Greenhouse photovoltaic roof adaptive power generation optimization control system

Abstract

The application discloses a greenhouse photovoltaic roof adaptive power generation optimization control system, relates to the technical field of roof power generation control, and is used for solving the problem that crops are in insufficient illumination or excessive illumination state in the growth stage, affecting photosynthetic efficiency and yield. The crop type and growth stage are acquired through image recognition, the illumination deviation is calculated in combination with an illumination demand library and an illumination sensor, the illumination level is determined according to the deviation and photosynthetic response characteristics, the photosynthetic efficiency is calculated by collecting leaf potential and transpiration rate, whether the photovoltaic panel angle is adjusted is comprehensively judged, and an execution instruction is output, different control mechanisms are set, the balance optimization strategy is executed when the power generation efficiency is high, the illumination adaptability and power generation stability are maintained, the intelligent switching strategy is executed when the power generation efficiency is low, the production capacity is preferentially improved and the crop illumination tolerance is considered, the angle is dynamically adjusted, the collaborative optimization of agriculture and energy is realized, and the system adaptability and operation efficiency are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of roof power generation control, more particularly, the present application relates to a greenhouse photovoltaic roof adaptive power generation optimization control system. BACKGROUND

[0002] With the continuous improvement of the intelligent level of agriculture, as a key component of facility agriculture, the energy management and environmental regulation capability of the greenhouse has become an important factor restricting the efficient growth of crops. In order to achieve energy self-sufficiency and reduce carbon emissions, photovoltaic modules have been gradually integrated into the greenhouse roof in recent years, so that it has the functions of lighting and power generation. However, due to the shading characteristics of photovoltaic modules, the growth of crops is affected, and the traditional photovoltaic greenhouse generally has the following shortcomings:

[0003] At present, most of the current greenhouse photovoltaic power generation systems adopt fixed angle or preset schedule adjustment mode, which cannot dynamically adjust according to the actual light demand and growth state of crops, resulting in that crops are in insufficient or excessive illumination state during the growth stage, affecting photosynthetic efficiency and yield, and the contradiction between "photovoltaic power generation maximization" and "crop growth illumination optimization" cannot be effectively balanced. Therefore, a greenhouse photovoltaic roof adaptive power generation optimization control system is proposed.

[0004] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a greenhouse photovoltaic roof adaptive power generation optimization control system, which uses a light deviation analysis model driven by crop physiological parameters and a photovoltaic angle dynamic optimization strategy based on power generation efficiency feedback coupling mechanism to solve the problems raised in the above background.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical scheme, a greenhouse photovoltaic roof adaptive power generation optimization control system, comprising a light receiving analysis module, an illumination evaluation module, an angle optimization module and a strategy control module, the functions of each module are as follows:

[0007] The light receiving analysis module is used to identify the crop type and growth stage of the current crop and obtain the target crop light intensity, collect the light illumination of the current crop, and calculate the light deviation value of the current crop in combination with the target crop light intensity and transmit it to the illumination evaluation module;

[0008] The illumination evaluation module is used to receive the light deviation value transmitted by the light receiving analysis module, evaluate the light condition level of the current crop, detect the leaf potential change and transpiration rate of the current crop, calculate the illumination photosynthetic efficiency of the current crop, and send the light condition level and illumination photosynthetic efficiency to the angle optimization module.

[0009] an angle optimization module configured to integrate the light condition level and the photosynthetic efficiency of illumination transmitted by the illumination evaluation module, determine whether to adjust the angle of the photovoltaic panel, set an execution instruction according to the determination result, and transmit the execution instruction to the strategy control module;

[0010] the strategy control module configured to receive the execution instruction transmitted by the angle optimization module, determine whether to enter the optimization mechanism based on the execution instruction, and when entering the optimization mechanism, monitor the solar radiation data and the photovoltaic operation data to analyze the photovoltaic power generation efficiency and execute the balance optimization strategy or the intelligent switching strategy according to the photovoltaic power generation efficiency.

[0011] In a preferred embodiment, in the light receiving analysis module, an image recognition unit is configured to collect images of crops in the current greenhouse area, and a crop feature recognition model is configured to process the image data to identify the crop type and the growth stage of the current crops.

[0012] The crop type represents specific classification information of the current crops.

[0013] The growth stage represents a specific growth stage of the crops in the life cycle.

[0014] In a preferred embodiment, in the light receiving analysis module, the corresponding target crop light intensity is retrieved from the light demand database according to the identified crop type and growth stage.

[0015] The current actual light condition is collected in real time by an illumination sensor arranged above the crop canopy to obtain the light receiving illumination of the current crops.

[0016] The target crop light intensity and the light receiving illumination of the current crops are subjected to difference operation to calculate the light deviation value of the current crops.

[0017] The light deviation value is transmitted to the illumination evaluation module.

[0018] In a preferred embodiment, in the illumination evaluation module, two critical thresholds are derived and set through the photosynthesis-illumination response curve of the crops, which are the lower limit threshold of suitable light and the upper limit threshold of suitable light.

[0019] When the light deviation value is less than the lower limit threshold of suitable light, it is determined that the light condition level is sufficient.

[0020] When the light deviation value is greater than or equal to the lower limit threshold of suitable light and less than or equal to the upper limit threshold of suitable light, it is determined that the light condition level is suitable.

[0021] When the light deviation value is greater than the upper limit threshold of suitable light, it is determined that the light condition level is insufficient.

[0022] In a preferred embodiment, in the illumination evaluation module, the potential values of different positions on the leaf surface are obtained in real time by the leaf potential sensor arranged in the greenhouse environment;

[0023] The potential values are calculated by using the numerical differentiation method to obtain the instantaneous change rate of the leaf potential, and the average value of the instantaneous change rates calculated at multiple time points is obtained as the change of the leaf potential;

[0024] The stomatal conductance, relative humidity on the leaf surface of the crops are collected in real time by the stomatal conductance sensor and the environmental humidity and temperature sensor arranged in the greenhouse environment, and the transpiration rate is calculated by using the standard transpiration calculation model combined with the leaf surface temperature;

[0025] After the change of the leaf potential and the transpiration rate are standardized, the weighted average calculation is performed to obtain the illumination photosynthetic efficiency of the current crops;

[0026] The illumination condition level and the illumination photosynthetic efficiency are transmitted to the angle optimization module.

[0027] In a preferred embodiment, in the angle optimization module, the illumination photosynthetic efficiency is fuzzified, the fuzzy set is defined as high, medium and low, and the first layer fuzzy rule base is established according to the set threshold range;

[0028] The photosynthesis level is inferred according to the first layer fuzzy rule base, including high, medium and low;

[0029] The photosynthesis level and the illumination condition level are combined to establish the second layer fuzzy rule base, and whether to adjust the angle of the photovoltaic panel is determined by the second layer fuzzy rule base;

[0030] The Mamdani type inference method and the maximum-minimum synthesis method are used to infer the fuzzy membership degree set, the de-fuzzification processing is performed by the centroid method, and the adjustment discrimination output value is obtained.

[0031] In a preferred embodiment, in the angle optimization module, if the adjustment discrimination output value is less than or equal to the adjustment judgment threshold value, the angle of the photovoltaic panel is not adjusted;

[0032] If the adjustment discrimination output value is greater than the adjustment judgment threshold value, the angle of the photovoltaic panel is adjusted;

[0033] When the determination result is to adjust the angle of the photovoltaic panel, the illumination optimization trigger instruction is generated;

[0034] When the determination result is not to adjust the angle of the photovoltaic panel, the angle keeping confirmation instruction is generated;

[0035] The illumination optimization trigger instruction or the angle keeping confirmation instruction is transmitted to the strategy control module.

[0036] In a preferred embodiment, in the strategy control module, the light optimization trigger instruction or the angle maintenance confirmation instruction is received, when the light optimization trigger instruction is received, the optimization mechanism is entered;

[0037] When the angle maintenance confirmation instruction is received, the current running state is maintained, and the photovoltaic angle is operated according to the determined photovoltaic angle.

[0038] When the optimization mechanism is entered, the solar radiation data is collected in real time through the solar radiation sensor arranged on the top of the greenhouse.

[0039] The solar radiation data refers to the total solar radiation energy received per unit area per unit time.

[0040] The photovoltaic running data includes the output voltage and the output current of the photovoltaic panel, and the product of the output voltage and the output current is taken as the photovoltaic output power.

[0041] In a preferred embodiment, in the strategy control module, the photovoltaic output power is divided by the product of the solar radiation data and the effective area of the photovoltaic panel to obtain the photovoltaic power generation efficiency.

[0042] The photovoltaic power generation efficiency that can be reached by the full-power output of the photovoltaic under the standard irradiation condition is counted, and the percentage is taken as the power generation efficiency judgment threshold.

[0043] If the photovoltaic power generation efficiency is greater than or equal to the power generation efficiency judgment threshold, it is determined to execute the balance optimization strategy.

[0044] If the photovoltaic power generation efficiency is less than the power generation efficiency judgment threshold, it is determined to execute the intelligent switching strategy.

[0045] Technical effects and advantages of the present application:

[0046] The present application obtains the crop type and growth stage through image recognition technology, combines the light demand database and the illuminance sensor data, calculates the current crop light deviation value, determines the light condition level according to the light deviation and the crop photosynthetic response characteristics, collects the leaf potential and the transpiration rate through the sensor, calculates the photosynthetic efficiency of the illuminance, determines whether the photovoltaic panel angle needs to be adjusted based on the light condition level and the photosynthetic efficiency of the illuminance, outputs the execution instruction, enters different control mechanisms according to the execution instruction, executes the balance optimization strategy when the power generation efficiency is high, maintains the dual balance of the crop light adaptability and the power generation stability, executes the intelligent switching strategy when the power generation efficiency is low, preferentially improves the photovoltaic power generation capacity, and considers the tolerance of the crop to the light, dynamically adjusts the angle of the photovoltaic component, realizes the collaborative optimization of the dual goals of agriculture and energy, improves the self-adaptive ability, the light management precision and the overall operation efficiency of the greenhouse photovoltaic roof system, improves the crop quality and the yield while ensuring the optimization of the operation efficiency of the power generation system. BRIEF DESCRIPTION OF DRAWINGS

[0047] Fig. 1 The implementation flow chart of the greenhouse photovoltaic roof adaptive power generation optimization control system.

[0048] Fig. 2 The module schematic diagram of the greenhouse photovoltaic roof adaptive power generation optimization control system. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0050] Please refer to Figs. 1-2 , the greenhouse photovoltaic roof adaptive power generation optimization control system comprises a light receiving analysis module, an illumination evaluation module, an angle optimization module and a strategy control module, and the functions of the modules are as follows:

[0051] The light receiving analysis module is used for identifying the crop type and growth stage of the current crop and obtaining the target crop light intensity, collecting the light illumination of the current crop, and combining the target crop light intensity to calculate the light deviation value of the current crop and transmit it to the illumination evaluation module;

[0052] The illumination evaluation module is used for receiving the light deviation value transmitted by the light receiving analysis module, evaluating the light condition level of the current crop, detecting the leaf potential change and transpiration rate of the current crop, calculating the illumination photosynthetic efficiency of the current crop, and sending the light condition level and the illumination photosynthetic efficiency to the angle optimization module;

[0053] The angle optimization module is used for comprehensively receiving the light condition level and the illumination photosynthetic efficiency transmitted by the illumination evaluation module, judging whether to adjust the angle of the photovoltaic panel, setting an execution instruction (light optimization trigger instruction or angle retention confirmation instruction) according to the judgment result, and sending the execution instruction to the strategy control module;

[0054] The strategy control module is used for receiving the execution instruction transmitted by the angle optimization module, judging whether to enter the optimization mechanism based on the execution instruction, monitoring the solar radiation data and the photovoltaic operation data when entering the optimization mechanism, analyzing the photovoltaic power generation efficiency, and executing the balance optimization strategy or the intelligent switching strategy according to the photovoltaic power generation efficiency.

[0055] The specific implementation is as follows:

[0056] In the light receiving analysis module, the image recognition unit is used to collect the images of the crops in the current greenhouse area, and the image data is processed based on the crop feature recognition model to identify the crop type and growth stage of the current crop.

[0057] The crop category represents specific classification information of the current crop planting, including but not limited to tomato, cucumber, lettuce, etc. In specific implementation, the identification of the crop category is determined according to the planting type of the selected crop in the actual planting area, and the crop category is output by extracting and matching the multi-dimensional vector of the visual feature parameters such as the shape of the crop leaf, the stem structure, the color distribution, and the fruit shape.

[0058] The growth stage represents the specific growth stage of the crop in the life cycle, including but not limited to the emergence stage, the growth stage, the flowering stage, and the fruiting stage. In specific implementation, the judgment of the growth stage is determined according to the actual crop growth characteristics and the stage division standard, and the growth stage of the current crop is output by identifying the key growth characteristics such as the plant height, the leaf number, the internode length, and the appearance state of the flower or fruit, combining the time series image analysis and the threshold model of the stage characteristics.

[0059] It should be noted that the image recognition unit refers to a functional component configured in the light analysis module for collecting crop images and performing feature extraction and classification recognition on the crop image information; the crop feature recognition model refers to a crop visual feature classification model based on a deep learning algorithm deployed in the image recognition unit, which is used for classifying the crop target in the input image.

[0060] According to the identified crop category and growth stage, the corresponding target crop light intensity is retrieved in the light demand database. The target crop light intensity is a standard value preset according to the optimal light conditions required by different crops in different growth periods. The setting of the target crop light intensity is determined comprehensively according to the physiological light demand of the crop category and its growth stage. Specifically, it includes the recommended light range given in literature such as agricultural planting standards and crop cultivation manuals, combined with the experience of agricultural experts and the actual planting conditions such as region and season, for parameter calibration, and in the machine learning model with adaptive learning function, the initial setting value is dynamically modified according to long-term monitoring data, which is not described here.

[0061] The actual light condition is collected in real time by the illuminance sensor configured above the crop canopy to obtain the light intensity of the current crop.

[0062] After obtaining the target crop light intensity and the light intensity of the current crop, the difference between the two is calculated to obtain the light deviation value of the current crop. The light deviation value reflects the numerical difference between the current light and the target light. When it is positive, it means that the current light is insufficient, and when it is negative, it means that the light is too strong.

[0063] It needs to be explained that the above-mentioned light requirement database refers to a structured data set pre-constructed and stored with light requirement parameters of various target crops at various growth stages, specifically organized in the form of two-dimensional or multi-dimensional mapping tables, with structured retrieval function; the illuminance sensor refers to an optical sensing device configured above the crops for measuring the visible light intensity per unit area.

[0064] After completing the light deviation value calculation, the light analysis module transmits the light deviation value to the illuminance evaluation module to provide basic data support for subsequent light adaptability evaluation and photovoltaic angle adjustment.

[0065] In the illuminance evaluation module, after receiving the light deviation value transmitted by the light analysis module, the light state of the current crop is quantitatively evaluated, and then the light condition level of the crop is determined.

[0066] By interval mapping operation on the light deviation value, the light condition level is divided into three levels, namely sufficient, suitable and insufficient;

[0067] Two critical thresholds are set through the photosynthesis-illumination response curve of the crop, namely the lower limit threshold of light suitability and the upper limit threshold of light suitability, which are used to determine the allowable deviation interval of the light deviation value. The lower limit threshold of light suitability corresponds to the starting point of the photosynthetic rate changing from zero to effective positive value when the light intensity changes from low to high, representing the minimum requirement for light to meet the basic photosynthesis start. The upper limit threshold of light suitability corresponds to the upper limit point of the light increase but the photosynthetic efficiency no longer significantly improves, representing the physiological saturation point of the crop photosynthetic system to light;

[0068] The specific division logic of the light condition level is as follows:

[0069] When the light deviation value is less than the lower limit threshold of light suitability, the light condition level is determined to be sufficient;

[0070] When the light deviation value is greater than or equal to the lower limit threshold of light suitability and less than or equal to the upper limit threshold of light suitability, the light condition level is determined to be suitable;

[0071] When the light deviation value is greater than the upper limit threshold of light suitability, the light condition level is determined to be insufficient.

[0072] It needs to be explained that the photosynthesis-illumination response curve refers to a typical physiological response curve reflecting the relationship between the photosynthetic rate of plants and the change of light intensity, which is used to describe the photosynthetic efficiency and response ability of plants under different light conditions.

[0073] After completing the light condition level determination, the leaf potential change and transpiration rate of the current crop are detected to calculate the illuminance photosynthetic efficiency of the current crop;

[0074] The leaf potential values at different positions on the leaf surface are obtained in real time by a leaf potential sensor arranged in a greenhouse environment, the instantaneous change rate of the leaf potential is calculated by using a numerical differentiation method, the instantaneous change rates calculated at multiple time points are averaged, and the leaf potential change is obtained.

[0075] The stomatal conductance and relative humidity on the leaf surface of crops are collected in real time by a stomatal conductance sensor and an environmental humidity and temperature sensor arranged in a greenhouse environment, and the water evaporation rate per unit area, i.e., the transpiration rate, is calculated by using a standard transpiration calculation model combined with the leaf surface temperature, and the calculation formula is as follows:

[0076] ;

[0077] Among them, is the transpiration rate, is the stomatal conductance, is the standard atmospheric pressure, is the vapor pressure difference, is the leaf surface temperature, is the relative humidity, is the Tetens formula for calculating the saturated water vapor pressure at the leaf surface temperature, and the formula is defined as .

[0078] It should be noted that the leaf potential sensor refers to an electrochemical sensing device for real-time detection of changes in the cell membrane potential of crop leaves, which uses a non-polarized electrode to adhere to the surface of crop leaves, and uses the potential difference between the leaf tissue cells and the reference electrode to reflect the dynamic activity of the electron transport chain in photosynthesis; the numerical differentiation method refers to a mathematical calculation method for approximating the derivative value of a function at a certain point based on the data of a finite number of sampling points under the condition that the explicit function expression is lacking; the stomatal conductance sensor refers to a plant physiological parameter detection device for real-time measurement of the change in water vapor flux caused by the opening and closing state of plant leaf stomata; the environmental humidity and temperature sensor refers to a sensing device for real-time measurement of leaf temperature and relative humidity; and the standard transpiration calculation model refers to a mathematical model established based on the relationship between plant physiological parameters and environmental meteorological conditions, which is used to calculate the transpiration rate per unit area of plant leaves per unit time.

[0079] After the leaf potential change and the transpiration rate are standardized, a weighted average calculation is performed to obtain the current crop's light photosynthetic efficiency, and the calculation formula is as follows:

[0080] ;

[0081] Among them, is the light photosynthetic efficiency, is the standardized leaf potential change, is the standardized transpiration rate, and The weight parameters are obtained by experimental calibration, reflecting the contribution of blade potential change and transpiration rate to photosynthetic efficiency, and the photosynthetic efficiency under illumination comprehensively reflects the influence of electrochemical activity and water metabolism rate on crop photosynthetic efficiency.

[0082] The illumination condition level and the photosynthetic efficiency under illumination are transmitted to the angle optimization module.

[0083] In the angle optimization module, the illumination condition level and the photosynthetic efficiency under illumination transmitted by the illumination evaluation module are received, the photosynthetic efficiency under illumination is fuzzified, the fuzzy set is defined as high, medium and low, quantification is performed by a triangular membership function, and a first layer fuzzy rule base is established according to a set threshold range.

[0084] The threshold range is determined by the frequency distribution curve of the photosynthetic efficiency under illumination in historical operation data and the industry limit standard in this embodiment, and will not be repeated here.

[0085] The photosynthesis level is inferred according to the first layer fuzzy rule base, the fuzzy set includes excellent, medium and poor, and the fuzzy rule is as follows:

[0086] If the photosynthetic efficiency under illumination is high, the photosynthesis level is excellent;

[0087] If the photosynthetic efficiency under illumination is medium, the photosynthesis level is medium;

[0088] If the photosynthetic efficiency under illumination is low, the photosynthesis level is poor;

[0089] The membership degrees of each fuzzy output item are obtained by calculating the membership degree and the maximum-minimum synthesis method, and then the de-fuzzification processing is performed by the centroid method to obtain the photosynthesis level score value with a value interval of [0, 1], and the photosynthesis level is determined according to the photosynthesis determination interval.

[0090] The photosynthesis determination interval is set by the three-point method in this embodiment, corresponding to the center point of the fuzzy set, and can be adjusted based on the frequency distribution statistics of historical data in the operation process and the plant photosynthesis rate limit value in the industry standard.

[0091] The photosynthesis level inferred from the photosynthetic efficiency under illumination is combined with the illumination condition level to establish a second layer fuzzy rule base, whether to adjust the angle of the photovoltaic panel is determined by the second layer fuzzy rule base, and the fuzzy rule is as follows:

[0092] If the photosynthesis level is excellent and the illumination condition level is high, the angle of the photovoltaic panel is not adjusted;

[0093] If the photosynthesis level is medium and the illumination condition level is medium, the angle of the photovoltaic panel is not adjusted;

[0094] If the photosynthesis level is poor and the light condition level is high, then adjust the angle of the photovoltaic panel.

[0095] If the photosynthesis level is medium and the light condition level is high, then adjust the angle of the photovoltaic panel.

[0096] In the fuzzy reasoning process, the Mamdani type reasoning method and the maximum-minimum composition method are used to reason the fuzzy membership degree set, and the centroid method is used for defuzzification processing to obtain the adjustment discrimination output value with a value interval of [0, 1].

[0097] The adjustment discrimination threshold is set, and in this embodiment, the adjustment discrimination threshold is set as the median value of the fuzzy output, which can be dynamically set through historical operation data and optimization training.

[0098] If the adjustment discrimination output value is less than or equal to the adjustment discrimination threshold, then the angle of the photovoltaic panel is not adjusted.

[0099] If the adjustment discrimination output value is greater than the adjustment discrimination threshold, then the angle of the photovoltaic panel is adjusted.

[0100] It should be noted that the triangular membership function is a commonly used fuzzy membership function for representing the degree of membership of an element in a fuzzy set to a certain semantic label; the Mamdani type reasoning method is a widely used fuzzy rule reasoning method, and its core is to perform fuzzy mapping and fuzzy output on the input membership degree based on a rule set; the maximum-minimum composition method is a logical operation method for synthesizing the relationship between the premises and conclusions of multiple rules in fuzzy reasoning, and its core idea is to represent the rule matching strength by minimum value operation and aggregate multiple rule results by maximum value operation; the centroid method is a commonly used defuzzification means, which represents the exact value of the output variable by calculating the centroid position of the fuzzy output function graph, and is used to convert the fuzzy output set into a single accurate numerical result, which will not be described here.

[0101] When the determination result is to adjust the angle of the photovoltaic panel, a light optimization trigger instruction is generated; when the determination result is not to adjust the angle of the photovoltaic panel, an angle maintaining confirmation instruction for maintaining the current configuration is generated, and the light optimization trigger instruction or the angle maintaining confirmation instruction is transmitted to the strategy control module.

[0102] In the strategy control module, the light optimization trigger instruction or the angle maintaining confirmation instruction is received, the light optimization trigger instruction is received, and the optimization mechanism is entered; when the angle maintaining confirmation instruction is received, the current running state is maintained, and the photovoltaic panel is operated according to the predetermined angle.

[0103] When the optimization mechanism is entered, the strategy control module collects solar radiation data in real time through the solar radiation sensor arranged at the top of the greenhouse, and the solar radiation data refers to the total solar radiation energy received per unit area per unit time.

[0104] It needs to be explained that the solar radiation sensor refers to an optical sensing device for measuring the total solar radiation energy received per unit area per unit time, which is used to collect solar radiation data of the greenhouse roof in real time in this embodiment;

[0105] The collection of photovoltaic operation data includes the output voltage and output current of the photovoltaic panel, and the product of the output voltage and the output current is taken as the photovoltaic output power;

[0106] The photovoltaic operation data is collected in real time by the electrical measurement module built in the photovoltaic system, and the sampling frequency is set according to the system requirements, generally once per second or once per minute.

[0107] Based on the solar radiation data, the effective area of the photovoltaic panel, and the photovoltaic output power, the photovoltaic power generation efficiency is calculated, and the calculation formula is: , wherein, is the photovoltaic output power, is the effective area of the photovoltaic panel, is the solar radiation data, is the photovoltaic power generation efficiency.

[0108] It needs to be explained that the effective area of the photovoltaic panel refers to the physical surface area of the photovoltaic component that actually participates in the reception of light energy and can be used for photoelectric conversion. The effective area of the photovoltaic panel is a fixed value according to the design specifications of the photovoltaic panel, which can be obtained from the photovoltaic structure archive database. The photovoltaic structure archive database refers to a special data collection that pre-establishes and stores the structural parameters of the photovoltaic components deployed in the greenhouse photovoltaic roof.

[0109] The photovoltaic power generation efficiency under standard irradiation conditions is calculated, and the percentage is taken as the power generation efficiency judgment threshold. The above standard irradiation conditions are determined according to the International Electrotechnical Commission standard, including an illumination intensity of 1000 watts per square meter, an ambient temperature of 25 degrees Celsius, and a standard solar spectrum AM1.5, to ensure the uniformity of the test environment and the comparability of the data. The percentage value is not unique, and the range selected in this embodiment is between 70% and 80%, and the specific value is adjusted according to the actual application requirements and data distribution characteristics;

[0110] The photovoltaic power generation efficiency is compared with the power generation efficiency judgment threshold:

[0111] If the photovoltaic power generation efficiency is greater than or equal to the power generation efficiency judgment threshold, it is determined to execute the balance optimization strategy;

[0112] If the photovoltaic power generation efficiency is less than the power generation efficiency judgment threshold, it is determined to execute the intelligent switching strategy.

[0113] The balance optimization strategy ensures that the crop illumination demand is met while maintaining a high power generation efficiency, and reduces the energy consumption and mechanical wear caused by frequent adjustment of the photovoltaic panel as much as possible.

[0114] In the specific implementation process, firstly, it is evaluated whether the current crop light state is in the appropriate range. If the crop light condition meets the set physiological light requirement interval, and the current photovoltaic panel angle is stable without significant fluctuation, the existing angle configuration is kept unchanged. If there is slight deviation, for example, the light is in a critical state but has not yet exceeded the tolerance interval, a slight adjustment is made according to the light feedback signal to optimize the crop light balance.

[0115] The intelligent switching strategy takes improving the photovoltaic power generation capacity as the priority target, and allows large-scale reconstruction and adjustment of the photovoltaic panel angle within the light fluctuation range that the crop can bear.

[0116] When the intelligent switching strategy is implemented, the theoretical power generation capacity that can be obtained by different photovoltaic panel angles under the current environment is comprehensively analyzed, the prediction result and the current system operation state are combined, and the angle with the highest power generation potential is selected as the adjustment target to implement actual angle switching.

[0117] Finally, it should be noted that in this document, the terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations.

[0118] Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0119] In this document, the singular forms "a", "an" and "the" can also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms "include", "contain" or "have" and the like specify the presence of the stated features, integers, steps, operations, components, parts or combinations thereof, but do not exclude the presence or addition of one or more other features, integers, steps, operations, components, parts or combinations thereof. The possibility, the term "and / or" used in this specification includes any and all combinations of the related listed items.

[0120] The various embodiments in the specification are described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the various embodiments can be combined as needed, and the same and similar parts refer to each other.

[0121] The above description of the disclosed embodiments will enable those skilled in the art to make or use various modifications to these embodiments. It will be readily apparent to those skilled in the art that the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A greenhouse photovoltaic roof adaptive power generation optimization control system, characterized in that: It includes a light reception analysis module, an illuminance assessment module, an angle optimization module, and a strategy control module. The functions of each module are as follows: The light reception analysis module is used to identify the crop type and growth stage of the current crop and obtain the light intensity of the target crop. It collects the light reception of the current crop and combines it with the light intensity of the target crop to calculate the light deviation value of the current crop and transmit it to the illuminance evaluation module. The illuminance assessment module receives the illuminance deviation value from the light analysis module, assesses the current crop's illuminance level, detects changes in leaf potential and transpiration rate, calculates the current crop's illuminance photosynthetic efficiency, and sends the illuminance level and illuminance photosynthetic efficiency to the angle optimization module. The angle optimization module is used to comprehensively evaluate the light condition level and illuminance photosynthetic efficiency input from the illuminance assessment module, determine whether to adjust the angle of the photovoltaic panel, set the execution command based on the judgment result, and send the execution command to the strategy control module. The strategy control module is used to receive the execution instructions from the angle optimization module, determine whether to enter the optimization mechanism based on the execution instructions, and when entering the optimization mechanism, monitor solar radiation data and photovoltaic operation data, analyze photovoltaic power generation efficiency, and execute the balance optimization strategy or intelligent switching strategy according to the photovoltaic power generation efficiency. In the light analysis module, based on the identified crop type and growth stage, the corresponding target crop light intensity is retrieved from the light demand database. The actual light conditions are collected in real time by an illuminance sensor configured above the crop canopy to obtain the current illuminance received by the crop. The difference between the light intensity of the target crop and the light intensity of the current crop is calculated to obtain the light deviation value of the current crop. Transmit the illumination deviation value to the illuminance assessment module; In the illumination assessment module, the potential values ​​at different locations on the leaf surface are acquired in real time by using leaf potential sensors configured in the greenhouse environment. The potential value is calculated using the numerical differentiation method to obtain the instantaneous rate of change of the blade potential. The average value of the instantaneous rate of change calculated at multiple time points is taken to obtain the change of the blade potential. By using stomatal conductance sensors and ambient humidity and temperature sensors configured in the greenhouse environment, the stomatal conductance and relative humidity of crop leaf surfaces are collected in real time. Combined with leaf surface temperature, the transpiration rate is calculated using a standard transpiration calculation model. After standardizing the changes in leaf potential and transpiration rate, a weighted average was calculated to obtain the current illuminance photosynthetic efficiency of the crop. The illumination condition level and illuminance photosynthetic efficiency are transmitted to the angle optimization module.

2. The adaptive power generation optimization control system for greenhouse photovoltaic roofs according to claim 1, characterized in that: In the light analysis module, the image recognition unit acquires images of crops in the current greenhouse area, and processes the image data based on the crop feature recognition model to identify the crop type and growth stage of the current crop. Crop type indicates the specific classification information of the currently planted crop; The growth stage refers to the specific growth stage a crop is in during its life cycle.

3. The adaptive power generation optimization control system for greenhouse photovoltaic roofs according to claim 1, characterized in that: In the illuminance assessment module, two critical thresholds are derived and set based on the crop's photosynthesis-illuminance response curve: the lower limit threshold for suitable light and the upper limit threshold for suitable light. When the light deviation value is less than the lower limit threshold of suitable light, the light condition level is determined to be sufficient. When the light deviation value is greater than or equal to the lower limit threshold of suitable light and less than or equal to the upper limit threshold of suitable light, the light condition level is determined to be suitable. When the light deviation value exceeds the upper limit threshold of suitable light, the light condition level is determined to be insufficient.

4. The adaptive power generation optimization control system for greenhouse photovoltaic roofs according to claim 1, characterized in that: In the angle optimization module, the fuzzy processing of the photosynthetic efficiency is performed, and the fuzzy sets are defined as high, medium and low. Based on the set threshold range, the first layer of fuzzy rule base is established. The photosynthesis level is derived from the first-layer fuzzy rule base, including excellent, medium and poor. By combining the photosynthesis level with the light condition level, a second-layer fuzzy rule base is established, and the photovoltaic panel angle is adjusted based on the second-layer fuzzy rule base. The Mamdani-type inference method and the maximum-minimum synthesis method are used to infer the fuzzy membership set. The centroid method is then used to defuzzify the set to obtain the adjusted discriminant output value.

5. The adaptive power generation optimization control system for greenhouse photovoltaic roofs according to claim 4, characterized in that: In the angle optimization module, if the adjustment judgment output value is less than or equal to the adjustment judgment threshold, the photovoltaic panel angle will not be adjusted. If the adjustment judgment output value is greater than the adjustment judgment threshold, then adjust the angle of the photovoltaic panel; When the determination result is to adjust the angle of the photovoltaic panel, a light optimization trigger command is generated. When the determination result is that the photovoltaic panel angle should not be adjusted, an angle hold confirmation command is generated. The illumination optimization trigger command or angle hold confirmation command is transmitted to the strategy control module.

6. The adaptive power generation optimization control system for greenhouse photovoltaic roofs according to claim 5, characterized in that: In the strategy control module, it receives a lighting optimization trigger command or an angle hold confirmation command. When it receives a lighting optimization trigger command, it enters the optimization mechanism. Upon receiving an angle hold confirmation command, the current operating state is maintained, and the photovoltaic system operates according to the predetermined angle. When the optimization mechanism is activated, solar radiation data is collected in real time by a solar radiation sensor configured on the top of the greenhouse. Solar radiation data refers to the total solar radiation energy received per unit area per unit time. Photovoltaic operating data includes the output voltage and output current of the photovoltaic panel. The product of the output voltage and output current is taken as the photovoltaic output power.

7. The greenhouse photovoltaic roof adaptive power generation optimization control system according to claim 6, characterized in that: In the strategy control module, the photovoltaic output power is divided by the product of the solar radiation data and the effective area of ​​the photovoltaic panel to obtain the photovoltaic power generation efficiency. The photovoltaic power generation efficiency that can be achieved at full power output under standard irradiance conditions is statistically analyzed, and the percentile is used as the threshold for judging power generation efficiency. If the photovoltaic power generation efficiency is greater than or equal to the power generation efficiency judgment threshold, then the balance optimization strategy is executed. If the photovoltaic power generation efficiency is less than the power generation efficiency judgment threshold, then the intelligent switching strategy will be executed.

Images