difference feature data; A time analysis module: based on the real-time power generation and energy storage state data, analyzes the fluctuation features of the battery energy storage state in time, and outputs time fluctuation feature data; A power generation evaluation module: based on the spatial difference feature data, evaluates the power generation imbalance distribution characteristics caused by dynamic shading, and outputs power generation spatial imbalance evaluation data; An energy storage evaluation module: based on the time fluctuation feature data, identifies the battery energy storage state mutation characteristics caused by temporary shading, and outputs energy storage time mutation evaluation data; An imbalance prediction module: according to the power generation spatial imbalance evaluation data and the energy storage time mutation evaluation data, a local energy link imbalance prediction model is constructed to output energy link imbalance prediction data. Strategy adjustment module: based on the energy link imbalance prediction data, dynamically adjust the power distribution and brightness control strategy of solar street lamp.

Images