Tea garden temperature and humidity regulation and control method based on photovoltaic light supplement

Abstract

The invention relates to the technical field of agricultural management, in particular to a tea garden temperature and humidity regulation and control method based on photovoltaic light supplement. The method comprises the following steps: acquiring temperature and humidity data of a tea garden; obtaining tea tree distribution data, and obtaining a tea tree temperature and humidity environment model according to the tea tree distribution data and the tea garden temperature and humidity data; obtaining photovoltaic parameter data, and performing photovoltaic light supplement simulation according to the photovoltaic parameter data and the tea tree temperature and humidity environment model to obtain tea tree temperature and humidity photovoltaic light supplement data; performing temperature and humidity light supplement coupling relation calculation according to the tea tree temperature and humidity photovoltaic light supplement data to obtain temperature and humidity light supplement coupling relation data; and obtaining tea tree variety data, and performing light supplement effect optimization matching according to the temperature and humidity light supplement coupling relation data and the tea tree variety data to obtain light supplement effect optimization data. The light supplementing intensity and duration can be dynamically adjusted according to environment changes and tea tree growth requirements, and the utilization efficiency and the environment regulation and control effect of a photovoltaic system are improved.

Description

Technical Field

[0001] The invention relates to the technical field of agricultural management, and in particular to a method for controlling temperature and humidity in a tea garden based on photovoltaic supplementary lighting. Background Art

[0002] As an important economic crop in my country, the growing environment of tea has a vital impact on the yield and quality of tea. The growth of tea trees is extremely sensitive to changes in environmental factors such as temperature, humidity, and light. Especially during seasonal changes or extreme weather conditions, drastic changes in the tea garden environment often lead to poor growth of tea trees and increased incidence of pests and diseases, which in turn affects the yield and quality of tea. Traditional tea garden management mainly relies on manual experience, and adjusts the environmental conditions of the tea garden through manual observation and meteorological monitoring, such as irrigation, fertilization, and shading.

[0003] With the rapid development of photovoltaic technology, photovoltaic lighting, as a new agricultural environmental control method, has gradually been applied to greenhouses, vertical agriculture, tea garden management and other fields. Photovoltaic lighting uses the electricity generated by photovoltaic panels to provide additional light for tea trees or other crops, especially on rainy days or when there is insufficient light. It supplements light through artificial light sources to promote plant photosynthesis and improve crop yield and quality. However, the existing photovoltaic lighting technology still has limitations in the application process. Most of the existing photovoltaic lighting systems use preset lighting intensity and duration, lack effective integration with the dynamic changes of the crop growth environment, and cannot be flexibly adjusted according to actual environmental needs, which easily leads to problems such as insufficient or excessive lighting. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a method for controlling temperature and humidity in a tea garden based on photovoltaic supplementary lighting to solve at least one of the above technical problems.

[0005] The present application provides a method for controlling temperature and humidity in a tea garden based on photovoltaic supplementary lighting, characterized in that the method comprises:

[0006] S1. Obtain tea garden temperature and humidity data;

[0007] S2, obtaining tea tree distribution data, and constructing a tea tree temperature and humidity environment model based on the tea tree distribution data and tea garden temperature and humidity data to obtain a tea tree temperature and humidity environment model;

[0008] S3, obtaining photovoltaic parameter data, and performing photovoltaic lighting simulation according to the photovoltaic parameter data and the tea tree temperature and humidity environment model to obtain tea tree temperature and humidity photovoltaic lighting data;

[0009] S4. Calculate the temperature-humidity-fill-light coupling relationship according to the temperature-humidity-fill-light coupling data of the tea trees to obtain temperature-humidity-fill-light coupling relationship data; obtain tea tree variety data, and optimize and match the fill-light effect according to the temperature-humidity-fill-light coupling relationship data and the tea tree variety data to obtain fill-light effect optimization data, so as to carry out temperature and humidity control operations in the tea garden with photovoltaic fill-light.

[0010] In the present invention, by acquiring the real-time temperature and humidity data of the tea garden and the distribution data of the tea trees, a tea tree temperature and humidity environment model is established, which can accurately reflect the microenvironmental characteristics of different areas of the tea garden, thereby providing data support for refined management. By acquiring photovoltaic parameter data and combining the tea tree temperature and humidity environment model to perform photovoltaic lighting simulation, the intensity and duration of lighting can be dynamically adjusted according to the actual needs of the tea garden to avoid energy waste. By coupling photovoltaic lighting data with tea tree growth environment data, the impact of photovoltaic lighting on the temperature and humidity of the tea garden can be better understood, thereby optimizing the photovoltaic lighting strategy and improving the effectiveness and efficiency of lighting. By using tea tree variety data and temperature and humidity lighting coupling relationship data, the lighting effect can be optimized and matched for the growth characteristics of different varieties of tea trees to achieve differentiated refined management. The photovoltaic lighting system uses renewable energy to provide lighting for the tea garden, reduces dependence on traditional energy, and realizes a green and environmentally friendly management model for the tea garden. Through precise temperature and humidity control, behaviors such as over-irrigation and over-lighting are reduced, which effectively reduces resource waste and promotes the sustainable development of the tea garden.

[0011] Optionally, S1 includes:

[0012] S11, collecting temperature and humidity data through temperature and humidity sensor nodes, and obtaining preliminary tea garden temperature data and preliminary tea garden humidity data respectively;

[0013] S12, transmitting the preliminary tea garden temperature data and preliminary tea garden humidity data in slices to obtain tea garden temperature and humidity slice data;

[0014] S13, performing data aggregation on the tea garden temperature and humidity slice data to obtain tea garden temperature and humidity aggregation data;

[0015] S14, self-encoding the aggregated data of temperature and humidity in the tea garden to obtain self-encoded data of temperature and humidity in the tea garden;

[0016] S15, performing time series segmentation on the tea garden temperature and humidity self-encoded data to obtain tea garden temperature and humidity data.

[0017] In the present invention, through the distributed temperature and humidity sensor nodes, real-time and accurate data collection can be performed on the temperature and humidity in different areas of the tea garden, ensuring the extensiveness and representativeness of the data. Through the data segmentation transmission method, large-scale temperature and humidity data can be efficiently transmitted to the central control system to avoid delays and loss problems caused by excessive data volume during data transmission. The aggregated data can eliminate the accidental fluctuations and acquisition errors of local data, making the temperature and humidity data smoother and continuous, which is conducive to the stability and prediction accuracy of the model. Through self-encoding, high-dimensional temperature and humidity aggregation data are subjected to dimensionality reduction processing and feature extraction, and key features in the data are extracted, redundant information is removed, and the data dimension is reduced. Through the time series segmentation technology, the self-encoded data is segmented according to time, which can better capture the changing laws and patterns of the temperature and humidity in the tea garden in different time periods.

[0018] Optionally, S13 includes:

[0019] S131, performing change data retention aggregation on the tea garden temperature and humidity slice data to obtain first tea garden temperature and humidity aggregation data;

[0020] S132, performing graph data aggregation on the tea garden temperature and humidity slice data to obtain the second tea garden temperature and humidity aggregation data.

[0021] The change data retention aggregation method in the present invention can effectively identify significant change points in temperature and humidity data, retain the change trend and characteristics of temperature and humidity over time, and accurately identify dynamic changes in the tea garden environment, such as sudden temperature drop, sudden increase in humidity and other phenomena. By retaining only data points with significant changes, the storage amount of redundant data is reduced, the data storage and processing efficiency is optimized, and key information is retained to facilitate subsequent refined analysis. The graph data aggregation method can combine temperature and humidity data with the spatial location of the tea garden to reveal the spatial distribution characteristics of temperature and humidity in different areas of the tea garden. For example, it can be identified which areas in the tea garden have higher temperatures and lower humidity, which is helpful for precise positioning and targeted management. Through the aggregation of graph data, the spatial correlation of temperature and humidity between different areas can be analyzed, which is very helpful for understanding the impact of factors such as different terrains and planting density on temperature and humidity in the tea garden, and helps to optimize the layout and management strategies of the tea garden.

[0022] Optionally, S131 includes:

[0023] Extract the spatial distribution of the tea garden temperature and humidity slice data to obtain the tea garden temperature and humidity spatial distribution data;

[0024] Acquire tea garden electronic map data, and construct a tea garden space matrix according to the tea garden electronic map data to obtain tea garden space matrix data;

[0025] Mapping is performed based on the tea garden spatial matrix data and the tea garden temperature and humidity spatial distribution data to obtain the tea garden temperature and humidity matrix data;

[0026] According to the electronic map data of the tea garden, the spatial correlation data of the temperature and humidity matrix of the tea garden are processed to obtain the spatial correlation data of the temperature and humidity of the tea garden;

[0027] According to the spatial correlation data of temperature and humidity in the tea garden, spatial slicing is performed to obtain the spatial slicing data of temperature and humidity in the tea garden;

[0028] Perform change point detection based on the tea garden temperature and humidity spatial slice data to obtain the tea garden temperature and humidity spatial change point data;

[0029] Extract the change area of ​​the tea garden temperature and humidity spatial change point data to obtain the tea garden temperature and humidity change area data;

[0030] The change data is aggregated according to the regional data of temperature and humidity changes in the tea garden to obtain the aggregated temperature and humidity data of the first tea garden.

[0031] In the present invention, by extracting the spatial distribution of temperature and humidity slice data, the temperature and humidity distribution characteristics of each area in the tea garden can be fully grasped, such as the temperature height, humidity change and the like, which is helpful to identify environmental differences. By converting the tea garden electronic map data into a spatial matrix form, the complex terrain and environmental information of the tea garden can be accurately expressed as structured data. The tea garden spatial matrix data and the temperature and humidity distribution data are mapped and integrated, and the temperature and humidity information can be accurately located in each spatial cell of the tea garden to form an all-round temperature and humidity spatial matrix, which is helpful to fully understand the environmental conditions of each area of ​​the tea garden. Through spatial correlation analysis, the mutual relationship of temperature and humidity changes in different regions can be quantified, and the spatial law of environmental changes in the tea garden can be identified, such as which regions change synchronously and which regions change greatly. By spatially slicing the tea garden environmental data, the environmental characteristics of different heights and different regions can be hierarchically analyzed, revealing the changing laws of temperature and humidity at different levels, such as the difference between the tea tree canopy and the surface temperature and humidity. By performing change point detection on the spatial slice data, the time point and position of significant changes in the tea garden environment can be quickly captured, such as the area and time when the temperature rises sharply or the humidity drops sharply. By extracting the change area, we can accurately locate the area where the environmental changes are concentrated, helping managers focus on the areas where the tea garden environment has changed significantly, and improving the pertinence and effectiveness of management. By aggregating the change data, we can remove the noise components in the data, reduce the impact of accidental fluctuations in a single monitoring, and make the temperature and humidity data smoother and more continuous.

[0032] Optionally, S132 includes:

[0033] The tea garden temperature and humidity segmentation data are divided into tea garden space grids to obtain tea garden space grid division data;

[0034] According to the tea garden space grid division data, network node association is performed to obtain tea garden space network node association data;

[0035] According to the tea garden spatial network node association data, the adjacency matrix is ​​constructed to obtain the tea garden spatial adjacency matrix data;

[0036] The clustering coefficient is calculated based on the spatial adjacency matrix data of the tea garden to obtain the node feature data of the tea garden graph;

[0037] According to the spatial adjacency matrix data of the tea garden, the edge temperature and humidity correlation features are extracted to obtain the edge feature data of the tea garden graph;

[0038] The graph data is aggregated according to the node feature data and edge feature data of the tea garden graph to obtain the temperature and humidity aggregated data of the second tea garden.

[0039] In the present invention, by dividing the tea garden into multiple spatial grid units, a large area of ​​tea garden can be decomposed into several small areas, which is convenient for refined management. Each grid unit represents a specific location in the tea garden, making data analysis and management more accurate. Different grid units have different microenvironmental conditions (such as different temperatures, humidity, light, etc.), which helps to capture the changing laws of the microenvironment in the tea garden, thereby providing data support for precise regulation. By establishing node associations between each grid unit and adjacent units, the connection between adjacent areas in space can be identified, and the spatial diffusion effect and influence mechanism of temperature and humidity between different areas can be captured. Through the adjacency matrix, the temperature and humidity similarity or difference between each grid unit and the adjacent unit can be quantified, providing basic data for subsequent graph node and edge feature analysis. Through graph node features such as clustering coefficient, key areas where temperature and humidity characteristics are relatively concentrated in the tea garden can be identified. These areas have special microclimate characteristics and deserve special attention in management. By extracting the temperature and humidity correlation features on the spatial network edge (the line connecting two nodes), the mutual influence mechanism of temperature and humidity changes between different regions can be revealed. For example, the edge with high correlation indicates that the synchronization of temperature and humidity changes between adjacent regions is strong.

[0040] Optionally, S14 includes:

[0041] Extract the coded features of the aggregated data of temperature and humidity in the tea garden to obtain the coded feature data of temperature and humidity in the tea garden;

[0042] Clustering is performed on the tea garden temperature and humidity coding feature data to obtain the tea garden temperature and humidity coding cluster label data;

[0043] Perform time series prediction on the tea garden temperature and humidity encoded cluster label data to obtain the tea garden temperature and humidity time series prediction data;

[0044] According to the tea garden temperature and humidity time series forecast data, the self-encoding reconstruction error processing is performed to obtain the tea garden temperature and humidity reconstruction error data;

[0045] Anomaly detection and error elimination are performed on the reconstructed error data of temperature and humidity in the tea garden to obtain the self-encoded data of temperature and humidity in the tea garden.

[0046] In the present invention, the coded feature extraction of the aggregated data of temperature and humidity in the tea garden can reduce the dimension of the high-dimensional temperature and humidity data to a low-dimensional feature representation, reduce the redundancy of the data, and reduce the complexity of subsequent data processing. By clustering the coded feature data, the hidden patterns and laws in the temperature and humidity data of the tea garden are revealed, such as the temperature and humidity change characteristics in different time periods and different regions, providing a scientific basis for the refined management of the tea garden environment. Based on the clustered coded feature data, time series prediction can be performed to predict the changing trend of the temperature and humidity in the tea garden in the future, which is helpful to take preventive management measures in advance, such as starting the fill light system when the temperature is expected to drop sharply. Reconstruction error analysis can help identify and eliminate anomalies and errors in the data, thereby improving the accuracy and stability of the model and avoiding model misjudgment due to abnormal data.

[0047] Optionally, S2 includes:

[0048] S21, obtaining tea tree distribution data;

[0049] S22, calculating tea tree planting density according to the tea tree distribution data to obtain tea tree planting density data;

[0050] S23, performing spatial temperature and humidity interpolation on the tea tree temperature and humidity data according to the tea tree planting density data to obtain tea tree temperature and humidity interpolation data;

[0051] S24, analyzing the environmental adaptability of the tea trees according to the interpolation data of temperature and humidity of the tea trees, and obtaining the environmental adaptability scoring data of the tea trees;

[0052] S25. Construct a tea tree temperature and humidity environment model based on the tea tree environmental adaptability score data, tea tree distribution data, and tea garden temperature and humidity data to obtain a tea tree temperature and humidity environment model.

[0053] In the present invention, the distribution data of tea trees are obtained by means of UAV remote sensing, geographic information system (GIS) or field survey, and the geographical location of each tea tree can be accurately located, providing a comprehensive view of the tea garden planting layout. According to the tea tree distribution data, the planting density is calculated, and the over-dense or over-sparse planting areas can be identified, which provides a reference for optimizing the tea tree planting layout, and helps to improve the land utilization rate and the rationality of the tea tree growth space. By spatially interpolating the temperature and humidity data, the temperature and humidity information of each position in the tea garden can be obtained to form a spatial distribution map of the temperature and humidity of the tea garden. Identify the changes in the microenvironment in the tea garden and provide data support for precise regulation. According to the tea tree temperature and humidity interpolation data and the planting density data, the environmental adaptability analysis can be performed, and the growth adaptability of the tea tree under different environmental conditions can be evaluated, and the areas that are not suitable for the growth of tea trees can be identified, which provides a basis for the transformation and optimization of the tea garden. The environmental model constructed based on the tea tree distribution data, the planting density data and the temperature and humidity data can simulate the dynamic changes of the tea garden environment and provide technical support for the intelligent monitoring and early warning of the tea garden environment.

[0054] Optionally, S3 includes:

[0055] S31, obtaining photovoltaic parameter data;

[0056] S32, evaluating photovoltaic power generation capacity according to photovoltaic parameter data to obtain photovoltaic power generation evaluation data;

[0057] S33, calculating the photovoltaic panel inclination angle according to the photovoltaic parameter data to obtain the photovoltaic panel inclination angle data;

[0058] S34, performing photovoltaic power generation allocation according to the photovoltaic power generation evaluation data, the photovoltaic panel inclination data, and the tea tree temperature and humidity environment model to obtain tea tree photovoltaic power generation allocation data;

[0059] S35. Perform photovoltaic lighting simulation according to the photovoltaic power generation distribution data of the tea trees to obtain photovoltaic lighting data of temperature and humidity of the tea trees.

[0060] The present invention timely understands the actual working state of the photovoltaic panel, such as power generation efficiency, power output, etc., which helps to discover potential problems (such as photovoltaic panel surface shielding, system failure, etc.) and improve the operational stability and reliability of the system. Through the comprehensive analysis of photovoltaic parameter data, the power generation capacity of the photovoltaic system in different time periods can be accurately evaluated, the power generation potential of the photovoltaic system can be predicted, and the foundation for the rational use of photovoltaic power can be laid. By calculating the optimal inclination angle of the photovoltaic panel in different seasons and time periods, the efficiency of the photovoltaic panel receiving sunlight can be effectively improved, the power generation can be maximized, and the overall utilization rate of the photovoltaic system can be improved. According to the photovoltaic power generation capacity evaluation data, the photovoltaic panel inclination data and the tea tree temperature and humidity environment model, a reasonable power generation allocation plan can be formulated, and power resources can be intelligently allocated according to the actual needs of different regions to achieve precise control. The simulation results can help identify the optimal time, intensity and duration of photovoltaic lighting, avoid excessive or insufficient lighting behavior, and improve the suitability of the tea tree growth environment.

[0061] Optionally, S33 includes:

[0062] Obtain photovoltaic panel location data and tea garden structure data;

[0063] The solar radiation model is constructed based on the photovoltaic panel location data and the tea garden structure data to obtain the tea garden solar radiation model;

[0064] The photovoltaic panel inclination angle is calculated according to the tea garden solar radiation model and photovoltaic parameter data to obtain the photovoltaic panel inclination angle data.

[0065] In the present invention, by obtaining the precise position of the photovoltaic panel (including longitude and latitude, altitude, installation angle, etc.), the spatial layout of the photovoltaic panel can be accurately understood, and the structural data of the tea garden (such as terrain height, exposure degree of the tea garden, etc.) can be obtained, so that the environmental characteristics around the photovoltaic panel can be fully understood, and the shielding relationship between the photovoltaic panel and the tea tree can be taken into account to avoid the photovoltaic panel being shielded and causing the power generation efficiency to decrease. The solar radiation model constructed based on the photovoltaic panel position data and the tea garden structure data can accurately simulate the amount of solar radiation received by the photovoltaic panel under different time periods and seasonal conditions. By calculating the optimal inclination angle of the photovoltaic panel through the solar radiation model and photovoltaic parameter data, the photovoltaic panel can receive more solar radiation in different seasons and different time periods, thereby improving the overall power generation efficiency of the photovoltaic system.

[0066] Optionally, S4 includes:

[0067] S41, calculating the temperature-humidity-photovoltaic supplementary lighting coupling relationship according to the temperature-humidity-photovoltaic supplementary lighting data of the tea trees, and obtaining the temperature-humidity-photovoltaic supplementary lighting coupling relationship data;

[0068] S42, obtaining tea tree variety data;

[0069] S43, performing temperature and humidity cross sensitivity analysis according to the tea variety data and the temperature, humidity and light supplement coupling relationship data to obtain temperature and humidity cross sensitivity data;

[0070] S44, fitting the fill light intensity environment response curve according to the temperature and humidity fill light coupling relationship data to obtain fill light intensity environment response curve data;

[0071] S45. Perform collaborative optimization of supplementary lighting according to the temperature and humidity cross-sensitivity data and the supplementary lighting intensity environmental response curve data to obtain supplementary lighting effect optimization data to carry out temperature and humidity control operations in the photovoltaic supplementary lighting tea garden.

[0072] In the present invention, by calculating the coupling relationship of the photovoltaic supplementary lighting data of the temperature and humidity of the tea tree, the influence of photovoltaic supplementary lighting on the temperature and humidity environment of the tea garden can be accurately quantified, so as to understand how factors such as supplementary lighting intensity and duration affect the growth environment of the tea tree. Different tea varieties have different requirements for light, temperature and humidity. Acquiring tea variety data can identify the tea varieties planted in various areas of the tea garden. Through cross-sensitivity analysis, the degree of influence of temperature and humidity on the growth of different tea varieties can be quantified, and the varieties and environmental conditions with higher sensitivity can be identified to help managers take preventive measures in advance. Through curve fitting of supplementary lighting intensity and environmental response data, the influence of supplementary lighting intensity on the temperature and humidity environment of the tea garden can be accurately quantified, revealing the dynamic change law of temperature and humidity under different supplementary lighting intensities. Based on the temperature and humidity cross-sensitivity data and the supplementary lighting intensity environmental response curve data, collaborative optimization can be performed, and various factors such as tea variety characteristics, environmental conditions and supplementary lighting strategies can be considered to achieve the optimal supplementary lighting solution. Through the temperature, humidity and light coupling relationship and cross-sensitivity analysis, we can help tea gardens accurately control the growth environment of tea trees under complex environmental conditions (such as extreme weather, seasonal changes, etc.) and improve the adaptability and stability of the tea garden environment.

[0073] The object of the present invention is to obtain multi-source environmental data of tea gardens through a temperature and humidity sensor network, a photovoltaic parameter acquisition system and tea tree distribution remote sensing technology. The environmental model constructed based on tea tree distribution data and temperature and humidity data can accurately simulate the temperature and humidity distribution law and its changing trend in different areas of the tea garden, and provide a reliable prediction basis for refined management. The environmental model can reveal the influence of different microenvironments in the tea garden on the growth of tea trees, help identify key environmental factors, and provide a scientific basis for formulating regionalized and differentiated management strategies. Photovoltaic supplementary lighting simulation is carried out according to photovoltaic parameter data and tea tree temperature and humidity environmental model, and photovoltaic power generation resources can be intelligently allocated according to the needs of different areas of the tea garden, the utilization efficiency of the photovoltaic system can be maximized, and resource waste can be avoided. Through the calculation of the temperature and humidity supplementary lighting coupling relationship, the temperature and humidity regulation effect of photovoltaic supplementary lighting on the tea garden microenvironment can be quantitatively analyzed, and the deep-level influence of supplementary lighting behavior on the growth environment of tea trees can be revealed. Combined with tea tree variety data and temperature and humidity supplementary lighting coupling relationship data, the supplementary lighting effect is optimized and matched, and personalized supplementary lighting strategies can be formulated according to the illumination, temperature and humidity requirements of different tea tree varieties, so as to achieve "different for each tree" precise management. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting implementations made with reference to the following drawings:

[0075] Figure 1 A flowchart showing a method for controlling temperature and humidity in a tea garden based on photovoltaic supplementary lighting according to an embodiment of the present invention is shown;

[0076] Figure 2 A flowchart showing a method for collecting temperature and humidity data in a tea garden according to an embodiment of the present invention is shown;

[0077] Figure 3 A flowchart showing a method for constructing a tea tree temperature and humidity environment model according to an embodiment is shown;

[0078] Figure 4 A flowchart showing a method for simulating photovoltaic lighting for temperature and humidity of tea trees according to an embodiment of the present invention is provided;

[0079] Figure 5 A flowchart showing a method for optimizing and matching fill light effects according to an embodiment of the present invention is provided;

[0080] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0081] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0082] In addition, the drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0083] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0084] Photovoltaic supplementary lighting technology is used, and intelligent temperature and humidity control is carried out by combining the environmental data of the tea trees with the photovoltaic system parameters.

[0085] 1. Implementation Environment

[0086] Tea garden scale: 20 mu (about 13,333 square meters), geographical location: 28°36' north latitude, 113°30' east longitude, 250 meters above sea level, tea tree varieties: Longjing No. 43 and Fuding Dabaicha, with planting densities of 3,000 and 2,000 per mu respectively. Photovoltaic system: total power of photovoltaic panels: 30kWp (kilowatt peak), photovoltaic panel type: monocrystalline silicon photovoltaic panels, conversion efficiency 18%, photovoltaic panel installation angle: initial inclination 30° (optimized and adjusted according to specific conditions), energy storage system: 20kWh (kilowatt-hour) lithium battery energy storage system, used for supplementary lighting at night and rainy weather.

[0087] 2. Implementation steps

[0088] 20 temperature and humidity sensor nodes are evenly spaced in the tea garden, with a node spacing of 30 meters. Sensor model: DHT22, accuracy: temperature ±0.5℃, humidity ±2%. Temperature and humidity data are automatically collected every 15 minutes. Number of data collections per day: 96 times. Data sample: The data at 10:00 on a certain day is 22.8℃ temperature and 65% humidity.

[0089] The data is sent to the central control system through LoRa wireless transmission technology. The average of the four data points per hour is taken as the temperature and humidity value for that hour.

[0090] The distribution map of tea gardens was taken by drones equipped with high-definition cameras, and the precise positioning was combined with GPS. The location and density data of tea trees were extracted through image recognition technology. The planting density of Longjing No. 43: 3,000 plants per mu, with an average plant spacing of 60 cm. The planting density of Fuding Dabaicha: 2,000 plants per mu, with an average plant spacing of 75 cm. Based on the tea tree distribution data and the collected temperature and humidity data, a multivariate regression analysis was used to construct a tea tree temperature and humidity environment model. Model formula: T env =0.7×T air +0.2×D tree -0.1×H,T env is the environmental temperature of the tea tree (℃), T air is the air temperature (℃), D tree is the tea tree planting density (plants / square meter), and H is the air humidity.

[0091] The photovoltaic panel is installed in the northeast corner of the tea garden, 15° south-east, with an initial inclination of 30°. The average height of the tea trees is 1.2 meters, and there are no obvious obstructions. Photovoltaic power generation capacity assessment: average daily solar radiation: 4.5kWh / ㎡, theoretical power generation: average daily power generation is 30kWp×4.5h=135kWh. The optimal inclination angle calculated by the tea garden solar radiation model is 25° (summer), 30° (spring and autumn), and 35° (winter).

[0092] During the day, photovoltaic power generation is used to supply electricity to the tea garden, and the excess electricity is stored; at night, the energy storage battery provides power for the supplementary light. Supplementary light time: 17:00-21:00 every day, supplementary light intensity: 50W / ㎡, average supplementary light time 4 hours.

[0093] Calculation of the coupling relationship between temperature and humidity: The coupling relationship between the intensity of the supplementary light and the temperature and humidity is: ΔT = 0.05 × P light ,ΔH=-0.02×P light , ΔT is the temperature change (°C), ΔH is the humidity change (%), P light is the light supplement power density (W / ㎡). Longjing No. 43 is sensitive to temperature changes: high (optimal temperature range: 18-22℃). Fuding Dabaicha is sensitive to humidity changes: high (optimal humidity range: 60%-70%). Light supplement intensity environmental response curve: R light To rate the fill light effect, P lightis the light supplement power density (W / ㎡). The cross-sensitivity data and response curve data are combined to determine the best light supplement strategy for different varieties. The best light supplement strategy for Longjing No. 43: light supplement power density 40W / ㎡, duration 3 hours. The best light supplement strategy for Fuding Dabaicha: light supplement power density 60W / ㎡, duration 2 hours.

[0094] See also Figures 1 to 5 The present application provides a method for controlling temperature and humidity in a tea garden based on photovoltaic supplementary lighting, characterized in that the method comprises:

[0095] S1. Obtain tea garden temperature and humidity data;

[0096] In one embodiment, temperature and humidity sensors are arranged in the tea garden to ensure coverage of different areas of the entire tea garden, including different characteristic areas such as height, orientation, and terrain. The collected temperature and humidity data are transmitted to the data processing center through a wireless transmission module. The collection frequency can be set according to the actual situation of the tea garden, for example, once every 5 minutes.

[0097] S2, obtaining tea tree distribution data, and constructing a tea tree temperature and humidity environment model based on the tea tree distribution data and tea garden temperature and humidity data to obtain a tea tree temperature and humidity environment model;

[0098] In one embodiment, high-resolution images of tea gardens are obtained by drone aerial photography or satellite remote sensing technology. The precise distribution location of tea trees is identified by image processing technology (e.g., image segmentation). The spatial distribution coordinates of the tea trees are stored in a geographic information system (GIS) to form a tea tree distribution map. The tea tree distribution data is combined with the temperature and humidity data to construct a three-dimensional tea tree temperature and humidity environment map. The temperature and humidity data of each tea tree location are estimated by a spatial interpolation method (e.g., Kriging interpolation). According to the distribution of tea trees and surrounding environmental data (e.g., topography, soil moisture, wind speed, etc.), a regression model is constructed or curve fitting is performed to construct a tea tree temperature and humidity environment model. The model reflects the differences in the demand for temperature and humidity at different growth stages of tea trees.

[0099] S3, obtaining photovoltaic parameter data, and performing photovoltaic lighting simulation according to the photovoltaic parameter data and the tea tree temperature and humidity environment model to obtain tea tree temperature and humidity photovoltaic lighting data;

[0100] In one embodiment, data such as the output power of the photovoltaic power generation system, the tilt angle of the photovoltaic panel, and the intensity of sunlight radiation are collected. At the same time, the power storage capacity of the photovoltaic system and the equipment status data (such as battery power, conversion efficiency, etc.) are monitored. According to the terrain and light distribution of the tea garden, the lighting effect of photovoltaic panels at different positions on the tea trees is calculated, including light intensity, light duration, etc. The effect of photovoltaic lighting is simulated, and the influence of different photovoltaic parameters (such as the angle, position, and number of photovoltaic panels) on the temperature and humidity of the tea garden is analyzed. According to the simulation results, the temperature and humidity changes of tea trees at different positions under photovoltaic lighting conditions are obtained. Generate tea tree temperature and humidity photovoltaic lighting data, including the temperature and humidity changes at the tea tree position before and after photovoltaic lighting.

[0101] S4. Calculate the temperature-humidity-fill-light coupling relationship according to the temperature-humidity-fill-light coupling data of the tea trees to obtain temperature-humidity-fill-light coupling relationship data; obtain tea tree variety data, and optimize and match the fill-light effect according to the temperature-humidity-fill-light coupling relationship data and the tea tree variety data to obtain fill-light effect optimization data, so as to carry out temperature and humidity control operations in the tea garden with photovoltaic fill-light.

[0102] In one embodiment, the photovoltaic lighting data is compared with the actual temperature and humidity demand data of the tea tree, and the impact of photovoltaic lighting on the temperature and humidity control of the tea tree is calculated. Considering the growth stage of the tea tree and environmental changes (such as seasons and weather), the best lighting strategy is calculated. The temperature and humidity demand data of different tea varieties are obtained, including the suitable growth temperature, humidity range, and light duration requirements of each variety. According to the needs of different tea varieties, the effect of photovoltaic lighting is matched with the variety requirements, and the degree of optimization of the lighting effect is evaluated. Using a multi-factor analysis method (such as a hierarchical analysis method), the optimal lighting effect optimization strategy is obtained based on factors such as the energy consumption of the photovoltaic system, the growth status of the tea tree, and environmental changes. Adjust the angle and position of the photovoltaic panel according to the optimization data, and adjust the output power and lighting duration of the photovoltaic system. Monitor the temperature and humidity of the tea garden in real time, and dynamically adjust the photovoltaic lighting strategy according to the actual environmental changes to achieve refined temperature and humidity control of the tea garden.

[0103] Specifically, 20 temperature and humidity sensors are deployed in the tea garden, and each sensor collects data in real time with a sampling frequency of once every 10 minutes. The moving average algorithm is used to smooth the temperature and humidity data to reduce fluctuations. The tea garden images are taken by drones, and the tea tree distribution data is analyzed. The tea trees are spaced 1 meter apart, and there are 2,000 tea trees (1,000 varieties A and 1,000 varieties B). The Kriging interpolation method is used to distribute the tea garden temperature and humidity sensor data to each tea tree to generate a tea tree temperature and humidity environment map. Temperature and humidity sensor data near tea tree 1 (variety A): temperature 20.3°C, humidity 74.5%. Temperature and humidity sensor data near tea tree 2 (variety A): temperature 20.9°C, humidity 77.8%. Construct a model: Based on the temperature and humidity data at different locations and the distribution of tea trees, a two-dimensional temperature and humidity distribution map is generated. The data of each tea tree node is as follows:

[0104] 2D temperature and humidity distribution chart

[0105] Tea Tree Number variety Temperature(℃) humidity(%) 1 A 20.3 74.5 2 A 20.9 77.8 … … … .. 2000 B 17.7 71.9

[0106] Evenly distributed above the tea garden, with an inclination of 30 degrees and facing south. Simulate the lighting effects of different photovoltaic panel positions, inclinations, and distances on tea trees: Simulation scheme 1: All photovoltaic panels face south and are fixed in position. Simulation scheme 2: The angle of the photovoltaic panels is adjusted as the sun's altitude changes. When the photovoltaic panels output 300W, the average temperature of the tea trees rises by 1.2℃ and the humidity drops by 5%.

[0107] The simulation results of photovoltaic lighting for tea trees: Tea tree 1 (variety A): before photovoltaic lighting, the temperature was 20.3℃, and the humidity was 74.5%; after lighting, the temperature was 21.5℃, and the humidity was 69.5%. Tea tree 2 (variety A): before photovoltaic lighting, the temperature was 20.9℃, and the humidity was 77.8%; after lighting, the temperature was 22.1℃, and the humidity was 72.8%.

[0108] Consider the requirements of different tea varieties for temperature and humidity: Variety A: Suitable temperature 22-25℃, suitable humidity 70-80%. Variety B: Suitable temperature 20-23℃, suitable humidity 65-75%. Calculation results: After photovoltaic lighting, the temperature of tea tree 1 (variety A) increased to 21.5℃, and the humidity dropped to 69.5%, close to the suitable conditions. After photovoltaic lighting, the temperature of tea tree 2000 (variety B) increased to 20.9℃, and the humidity dropped to 67%, which is suitable conditions.

[0109] Optimize the layout and power output of photovoltaic panels so that both varieties of tea trees can achieve optimal growth conditions. Photovoltaic panels 1-5 are tilted at 30 degrees and are used in variety A areas with an output power of 80%. Photovoltaic panels 6-10 are tilted at 15 degrees and are used in variety B areas with an output power of 60%. Adjust the tilt and output power of photovoltaic panels in real time to ensure that temperature and humidity control meet the optimal growth needs of tea trees. For example: when the temperature rises in the afternoon, reduce the output power of photovoltaic panels to avoid overheating. After optimization, the temperature and humidity of each tea tree in the tea garden have reached their optimal growth conditions: Variety A area: average temperature 22.8℃, humidity 72%. Variety B area: average temperature 21.0℃, humidity 70%.

[0110] In the present invention, by acquiring the real-time temperature and humidity data of the tea garden and the distribution data of the tea trees, a tea tree temperature and humidity environment model is established, which can accurately reflect the microenvironmental characteristics of different areas of the tea garden, thereby providing data support for refined management. By acquiring photovoltaic parameter data and combining the tea tree temperature and humidity environment model to perform photovoltaic lighting simulation, the intensity and duration of lighting can be dynamically adjusted according to the actual needs of the tea garden to avoid energy waste. By coupling photovoltaic lighting data with tea tree growth environment data, the impact of photovoltaic lighting on the temperature and humidity of the tea garden can be better understood, thereby optimizing the photovoltaic lighting strategy and improving the effectiveness and efficiency of lighting. By using tea tree variety data and temperature and humidity lighting coupling relationship data, the lighting effect can be optimized and matched for the growth characteristics of different varieties of tea trees to achieve differentiated refined management. The photovoltaic lighting system uses renewable energy to provide lighting for the tea garden, reduces dependence on traditional energy, and realizes a green and environmentally friendly management model for the tea garden. Through precise temperature and humidity control, behaviors such as over-irrigation and over-lighting are reduced, which effectively reduces resource waste and promotes the sustainable development of the tea garden.

[0111] Optionally, S1 includes:

[0112] S11, collecting temperature and humidity data through temperature and humidity sensor nodes, and obtaining preliminary tea garden temperature data and preliminary tea garden humidity data respectively;

[0113] In one embodiment, multiple key points are selected in the tea garden to deploy temperature and humidity sensor nodes. Each node is composed of a temperature sensor, a humidity sensor, and a data transmission module. The sensor collects temperature and humidity data at fixed time intervals (e.g., every 10 minutes).

[0114] S12, transmitting the preliminary tea garden temperature data and preliminary tea garden humidity data in slices to obtain tea garden temperature and humidity slice data;

[0115] In one embodiment, the preliminary tea garden temperature data and humidity data are sliced ​​according to the time dimension and the space dimension. The time dimension slices can be divided according to a fixed time window (e.g., 1 hour), and the space dimension can be grouped according to the area where the sensor node is located. Sliced ​​data (part): Slice 1 (8:00-9:00, area 1): temperature data [20.5, 20.6, 20.4...], humidity data [75, 76, 74...] Slice 2 (8:00-9:00, area 2): temperature data [21.0, 20.9, 21.1...], humidity data [78, 77, 79...]. The sliced ​​data is packaged and transmitted to the data processing center through a wireless communication module (such as LoRa, ZigBee). During the transmission process, data compression technology (such as differential coding) can be used to reduce the amount of transmitted data and improve transmission efficiency.

[0116] S13, performing data aggregation on the tea garden temperature and humidity slice data to obtain tea garden temperature and humidity aggregation data;

[0117] In one embodiment, the fragmented data of different sensor nodes in the same time window are aggregated and processed to calculate the average, median, maximum and minimum statistics in each time window. Aggregated data: Time window 1 (8:00-9:00): average temperature 20.7°C, maximum temperature 21.1°C, minimum temperature 20.4°C, average humidity 76%, maximum humidity 79%, minimum humidity 74%. Time window 2 (9:00-10:00): average temperature 21.2°C, maximum temperature 21.6°C, minimum temperature 20.8°C, average humidity 77%, maximum humidity 80%, minimum humidity 75%.

[0118] S14, self-encoding the aggregated data of temperature and humidity in the tea garden to obtain self-encoded data of temperature and humidity in the tea garden;

[0119] In one embodiment, key features (such as the temperature difference between day and night, the rate of change of humidity, etc.) are extracted from the aggregated data to form a feature vector. Feature extraction: Feature vector 1 (8:00-9:00): [20.7, 21.1, 20.4, 76, 79, 74, 0.7, 0.3] (representing respectively: average temperature, maximum temperature, minimum temperature, average humidity, maximum humidity, minimum humidity, temperature difference, humidity difference), and the standardized data is reduced in dimension and represented by features using an autoencoder to generate autoencoded data. The autoencoder compresses high-dimensional data into a low-dimensional representation to retain the most critical information. Data after autoencoding (part): Autoencoded data 1 (8:00-9:00): [0.57, 0.43, 0.22, ...] (low-dimensional feature representation).

[0120] S15, performing time series segmentation on the tea garden temperature and humidity self-encoded data to obtain tea garden temperature and humidity data.

[0121] In one embodiment, the self-encoded data is segmented in chronological order to form time series data. Each time series segment can be of fixed length (such as 1 hour) or event-driven (such as segmentation when temperature and humidity change drastically). Time series segmented data (part): Time series data segment 1 (8:00-9:00): [[0.57, 0.43, 0.22, ...], [0.61, 0.40, 0.25, ...], ...], Time series data segment 2 (9:00-10:00): [[0.63, 0.41, 0.27, ...], [0.66, 0.39, 0.29, ...], ...].

[0122] In the present invention, through the distributed temperature and humidity sensor nodes, real-time and accurate data collection can be performed on the temperature and humidity in different areas of the tea garden, ensuring the extensiveness and representativeness of the data. Through the data segmentation transmission method, large-scale temperature and humidity data can be efficiently transmitted to the central control system to avoid delays and loss problems caused by excessive data volume during data transmission. The aggregated data can eliminate the accidental fluctuations and acquisition errors of local data, making the temperature and humidity data smoother and continuous, which is conducive to the stability and prediction accuracy of the model. Through self-encoding, high-dimensional temperature and humidity aggregation data are subjected to dimensionality reduction processing and feature extraction, and key features in the data are extracted, redundant information is removed, and the data dimension is reduced. Through the time series segmentation technology, the self-encoded data is segmented according to time, which can better capture the changing laws and patterns of the temperature and humidity in the tea garden in different time periods.

[0123] Optionally, S13 includes:

[0124] S131, performing change data retention aggregation on the tea garden temperature and humidity slice data to obtain first tea garden temperature and humidity aggregation data;

[0125] In one embodiment, the change data retention aggregation refers to retaining the change trend information of the temperature and humidity data in time or space as much as possible during the data aggregation process. By carefully analyzing the temperature and humidity data in each slice, statistics that can reflect the characteristics of data changes are extracted. The tea garden temperature and humidity slice data are grouped by time intervals, for example, every 15 minutes is a time interval. For the data in each time interval, the change characteristic values ​​of temperature and humidity are calculated. The change characteristics include: temperature / humidity change rate (such as the increase or decrease in unit time), fluctuation amplitude (such as the difference between the maximum and minimum values), trend direction (such as rising or falling), etc.

[0126] In one embodiment, the tea garden is divided into several spatial regions according to certain rules (such as sensor coverage or geographical division). For the temperature and humidity data in each spatial region, the spatial variation characteristics in each time interval are calculated. The variation characteristics include: temperature / humidity gradient in the region (such as the temperature difference between sensors), extreme value position (such as the position where the highest / lowest temperature and humidity appear), etc.

[0127] S132, performing graph data aggregation on the tea garden temperature and humidity slice data to obtain the second tea garden temperature and humidity aggregation data.

[0128] In one embodiment, graph data aggregation refers to converting the tea garden temperature and humidity slice data into a graph structure, and describing the spatial distribution and mutual correlation of the data through the relationship between nodes and edges. The node represents the location of the temperature and humidity sensor or a specific area, and the edge represents the relationship between these nodes, such as spatial distance or data correlation. Each sensor node is regarded as a node of a graph, and the attribute value of each node is the temperature and humidity data of the node within a time interval and its change characteristic value (such as average temperature, humidity, rate of change, etc.). The edges between nodes are constructed according to the geographical location or data correlation (such as Pearson correlation coefficient) of the sensor node. The attribute value of the edge can be spatial distance or data correlation strength. The attribute values ​​of adjacent nodes (such as nodes that are close in space) are aggregated to calculate the temperature and humidity data characteristics of the local area. The aggregation method can be weighted average, maximum / minimum value, etc. The edges between adjacent nodes are aggregated to calculate the spatial temperature and humidity distribution characteristics of the entire tea garden. The aggregation method is average distance, average correlation, etc. The second tea garden temperature and humidity aggregation data is obtained, including the attribute data of each aggregation node and the spatial distribution characteristics of the entire graph structure.

[0129] The change data retention aggregation method in the present invention can effectively identify significant change points in temperature and humidity data, retain the change trend and characteristics of temperature and humidity over time, and accurately identify dynamic changes in the tea garden environment, such as sudden temperature drop, sudden increase in humidity and other phenomena. By retaining only data points with significant changes, the storage amount of redundant data is reduced, the data storage and processing efficiency is optimized, and key information is retained to facilitate subsequent refined analysis. The graph data aggregation method can combine temperature and humidity data with the spatial location of the tea garden to reveal the spatial distribution characteristics of temperature and humidity in different areas of the tea garden. For example, it can be identified which areas in the tea garden have higher temperatures and lower humidity, which is helpful for precise positioning and targeted management. Through the aggregation of graph data, the spatial correlation of temperature and humidity between different areas can be analyzed, which is very helpful for understanding the impact of factors such as different terrains and planting density on temperature and humidity in the tea garden, and helps to optimize the layout and management strategies of the tea garden.

[0130] Optionally, S131 includes:

[0131] Extract the spatial distribution of the tea garden temperature and humidity data to obtain the tea garden temperature and humidity spatial distribution data;

[0132] In one embodiment, the tea garden is divided into several spatial areas according to certain rules (such as sensor coverage or geographical division).

[0133] Acquire tea garden electronic map data, and construct a tea garden space matrix according to the tea garden electronic map data to obtain tea garden space matrix data;

[0134] In one embodiment, electronic map data of the tea garden is obtained through remote sensing images, drone aerial photography or existing geographic information system (GIS). The electronic map data includes information such as the topography of the tea garden, distribution of tea trees, paths, water bodies, etc. The electronic map data of the tea garden is discretized into a spatial matrix. Each element of the spatial matrix represents a small area (such as 1m 2 ), each element records the basic information of the area (such as terrain, altitude, vegetation, etc.).

[0135] Mapping is performed based on the tea garden spatial matrix data and the tea garden temperature and humidity spatial distribution data to obtain the tea garden temperature and humidity matrix data;

[0136] In one embodiment, the temperature and humidity spatial distribution data is matched and mapped with the tea garden spatial matrix data. Each spatial matrix unit corresponds to a temperature and humidity value. According to the coordinate value of each element in the spatial matrix, the corresponding temperature and humidity value is filled into the matrix to form a tea garden temperature and humidity matrix.

[0137] According to the electronic map data of the tea garden, the spatial correlation data of the temperature and humidity matrix of the tea garden are processed to obtain the spatial correlation data of the temperature and humidity of the tea garden;

[0138] In one embodiment, the spatial correlation is calculated based on the temperature and humidity data of adjacent cells in the temperature and humidity matrix, such as the Pearson correlation coefficient, the Euclidean distance, etc. The temperature and humidity data of each cell and its surrounding adjacent cells are calculated to obtain the spatial correlation data of each cell.

[0139] According to the spatial correlation data of temperature and humidity in the tea garden, spatial slicing is performed to obtain the spatial slicing data of temperature and humidity in the tea garden;

[0140] In one embodiment, the tea garden space matrix is ​​sliced ​​according to the spatial correlation data, and regions with high similarity are divided into the same slice. The slicing method is a threshold-based clustering method (such as cluster analysis), and units with correlation exceeding a certain threshold are classified into the same slice.

[0141] Perform change point detection based on the tea garden temperature and humidity spatial slice data to obtain the tea garden temperature and humidity spatial change point data;

[0142] In one embodiment, in the spatial slice data, the temperature and humidity change points in each time period are detected. The change point refers to the point where the temperature and humidity change significantly in space or time. Using the sliding window method, the temperature and humidity change rate in the continuous time segment is calculated, and the point where the change rate exceeds the threshold is marked as a change point.

[0143] Extract the change area of ​​the tea garden temperature and humidity spatial change point data to obtain the tea garden temperature and humidity change area data;

[0144] In one embodiment, based on the change point data, the distribution density and range of the change points are analyzed, the densely distributed change points are classified into the same area, and the area with obvious changes is extracted. The region growing algorithm is used to merge adjacent change points into change areas. For example, change area 1: area [(10,5)-(15,10)], time period 8:30-9:00, temperature change +1.5℃ / 10 minutes, humidity change -3% / 10 minutes, change area 2: area [(20,15)-(25,20)], time period 9:00-9:30, temperature change -2.0℃ / 10 minutes, humidity change +4% / 10 minutes.

[0145] The change data is aggregated according to the regional data of temperature and humidity changes in the tea garden to obtain the aggregated temperature and humidity data of the first tea garden.

[0146] In one embodiment, the temperature and humidity change data in each change area are aggregated to calculate the average change amount, the maximum change amount and other statistics. At the same time, the temperature and humidity change trend in the change area (such as temperature increase and humidity decrease, temperature decrease and humidity increase, etc.) is analyzed.

[0147] In the present invention, by extracting the spatial distribution of temperature and humidity slice data, the temperature and humidity distribution characteristics of each area in the tea garden can be fully grasped, such as the temperature height, humidity change and the like, which is helpful to identify environmental differences. By converting the tea garden electronic map data into a spatial matrix form, the complex terrain and environmental information of the tea garden can be accurately expressed as structured data. The tea garden spatial matrix data and the temperature and humidity distribution data are mapped and integrated, and the temperature and humidity information can be accurately located in each spatial cell of the tea garden to form an all-round temperature and humidity spatial matrix, which is helpful to fully understand the environmental conditions of each area of ​​the tea garden. Through spatial correlation analysis, the mutual relationship of temperature and humidity changes in different regions can be quantified, and the spatial law of environmental changes in the tea garden can be identified, such as which regions change synchronously and which regions change greatly. By spatially slicing the tea garden environmental data, the environmental characteristics of different heights and different regions can be hierarchically analyzed, revealing the changing laws of temperature and humidity at different levels, such as the difference between the tea tree canopy and the surface temperature and humidity. By performing change point detection on the spatial slice data, the time point and position of significant changes in the tea garden environment can be quickly captured, such as the area and time when the temperature rises sharply or the humidity drops sharply. By extracting the change area, we can accurately locate the area where the environmental changes are concentrated, helping managers focus on the areas where the tea garden environment has changed significantly, and improving the pertinence and effectiveness of management. By aggregating the change data, we can remove the noise components in the data, reduce the impact of accidental fluctuations in a single monitoring, and make the temperature and humidity data smoother and more continuous.

[0148] Optionally, S132 includes:

[0149] The tea garden temperature and humidity segmentation data are divided into tea garden space grids to obtain tea garden space grid division data;

[0150] In one embodiment, the tea garden area is divided into grid units of equal size according to certain rules, and each grid unit represents a small area in the tea garden. The size of the grid depends on the actual area of ​​the tea garden and the resolution of the data (e.g., each grid unit is 1m 2 or 5m 2 ). According to the geographic coordinates of the sensor nodes, the collected temperature and humidity slice data are distributed to the corresponding grid cells. For the case where there are multiple sensor data in the same grid cell, the average value or other statistics are calculated.

[0151] According to the tea garden space grid division data, network node association is performed to obtain tea garden space network node association data;

[0152] In one embodiment, each grid unit is regarded as a network node, and the association between nodes is established based on the spatial proximity relationship. The connection relationship between adjacent nodes is determined by a four-neighborhood or eight-neighborhood approach. If grid units No. 1 and No. 2 are adjacent in the X or Y direction, an association is established between them.

[0153] According to the tea garden spatial network node association data, the adjacency matrix is ​​constructed to obtain the tea garden spatial adjacency matrix data;

[0154] In one embodiment, the adjacency matrix is ​​a square matrix used to represent the connection relationship between nodes. If there is an edge between node i and node j, the value of position (i, j) in the matrix is ​​1; otherwise, it is 0. The size of the tea garden space adjacency matrix depends on the number of grid cells. For example, if there are 2500 grid cells, the adjacency matrix is ​​2500×2500.

[0155] The clustering coefficient is calculated based on the spatial adjacency matrix data of the tea garden to obtain the node feature data of the tea garden graph;

[0156] In one embodiment, the clustering coefficient is used to measure the degree of node clustering. It indicates the probability that the neighbors of a node are also connected to each other, and is an indicator for evaluating the local clustering characteristics of nodes. Calculation formula (based on the adjacency matrix): For node i, calculate the ratio of the actual number of edges between its neighbor nodes to the maximum possible number of edges. C i is the clustering coefficient of node i, e is the number of edges actually existing between the neighboring nodes of node i, N is the number of neighboring nodes of node i, and |N|(|N|-1|) is the maximum possible number of edges that can be formed between the neighboring nodes of node i.

[0157] According to the spatial adjacency matrix data of the tea garden, the edge temperature and humidity correlation features are extracted to obtain the edge feature data of the tea garden graph;

[0158] In one embodiment, each edge connects two nodes, and the correlation of the temperature and humidity data of the two nodes can be used as the feature of the edge. The correlation can be calculated using methods such as Pearson correlation coefficient and Euclidean distance.

[0159] The graph data is aggregated according to the node feature data and edge feature data of the tea garden graph to obtain the temperature and humidity aggregated data of the second tea garden.

[0160] In one embodiment, the node feature data and edge feature data are aggregated using statistical methods such as weighted average, maximum value, and minimum value, including: for node features: calculating the average clustering coefficient and maximum clustering coefficient of all nodes. For edge features: calculating the average, minimum, and maximum value of the temperature and humidity correlation of all edges.

[0161] In the present invention, by dividing the tea garden into multiple spatial grid units, a large area of ​​tea garden can be decomposed into several small areas, which is convenient for refined management. Each grid unit represents a specific location in the tea garden, making data analysis and management more accurate. Different grid units have different microenvironmental conditions (such as different temperatures, humidity, light, etc.), which helps to capture the changing laws of the microenvironment in the tea garden, thereby providing data support for precise regulation. By establishing node associations between each grid unit and adjacent units, the connection between adjacent areas in space can be identified, and the spatial diffusion effect and influence mechanism of temperature and humidity between different areas can be captured. Through the adjacency matrix, the temperature and humidity similarity or difference between each grid unit and the adjacent unit can be quantified, providing basic data for subsequent graph node and edge feature analysis. Through graph node features such as clustering coefficient, key areas where temperature and humidity characteristics are relatively concentrated in the tea garden can be identified. These areas have special microclimate characteristics and deserve special attention in management. By extracting the temperature and humidity correlation features on the spatial network edge (the line connecting two nodes), the mutual influence mechanism of temperature and humidity changes between different regions can be revealed. For example, the edge with high correlation indicates that the synchronization of temperature and humidity changes between adjacent regions is strong.

[0162] Optionally, S14 includes:

[0163] Extract the coded features of the aggregated data of temperature and humidity in the tea garden to obtain the coded feature data of temperature and humidity in the tea garden;

[0164] In one embodiment, coded feature extraction is the process of characterizing the aggregated data of temperature and humidity in the tea garden, converting high-dimensional data into low-dimensional representations through an autoencoder or a dimensionality reduction algorithm (such as PCA, feature selection, etc.), while retaining the main feature information of the data. Use the autoencoder to extract features from the input data, first encode the data into a low-dimensional representation, and then reconstruct the high-dimensional data through decoding. The output of the encoding layer in the extraction process is the coded feature data of temperature and humidity in the tea garden. For example, the input temperature and humidity data is 50-dimensional, and after dimensionality reduction processing by the autoencoder, a 10-dimensional coded feature representation is obtained.

[0165] Clustering is performed on the tea garden temperature and humidity coding feature data to obtain the tea garden temperature and humidity coding cluster label data;

[0166] In one embodiment, the coded feature data is clustered, similar coded features are classified into the same category, and the characteristic patterns of tea gardens under different temperature and humidity conditions are identified. Common clustering algorithms include K-means clustering, hierarchical clustering, etc. Using the K-means clustering algorithm, the coded feature data is divided into different clusters (such as K=3, the data is divided into 3 categories). The distance between each data point and the cluster center is calculated, the data point is assigned to the nearest cluster center, and the cluster center position is updated until the cluster center is stable.

[0167] Perform time series prediction on the tea garden temperature and humidity encoded cluster label data to obtain the tea garden temperature and humidity time series prediction data;

[0168] In one embodiment, according to the cluster label data encoded by the temperature and humidity of the tea garden, a time series prediction model (such as LSTM, ARIMA, etc.) is used to predict the temperature and humidity state at future times, and to determine the time series evolution trend of the temperature and humidity clustering pattern. The input data is the cluster label data encoded by the temperature and humidity of the tea garden, which contains time dimension information and cluster label sequence. Use the LSTM (Long Short-Term Memory Network) model for training, input the cluster label sequence of several time steps in the past, and predict the cluster label sequence of several time steps in the future. The input layer is the cluster label sequence of the time step, the LSTM layer captures the time dependency relationship, and the output layer is the cluster label prediction value of the future time step. The cluster label sequence prediction value of several time steps in the future.

[0169] In one embodiment, a moving average method is used for short-term prediction, and time series prediction is performed on the tea garden temperature and humidity encoded cluster label data to obtain tea garden temperature and humidity time series prediction data.

[0170] According to the tea garden temperature and humidity time series forecast data, the self-encoding reconstruction error processing is performed to obtain the tea garden temperature and humidity reconstruction error data;

[0171] In one embodiment, the time series prediction data is mapped to the coding space by an autoencoder, and then the original data is decoded and reconstructed. The reconstruction error represents the difference between the decoded data and the original data, and is used to evaluate the accuracy of the prediction data. The time series prediction data is input into the autoencoder for reconstruction, and the difference between the decoded data and the original temperature and humidity clustering label data is calculated. For each time step of the predicted label sequence, the reconstruction error (such as the mean square error MSE) is calculated to measure the error between the decoded data and the actual data.

[0172] Anomaly detection and error elimination are performed on the reconstructed error data of temperature and humidity in the tea garden to obtain the self-encoded data of temperature and humidity in the tea garden.

[0173] In one embodiment, by analyzing the reconstruction error data, abnormal time steps (such as errors exceeding a set threshold) are detected, and the abnormal points are removed or corrected from the prediction results to eliminate the impact of the errors on the prediction results. A reconstruction error threshold (such as 0.1) is set, and time steps exceeding the threshold are marked as abnormal. The reconstruction errors of all time steps are detected and abnormal time steps are marked. For time steps marked as abnormal, normal data of adjacent time steps are used for replacement or interpolation correction to reduce the impact of errors on the overall results. The corrected prediction data is the tea garden temperature and humidity auto-encoding data, which represents the temperature and humidity prediction results in the time series dimension, removing abnormal interference.

[0174] In the present invention, the coded feature extraction of the aggregated data of temperature and humidity in the tea garden can reduce the dimension of the high-dimensional temperature and humidity data to a low-dimensional feature representation, reduce the redundancy of the data, and reduce the complexity of subsequent data processing. By clustering the coded feature data, the hidden patterns and laws in the temperature and humidity data of the tea garden are revealed, such as the temperature and humidity change characteristics in different time periods and different regions, providing a scientific basis for the refined management of the tea garden environment. Based on the clustered coded feature data, time series prediction can be performed to predict the changing trend of the temperature and humidity in the tea garden in the future, which is helpful to take preventive management measures in advance, such as starting the fill light system when the temperature is expected to drop sharply. Reconstruction error analysis can help identify and eliminate anomalies and errors in the data, thereby improving the accuracy and stability of the model and avoiding model misjudgment due to abnormal data.

[0175] Optionally, S2 includes:

[0176] S21, obtaining tea tree distribution data;

[0177] In one embodiment, a high-resolution image of the tea garden is obtained using remote sensing images or drone aerial photography technology. The image should cover the entire tea garden area to ensure that each tea tree can be identified. Image processing technology (such as convolutional neural network CNN, edge detection, etc.) is used to analyze the acquired image to identify the specific location of each tea tree. The coordinates (such as X, Y coordinates) and canopy information of each tea tree are extracted and recorded in the database.

[0178] In one embodiment, data is imported through a preset database.

[0179] S22, calculating tea tree planting density according to the tea tree distribution data to obtain tea tree planting density data;

[0180] In one embodiment, the tea garden is divided into a number of small grid units (e.g., 1 m 2 ). For each grid cell, the number of tea trees in it is calculated to obtain the planting density data. Tea tree planting density = number of tea trees in a cell / cell area. The total number of tea trees and the area of ​​the tea garden are counted to calculate the overall planting density.

[0181] S23, performing spatial temperature and humidity interpolation on the tea tree temperature and humidity data according to the tea tree planting density data to obtain tea tree temperature and humidity interpolation data;

[0182] In one embodiment, according to the spatial density of tea tree distribution, a suitable interpolation algorithm is selected, such as Kriging interpolation, inverse distance weighted (IDW), spline interpolation, etc. The collected tea tree temperature and humidity data are interpolated, and the discrete sensor data are expanded to the entire tea garden area so that each tea tree position has corresponding temperature and humidity data. For each tea tree position, interpolation is performed according to the weight of the neighboring sensor data to obtain the temperature and humidity data of the tea tree.

[0183] S24, analyzing the environmental adaptability of the tea trees according to the interpolation data of temperature and humidity of the tea trees, and obtaining the environmental adaptability scoring data of the tea trees;

[0184] In one embodiment, the optimal growth temperature and humidity range of each variety is determined according to the growth habits of the tea tree variety (for example, the suitable temperature of variety A is 20-25°C and the suitable humidity is 70%-80%). The temperature and humidity interpolation data of the tea tree location are compared with the suitable growth conditions of the variety. If the temperature and humidity values ​​are within the optimal range, the score is higher; otherwise, the score is lower. Adaptability score = (temperature adaptability score + humidity adaptability score) / 2, temperature adaptability score: score according to the degree of temperature deviation from the optimal range (0-100 points). Humidity adaptability score: score according to the degree of humidity deviation from the optimal range (0-100 points).

[0185] S25. Construct a tea tree temperature and humidity environment model based on the tea tree environmental adaptability score data, tea tree distribution data, and tea garden temperature and humidity data to obtain a tea tree temperature and humidity environment model.

[0186] In one embodiment, the tea tree environmental adaptability score data, tea tree distribution data (tea tree coordinates, planting density, etc.), and tea garden temperature and humidity data (from sensors and interpolation data) are fused to form a complete environmental data set. A tea tree temperature and humidity environmental model is established to analyze the relationship between the temperature and humidity of tea trees in different regions and the adaptability score. The model can use methods such as multivariate regression analysis, decision trees, and neural networks. The model is trained using historical data, and some data is used for model verification to evaluate the accuracy and predictive ability of the model. The model predicts the changes in the adaptability score of tea trees under different environmental conditions, providing data support for the temperature and humidity control strategy of the tea garden.

[0187] In the present invention, the distribution data of tea trees are obtained by means of UAV remote sensing, geographic information system (GIS) or field survey, and the geographical location of each tea tree can be accurately located, providing a comprehensive view of the tea garden planting layout. According to the tea tree distribution data, the planting density is calculated, and the over-dense or over-sparse planting areas can be identified, which provides a reference for optimizing the tea tree planting layout, and helps to improve the land utilization rate and the rationality of the tea tree growth space. By spatially interpolating the temperature and humidity data, the temperature and humidity information of each position in the tea garden can be obtained to form a spatial distribution map of the temperature and humidity of the tea garden. Identify the changes in the microenvironment in the tea garden and provide data support for precise regulation. According to the tea tree temperature and humidity interpolation data and the planting density data, the environmental adaptability analysis can be performed, and the growth adaptability of the tea tree under different environmental conditions can be evaluated, and the areas that are not suitable for the growth of tea trees can be identified, which provides a basis for the transformation and optimization of the tea garden. The environmental model constructed based on the tea tree distribution data, the planting density data and the temperature and humidity data can simulate the dynamic changes of the tea garden environment and provide technical support for the intelligent monitoring and early warning of the tea garden environment.

[0188] Optionally, S3 includes:

[0189] S31, obtaining photovoltaic parameter data;

[0190] In one embodiment, photovoltaic panels installed in different areas of the tea garden collect their operating parameters in real time through sensors, including voltage, current, power output, panel surface temperature, photovoltaic panel inclination, etc.

[0191] S32, evaluating photovoltaic power generation capacity according to photovoltaic parameter data to obtain photovoltaic power generation evaluation data;

[0192] In one embodiment, the actual output power of the photovoltaic panel is calculated based on the voltage, current and radiation intensity data of the photovoltaic panel. Calculation formula: actual output power = voltage * current. If the radiation intensity is insufficient (such as cloudy or foggy days), the reduction in the efficiency of the photovoltaic panel needs to be considered. The output power of all photovoltaic panels is summed up to obtain the total power generation capacity of the entire photovoltaic system. The daily and hourly power generation capacity is evaluated, taking into account the changes in sunshine and the fluctuations in the working efficiency of the photovoltaic panels.

[0193] S33, calculating the photovoltaic panel inclination angle according to the photovoltaic parameter data to obtain the photovoltaic panel inclination angle data;

[0194] In one embodiment, the optimal inclination angle of the photovoltaic panel is calculated according to the geographical location (latitude, longitude) of the tea garden and the current season to maximize the absorption of solar radiation by the photovoltaic panel. Calculation formula: Optimal inclination angle = geographical latitude ± 23.5° (± is seasonal adjustment) Combined with real-time solar position and radiation intensity data, the inclination angle of the photovoltaic panel is dynamically adjusted to maximize power generation efficiency. Calculation method: Calculate the optimal inclination angle at the current time through the solar position formula (sun altitude angle, azimuth angle).

[0195] S34, performing photovoltaic power generation allocation according to the photovoltaic power generation evaluation data, the photovoltaic panel inclination data, and the tea tree temperature and humidity environment model to obtain tea tree photovoltaic power generation allocation data;

[0196] In one embodiment, the temperature and humidity requirements of tea trees in different areas are analyzed based on the temperature and humidity environment model of tea trees. For areas with higher temperature and humidity requirements (such as colder or drier areas), more photovoltaic power generation is preferentially allocated for supplementary lighting. The output power of the photovoltaic panels is allocated to tea trees in different areas according to factors such as the environmental requirements of each area, the location of the photovoltaic panels, and the power generation capacity. Allocation formula: Allocated power = regional demand weight * photovoltaic panel output power, real-time monitoring of changes in temperature and humidity in the tea garden and power generation of photovoltaic panels, dynamic adjustment of power generation allocation strategy, to ensure the optimization of tea tree growth conditions in each area.

[0197] S35. Perform photovoltaic lighting simulation according to the photovoltaic power generation distribution data of the tea trees to obtain photovoltaic lighting data of temperature and humidity of the tea trees.

[0198] In one embodiment, a photovoltaic lighting simulation model is established based on the tea tree position, photovoltaic panel position, photovoltaic panel inclination and power generation distribution data. The simulation model should consider the impact of photovoltaic lighting on the temperature and humidity of the environment around the tea tree. Input parameters include photovoltaic panel output power, inclination, solar radiation intensity, tea tree position and its temperature and humidity requirements. The effect of photovoltaic lighting on the improvement of tea tree temperature and humidity is simulated by ray tracing, energy balance and other methods. The impact of different lighting schemes on the growth environment of tea trees is analyzed based on the simulation results, and the optimal scheme is selected for practical application.

[0199] The present invention timely understands the actual working state of the photovoltaic panel, such as power generation efficiency, power output, etc., which helps to discover potential problems (such as photovoltaic panel surface shielding, system failure, etc.) and improve the operational stability and reliability of the system. Through the comprehensive analysis of photovoltaic parameter data, the power generation capacity of the photovoltaic system in different time periods can be accurately evaluated, the power generation potential of the photovoltaic system can be predicted, and the foundation for the rational use of photovoltaic power can be laid. By calculating the optimal inclination angle of the photovoltaic panel in different seasons and time periods, the efficiency of the photovoltaic panel receiving sunlight can be effectively improved, the power generation can be maximized, and the overall utilization rate of the photovoltaic system can be improved. According to the photovoltaic power generation capacity evaluation data, the photovoltaic panel inclination data and the tea tree temperature and humidity environment model, a reasonable power generation allocation plan can be formulated, and power resources can be intelligently allocated according to the actual needs of different regions to achieve precise control. The simulation results can help identify the optimal time, intensity and duration of photovoltaic lighting, avoid excessive or insufficient lighting behavior, and improve the suitability of the tea tree growth environment.

[0200] Optionally, S33 includes:

[0201] Obtain photovoltaic panel location data and tea garden structure data;

[0202] In one embodiment, the geographic coordinates (latitude and longitude) and height information of each photovoltaic panel are accurately obtained using measuring equipment such as GPS or total station. Determine the distance and orientation of the photovoltaic panel relative to the tea tree in order to evaluate the lighting effect of the photovoltaic panel on the tea tree. Obtain the specific location, crown width, tree height and other information of each tea tree. It can be obtained by using drone aerial image processing or on-site measurement. Use topographic mapping instruments to obtain the terrain data of the tea garden, such as slope, slope direction, altitude, etc. Analyze the impact of obstructions (such as tall trees and buildings) inside and outside the tea garden on solar radiation, and record their location, height, obstruction range, etc.

[0203] The solar radiation model is constructed based on the photovoltaic panel location data and the tea garden structure data to obtain the tea garden solar radiation model;

[0204] In one embodiment, the solar position formula is used to calculate the altitude and azimuth of the sun according to the geographical location, time and date. The direct radiation, scattered radiation and reflected radiation at each position in the tea garden at different times are calculated. According to the inclination, azimuth and position of the photovoltaic panel, the shielding of the tea tree and other photovoltaic panels by the photovoltaic panel at different times is calculated. A geometric light and shadow model is used to simulate the impact of photovoltaic panels, tea trees and surrounding obstructions on solar radiation. The digital terrain model (DEM) is combined with the position of photovoltaic panels and tea trees to simulate the distribution of solar radiation in the entire tea garden at different times and different positions. Combined with the inclination and azimuth of the photovoltaic panel, the received radiation of each photovoltaic panel at different times is calculated. Calculation formula: Received radiation = direct radiation * cos (incident angle) + scattered radiation + reflected radiation.

[0205] The photovoltaic panel inclination angle is calculated according to the tea garden solar radiation model and photovoltaic parameter data to obtain the photovoltaic panel inclination angle data.

[0206] In one embodiment, the optimal inclination angle for maximizing photovoltaic power generation at different times and different photovoltaic panel positions is calculated through a solar radiation model, and the calculation factors include: solar altitude angle, current azimuth angle of the photovoltaic panel, shading conditions, temperature and humidity requirements of the tea tree, etc. According to the mechanical structure and adjustment capability of the photovoltaic panel, the actual adjustable inclination angle range (such as ±30°) is determined, and the optimal inclination angle that is actually feasible is calculated. Inclination calculation formula: optimal inclination angle = arctan (sun altitude angle / solar azimuth angle), combined with the actual adjustment capability, the actual installation angle is taken. According to the season and the geographical location of the tea garden, a fixed inclination angle is set, which is suitable for photovoltaic panels without automatic adjustment devices. For example, the inclination angle in summer = geographical latitude -15°; the inclination angle in winter = geographical latitude +15°. Combined with the real-time solar radiation model and photovoltaic panel location data, the inclination angle of the photovoltaic panel is dynamically adjusted. For example, the inclination angle is adjusted once an hour to ensure that the amount of radiation received by the photovoltaic panel is maximized.

[0207] In the present invention, by obtaining the precise position of the photovoltaic panel (including longitude and latitude, altitude, installation angle, etc.), the spatial layout of the photovoltaic panel can be accurately understood, and the structural data of the tea garden (such as terrain height, exposure degree of the tea garden, etc.) can be obtained, so that the environmental characteristics around the photovoltaic panel can be fully understood, and the shielding relationship between the photovoltaic panel and the tea tree can be taken into account to avoid the photovoltaic panel being shielded and causing the power generation efficiency to decrease. The solar radiation model constructed based on the photovoltaic panel position data and the tea garden structure data can accurately simulate the amount of solar radiation received by the photovoltaic panel under different time periods and seasonal conditions. By calculating the optimal inclination angle of the photovoltaic panel through the solar radiation model and photovoltaic parameter data, the photovoltaic panel can receive more solar radiation in different seasons and different time periods, thereby improving the overall power generation efficiency of the photovoltaic system.

[0208] Optionally, S4 includes:

[0209] S41, calculating the temperature-humidity-photovoltaic supplementary lighting coupling relationship according to the temperature-humidity-photovoltaic supplementary lighting data of the tea trees, and obtaining the temperature-humidity-photovoltaic supplementary lighting coupling relationship data;

[0210] In one embodiment, the effects of temperature and humidity on the growth environment of tea trees are interrelated, and photovoltaic lighting will affect the temperature and humidity of the tea garden at the same time. Therefore, it is necessary to analyze the coupling relationship between temperature and humidity under photovoltaic lighting conditions. The photovoltaic lighting data of tea tree temperature and humidity includes the changes in temperature and humidity before and after lighting at each tea tree position. Use regression analysis or multivariate analysis methods to calculate the comprehensive impact of photovoltaic lighting on temperature and humidity. Establish a coupling relationship model between temperature changes and humidity changes, and analyze the coupling characteristics of temperature and humidity under different lighting intensities.

[0211] S42, obtaining tea tree variety data;

[0212] In one embodiment, the variety information of tea trees is obtained through field surveys or tea garden management systems. Each variety may correspond to different growth characteristics and temperature and humidity requirements. The tea variety information is associated with its geographical location (X / Y coordinates) and stored to form a complete tea variety distribution data set. The growth habit data of each variety includes the optimal temperature range, the optimal humidity range, the light requirements, etc.

[0213] S43, performing temperature and humidity cross sensitivity analysis according to the tea variety data and the temperature, humidity and light supplement coupling relationship data to obtain temperature and humidity cross sensitivity data;

[0214] In one embodiment, temperature and humidity cross sensitivity analysis is used to evaluate the sensitivity of tea varieties to changes in temperature and humidity. Different tea varieties react differently to changes in temperature or humidity, so the effects of temperature and humidity need to be analyzed separately. Tea variety data and temperature and humidity supplementary light coupling relationship data. Use sensitivity analysis models (such as local sensitivity analysis, global sensitivity analysis) to calculate the degree of influence of temperature changes and humidity changes on tea growth. For each tea variety, calculate its sensitivity coefficient to temperature and humidity. Cross-sensitivity coefficient calculation formula: Cross-sensitivity = temperature sensitivity coefficient * humidity sensitivity coefficient.

[0215] S44, fitting the fill light intensity environment response curve according to the temperature and humidity fill light coupling relationship data to obtain fill light intensity environment response curve data;

[0216] In one embodiment, the fill-light intensity environmental response curve is used to describe the relationship between photovoltaic fill-light intensity and the tea tree growth environment (temperature and humidity changes). The curve can reflect the changing trend of the tea tree environment under different fill-light intensities. Temperature and humidity fill-light coupling relationship data, as well as photovoltaic fill-light intensity data. Select a curve fitting method (such as polynomial fitting, exponential fitting, S-curve fitting, etc.), and fit the environmental response curve according to the temperature and humidity change data under different fill-light intensities. Fitting formula: Environmental change = f (fill-light intensity), f is one of linear, polynomial or other nonlinear functions.

[0217] S45. Perform collaborative optimization of supplementary lighting according to the temperature and humidity cross-sensitivity data and the supplementary lighting intensity environmental response curve data to obtain supplementary lighting effect optimization data to carry out temperature and humidity control operations in the photovoltaic supplementary lighting tea garden.

[0218] In one embodiment, supplementary lighting collaborative optimization refers to optimizing the photovoltaic supplementary lighting strategy based on the cross-sensitivity analysis of temperature and humidity, combined with the supplementary lighting intensity environmental response curve, so that the tea tree growth environment reaches the best state. Maximize the environmental adaptability score of the tea tree (i.e., the comprehensive suitability of temperature and humidity). Minimize the energy consumption of the photovoltaic system (i.e., reduce the photovoltaic supplementary lighting intensity while meeting the growth needs). Use a multi-objective optimization algorithm (such as genetic algorithm, particle swarm optimization, etc.) to optimize parameters such as supplementary lighting intensity, supplementary lighting duration, and supplementary lighting area. Based on the optimization results, generate the optimal supplementary lighting strategy for different tea varieties and regions.

[0219] In the present invention, by calculating the coupling relationship of the photovoltaic supplementary lighting data of the temperature and humidity of the tea tree, the influence of photovoltaic supplementary lighting on the temperature and humidity environment of the tea garden can be accurately quantified, so as to understand how factors such as supplementary lighting intensity and duration affect the growth environment of the tea tree. Different tea varieties have different requirements for light, temperature and humidity. Acquiring tea variety data can identify the tea varieties planted in various areas of the tea garden. Through cross-sensitivity analysis, the degree of influence of temperature and humidity on the growth of different tea varieties can be quantified, and the varieties and environmental conditions with higher sensitivity can be identified to help managers take preventive measures in advance. Through curve fitting of supplementary lighting intensity and environmental response data, the influence of supplementary lighting intensity on the temperature and humidity environment of the tea garden can be accurately quantified, revealing the dynamic change law of temperature and humidity under different supplementary lighting intensities. Based on the temperature and humidity cross-sensitivity data and the supplementary lighting intensity environmental response curve data, collaborative optimization can be performed, and various factors such as tea variety characteristics, environmental conditions and supplementary lighting strategies can be considered to achieve the optimal supplementary lighting solution. Through the temperature, humidity and light coupling relationship and cross-sensitivity analysis, we can help tea gardens accurately control the growth environment of tea trees under complex environmental conditions (such as extreme weather, seasonal changes, etc.) and improve the adaptability and stability of the tea garden environment.

[0220] The object of the present invention is to obtain multi-source environmental data of tea gardens through a temperature and humidity sensor network, a photovoltaic parameter acquisition system and tea tree distribution remote sensing technology. The environmental model constructed based on tea tree distribution data and temperature and humidity data can accurately simulate the temperature and humidity distribution law and its changing trend in different areas of the tea garden, and provide a reliable prediction basis for refined management. The environmental model can reveal the influence of different microenvironments in the tea garden on the growth of tea trees, help identify key environmental factors, and provide a scientific basis for formulating regionalized and differentiated management strategies. Photovoltaic supplementary lighting simulation is carried out according to photovoltaic parameter data and tea tree temperature and humidity environmental model, and photovoltaic power generation resources can be intelligently allocated according to the needs of different areas of the tea garden, the utilization efficiency of the photovoltaic system can be maximized, and resource waste can be avoided. Through the calculation of the temperature and humidity supplementary lighting coupling relationship, the temperature and humidity regulation effect of photovoltaic supplementary lighting on the tea garden microenvironment can be quantitatively analyzed, and the deep-level influence of supplementary lighting behavior on the growth environment of tea trees can be revealed. Combined with tea tree variety data and temperature and humidity supplementary lighting coupling relationship data, the supplementary lighting effect is optimized and matched, and personalized supplementary lighting strategies can be formulated according to the illumination, temperature and humidity requirements of different tea tree varieties, so as to achieve "different for each tree" precise management.

[0221] Therefore, from any point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the attached application documents rather than the above description, and it is intended that all changes falling within the meaning and scope of equivalent elements of the application documents are included in the present invention.

[0222] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for controlling temperature and humidity in a tea garden based on photovoltaic supplementary lighting, characterized in that: The method comprises: S1. Obtain tea garden temperature and humidity data; S2, obtaining tea tree distribution data, and constructing a tea tree temperature and humidity environment model based on the tea tree distribution data and tea garden temperature and humidity data to obtain a tea tree temperature and humidity environment model; S3, obtaining photovoltaic parameter data, and performing photovoltaic lighting simulation according to the photovoltaic parameter data and the tea tree temperature and humidity environment model to obtain tea tree temperature and humidity photovoltaic lighting data; S4. Calculate the temperature-humidity-fill-light coupling relationship according to the temperature-humidity-fill-light coupling data of the tea trees to obtain temperature-humidity-fill-light coupling relationship data; obtain tea tree variety data, and optimize and match the fill-light effect according to the temperature-humidity-fill-light coupling relationship data and the tea tree variety data to obtain fill-light effect optimization data, so as to carry out temperature and humidity control operations in the tea garden with photovoltaic fill-light.

2. The method according to claim 1, characterized in that: S1 includes: S11, collecting temperature and humidity data through temperature and humidity sensor nodes, and obtaining preliminary tea garden temperature data and preliminary tea garden humidity data respectively; S12, transmitting the preliminary tea garden temperature data and preliminary tea garden humidity data in slices to obtain tea garden temperature and humidity slice data; S13, performing data aggregation on the tea garden temperature and humidity slice data to obtain tea garden temperature and humidity aggregation data; S14, self-encoding the aggregated data of temperature and humidity in the tea garden to obtain self-encoded data of temperature and humidity in the tea garden; S15, performing time series segmentation on the tea garden temperature and humidity self-encoded data to obtain tea garden temperature and humidity data.

3. The method according to claim 2, characterized in that S13 includes: S131, performing change data retention aggregation on the tea garden temperature and humidity slice data to obtain the first tea garden temperature and humidity aggregation data; S132, performing graph data aggregation on the tea garden temperature and humidity slice data to obtain the second tea garden temperature and humidity aggregation data.

4. The method according to claim 3, characterized in that S131 includes: Extract the spatial distribution of the tea garden temperature and humidity data to obtain the tea garden temperature and humidity spatial distribution data; Acquire tea garden electronic map data, and construct a tea garden space matrix according to the tea garden electronic map data to obtain tea garden space matrix data; Mapping is performed based on the tea garden spatial matrix data and the tea garden temperature and humidity spatial distribution data to obtain the tea garden temperature and humidity matrix data; According to the electronic map data of the tea garden, the spatial correlation data of the temperature and humidity matrix of the tea garden are processed to obtain the spatial correlation data of the temperature and humidity of the tea garden; According to the spatial correlation data of temperature and humidity in the tea garden, spatial slicing is performed to obtain the spatial slicing data of temperature and humidity in the tea garden; Perform change point detection based on the tea garden temperature and humidity spatial slice data to obtain the tea garden temperature and humidity spatial change point data; Extract the change area of ​​the tea garden temperature and humidity spatial change point data to obtain the tea garden temperature and humidity change area data; The change data is aggregated according to the regional data of temperature and humidity changes in the tea garden to obtain the aggregated temperature and humidity data of the first tea garden.

5. The method according to claim 3, characterized in that: S132 includes: The tea garden temperature and humidity segmentation data are divided into tea garden space grids to obtain tea garden space grid division data; According to the tea garden space grid division data, network node association is performed to obtain tea garden space network node association data; According to the tea garden spatial network node association data, the adjacency matrix is ​​constructed to obtain the tea garden spatial adjacency matrix data; The clustering coefficient is calculated based on the spatial adjacency matrix data of the tea garden to obtain the node feature data of the tea garden graph; According to the spatial adjacency matrix data of the tea garden, the edge temperature and humidity correlation features are extracted to obtain the edge feature data of the tea garden graph; The graph data is aggregated according to the node feature data and edge feature data of the tea garden graph to obtain the temperature and humidity aggregated data of the second tea garden.

6. The method according to claim 2, characterized in that S14 includes: Extract the coded features of the aggregated data of temperature and humidity in the tea garden to obtain the coded feature data of temperature and humidity in the tea garden; Clustering is performed on the tea garden temperature and humidity coding feature data to obtain the tea garden temperature and humidity coding cluster label data; Perform time series prediction on the tea garden temperature and humidity encoded cluster label data to obtain the tea garden temperature and humidity time series prediction data; According to the tea garden temperature and humidity time series forecast data, the self-encoding reconstruction error processing is performed to obtain the tea garden temperature and humidity reconstruction error data; Anomaly detection and error elimination are performed on the reconstructed error data of temperature and humidity in the tea garden to obtain the self-encoded data of temperature and humidity in the tea garden.

7. The method according to claim 2, characterized in that S2 include: S21, obtaining tea tree distribution data; S22, calculating tea tree planting density according to the tea tree distribution data to obtain tea tree planting density data; S23, performing spatial temperature and humidity interpolation on the tea tree temperature and humidity data according to the tea tree planting density data to obtain tea tree temperature and humidity interpolation data; S24, analyzing the environmental adaptability of the tea trees according to the interpolation data of temperature and humidity of the tea trees, and obtaining the environmental adaptability scoring data of the tea trees; S25. Construct a tea tree temperature and humidity environment model based on the tea tree environmental adaptability score data, tea tree distribution data, and tea garden temperature and humidity data to obtain a tea tree temperature and humidity environment model.

8. The method according to claim 1, characterized in that S3 include: S31, obtaining photovoltaic parameter data; S32, evaluating photovoltaic power generation capacity according to photovoltaic parameter data to obtain photovoltaic power generation evaluation data; S33, calculating the photovoltaic panel inclination angle according to the photovoltaic parameter data to obtain the photovoltaic panel inclination angle data; S34, performing photovoltaic power generation allocation according to the photovoltaic power generation evaluation data, the photovoltaic panel inclination data, and the tea tree temperature and humidity environment model to obtain tea tree photovoltaic power generation allocation data; S35. Perform photovoltaic lighting simulation according to the photovoltaic power generation distribution data of the tea trees to obtain photovoltaic lighting data of temperature and humidity of the tea trees.

9. The method according to claim 7, characterized in that: S33 includes: Obtain photovoltaic panel location data and tea garden structure data; The solar radiation model is constructed based on the photovoltaic panel location data and the tea garden structure data to obtain the tea garden solar radiation model; The photovoltaic panel inclination angle is calculated according to the tea garden solar radiation model and photovoltaic parameter data to obtain the photovoltaic panel inclination angle data.

10. The method according to claim 1, characterized in that S4 include: S41, calculating the temperature-humidity-photovoltaic supplementary lighting coupling relationship according to the temperature-humidity-photovoltaic supplementary lighting data of the tea trees, and obtaining the temperature-humidity-photovoltaic supplementary lighting coupling relationship data; S42, obtaining tea tree variety data; S43, performing temperature and humidity cross sensitivity analysis according to the tea variety data and the temperature, humidity and light supplement coupling relationship data to obtain temperature and humidity cross sensitivity data; S44, fitting the fill light intensity environment response curve according to the temperature and humidity fill light coupling relationship data to obtain fill light intensity environment response curve data; S45. Perform collaborative optimization of supplementary lighting according to the temperature and humidity cross-sensitivity data and the supplementary lighting intensity environmental response curve data to obtain supplementary lighting effect optimization data to carry out temperature and humidity control operations in the photovoltaic supplementary lighting tea garden.

Images