Greening irrigation system for roof photovoltaic rainwater collection

Abstract

The invention provides a roof photovoltaic rainwater collection greening irrigation system, which comprises a rainwater monitoring module for analyzing rainwater flow and water quality parameters and generating a rainwater distribution state value; the filtering parameter optimization module is used for screening an optimal angle and duration combination of the filtering device and generating a filtering parameter set; the environment response adjusting module is used for matching the environment factors with the filtering combination and generating an environment response parameter set; the irrigation threshold setting module is used for setting a water level and flow distribution threshold and generating an irrigation load threshold; the irrigation prediction module is used for deducing a flow change trend and generating an irrigation distribution prediction value; and the nozzle feedback control module is used for adjusting nozzle parameters and generating an automatic balance irrigation scheme. The water resource utilization rate can be increased, energy consumption can be reduced, and the balanced irrigation requirement of greening vegetation is met.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic building integration, and more particularly to a rooftop photovoltaic rainwater collection and greening irrigation system. Background Art

[0002] In today's society, with the continuous acceleration of urbanization and the growing awareness of environmental protection, rooftop greening has received increasing attention as an effective means of improving urban ecology. Rooftop greening not only beautifies the urban environment and reduces the surface temperature of buildings, but also effectively reduces the urban heat island effect. It is also of great significance for the collection and utilization of rainwater. Traditional rooftop greening irrigation systems mostly rely on municipal water supply. This method not only consumes a large amount of water resources, but also fails to fully utilize natural precipitation in areas with abundant rainfall, resulting in water waste. In addition, existing rainwater collection systems have many shortcomings in terms of filtration, distribution, and irrigation control. For example, the parameter settings of the filtration device are not flexible enough and cannot be adjusted in real time according to changes in rainwater flow and water quality. The irrigation system lacks accurate prediction and feedback mechanisms, resulting in uneven irrigation and inefficient water resource utilization.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: the existing roof greening irrigation system has low efficiency in collecting and utilizing rainwater, the filtration device cannot be optimized and adjusted according to the real-time status of rainwater, the irrigation control is not precise enough, and automatic balanced irrigation cannot be achieved, resulting in waste of water resources and poor greening effects. Summary of the Invention

[0004] The present invention provides a rooftop photovoltaic rainwater collection and greening irrigation system, comprising:

[0005] The rainwater monitoring module analyzes the regional flow and water quality differences based on the rainwater flow and water quality parameters of the rooftop photovoltaic area, calculates the rainwater distribution differences between regions, integrates them into a rainwater distribution parameter set, and obtains the rainwater distribution status value;

[0006] The filtering parameter optimization module extracts the parameter combination of the opening and closing angle and the duration of the filtering device based on the rainwater distribution state value, selects the optimal angle and duration combination, and obtains the filtering parameter set;

[0007] The environmental response adjustment module extracts the current environmental factor change based on the filtering parameter set, analyzes the relationship between the filtering angle and the duration, matches the environmental factors with the filtering combination, and obtains the environmental response parameter set;

[0008] The irrigation threshold setting module extracts the current water level change value based on the environmental response parameter set, combines the real-time flow data, allocates the water level and flow, sets the threshold, and applies the threshold to the regional irrigation allocation to obtain the irrigation load threshold;

[0009] The irrigation prediction module captures flow data from water level sampling points based on the irrigation load threshold, and uses the photovoltaic area irrigation algorithm to infer the flow change trend of the water level sampling points. It analyzes the flow change trend corresponding to the water level load, classifies and organizes the flow change trend based on the inference results, and dynamically adjusts and analyzes the classified data based on the flow change information to obtain the irrigation distribution prediction value.

[0010] The sprinkler feedback control module analyzes the error value of water level and flow based on the irrigation distribution prediction value and real-time water level and flow data, and adjusts the sprinkler spraying angle and duration based on the error value to obtain an automatic balanced irrigation plan for roof greening.

[0011] Furthermore, the rainwater distribution state value includes a flow parameter set, a water quality parameter set, and a distribution difference parameter set; the filtering parameter set includes a screening angle parameter and a duration parameter; the environmental response parameter set includes an environmental factor change parameter and a filtering angle duration matching parameter; the irrigation load threshold includes a water level change parameter, a flow matching parameter, and a threshold setting parameter; the irrigation distribution prediction value includes a flow trend analysis parameter and a water level-flow relationship parameter; and the roof greening automatic balancing irrigation plan includes an error analysis parameter and a sprinkler adjustment parameter.

[0012] Furthermore, the rain monitoring module includes:

[0013] The rainwater data collection submodule collects flow and water quality parameters based on the rooftop photovoltaic area. It locates invalid data, removes abnormal data, and arranges the extracted flow and water quality values in regional order to generate a regional flow and water quality dataset.

[0014] The rainwater difference analysis submodule analyzes the flow and water quality between regions based on the regional flow and water quality dataset, calculates the regional parameter change ratio, sorts the regional difference values by weight, marks areas with excessive fluctuation differences, and obtains regional rainwater difference data;

[0015] The rainwater distribution integration submodule is based on the regional rainwater difference data, calls the regional rainwater difference value for multi-dimensional aggregation, screens the regional rainwater value differences, classifies them according to the size of the rainwater value, and arranges the regional rainwater values in order to generate a rainwater distribution status value.

[0016] Furthermore, the filtering parameter optimization module includes:

[0017] The filtering parameter acquisition submodule identifies the open and closed status of the filter device in each area based on the rainwater distribution state value, records the angle and opening and closing duration of the filter device, standardizes the recorded data, organizes the standardized data and classifies them by angle and duration to generate a filtering parameter data set;

[0018] The parameter optimization submodule analyzes the angle and duration values in the data set according to the filtered parameter data set, selects the parameter combination with the high matching degree with the rain state, adjusts the parameter combination through pattern matching and records the matching results, and generates the parameter combination optimization result;

[0019] The filtering control submodule retrieves the parameter combination optimization result, determines the optimal matching angle and duration combination, adjusts the filtering control parameters, inputs the control configuration, verifies the stability of the parameter set, and generates a filtering parameter set.

[0020] Furthermore, the environmental response adjustment module includes:

[0021] The environmental monitoring submodule collects key data, including temperature, water level, and flow rate, through environmental monitoring based on the filter parameter set, performs time series analysis on the data, removes outliers, and partitions the remaining data to obtain environmental factor analysis data;

[0022] The environmental adaptation submodule analyzes the data based on the environmental factors, analyzes the impact of environmental variables on the filtering angle and duration, calculates the impact of changes in each environmental factor on parameter adjustment, determines the optimal matching parameter settings based on the impact score, cyclically adjusts the parameters to capture the optimal combination, and obtains the parameter docking results;

[0023] The response parameter solidification submodule selects the angle and duration combination that matches the current environmental conditions from the parameter docking results, performs parameter adjustment tests, optimizes the parameter settings through multiple adjustments and verifications, determines and solidifies the parameters as operating standards, and generates an environmental response parameter set.

[0024] Furthermore, the irrigation threshold setting module includes:

[0025] The water level monitoring submodule locates the water level change monitoring point based on the environmental response parameter set, extracts the water level change value in the monitoring area, continuously records the water level increase and decrease rate, extracts multiple key change nodes corresponding to the change rate, sorts the node values in order, and obtains the current water level change characteristic value;

[0026] The flow adapter module analyzes the node change value and the real-time flow data based on the current water level change characteristic value, calibrates according to a predetermined matching criterion, calls the matching criterion to perform distribution redistribution within the flow interval, and obtains a water level flow matching structure;

[0027] The threshold allocation submodule is based on the water level flow matching structure and adopts a dynamic threshold adjustment method to measure the distribution of flow between water level change nodes, set the upper and lower limits of the node threshold, apply the threshold to the regional load value, and distribute it to obtain the irrigation load threshold.

[0028] Furthermore, the formula of the dynamic threshold adjustment method is as follows:

[0029] Get the assigned load value of the node that matches the water level change, where:

[0030] L=α·Q+β·H+γ·(Q up -Q down )

[0031] Where: L represents the distributed load value of the node matching the water level change; L represents the real-time flow measured by the current node; Q up Represents the traffic matching value adjusted by the upstream node; Q down represents the flow matching value after adjustment of the downstream node; H represents the real-time water level height measured by the current node; α represents the weight coefficient of flow; β represents the weight coefficient of water level; γ represents the dynamic adjustment weight coefficient; L min The lower threshold set for the node to control the minimum load.

[0032] Furthermore, the irrigation prediction module includes:

[0033] The flow monitoring submodule applies an irrigation prediction algorithm based on the irrigation load threshold, captures the flow data of the sampling points, removes outliers and corrects errors, stores them in layers by interval, performs dynamic processing, and generates a dynamic flow data set;

[0034] The irrigation trend analysis submodule divides the intervals according to the water level load based on the dynamic flow data set, extracts the change trend and fluctuation characteristics, and generates a water level load and flow change feature set;

[0035] The irrigation prediction submodule adjusts characteristic parameters and calibrates trend data based on the water level load and flow change characteristic set, extracts distribution intervals, and performs numerical prediction to obtain irrigation distribution prediction values.

[0036] Furthermore, the formula of the irrigation prediction algorithm is as follows:

[0037] Calculate the traffic prediction value and generate a dynamic traffic data set, where

[0038]

[0039] Among them: F i represents the predicted flow value of the i-th sampling point; w j represents the weight of the j-th data point; Q jrepresents the original flow value of the kth sampling point; H j represents the water level value of the jth sampling point; L j Represents the load factor of the jth sampling point; N is the total number of sampling points.

[0040] Furthermore, the nozzle feedback control module includes:

[0041] The irrigation error analysis submodule extracts real-time water level and flow data based on the irrigation distribution prediction value, analyzes the real-time flow value and the prediction value, matches the flow difference with the current water level information, and generates a water level and flow error value;

[0042] The nozzle control submodule sets the nozzle spray adjustment parameters based on the water level and flow rate error values. It sets the adjustment range for areas with large errors and makes fine adjustments for areas with low errors. By comparing the spraying effects, it selects matching parameter sets and integrates them to generate a nozzle adjustment parameter set.

[0043] The irrigation execution submodule applies the adjustment parameters at each sprinkler position based on the sprinkler adjustment parameter set, performs spraying operations item by item, synchronously monitors the water level and flow, gradually adjusts the spraying operation order of each area, and generates an automatic balanced irrigation plan for roof greening.

[0044] The above-described embodiments of the present invention have at least the following beneficial effects: The rooftop photovoltaic rainwater harvesting and greening irrigation system of the present invention can achieve efficient rainwater collection and utilization. The rainwater monitoring module accurately analyzes rainwater flow and water quality parameters in the rooftop photovoltaic area and calculates rainwater distribution differences between areas, providing a scientific basis for subsequent filtration, irrigation, and other processes. The filtration parameter optimization module can select the optimal filtration angle and duration combination based on the rainwater distribution status value, making the filtration device more efficient, effectively removing impurities in rainwater, improving rainwater quality, and providing a high-quality water source for greening irrigation. The environmental response adjustment module can dynamically adjust filtration parameters based on changes in current environmental factors, ensuring stable system operation under different environmental conditions and further improving the efficiency of rainwater collection and utilization. The irrigation threshold setting module combines real-time water level changes and flow data to set a reasonable irrigation load threshold, achieving precise irrigation water allocation, avoiding water waste, and ensuring that the irrigation needs of green plants are met. The irrigation prediction module predicts flow rate trends in advance by inferring and analyzing flow data trends at water level sampling points. This provides strong support for irrigation decision-making, further optimizes irrigation plans, and improves the scientific and rational nature of irrigation. The sprinkler feedback control module adjusts the sprinkler angle and duration in real time based on the predicted irrigation distribution, achieving automatic balanced irrigation for rooftop greening, ensuring that green plants in all areas receive even irrigation, improving greening effects and water resource utilization efficiency.

[0045] Furthermore, the system described in this invention can reduce irrigation costs, reduce reliance on municipal water supplies, and fully utilize renewable energy (photovoltaic) to power system operations, resulting in significant economic and social benefits. Through the coordinated operation of various modules, rainwater collection, filtration, and irrigation can be automated and intelligently implemented, improving the overall system's operational efficiency and stability. This provides a highly efficient, energy-saving, and environmentally friendly solution for the development of urban rooftop greening, and is of great significance for promoting urban ecological civilization and sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily apparent by reading the following detailed description with reference to the accompanying drawings, in which several embodiments of the present invention are shown by way of example and not limitation, in which:

[0047] Figure 1 This is a structural diagram of a rooftop photovoltaic rainwater collection and greening irrigation system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0048] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. Rather, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0049] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0050] It should be noted that any number of elements in the drawings is for illustration only and not for limitation, and any naming is only for distinction and does not have any limiting meaning.

[0051] Reference below Figure 1 , Figure 1 This is a schematic diagram of the structure of a rooftop photovoltaic rainwater collection and greening irrigation system provided by one embodiment of the present invention. Figure 1 As shown, a rooftop photovoltaic rainwater collection and greening irrigation system includes:

[0052] The rainwater monitoring module 101 analyzes regional flow and water quality differences based on the rainwater flow and water quality parameters of the rooftop photovoltaic area, calculates the rainwater distribution differences between regions, integrates them into a rainwater distribution parameter set, and obtains the rainwater distribution status value;

[0053] The filtering parameter optimization module 102 extracts the parameter combination of the opening and closing angle and the duration of the filtering device based on the rain distribution state value, selects the optimal angle and duration combination, and obtains a filtering parameter set;

[0054] The environmental response adjustment module 103 extracts the current environmental factor variation based on the filtering parameter set, analyzes the relationship between the filtering angle and the duration, matches the environmental factors with the filtering combination, and obtains the environmental response parameter set;

[0055] The irrigation threshold setting module 104 extracts the current water level change value based on the environmental response parameter set, combines the real-time flow data, allocates the water level and flow, sets a threshold, and applies the threshold to the regional irrigation allocation to obtain an irrigation load threshold;

[0056] The irrigation prediction module 105 captures flow data at water level sampling points based on the irrigation load threshold, infers the flow rate change trend of the water level sampling points in combination with the photovoltaic area irrigation algorithm, analyzes the flow rate change trend corresponding to the water level load, categorizes the flow rate change trend based on the inference result, and dynamically adjusts and analyzes the categorized data in combination with the flow rate change information to obtain the irrigation distribution prediction value;

[0057] The sprinkler feedback control module 106 analyzes the error between the water level and flow rate based on the irrigation distribution prediction value and the real-time water level and flow rate data, and adjusts the sprinkler spraying angle and duration based on the error value to obtain an automatic balanced irrigation plan for the roof greening.

[0058] It should be noted that the rooftop photovoltaic rainwater collection and greening irrigation system of the present invention monitors the rainwater flow and water quality parameters of the rooftop photovoltaic area through a rainwater monitoring module, analyzes regional flow and water quality differences, calculates the rainwater distribution differences between regions, and integrates them into a rainwater distribution parameter set to obtain a rainwater distribution state value. The rainwater distribution state value here refers to a set of parameters such as flow, water quality, and distribution differences, which is used to characterize the overall distribution of rainwater in the rooftop photovoltaic area. By monitoring and analyzing these parameters, the system can accurately grasp the distribution of rainwater in different areas, provide a scientific basis for subsequent filtration, irrigation and other links, thereby realizing the effective collection and utilization of rainwater.

[0059] Specifically, the rainwater monitoring module includes a rainwater data collection submodule, a rainwater difference analysis submodule, and a rainwater distribution integration submodule. The rainwater data collection submodule performs regional collection of flow and water quality values based on the rainwater flow and water quality parameters of the rooftop photovoltaic area, locates invalid data, removes abnormal data, and arranges the extracted flow and water quality values in regional order to generate a regional flow and water quality data set. Regional collection here refers to collecting rainwater flow and water quality data for each area according to the division of the rooftop photovoltaic area, so as to conduct subsequent difference analysis. The rainwater difference analysis submodule analyzes the flow and water quality between regions based on the regional flow and water quality data set, calculates the ratio of regional parameter changes, sorts the difference values between regions by weight, marks areas with excessive fluctuation differences, and obtains regional rainwater difference data. Weight sorting here refers to sorting the difference values between regions according to a pre-set weight coefficient, so as to more accurately identify areas with large differences. The Rainfall Distribution Integration submodule uses regional rainfall difference data to perform multi-dimensional aggregation of regional rainfall difference values. This module screens regional rainfall value differences, classifies them by magnitude, and arranges the regional rainfall values in an orderly manner to generate a rainfall distribution status value. Multi-dimensional aggregation here refers to integrating regional rainfall difference data from multiple perspectives to obtain a more comprehensive rainfall distribution status.

[0060] Preferably, the rainwater data collection submodule can utilize a variety of sensors, such as flow sensors and water quality sensors, to monitor rainwater flow and water quality in real time. Flow sensors can be electromagnetic or ultrasonic flowmeters, and their accuracy should meet certain standards, such as an error range of ±2%, to ensure accurate and reliable flow data. Water quality sensors can detect parameters such as pollutant concentration and pH in water, and their detection range and accuracy should be selected based on actual needs. During data collection, the system automatically identifies and removes invalid and abnormal data. For example, by setting a threshold, data outside the normal range is considered abnormal and removed. When calculating regional parameter change ratios, the rainwater difference analysis submodule can set different weighting coefficients based on actual needs. For example, the weighting coefficient for flow parameters can be set to 0.6, and the weighting coefficient for water quality parameters can be set to 0.4, to reflect the importance of different parameters in rainwater distribution. When generating the rainwater distribution status value, the system categorizes the rainwater values for each region by size and arranges them in an orderly manner to provide accurate input data for the subsequent filtering parameter optimization module.

[0061] In some embodiments, the rainwater distribution status value includes a flow parameter set, a water quality parameter set, and a distribution difference parameter set; the filtering parameter set includes a screening angle parameter and a duration parameter; the environmental response parameter set includes an environmental factor change parameter and a filtering angle duration matching parameter; the irrigation load threshold includes a water level change parameter, a flow matching parameter, and a threshold setting parameter; the irrigation distribution prediction value includes a flow trend analysis parameter and a water level-flow relationship parameter; and the roof greening automatic balancing irrigation plan includes an error analysis parameter and a nozzle adjustment parameter.

[0062] It should be noted that the rainwater distribution state value, filtering parameter set, environmental response parameter set, irrigation load threshold, irrigation distribution prediction value, and rooftop greening automatic balancing irrigation plan mentioned in this invention are all key parameter sets during system operation. These parameter sets cover multiple aspects, including flow rate, water quality, distribution differences, screening angles, duration, changes in environmental factors, water level changes, flow matching, threshold setting, flow trend analysis, water level-flow relationship, error analysis, and sprinkler adjustment. Through the definition and application of these parameter sets, the system can achieve precise control and optimized management of rainwater collection, filtration, irrigation, and other links, thereby improving the overall system's operating efficiency and water resource utilization.

[0063] Specifically, the rainwater distribution state value includes a flow parameter set, a water quality parameter set, and a distribution difference parameter set. The flow parameter set refers to a collection of rainwater flow data monitored in different regions, used to characterize the magnitude and variability of rainwater flow in each region. The water quality parameter set refers to a collection of monitored rainwater quality data, including parameters such as pollutant concentration and pH value, used to assess rainwater quality. The distribution difference parameter set refers to a collection of regional rainwater flow and water quality difference data, calculated through analysis and calculation, used to reflect the uneven distribution of rainwater across regions. The filtration parameter set includes a screening angle parameter and a duration parameter. The screening angle parameter refers to the optimal opening and closing angle of the filter device under different operating conditions, while the duration parameter refers to the optimal operating duration of the filter device at different angles. These two parameters together determine the filtration effect and operating efficiency of the filter device. The environmental response parameter set includes an environmental factor change parameter and a filtration angle and duration matching parameter. The environmental factor change parameter refers to the changes in environmental factors such as temperature, water level, and flow rate. The filtration angle and duration matching parameter refers to the optimal angle and duration combination of the filter device adjusted according to changes in environmental factors, used to achieve adaptive operation of the filter device under different environmental conditions. Irrigation load thresholds include water level change parameters, flow matching parameters, and threshold setting parameters. Water level change parameters refer to water level changes during the irrigation process. Flow matching parameters refer to flow distribution adjusted based on water level changes. Threshold setting parameters refer to irrigation load thresholds set based on water level and flow changes, and are used to control water distribution and irrigation timing during the irrigation process. Irrigation distribution prediction values include flow trend analysis parameters and water level-flow relationship parameters. Flow trend analysis parameters refer to prediction parameters obtained through trend analysis of flow data. Water level-flow relationship parameters refer to correlation parameters between water level and flow, and are used to predict flow change trends and water level changes during the irrigation process. The automatic balanced irrigation scheme for roof greening includes error analysis parameters and sprinkler adjustment parameters. Error analysis parameters refer to parameters obtained by analyzing the error between the actual water level and flow and the predicted values during the irrigation process. Sprinkler adjustment parameters refer to parameters used to adjust the sprinkler spraying angle and duration based on the error analysis results, and are used to achieve automatic balanced irrigation for roof greening.

[0064] Preferably, the irrigation load threshold can be set using a dynamic threshold adjustment method based on actual irrigation needs and environmental conditions. For example, first, the allocated load value for the node matching the water level change is obtained. This value is calculated based on parameters such as the real-time flow rate measured at the current node, the adjusted flow matching value of the upstream node, the adjusted flow matching value of the downstream node, the real-time water level measured at the current node, and the weight coefficients for flow and water level. Then, based on the flow weight coefficient, the water level weight coefficient, and the dynamically adjusted weight coefficient, the allocated load value is dynamically adjusted to adapt to different irrigation scenarios and environmental changes. Finally, the upper and lower limits of the irrigation load threshold are determined based on the lower threshold set for the node, thereby achieving precise control of the irrigation load. In the irrigation prediction module, the irrigation prediction algorithm generates a dynamic flow dataset by calculating the predicted flow value for each sampling point based on the flow and water level data at the sampling point. Specifically, the predicted flow value is calculated based on the original flow value, water level value, load coefficient, and corresponding weight parameters for each sampling point. This method accurately predicts flow trends during the irrigation process, providing a scientific basis for irrigation decision-making.

[0065] In some embodiments, the rain monitoring module includes:

[0066] The rainwater data collection submodule collects flow and water quality parameters based on the rooftop photovoltaic area. It locates invalid data, removes abnormal data, and arranges the extracted flow and water quality values in regional order to generate a regional flow and water quality dataset.

[0067] The rainwater difference analysis submodule analyzes the flow and water quality between regions based on the regional flow and water quality dataset, calculates the regional parameter change ratio, sorts the regional difference values by weight, marks areas with excessive fluctuation differences, and obtains regional rainwater difference data;

[0068] The rainwater distribution integration submodule is based on the regional rainwater difference data, calls the regional rainwater difference value for multi-dimensional aggregation, screens the regional rainwater value differences, classifies them according to the size of the rainwater value, and arranges the regional rainwater values in order to generate a rainwater distribution status value.

[0069] It should be noted that the rainwater monitoring module of the present invention is an important component of the entire rooftop photovoltaic rainwater collection and greening irrigation system. Its main function is to monitor the rainwater flow and water quality parameters of the rooftop photovoltaic area, analyze the differences in flow and water quality between regions, calculate the differences in rainwater distribution between regions, and ultimately integrate them into a set of rainwater distribution parameters to obtain a rainwater distribution state value. This process provides basic data support for subsequent filtering parameter optimization and irrigation control. Among them, the rainwater distribution state value is the result obtained through a comprehensive analysis of multiple parameters. It can reflect the overall distribution of rainwater in the rooftop photovoltaic area and provide a basis for the system's subsequent intelligent decision-making.

[0070] Specifically, the rainwater monitoring module includes a rainwater data collection submodule, a rainwater difference analysis submodule, and a rainwater distribution integration submodule. The rainwater data collection submodule is responsible for regionalized collection of rainwater flow and water quality parameters based on the rooftop photovoltaic area. Regionalized collection here refers to collecting rainwater flow and water quality data for each area based on the rooftop photovoltaic area. For example, the rooftop can be divided into several monitoring areas, each equipped with flow sensors and water quality sensors to monitor rainwater flow and water quality parameters in real time. During the collection process, the system locates and removes invalid and abnormal data to ensure data accuracy and reliability. The rainwater difference analysis submodule analyzes the differences in flow and water quality between areas based on the collected regional flow and water quality datasets and calculates the regional parameter change ratio. The regional parameter change ratio is calculated by comparing the flow and water quality parameters of different areas and is used to quantify the degree of regional differences. The regional difference values are then sorted by weight, and areas with excessive fluctuations are marked to obtain regional rainwater difference data. Weighted sorting here refers to sorting regional difference values according to pre-set weight coefficients to more accurately identify areas with significant differences. The rainwater distribution integration submodule, based on regional rainwater difference data, uses regional rainwater difference values for multi-dimensional aggregation. It screens regional rainwater value differences, classifies them by magnitude, and arranges regional rainwater values in an orderly manner to generate a rainwater distribution status value. Multi-dimensional aggregation here refers to integrating regional rainwater difference data from multiple perspectives to obtain a more comprehensive rainwater distribution status.

[0071] The rainwater data collection submodule preferably uses high-precision sensors when collecting data. For example, flow sensors should have an accuracy of within ±1%, and water quality sensors should have a detection accuracy sufficient to accurately monitor parameters such as pollutant concentration and pH. During the data collection process, the system can identify and remove abnormal data by setting thresholds. For example, if flow data in a particular area suddenly exceeds the normal range by more than twice, it can be considered abnormal and eliminated. The rainwater difference analysis submodule can set different weighting coefficients when calculating regional parameter change ratios based on actual needs. For example, flow parameters can be assigned a higher weight, such as 0.7, while water quality parameters can be assigned a lower weight, such as 0.3, to reflect the importance of different parameters in rainwater distribution. When generating rainwater distribution status values, the system can categorize rainwater values for each area by size and arrange them in an orderly manner. For example, rainwater values can be categorized into three levels: high, medium, and low, and arranged in descending order to provide accurate input data for the subsequent filtering parameter optimization module. In addition, the system can also process the collected data through data smoothing algorithms to reduce data fluctuations and improve data stability.

[0072] In some embodiments, the filtering parameter optimization module includes:

[0073] The filtering parameter acquisition submodule identifies the open and closed status of the filter device in each area based on the rainwater distribution state value, records the angle and opening and closing duration of the filter device, standardizes the recorded data, organizes the standardized data and classifies them by angle and duration to generate a filtering parameter data set;

[0074] The parameter optimization submodule analyzes the angle and duration values in the data set according to the filtered parameter data set, selects the parameter combination with the high matching degree with the rain state, adjusts the parameter combination through pattern matching and records the matching results, and generates the parameter combination optimization result;

[0075] The filtering control submodule retrieves the parameter combination optimization result, determines the optimal matching angle and duration combination, adjusts the filtering control parameters, inputs the control configuration, verifies the stability of the parameter set, and generates a filtering parameter set.

[0076] It should be noted that the filter parameter optimization module of the present invention operates based on the rainwater distribution state. Its main function is to extract the parameter combinations of the filter device's opening and closing angles and durations, screen the optimal angle and duration combination, and ultimately obtain a filter parameter set. This process is crucial for improving the filter device's operating efficiency and filtering effect. The filter parameter set refers to the optimized set of parameters that enable the filter device to achieve the optimal filtering effect under the current rainwater distribution state.

[0077] Specifically, the filtering parameter optimization module includes a filtering parameter acquisition submodule, a parameter optimization submodule, and a filtering control submodule. The filtering parameter acquisition submodule identifies the open and closed status of each filter in each area based on the rain distribution status values, records the filter angles and opening and closing durations, and normalizes the recorded data into a filtering parameter dataset categorized by angle and duration. Standardization here refers to converting the collected data into a unified format or range to facilitate subsequent analysis and processing. The parameter optimization submodule analyzes the angle and duration values in the filtering parameter dataset, selects parameter combinations that highly match the rain conditions, records the matching results through pattern matching, adjusts the parameter combinations, and generates optimized parameter combination results. Pattern matching here refers to comparing the collected parameter combinations with preset patterns to identify the parameter combination that best matches the current rain conditions. The filtering control submodule retrieves the parameter combination optimization results, determines the angle and duration combination with the best match, adjusts the filtering control parameters, inputs the control configuration, and verifies the stability of the parameter set, ultimately generating the filtering parameter set. The stability of the verification parameter set here refers to ensuring, through a series of tests and verifications, that the generated filter parameter set can remain stable in actual operation and will not experience large fluctuations due to interference from external factors.

[0078] Preferably, when collecting data, the filtration parameter acquisition submodule can use high-precision sensors to monitor the filter device's opening and closing status, angle, and duration. For example, the angle sensor can achieve an accuracy of ±0.5 degrees, and the duration sensor can achieve an accuracy of ±0.1 seconds. During data acquisition, the system can set a time interval, such as collecting data every 10 minutes, to ensure real-time and accurate data. When selecting parameter combinations, the parameter optimization submodule can use a rule-based algorithm. This algorithm selects the optimal parameter combination from the filtration parameter dataset based on preset rules and conditions. For example, different rules can be set based on rainwater flow rate and water quality parameters. For example, when the flow rate is high, a larger opening and closing angle and a shorter duration are selected; when the water quality is poor, a smaller opening and closing angle and a longer duration are selected. When adjusting filtration control parameters, the filtration control submodule can use a feedback control mechanism to dynamically adjust the filter device's opening and closing angle and duration based on real-time monitoring of filtration performance. For example, if the filtered water quality does not meet the expected standard, the system can automatically adjust the filter device's angle and duration to improve filtration effectiveness. At the same time, the system can also record the parameter combination and corresponding filtering effect after each adjustment, so as to continuously optimize the filtering parameter set.

[0079] In some embodiments, the environmental response adjustment module includes:

[0080] The environmental monitoring submodule collects key data, including temperature, water level, and flow rate, through environmental monitoring based on the filter parameter set, performs time series analysis on the data, removes outliers, and partitions the remaining data to obtain environmental factor analysis data;

[0081] The environmental adaptation submodule analyzes the data based on the environmental factors, analyzes the impact of environmental variables on the filtering angle and duration, calculates the impact of changes in each environmental factor on parameter adjustment, determines the optimal matching parameter settings based on the impact score, cyclically adjusts the parameters to capture the optimal combination, and obtains the parameter docking results;

[0082] The response parameter solidification submodule selects the angle and duration combination that matches the current environmental conditions from the parameter docking results, performs parameter adjustment tests, optimizes the parameter settings through multiple adjustments and verifications, determines and solidifies the parameters as operating standards, and generates an environmental response parameter set.

[0083] It should be noted that the environmental response adjustment module of the present invention operates based on a filter parameter set. Its main function is to extract the change in current environmental factors, analyze the relationship between the filtering angle and duration, and match environmental factors with filtering combinations to ultimately obtain an environmental response parameter set. This process is crucial for the adaptive operation of the filter device under different environmental conditions. Among them, the environmental response parameter set refers to a set of filter parameters adjusted according to the changes in current environmental factors. These parameters enable the filter device to maintain an optimal operating state under different environmental conditions.

[0084] Specifically, the environmental response adjustment module includes an environmental monitoring submodule, an environmental adaptation submodule, and a response parameter fixation submodule. Based on the filtering parameter set, the environmental monitoring submodule collects key data, including temperature, water level, and flow rate, from environmental monitoring equipment. This data undergoes time series analysis, removes outliers, and then undergoes partitioning to generate environmental factor analysis data. Time series analysis refers to the chronological analysis of continuously collected environmental data to identify trends and cyclical changes. The environmental adaptation submodule analyzes the environmental factor analysis data to determine the impact of environmental variables on filtering angles and durations. It calculates the degree of influence of each environmental factor change on parameter adjustment and determines the optimal matching parameter settings based on the impact score. The impact score quantitatively assesses the impact of environmental factor changes on filtering effectiveness to determine which environmental factors are most critical for adjusting filtering parameters. The response parameter fixation submodule selects angle and duration combinations from the parameter matching results that match the current environmental conditions, conducts parameter adjustment experiments, and optimizes the parameter settings through multiple adjustments and verifications. Ultimately, the parameters are fixed and solidified as operating standards, generating the environmental response parameter set. The parameter adjustment test here refers to testing the selected parameter combinations in the actual operating environment to verify their effectiveness and stability.

[0085] Preferably, the environmental monitoring submodule can use a variety of high-precision sensors to collect environmental data. For example, temperature sensors with an accuracy of ±0.1°C, water level sensors with an accuracy of ±1cm, and flow rate sensors with an accuracy of ±0.05m / s. These sensors can collect environmental data in real time and transmit the data to the system for analysis. During time series analysis, the system can use sliding average or exponential smoothing to smooth the data and reduce noise. The environmental adaptation submodule can use a weighted evaluation model to calculate the impact of environmental factors on filtration parameters. For example, temperature, water level, and flow rate can be assigned different weights, and the impact of each environmental factor on filtration parameter adjustment can be calculated based on these weights. The response parameter fixation submodule can use a stepwise approximation method when conducting parameter adjustment experiments, starting with an initial parameter combination and gradually adjusting the angle and duration until the optimal parameter combination is found. After each adjustment, the system can record evaluation indicators of filtration effectiveness, such as filtered water quality and flow rate, to ensure the effectiveness of the parameter adjustment. Ultimately, the system solidifies the optimal parameter combination that has been verified multiple times into standard operating parameters to guide the operation of the filtration device under different environmental conditions.

[0086] In some embodiments, the irrigation threshold setting module includes:

[0087] The water level monitoring submodule locates the water level change monitoring point based on the environmental response parameter set, extracts the water level change value in the monitoring area, continuously records the water level increase and decrease rate, extracts multiple key change nodes corresponding to the change rate, sorts the node values in order, and obtains the current water level change characteristic value;

[0088] The flow adapter module analyzes the node change value and the real-time flow data based on the current water level change characteristic value, calibrates according to a predetermined matching criterion, calls the matching criterion to perform distribution redistribution within the flow interval, and obtains a water level flow matching structure;

[0089] The threshold allocation submodule is based on the water level flow matching structure and adopts a dynamic threshold adjustment method to measure the distribution of flow between water level change nodes, set the upper and lower limits of the node threshold, apply the threshold to the regional load value, and distribute it to obtain the irrigation load threshold.

[0090] It should be noted that the irrigation threshold setting module operates based on an environmental response parameter set. Its primary function is to extract the current water level change value, combine it with real-time flow data, allocate water level and flow, set irrigation load thresholds, and apply these thresholds to regional irrigation allocation, ultimately obtaining the irrigation load thresholds. This process is crucial for achieving precision irrigation and optimizing water resource allocation. The irrigation load thresholds refer to the upper and lower limits of irrigation water volume set based on water level changes and flow data. They are used to control water allocation during the irrigation process and ensure scientific and rational irrigation.

[0091] Specifically, the irrigation threshold setting module includes a water level monitoring submodule, a flow adaptation submodule, and a threshold allocation submodule. The water level monitoring submodule locates water level change monitoring points based on an environmental response parameter set, extracts water level change values within the monitoring area, continuously records the water level increase and decrease rates, and extracts multiple key change nodes corresponding to these change rates. These node values are sorted sequentially to obtain the current water level change characteristic value. Key change nodes are defined as points with significant changes during the water level change process, such as turning points where the water level rises or falls. The flow adaptation submodule analyzes the node change values and real-time flow data based on the current water level change characteristic values, calibrates them according to a predetermined matching criterion, and then applies the matching criterion to redistribute the flow distribution within the flow interval, resulting in a water level-flow matching structure. The predetermined matching criterion refers to a predefined rule based on the relationship between the water level change characteristic value and flow data, which is used to adjust flow distribution. The threshold allocation submodule, based on the water level-flow matching structure, employs a dynamic threshold adjustment method to measure the flow distribution among water level change nodes, set upper and lower node thresholds, apply the thresholds to the regional load values, and allocate them to obtain the irrigation load threshold. The dynamic threshold adjustment method here is a method of adjusting the threshold in real time according to changes in water level and flow to adapt to different irrigation needs.

[0092] Preferably, the water level monitoring submodule can use high-precision water level sensors, such as ultrasonic water level sensors with an accuracy of ±0.5 cm, to monitor water level changes. These sensors can monitor water level changes in real time and transmit the data to the system for analysis. When extracting key change nodes, the system can use differential or sliding window methods to identify turning points in water level changes. When allocating flow, the flow adaptation submodule can use linear or nonlinear matching criteria based on the correlation between water level change characteristic values and flow data. For example, when the rate of water level change is high, flow allocation can be appropriately increased; when the rate of water level change is low, flow allocation can be reduced. When setting dynamic thresholds, the threshold allocation submodule can dynamically adjust the upper and lower thresholds based on the flow distribution between water level change nodes. For example, when flow is concentrated in a certain water level interval, the upper threshold limit for that interval can be appropriately raised to ensure uniform irrigation. Furthermore, the system can record each threshold adjustment and the corresponding irrigation effect to continuously optimize the setting of the irrigation load threshold.

[0093] In some embodiments, the formula of the dynamic threshold adjustment method is as follows:

[0094] Get the assigned load value of the node that matches the water level change, where:

[0095] L=α·Q+β·H+γ·(Q up -Q down )

[0096] Where: L represents the distributed load value of the node matching the water level change; L represents the real-time flow measured by the current node; Q up Represents the traffic matching value adjusted by the upstream node; Q down represents the flow matching value after adjustment of the downstream node; H represents the real-time water level height measured by the current node; α represents the weight coefficient of flow; β represents the weight coefficient of water level; γ represents the dynamic adjustment weight coefficient; L min The lower threshold set for the node to control the minimum load.

[0097] It's important to note that the dynamic threshold adjustment method is a crucial component of the irrigation threshold setting module. Its purpose is to dynamically adjust the irrigation load threshold based on the assigned load value at the water level-changing node to accommodate the needs of different irrigation scenarios. This method calculates a reasonable irrigation load threshold by comprehensively considering the current node's real-time flow rate, the flow matching values of upstream and downstream nodes, the real-time water level, and relevant weight coefficients. The dynamic adjustment weight coefficient is a key parameter, adjusting according to actual irrigation needs and environmental conditions to ensure a scientific and rational irrigation process.

[0098] Specifically, the dynamic threshold adjustment method involves the calculation and adjustment of multiple parameters. First, the allocated load value for the node matching the water level change refers to the irrigation load value calculated based on the current real-time flow rate at the node and the upstream and downstream flow matching values. This value reflects the irrigation load that should be allocated to each node under the current water level conditions. Second, the real-time flow rate refers to the currently monitored flow data, which directly reflects the current water flow conditions in the irrigation system. The adjusted flow matching value for the upstream node and the adjusted flow matching value for the downstream node represent the flow values adjusted after considering upstream and downstream water level and flow changes, respectively, and are used to balance water distribution across the entire irrigation system. Furthermore, the real-time water level refers to the currently monitored water level, which, together with the flow data, determines the irrigation load distribution. Finally, the flow weight coefficient and the water level weight coefficient are used to adjust the relative importance of flow and water level in the irrigation load calculation. Dynamic adjustment of the weight coefficients is used to further fine-tune the irrigation load threshold to adapt to varying irrigation needs. The node-set lower threshold serves as a protection mechanism to ensure that the irrigation load does not fall below a certain minimum value, thereby ensuring the normal operation of the irrigation system.

[0099] When constructing a dynamic threshold adjustment model, the specific values of each parameter must first be determined based on the actual irrigation system layout and requirements. For example, the flow rate weighting coefficient can be set based on the irrigation system's flow sensitivity. If the system is more sensitive to flow rate fluctuations, the flow rate weighting coefficient can be set higher. Similarly, the water level weighting coefficient can be set based on the impact of water level fluctuations on irrigation effectiveness. Dynamically adjusted weighting coefficients can be adjusted based on historical irrigation data and experience. For example, in the early stages of irrigation, the weighting coefficient can be set lower to observe system performance. During the irrigation process, the weighting coefficient can be gradually adjusted based on real-time data to achieve optimal irrigation results. The calculation process first obtains the current node's real-time flow rate, the flow matching values of upstream and downstream nodes, and the real-time water level. Based on this data and the weighting coefficients, the distributed load value for the node matching the water level fluctuation is calculated. Finally, the distributed load value is adjusted based on the dynamically adjusted weighting coefficient, and the node threshold lower limit is set to ensure that the irrigation load does not fall below the minimum value. The entire calculation process can be performed dynamically based on real-time monitoring data to achieve real-time optimization and adjustment of the irrigation load.

[0100] In some embodiments, the irrigation prediction module includes:

[0101] The flow monitoring submodule applies an irrigation prediction algorithm based on the irrigation load threshold, captures the flow data of the sampling points, removes outliers and corrects errors, stores them in layers by interval, performs dynamic processing, and generates a dynamic flow data set;

[0102] The irrigation trend analysis submodule divides the intervals according to the water level load based on the dynamic flow data set, extracts the change trend and fluctuation characteristics, and generates a water level load and flow change feature set;

[0103] The irrigation prediction submodule adjusts characteristic parameters and calibrates trend data based on the water level load and flow change characteristic set, extracts distribution intervals, and performs numerical prediction to obtain irrigation distribution prediction values.

[0104] It should be noted that the irrigation prediction module operates based on irrigation load thresholds. Its core function is to apply an irrigation prediction algorithm to capture flow data at sampling points, remove outliers, correct errors, and dynamically process the data by interval-based stratification storage to generate a dynamic flow dataset. This process is crucial for predicting flow trends during the irrigation process and provides a scientific basis for subsequent irrigation decisions. The irrigation prediction algorithm, based on historical and real-time monitoring data, is used to predict flow trends over a period of time. The dynamic flow dataset is a collection of processed flow data used to support dynamic adjustments to the irrigation system.

[0105] Specifically, the irrigation forecasting module includes a flow monitoring submodule, an irrigation trend analysis submodule, and an irrigation forecasting submodule. The flow monitoring submodule applies an irrigation forecasting algorithm to capture flow data at sampling points based on irrigation load thresholds. This flow data refers to flow data monitored at different locations within the irrigation system and forms the basis for irrigation forecasting. During data processing, outliers must be removed and errors corrected to ensure data accuracy and reliability. Outliers can be removed by setting thresholds. For example, if the flow data at a sampling point exceeds the normal range by more than twice, it can be considered an outlier and removed. Error correction can be achieved using data smoothing algorithms, such as moving averages or exponential smoothing. Next, dynamic processing is performed using interval-based tiered storage to generate a dynamic flow dataset. Interval-based tiered storage refers to categorizing and storing flow data according to different flow ranges for subsequent analysis and processing. Dynamic processing involves continuously updating the flow dataset based on real-time data to reflect flow changes during the irrigation process.

[0106] Preferably, when constructing an irrigation forecasting algorithm, time series analysis methods, such as the Autoregressive Moving Average (ARMA) model or the Seasonal Autoregressive Moving Average (SARIMA) model, can be employed. These models can predict future flow trends based on historical flow data. Input parameters include historical flow data, time step, and seasonal period. For example, if the irrigation system exhibits significant seasonal variation, a SARIMA model can be employed with a seasonal period set to one year. During data processing, the following steps can be employed: First, the collected flow data is preprocessed, including noise removal and missing value filling. Second, the preprocessed data is input into the irrigation forecasting algorithm to calculate the predicted flow value for each sampling point. Finally, a dynamic flow dataset is generated based on the predicted flow values and stored in corresponding intervals. To improve forecast accuracy, model parameters can be updated regularly, for example, by retraining the model every two weeks or monthly based on the latest flow data. Furthermore, to address unexpected situations, uncertainty analysis can be incorporated into the forecasting process, such as by using Monte Carlo simulation to assess the confidence intervals of the forecast results.

[0107] In some embodiments, the irrigation prediction algorithm is formulated as follows:

[0108] Calculate the traffic prediction value and generate a dynamic traffic data set, where

[0109]

[0110] Among them: F i represents the predicted flow value of the i-th sampling point; w j represents the weight of the j-th data point; Q j represents the original flow value of the kth sampling point; H j represents the water level value of the jth sampling point; L j Represents the load factor of the jth sampling point; N is the total number of sampling points.

[0111] It's important to note that the irrigation prediction algorithm is the core component of the irrigation prediction module. Its primary function is to generate a dynamic flow dataset by calculating flow prediction values. This algorithm uses parameters such as the raw flow rate, water level, and load factor at the sampling point, combined with the weight of each data point, to predict and analyze flow data. This process is crucial for predicting flow trends during the irrigation process and provides a scientific basis for dynamic adjustments to the irrigation system, thereby improving irrigation accuracy and water resource efficiency.

[0112] Specifically, the irrigation prediction algorithm involves the calculation and processing of multiple parameters. First, the raw flow value at the sampling point refers to the actual flow data monitored at different locations in the irrigation system. This data forms the basis for irrigation prediction. Second, the water level value refers to the water level monitored at the corresponding sampling point. Together with the flow value, it reflects the operating status of the irrigation system. The load factor is a parameter calculated based on the irrigation load threshold and is used to represent the irrigation load at each sampling point. In addition, the weight of the data point is a key parameter that can be adjusted based on the importance of the sampling point or the reliability of the data to ensure the accuracy of the prediction results. During the calculation process, the algorithm comprehensively considers these parameters to calculate the predicted flow value for each sampling point and generate a dynamic flow dataset. This dataset can be used for subsequent irrigation trend analysis and prediction, supporting the dynamic adjustment of the irrigation system.

[0113] Preferably, the irrigation prediction algorithm can be constructed using a multi-parameter comprehensive analysis method. First, the weight assignment for each sampling point needs to be determined. For example, higher weights can be assigned based on the sampling point's location and importance in the irrigation system. Sampling points close to the irrigation source or in key areas can be assigned higher weights, such as 0.8; while sampling points farther away or in less important areas can be assigned lower weights, such as 0.5. When calculating the predicted flow rate, a weighted average method can be used: multiplying the raw flow rate value of each sampling point by its corresponding weight and then summing the results to obtain the predicted flow rate value. For example, if there are three sampling points with raw flow rates of 100, 120, and 110, and corresponding weights of 0.8, 0.7, and 0.5, respectively, the predicted flow rate can be calculated as: (100 × 0.8 + 120 × 0.7 + 110 × 0.5) / (0.8 + 0.7 + 0.5). Furthermore, to improve the accuracy of the prediction, time series analysis can be introduced to consider the temporal trends of flow data. For example, a moving average method can be used to smooth historical flow data to reduce data volatility. At the same time, algorithm parameters can be regularly updated based on the actual operation of the irrigation system. For example, weights and load factors can be recalculated hourly or daily based on the latest flow and water level data to ensure the real-time and accuracy of the prediction results.

[0114] In some embodiments, the nozzle feedback control module includes:

[0115] The irrigation error analysis submodule extracts real-time water level and flow data based on the irrigation distribution prediction value, analyzes the real-time flow value and the prediction value, matches the flow difference with the current water level information, and generates a water level and flow error value;

[0116] The nozzle control submodule sets the nozzle spray adjustment parameters based on the water level and flow rate error values. It sets the adjustment range for areas with large errors and makes fine adjustments for areas with low errors. By comparing the spraying effects, it selects matching parameter sets and integrates them to generate a nozzle adjustment parameter set.

[0117] The irrigation execution submodule applies the adjustment parameters at each sprinkler position based on the sprinkler adjustment parameter set, performs spraying operations item by item, synchronously monitors the water level and flow, gradually adjusts the spraying operation order of each area, and generates an automatic balanced irrigation plan for roof greening.

[0118] It's important to note that the sprinkler feedback control module is a key component in achieving precise irrigation within the entire rooftop photovoltaic rainwater harvesting greening irrigation system. Its primary function is to analyze the water level and flow rate errors based on irrigation distribution predictions and real-time water level and flow data. This error-based analysis adjusts the sprinkler angles and duration, ultimately generating an automatically balanced irrigation plan for the rooftop greening. This process ensures the intelligent and automated irrigation system, enabling dynamic adjustments to irrigation strategies based on real-time data to improve irrigation efficiency and water resource utilization.

[0119] Specifically, the sprinkler feedback control module includes an irrigation error analysis submodule, a sprinkler control submodule, and an irrigation execution submodule. The irrigation error analysis submodule extracts real-time water level and flow data based on the irrigation distribution prediction value. It analyzes the real-time flow value and the predicted value, calculates the flow difference, and compares the flow difference with the current water level information to generate a water level and flow error value. The water level and flow error value here refers to the difference between the real-time monitored flow rate and the predicted flow rate, reflecting the deviation in the current state of the irrigation system. The sprinkler control submodule sets sprinkler spray adjustment parameters based on the water level and flow error value. Larger adjustments are set for areas with large errors to quickly correct the deviation, while finer adjustments are made for areas with smaller errors to maintain irrigation stability. The sprinkler adjustment parameter set is a set of parameters generated based on the error analysis results and used to adjust the sprinkler spray angle and duration. Based on the sprinkler adjustment parameter set, the irrigation execution submodule applies the adjustment parameters at each sprinkler location, performs spraying operations one by one, and simultaneously monitors the water level and flow rate. It gradually adjusts the spraying order for each area to generate an automatically balanced irrigation plan for the roof greening. The automatic balanced irrigation scheme for roof greening here refers to an irrigation strategy dynamically generated based on real-time monitoring data and prediction results, which can achieve uniform irrigation of the roof greening area.

[0120] Preferably, within the sprinkler feedback control module, the irrigation error analysis submodule can identify areas requiring adjustment by setting error thresholds. For example, when the flow rate error exceeds a preset threshold (e.g., 10%), that area is considered to require adjustment. When setting sprinkler adjustment parameters, the sprinkler control submodule can dynamically adjust the sprinkler's spray angle and duration based on the error magnitude. For example, for areas with an error exceeding 20%, the sprinkler's spray angle can be increased by 10 degrees, and the spray duration extended by 10 minutes; whereas, for areas with an error within 5%, the sprinkler angle can be fine-tuned by only 1-2 degrees and the spray duration by 1-2 minutes. When implementing spraying operations, the irrigation execution submodule can adopt a gradual adjustment approach, first adjusting areas with larger errors, then gradually adjusting other areas to ensure a smooth transition throughout the irrigation process. Simultaneously, the system can monitor water level and flow rate changes in real time and dynamically update sprinkler adjustment parameters based on the monitoring results to achieve automatic balancing of the irrigation process. Furthermore, to improve the system's adaptability, the error threshold and sprinkler adjustment strategy can be adjusted based on seasonal changes and plant growth stages to meet irrigation needs under different conditions.

[0121] The above-mentioned embodiments of the present invention have the following beneficial effects: the system can use the rainwater monitoring module to analyze the differences in rainwater distribution in the roof photovoltaic area in real time, dynamically generate rainwater distribution status values, and provide accurate data support for subsequent processing. The filtering parameter optimization module can intelligently screen the optimal filtering parameter combination based on the rainwater status to improve rainwater filtration efficiency; the environmental response adjustment module can automatically match the optimal filtering scheme based on environmental changes to enhance system adaptability. The irrigation threshold setting module can achieve precise threshold allocation through dynamic matching of water level and flow, optimizing water resource utilization; the irrigation prediction module can analyze flow trends and dynamically adjust the prediction model to improve the accuracy of irrigation planning. The sprinkler feedback control module can automatically adjust sprinkler parameters through real-time error analysis to achieve dynamic balance of irrigation schemes.

[0122] Multi-dimensional analysis of rainwater variability can enhance the intelligence of rainwater collection. Optimizing filtration parameters ensures efficient operation, and dynamic adaptation to environmental factors enhances system stability. Intelligent matching of water levels and flows optimizes irrigation load distribution. Predictive analysis of flow trends enhances the foresight of irrigation planning. Closed-loop control of sprinkler parameters ensures irrigation uniformity. Through the coordinated operation of various modules, this system enables intelligent management of the entire process of rainwater collection and greening irrigation in rooftop photovoltaic areas, improving water resource utilization efficiency while reducing system energy consumption and maintenance costs.

[0123] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or a terminal device such as a computer, a server, a mobile phone, or a tablet.

[0124] The above descriptions are merely some preferred embodiments of the present invention and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also encompass other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned inventive concept. For example, a technical solution formed by mutually replacing the above-mentioned features with (but not limited to) technical features having similar functions disclosed in the embodiments of the present invention.

Claims

1. A rooftop photovoltaic rainwater collection and greening irrigation system, characterized in that: The system comprises: The rainwater monitoring module is used to analyze regional flow and water quality differences based on the rainwater flow and water quality parameters of the rooftop photovoltaic area, calculate the rainwater distribution differences between regions, integrate them into a rainwater distribution parameter set, and obtain the rainwater distribution status value; A filtering parameter optimization module is used to extract the parameter combination of the opening and closing angle and duration of the filtering device based on the rainwater distribution state value, select the optimal angle and duration combination, and obtain a filtering parameter set; An environmental response adjustment module is used to extract the current environmental factor change based on the filtering parameter set, analyze the relationship between the filtering angle and the duration, match the environmental factors with the filtering combination, and obtain the environmental response parameter set; An irrigation threshold setting module is used to extract the current water level change value based on the environmental response parameter set, combine it with real-time flow data, allocate water level and flow, set a threshold, and apply the threshold to the allocation of regional irrigation to obtain an irrigation load threshold; An irrigation prediction module is configured to capture flow data from water level sampling points based on the irrigation load threshold, perform trend inference on flow changes at the water level sampling points in combination with a photovoltaic area irrigation algorithm, analyze the flow change trend corresponding to the water level load, classify and organize the flow change trend based on the inference results, and dynamically adjust and analyze the classified data in combination with the flow change information to obtain an irrigation distribution prediction value; The sprinkler feedback control module is used to analyze the error value of water level and flow based on the irrigation distribution prediction value and real-time water level and flow data, and adjust the sprinkler spraying angle and duration in combination with the error value to obtain an automatic balanced irrigation plan for roof greening.

2. The rooftop photovoltaic rainwater collection and greening irrigation system according to claim 1, characterized in that: The rainwater distribution state value includes a flow parameter set, a water quality parameter set, and a distribution difference parameter set; the filtering parameter set includes a screening angle parameter and a duration parameter; the environmental response parameter set includes an environmental factor change parameter and a filtering angle duration matching parameter; the irrigation load threshold includes a water level change parameter, a flow matching parameter, and a threshold setting parameter; the irrigation distribution prediction value includes a flow trend analysis parameter and a water level-flow relationship parameter; and the roof greening automatic balancing irrigation plan includes an error analysis parameter and a sprinkler adjustment parameter.

3. The rooftop photovoltaic rainwater collection and greening irrigation system according to claim 1 is characterized in that: The rainwater monitoring module includes: The rainwater data collection submodule is used to collect flow and water quality values based on the rainwater flow and water quality parameters of the roof photovoltaic area, locate invalid data, remove abnormal data, and arrange the extracted flow and water quality values in regional order to generate a regional flow and water quality dataset; A rainwater difference analysis submodule is used to analyze the flow and water quality between regions based on the regional flow and water quality dataset, calculate the regional parameter change ratio, sort the regional difference values by weight, mark the areas with excessive fluctuation differences, and obtain regional rainwater difference data; The rainwater distribution integration submodule is used to call the regional rainwater difference value for multi-dimensional aggregation based on the regional rainwater difference data, screen the regional rainwater value differences, classify them according to the size of the rainwater value, and arrange the regional rainwater values in order to generate a rainwater distribution status value.

4. The rooftop photovoltaic rainwater collection and greening irrigation system according to claim 1 is characterized in that: The filtering parameter optimization module includes: A filtering parameter acquisition submodule is used to identify the open and closed status of the filter device in each area based on the rainwater distribution state value, record the angle and opening and closing duration of the filter device, standardize the recorded data, organize the standardized data and classify it by angle and duration to generate a filtering parameter data set; A parameter optimization submodule is used to analyze the angle and duration values in the filtered parameter data set, select parameter combinations that have a high degree of matching with the rain state, adjust the parameter combinations through pattern matching and record the matching results, and generate parameter combination optimization results; The filtering control submodule is used to retrieve the parameter combination optimization results, determine the optimal matching angle and duration combination, adjust the filtering control parameters, input the control configuration, verify the stability of the parameter set, and generate the filtering parameter set.

5. The rooftop photovoltaic rainwater collection and greening irrigation system according to claim 1 is characterized by: The environmental response adjustment module includes: The environmental monitoring submodule is used to collect key data, including temperature, water level and flow rate, through environmental monitoring based on the filter parameter set, perform time series analysis on the data, eliminate outliers, partition the remaining data, and obtain environmental factor analysis data; The environmental adaptation submodule is used to analyze the data based on the environmental factors, analyze the impact of environmental variables on the filtering angle and duration, calculate the impact of changes in each environmental factor on parameter adjustment, determine the optimal matching parameter settings based on the impact score, cyclically adjust the parameters to capture the optimal combination, and obtain the parameter docking results; The response parameter solidification submodule is used to select an angle and duration combination that matches the current environmental conditions from the parameter docking results, conduct parameter adjustment tests, optimize parameter settings through multiple adjustments and verifications, determine and solidify the parameters as operating standards, and generate an environmental response parameter set.

6. The rooftop photovoltaic rainwater collection and greening irrigation system according to claim 1 is characterized by: The irrigation threshold setting module includes: The water level monitoring submodule is used to locate the water level change monitoring point based on the environmental response parameter set, extract the water level change value in the monitoring area, continuously record the water level increase and decrease rate, extract multiple key change nodes corresponding to the change rate, sort the node values in order, and obtain the current water level change characteristic value; A flow adapter module is used to analyze the node change value and the real-time flow data based on the current water level change characteristic value, calibrate according to a predetermined matching criterion, call the matching criterion to perform distribution redistribution within the flow interval, and obtain a water level flow matching structure; The threshold allocation submodule is used to calculate the distribution of flow between water level change nodes based on the water level flow matching structure and adopt a dynamic threshold adjustment method, set the upper and lower limits of the node threshold, apply the threshold to the regional load value, and distribute it to obtain the irrigation load threshold.

7. The rooftop photovoltaic rainwater collection and greening irrigation system according to claim 6, characterized in that: The formula of the dynamic threshold adjustment method is as follows: Get the assigned load value of the node that matches the water level change, where: L=α·Q+β·H+γ·(Q up -Q down ) Where: L represents the distributed load value of the node matching the water level change; L represents the real-time flow measured by the current node; Q up Represents the traffic matching value adjusted by the upstream node; Q down represents the flow matching value after adjustment of the downstream node; H represents the real-time water level height measured by the current node; α represents the weight coefficient of flow; β represents the weight coefficient of water level; γ represents the dynamic adjustment weight coefficient; L min The lower threshold set for the node to control the minimum load.

8. The rooftop photovoltaic rainwater collection and greening irrigation system according to claim 1, characterized in that: The irrigation prediction module includes: A flow monitoring submodule is used to apply an irrigation prediction algorithm based on the irrigation load threshold, capture flow data at sampling points, remove outliers and correct errors, store data in layers by interval, perform dynamic processing, and generate a dynamic flow data set; An irrigation trend analysis submodule is used to divide the intervals according to the water level load based on the dynamic flow data set, extract the change trend and fluctuation characteristics, and generate a water level load and flow change feature set; The irrigation prediction submodule is used to adjust characteristic parameters and calibrate trend data based on the water level load and flow change characteristic set, extract distribution intervals, and perform numerical prediction to obtain irrigation distribution prediction values.

9. The rooftop photovoltaic rainwater collection and greening irrigation system according to claim 8, characterized in that: The formula of the irrigation prediction algorithm is as follows: Calculate the traffic prediction value and generate a dynamic traffic data set, where Among them: F i represents the predicted flow value of the i-th sampling point; w j represents the weight of the j-th data point; Q j represents the original flow value of the jth sampling point; H j represents the water level value of the jth sampling point; L j Represents the load factor of the jth sampling point; N is the total number of sampling points.

10. The rooftop photovoltaic rainwater collection and greening irrigation system according to claim 1, characterized in that: The nozzle feedback control module includes: An irrigation error analysis submodule is used to extract real-time water level and flow data based on the irrigation distribution prediction value, analyze the real-time flow value and the prediction value, match the flow difference with the current water level information, and generate a water level and flow error value; The nozzle control submodule is used to set the nozzle spray adjustment parameters based on the water level and flow rate error values. The adjustment range is set for areas with large errors, and fine-tuning is performed for areas with low errors. By comparing the spraying effects, matching parameter sets are screened and integrated to generate a nozzle adjustment parameter set. The irrigation execution submodule is used to apply the adjustment parameters at each sprinkler position based on the sprinkler adjustment parameter set, implement the spraying operation item by item, synchronously monitor the water level and flow, gradually adjust the spraying operation order of each area, and generate an automatic balanced irrigation plan for roof greening.

Images