Solar energy irrigation method and system based on data fusion

Abstract

The application relates to the technical field of solar irrigation, and discloses a solar irrigation method and system based on data fusion, which comprises the following steps: collecting and preprocessing environmental data, soil data, crop growth stage data, irrigation water quantity, solar energy and electricity consumption data; predicting crop water demand based on the fusion data, calculating solar energy supply capacity and energy required for irrigation, selecting an energy supply strategy after matching; selecting an irrigation mode in combination with the crop stage and water demand, comprehensively evaluating and selecting an optimal scheme for the combination of the energy supply strategy and the irrigation mode based on preset indexes; recording real-time electricity consumption, water discharge and soil response data during the irrigation process, and dynamically updating a data fusion model based on the data, so that adaptive optimization of the strategy combination is realized, and thus the collaborative and efficient operation of irrigation control and energy scheduling is realized. The application can realize dynamic collaboration and efficient regulation and control of the irrigation strategy and the energy supply path.

Description

Technical Field

[0001] This invention relates to the field of solar irrigation technology, and more specifically, to a solar irrigation method and system based on data fusion. Background Technology

[0002] With the development of agricultural modernization, precision irrigation technology has played a vital role in improving water resource utilization efficiency and ensuring crop yields. Among these technologies, solar irrigation, due to its clean and efficient characteristics, has been widely adopted in areas lacking electricity or far from the power grid. However, existing solar irrigation systems typically suffer from the following problems: Single decision-making basis: Traditional solar irrigation control systems often rely on a single data source (such as soil moisture or timed control) for irrigation execution, lacking comprehensive perception and coordinated judgment of environmental changes, crop water requirements, and energy supply capacity, easily leading to over-irrigation or irrigation delays; Imperfect energy matching mechanism: Existing solar irrigation methods typically rely on simple judgments based on real-time photovoltaic power generation capacity, failing to fully consider energy storage status, grid intervention conditions, and irrigation load response relationships, resulting in coarse energy dispatch strategies and insufficient system energy supply stability; Fixed irrigation mode selection: Some systems only support a single irrigation mode, lacking the ability to flexibly select irrigation strategies based on crop growth stages, water sensitivity, and energy consumption characteristics, limiting healthy crop growth and resource utilization efficiency; Lack of self-learning and feedback mechanisms: Existing technologies rarely establish post-irrigation status feedback and model optimization pathways, failing to dynamically update strategy parameters based on historical irrigation effects, resulting in insufficient system intelligence and difficulty adapting to diverse farmland scenarios and climate changes.

[0003] Therefore, there is an urgent need for an intelligent irrigation method and system that can integrate multi-source data to establish a mechanism for water demand prediction, energy analysis, strategy evaluation and model optimization, so as to achieve dynamic coordination and efficient regulation of irrigation strategies and energy supply paths. Summary of the Invention

[0004] In view of this, the present invention proposes a solar irrigation method and system based on data fusion to solve the above problems.

[0005] On the one hand, the present invention proposes a solar irrigation method based on data fusion, comprising:

[0006] Collect environmental data, soil data, crop growth stage data, irrigation water data, solar energy data, and electricity consumption data;

[0007] Preprocessing environmental data, soil data, crop growth stage data, irrigation water data, solar energy data, and electricity consumption data yields first environmental data, first soil data, first crop growth stage data, first irrigation water data, first solar energy data, and first electricity consumption data.

[0008] Based on the data from the first crop growth stage, combined with the first environmental data and the first soil data, the water requirement of the target crop in the future time period is predicted.

[0009] Based on the first solar energy data and the first electricity consumption data, the solar energy supply capacity and irrigation energy required in the future time period are obtained.

[0010] Different energy supply strategies are selected based on the matching relationship between solar energy supply capacity and irrigation energy requirements;

[0011] Based on the energy supply strategy, and combined with the data of the first crop growth stage and the water requirement of the target crop, different irrigation modes are selected.

[0012] Based on preset values, a comprehensive evaluation of the energy supply strategy and irrigation mode combination scheme is conducted, and the scheme with the highest evaluation is selected.

[0013] When implementing the combined scheme, real-time electricity consumption data, actual water output data, and soil moisture response data are recorded.

[0014] Based on soil moisture response data before and after irrigation and real-time electricity consumption data, the data fusion model is updated to adaptively optimize the combination scheme of energy supply strategy and irrigation mode.

[0015] Furthermore, the environmental data includes air temperature, air humidity, wind speed, precipitation, evaporation, and solar radiation intensity;

[0016] The soil data includes soil temperature, soil moisture, salinity, and infiltration rate;

[0017] The solar energy data includes the photovoltaic system's power generation and the photovoltaic system's energy storage status;

[0018] The electricity consumption data includes the historical and real-time electricity consumption of the irrigation system.

[0019] The crop growth stage data includes crop type, crop planting time, and crop growth stage.

[0020] Furthermore, the preprocessing includes time alignment, anomaly removal, and multidimensional normalization of environmental data, soil data, crop growth stage data, irrigation water data, solar energy data, and electricity consumption data.

[0021] Furthermore, the specific content of predicting the target crop water demand in the future time period is as follows: the water demand weight is adjusted according to the first evaporation in the first environmental data, the first soil moisture in the first soil data, and the first crop growth stage in the first crop growth stage data, and the water demand is corrected in combination with the first precipitation.

[0022] Furthermore, the specific content of obtaining the solar energy supply capacity and irrigation energy required in the future time period is as follows: based on the power generation of the first photovoltaic system in the first solar energy data, estimate the remaining released electricity in the energy storage state of the first photovoltaic system, calculate the solar energy supply capacity in the future time period, and combine it with the first electricity consumption data to calculate the energy required for irrigation.

[0023] Furthermore, based on the matching relationship between solar energy supply capacity and irrigation energy requirements, different energy supply strategies are selected as follows: when solar energy supply capacity is greater than irrigation energy requirements, a pure solar irrigation energy supply strategy is selected; when solar energy supply capacity is less than irrigation energy requirements, but the remaining released electricity in the first photovoltaic system's energy storage state is greater than irrigation energy requirements, a combined solar and energy storage irrigation energy supply strategy is selected; when both solar energy supply capacity and the remaining released electricity in the first photovoltaic system's energy storage state are less than irrigation energy requirements, grid energy is called upon, and a grid-connected irrigation energy supply strategy is selected.

[0024] Furthermore, the selection of different irrigation modes includes low-pressure irrigation mode, periodic irrigation mode, and load-controlled time-sharing irrigation mode;

[0025] Establish indicators for unit irrigation water volume, unit electricity consumption, and target crop water requirement satisfaction under different irrigation modes.

[0026] Furthermore, the specific content of selecting the highest-rated energy supply strategy and irrigation mode combination scheme is as follows: using a weighted algorithm to calculate the highest-rated energy supply strategy and irrigation mode combination scheme based on unit irrigation water volume, unit electricity consumption data, and target crop water requirement satisfaction index.

[0027] Furthermore, the updated data fusion model specifically involves: adjusting the water requirement weights based on the target crop water requirement satisfaction index;

[0028] A calculation model for calculating solar energy supply capacity in the future time period based on the correction of the mismatch between solar energy supply capacity and irrigation energy requirements.

[0029] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0030] A water demand prediction model is constructed by considering crop type, growth stage, and real-time environmental information. This model is then refined by incorporating evaporation, soil moisture, and precipitation trends to improve the accuracy and adaptability of irrigation decisions. Based on the dynamic matching of solar energy supply capacity and irrigation energy requirements, strategies such as pure solar power, combined solar and energy storage, and grid-supplemented power are differentiated to enhance energy flexibility and system stability. Low-pressure irrigation, periodic irrigation, or time-sharing irrigation modes are flexibly selected based on crop stage-specific water demand characteristics and energy consumption, further optimizing hydropower resource allocation and improving the targetedness and efficiency of irrigation response. Indicators for unit irrigation water volume, unit electricity consumption, and target crop water demand satisfaction are established. A weighted algorithm is used to comprehensively evaluate and optimize different irrigation strategies and energy supply methods, enhancing the system's intelligent decision-making capabilities. During irrigation, changes in electricity consumption, water output, and soil moisture response are monitored in real-time. Feedback is used to refine water demand prediction parameters and energy supply estimation models, constructing a closed-loop self-learning path that significantly improves irrigation control accuracy and system evolution capabilities.

[0031] On the other hand, the present invention proposes a solar irrigation system based on data fusion, the system comprising:

[0032] The data acquisition module is configured to collect environmental data, soil data, crop growth stage data, irrigation water data, solar energy data, and electricity consumption data.

[0033] The data preprocessing module is configured to preprocess environmental data, soil data, crop growth stage data, irrigation water data, solar energy data, and electricity consumption data to obtain first environmental data, first soil data, first crop growth stage data, first irrigation water data, first solar energy data, and first electricity consumption data.

[0034] The water demand prediction module is configured to predict the water demand of the target crop within a future time period based on data from the first crop growth stage, combined with first environmental data and first soil data.

[0035] The energy supply analysis module is configured to obtain the solar energy supply capacity and irrigation energy requirements for a future time period based on the first solar energy data and the first electricity consumption data;

[0036] The strategy decision-making module is configured to select different energy supply strategies based on the matching relationship between solar energy supply capacity and irrigation energy requirements. Based on the energy supply strategies, combined with data from the first crop growth stage and the target crop water requirement, different irrigation modes are selected.

[0037] The execution control module is configured to comprehensively evaluate the combination scheme of energy supply strategy and irrigation mode based on preset values, and select the combination scheme of energy supply strategy and irrigation mode with the highest evaluation.

[0038] The status monitoring module is configured to record real-time power consumption data, actual water output data, and soil moisture response data when executing the combined scheme;

[0039] The model update module is configured to update the data fusion model based on soil moisture response data before and after irrigation and real-time electricity consumption data, and to adaptively optimize the combination scheme of energy supply strategy and irrigation mode.

[0040] It should be noted that the solar irrigation method based on data fusion of the present invention has the same beneficial effects as its system, and will not be described in detail here. Attached Figure Description

[0041] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0042] Figure 1 A flowchart of a solar irrigation method based on data fusion provided for an embodiment of the present invention.

[0043] Figure 2 This is a functional block diagram of a solar irrigation system based on data fusion, provided as an embodiment of the present invention. Detailed Implementation

[0044] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0045] See Figure 1 As shown, this embodiment of the invention provides a solar irrigation method based on data fusion, including:

[0046] S1: Collect environmental data, soil data, crop growth stage data, irrigation water data, solar energy data, and electricity consumption data;

[0047] S2: Preprocess the environmental data, soil data, crop growth stage data, irrigation water data, solar energy data, and electricity consumption data to obtain the first environmental data, first soil data, first crop growth stage data, first irrigation water data, first solar energy data, and first electricity consumption data;

[0048] S3: Based on the data of the first crop growth stage, combined with the first environmental data and the first soil data, predict the water requirement of the target crop in the future time period;

[0049] S4: Based on the first solar energy data and the first electricity consumption data, obtain the solar energy supply capacity and irrigation energy required in the future time period;

[0050] S5: Select different energy supply strategies based on the matching relationship between solar energy supply capacity and irrigation energy requirements;

[0051] S6: Based on the energy supply strategy, combined with the data of the first crop growth stage and the water requirement of the target crop, different irrigation modes are selected;

[0052] S7: Based on preset values, comprehensively evaluate the combination scheme of energy supply strategy and irrigation mode, and select the combination scheme of energy supply strategy and irrigation mode with the highest evaluation.

[0053] S8: When executing the combined scheme, record real-time power consumption data, actual water output data, and soil moisture response data.

[0054] S9: Based on soil moisture response data before and after irrigation and real-time electricity consumption data, update the data fusion model and adaptively optimize the combination scheme of energy supply strategy and irrigation mode.

[0055] In some embodiments of this application, environmental data include air temperature, air humidity, wind speed, precipitation, evaporation, and solar radiation intensity, used to characterize the impact of current external meteorological conditions on crop evapotranspiration rate and water demand.

[0056] Soil data, including soil temperature, soil moisture, salinity, and infiltration rate, are used to reflect soil water holding capacity, water flow characteristics, and the status of water available to the roots.

[0057] Solar energy data includes photovoltaic system power generation and photovoltaic system energy storage status, used to assess the energy supply level and remaining energy supply capacity of the solar system in the current period;

[0058] Electricity consumption data includes historical and real-time power consumption of the irrigation system, which is used to identify the load status and energy consumption trends of irrigation equipment, and further support the analysis of energy consumption per unit of irrigation water.

[0059] The crop growth stage data includes crop type, crop planting time, and crop growth stage, which is used to match the water requirement patterns of different crops at different times and to build a stage-based water response model and a water requirement prediction parameter library.

[0060] In some embodiments of this application, preprocessing includes time alignment, anomaly removal, and multidimensional normalization of environmental data, soil data, crop growth stage data, irrigation water data, solar energy data, and electricity consumption data. Time alignment maps data from different data sources with different sampling frequencies and timestamps to a unified time axis, ensuring synchronization during data fusion. Anomaly removal includes interpolation to complete missing data, boundary identification and filtering of abrupt changes, and consistency verification of persistent zero values ​​or static values ​​to improve data quality and validity. Multidimensional normalization uses Z-score standardization or interval scaling to uniformly transform different data according to their physical quantity dimensions and value ranges, eliminating dimensional differences and improving the stability and comparability of subsequent data fusion and modeling calculations.

[0061] It should be noted that by performing time alignment, anomaly removal, and multidimensional normalization on environmental data, soil data, crop growth stage data, irrigation water data, solar energy data, and electricity consumption data, the input data quality and structural consistency of the data fusion model can be significantly improved. This ensures that multidimensional data from different sources and at different time granularities have synchronization and reliability in the fusion calculation. At the same time, anomaly removal effectively eliminates data distortion caused by sensor failures, communication interruptions, or external disturbances, preventing errors from spreading to the irrigation strategy decision-making layer. Multidimensional normalization further enhances the model's sensitivity and stability to changes in various types of data, which is conducive to improving the accuracy and robustness of water demand forecasting, energy supply analysis, and strategy evaluation results, thereby improving the control precision and intelligence level of the entire solar irrigation system.

[0062] In some embodiments of this application, the specific content of predicting the target crop water demand in the future time period is as follows: the water demand weight is adjusted according to the first evaporation in the first environmental data, the first soil moisture in the first soil data, and the first crop growth stage in the first crop growth stage data, and the water demand is corrected in combination with the first precipitation.

[0063] Specifically, the water demand weights are adjusted based on the first evaporation from the first environmental data, the first soil moisture from the first soil data, and the first crop growth stage from the first crop growth stage data. The water demand is then corrected by incorporating the first precipitation data. Evaporation is derived using the Penman-Monteith method or meteorological parameters and preprocessed to reflect the intensity of potential water evaporation from the crop surface per unit time. Soil moisture is taken from the measured water content of the main root distribution layer and compared with the minimum effective water content threshold of the crop to determine whether the soil is currently experiencing water scarcity. Status; the current development stage of crops is calculated based on the planting time, and the stage-specific water demand sensitivity coefficient k is used to adjust the predicted water demand, so that the seedling demand is higher and the maturity demand is lower, thus reflecting the stage-specific water demand pattern of crops; the first precipitation is derived from the cumulative rainfall data of the past 24 or 48 hours, and the predicted rainfall is corrected by combining it with the short-term rainfall forecast. If the future expected rainfall is higher than 50% of the minimum water demand threshold, the predicted water demand is reduced proportionally to prevent repeated watering or soil oversaturation, and further improve the effectiveness and accuracy of water demand assessment;

[0064] The specific process is as follows: Based on the first evaporation rate, the crop water loss rate under the current meteorological conditions is determined. The ratio between the evaporation intensity and the target crop reference evapotranspiration (obtained by data on crop growth stages and then queried by crop type) is used to establish the initial basic water requirement. The first soil moisture is extracted and compared with the lower limit of the suitable water content range for the target crop. If it is lower than the set water content threshold, the current water requirement weight is increased; otherwise, the weight is appropriately reduced. The water requirement sensitivity coefficient for the current stage is determined according to the first crop growth stage, such as taking a high value for the seedling stage, a medium value for the heading stage, and a low value for the maturity stage. This coefficient is used to weight and correct the initial water requirement, forming the stage-specific water requirement. Finally, the first precipitation is summed by the cumulative value of the past 48 hours and the forecast value of the next 24 hours of rainfall. If the proportion of water that can be replenished exceeds 40% of the target crop's stage-specific water requirement, the predicted water requirement is deducted proportionally to form the final corrected crop water requirement.

[0065] It should be noted that by adjusting the water requirement weights based on the first evaporation in the first environmental data, the first soil moisture in the first soil data, and the first crop growth stage in the first crop growth stage data, and by correcting the water requirement in conjunction with the first precipitation, this method can achieve accurate dynamic assessment of the target crop's water requirement under specific climate, soil, and growth conditions. This avoids water waste or insufficient irrigation caused by using fixed irrigation thresholds or empirical estimations. By introducing a stage-specific water requirement sensitivity coefficient, the water requirement prediction results are made closer to the actual physiological water requirement curve of the crop, enhancing the responsiveness to stage characteristics such as high sensitivity during the seedling stage and low demand during the maturity stage. By adjusting the water requirement intensity in conjunction with real-time soil moisture, it ensures that water supply matches the soil's water-holding capacity. At the same time, considering the impact of short-term precipitation, it automatically deducts the substitution effect of natural precipitation on irrigation, avoiding duplicate irrigation. Overall, this method improves the accuracy, dynamism, and practicality of crop water requirement prediction, providing a more reasonable decision-making basis for subsequent irrigation strategy formulation, and further promoting the synergistic optimization of water conservation, yield increase, and energy regulation.

[0066] In some embodiments of this application, the specific content of obtaining the solar energy supply capacity and irrigation energy required in the future time period is as follows: based on the power generation of the first photovoltaic system in the first solar energy data, the remaining released electricity in the energy storage state of the first photovoltaic system is estimated, and the solar energy supply capacity in the future time period is calculated. Combined with the first electricity consumption data, the energy required for irrigation is calculated.

[0067] Specifically, the power generation data of the photovoltaic system at the current moment is read. The data comes from the photovoltaic power generation monitoring unit in the first solar energy data, and the unit is watts (W). At the same time, combined with the solar radiation intensity and sunshine angle at the current time, based on the sunshine trend forecast for the next 2 to 6 hours provided by the regional meteorological station, the expected power generation value for each hour in the future time period is calculated by using the light intensity-power generation efficiency correlation model and the linear extrapolation method.

[0068] The projected power generation for each hour within the predicted future time period is summed up to obtain the total projected power generation of the photovoltaic system for that future time period, expressed in watt-hours (Wh). This total projected power generation represents the solar energy supply capacity of the photovoltaic system. ;

[0069] Extract the current state of energy storage information of the photovoltaic system, including the current remaining battery capacity (in Wh) and maximum discharge power (in W). Combine this with the planned timing of future irrigation operations to calculate the maximum release of electrical energy from the photovoltaic system's energy storage state within that timeframe. If the remaining battery capacity is sufficient, this value is calculated by multiplying the maximum discharge rate by the available time. If the battery capacity is insufficient, the remaining capacity itself is used as the solar energy supply capacity of the energy storage component. , expressed as: ,in, This indicates the current remaining battery power. For maximum discharge power, Planning time for future irrigation operations;

[0070] Adding the two parts above, we obtain the solar energy supply capacity for the future preset time period starting from the current moment, denoted as . (Unit: Wh), and used as the upper limit of energy supply for subsequent irrigation energy dispatch, expressed as: ;

[0071] Then, historical electricity consumption records of the irrigation system are extracted from the first electricity consumption data to obtain the electricity consumption per unit volume of water (in Wh / m³) of a specific irrigation pump under different irrigation modes; combined with the target crop's water requirement (in m³), ​​the energy required to complete this round of irrigation is calculated and denoted as . , expressed as: ,in, Electricity consumption per unit of water volume The target crop's water requirement.

[0072] It should be noted that calculating the solar energy supply capacity and the energy required for irrigation can improve the reliability and accuracy of energy dispatch: by making short-term predictions of photovoltaic power generation trends and quantitatively estimating energy storage release capacity, a comprehensive assessment of the solar system's energy supply capacity in the future can be achieved, avoiding misjudgments or power outages caused by relying solely on current power generation values ​​in traditional systems; ensuring the continuity and stability of irrigation tasks: by combining water demand forecasts with power consumption models, the electrical energy required to complete the current irrigation plan can be accurately calculated, thus determining whether there is sufficient energy support before irrigation, avoiding crop damage or irrigation failure due to power outages during irrigation; and providing basic support for energy supply strategy selection: by analyzing the difference between energy supply capacity and the energy required for irrigation... Analysis can clarify whether current solar energy is sufficient to support the system, whether it is necessary to jointly utilize energy storage or grid resources, and thus trigger the energy supply mode selection logic to achieve optimal energy allocation; improve the system's response intelligence and control precision: this process incorporates dynamic environmental factors, system energy storage status, and historical load data into the decision-making scope, so that irrigation energy consumption is no longer based on experience values ​​or static settings, but is calculated based on real-time status, significantly improving the accuracy and adaptability of system control; optimize the efficiency of hydropower resource utilization: under the premise of ensuring sufficient energy supply, by identifying excessive or insufficient energy supply in advance, intelligent adjustment of irrigation timing can be achieved, avoiding high-energy-consuming tasks during low-efficiency periods, thereby improving the overall solar energy utilization efficiency and reducing unnecessary power consumption.

[0073] In some embodiments of this application, different energy supply strategies are selected based on the matching relationship between solar energy supply capacity and irrigation energy requirements. Specifically, when solar energy supply capacity is greater than irrigation energy requirements, a pure solar irrigation energy supply strategy is selected. When solar energy supply capacity is less than irrigation energy requirements, but the remaining released electricity in the first photovoltaic system's energy storage state is greater than irrigation energy requirements, a combined solar and energy storage irrigation energy supply strategy is selected. When both solar energy supply capacity and the remaining released electricity in the first photovoltaic system's energy storage state are less than irrigation energy requirements, grid energy is invoked, and a grid-connected irrigation energy supply strategy is selected.

[0074] Specifically, when the calculated solar power supply capacity is greater than or equal to the current irrigation energy requirement, the system determines that solar resources are sufficient and selects a pure solar irrigation power supply strategy. Under this strategy, all irrigation electricity is directly supplied by the photovoltaic system's power generation output, prioritizing the use of renewable energy to reduce system operating costs. When the solar power supply capacity is less than the irrigation energy requirement, but the sum of the remaining releaseable electricity calculated from the first photovoltaic system's energy storage state is still greater than or equal to the irrigation energy requirement, the system enters a combined solar and energy storage irrigation power supply strategy. In this case, the irrigation power requirement is jointly supplied by photovoltaic power generation and energy storage batteries, with the photovoltaic system providing the power generation portion and the energy storage system supplementing the insufficient portion, achieving energy supply without external power source participation. Source closed-loop scheduling: When the combined energy supply capacity of solar power and the energy storage release capacity is still insufficient to meet the energy requirements for irrigation, the system determines that the current renewable energy cannot independently support the irrigation task. In order to ensure the continuity and timeliness of crop water supply, external grid resources will be called to participate in power supply, and the grid-joint irrigation energy supply strategy will be implemented. In this mode, the system automatically switches energy paths and coordinates the power supply ratio of photovoltaic, energy storage and grid through the inverter controller to ensure that the irrigation operation is completed as planned. At the same time, the possibility of the system returning to self-sustaining operation will be reassessed in subsequent periods. The multi-strategy energy supply switching mechanism has real-time judgment and adaptive switching capabilities, which can effectively improve the operational stability and energy supply continuity of the irrigation system under complex weather conditions and energy fluctuations.

[0075] It should be noted that different energy supply strategies are selected to ensure the continuity and reliability of the irrigation process: In the event of insufficient sunlight or fluctuations in energy supply, the system can switch energy supply strategies in a timely manner according to the actual energy supply capacity, ensuring that the irrigation task is not interrupted and avoiding water stress or yield loss to crops due to irrigation delays; Prioritizing the use of renewable energy: The system prioritizes the real-time power generation of the photovoltaic system in the energy supply strategy judgment, and only combines energy storage or calls the grid when the power generation capacity is insufficient, thereby maximizing the utilization of solar energy resources, reducing the system's dependence on traditional electricity, and enhancing the efficiency of green energy application; Improving the economy and self-sufficiency of energy dispatch: By calculating the correspondence between solar energy supply capacity and irrigation energy consumption in a refined manner, the system ensures that, within the available resources... Under permissible conditions, grid power supply can be avoided, thus preventing unnecessary electricity costs and extending the cycle life of the energy storage system, thereby improving the overall operating efficiency of the energy system. It also enhances the system's adaptability to sudden environmental changes: in special circumstances such as sudden weather changes, continuous rain, or high-frequency irrigation demands, this strategy switching mechanism can autonomously adjust the energy supply path according to the supply and demand status, enabling the system to have a certain degree of self-recovery and load balancing capabilities, improving the system's robustness and intelligence. Furthermore, it provides fundamental data support for subsequent energy path optimization and strategy learning: each judgment and switching process of the energy supply strategy is accompanied by the recording of key energy consumption and feedback data, which can be used for subsequent model training and parameter adjustment, further promoting the system's evolution towards a more efficient and stable direction.

[0076] In some embodiments of this application, different irrigation modes are selected, including low-pressure irrigation mode, periodic irrigation mode, and load-controlled time-sharing irrigation mode;

[0077] Establish indicators for unit irrigation water volume, unit electricity consumption, and target crop water requirement satisfaction under different irrigation modes.

[0078] In some embodiments of this application, the specific content of selecting the highest-rated energy supply strategy and irrigation mode combination scheme is as follows: using a weighted algorithm to calculate the highest-rated energy supply strategy and irrigation mode combination scheme based on unit irrigation water volume, unit electricity consumption data, and target crop water requirement satisfaction index.

[0079] Specifically, an evaluation system of indicators will be constructed, including indicators for unit irrigation water volume, unit electricity consumption, and the degree to which the target crop's water requirements are met.

[0080] For each combination of energy supply strategy and irrigation mode (pure solar irrigation strategy + low-pressure irrigation mode, solar and energy storage combined irrigation strategy + periodic sprinkler irrigation mode, etc.), calculations are performed, including the total irrigation water volume and irrigation time required to meet the target crop water demand under the corresponding simulated combination of energy supply strategy and irrigation mode; historical energy consumption data and equipment characteristic curves are used to calculate the total electricity consumption data under this combination; the planned irrigation water volume is compared with the predicted water demand to obtain the water demand satisfaction rate;

[0081] The calculated values ​​are normalized to ensure comparability of indicators under different dimensions. Then, the system performs a weighted summation of the normalized indicators based on preset weight parameters (such as a weight of 0.2 for unit water consumption, 0.35 for unit energy consumption, and 0.45 for water demand satisfaction) to generate a comprehensive evaluation value of the combined scheme.

[0082] The system sorts the comprehensive evaluation values ​​of all candidate combinations and selects the one with the highest evaluation value as the execution plan for the current irrigation cycle. If the plan with the highest evaluation value involves a grid-connected irrigation power supply strategy and the evaluation value advantage is not obvious, the system can enter the decision-making process for delayed irrigation and re-evaluate whether to postpone irrigation based on electricity prices and weather forecasts.

[0083] It should be noted that the selection of combined schemes achieves multi-objective synergistic optimization: This evaluation mechanism comprehensively considers multiple dimensions of indicators such as water resource utilization efficiency, electricity consumption, crop water requirement satisfaction, growth stage sensitivity, and energy dispatch efficiency. This avoids the biases caused by traditional irrigation control decisions based on only a single parameter (such as soil moisture or electricity), ensuring that the final selected scheme achieves an optimal balance among multiple objectives. It enhances the scientific rigor and precision of irrigation strategy selection: By introducing a standardized scoring system and weighted scoring mechanism, candidate strategies can be quantitatively compared under different scenarios, providing clear mathematical basis for irrigation decisions, reducing human experience intervention, and improving the transparency and traceability of system dispatch decisions. It also improves the crop's responsiveness to stage-specific water requirements: The evaluation process incorporates crop growth stage priority factors. This enables the system to identify the sensitivity of different growth stages to water, assigning higher matching weights in the weight allocation, thereby improving its responsiveness to key water periods such as seedling and heading stages, ensuring stable and increased crop yields; it promotes a dual improvement in energy dispatch efficiency and operational economy: the comprehensive evaluation system considers parameters such as the proportion of photovoltaic energy supply, the proportion of grid dispatch, and energy allocation efficiency, prompting the system to meet irrigation needs while minimizing unnecessary grid loads and energy storage cycles, effectively extending equipment lifespan and reducing operating costs; it supports dynamic adaptation and continuous optimization of strategy selection: the comprehensive scoring results can serve as a feedback basis for subsequent model optimization and strategy learning, and the system can adjust the weight parameters of each evaluation indicator based on historical performance, achieving adaptive evolution and improving the accuracy of regulation and decision robustness in the next cycle.

[0084] In this example, real-time power consumption data, actual water output data, and soil moisture response data are recorded during the execution of the combined scheme to determine the system's operating status. If the increase in soil moisture before and after irrigation is lower than the set growth threshold, the irrigation efficiency diagnosis process is triggered to check for abnormalities such as pipe blockage, sprinkler failure, or insufficient water pressure.

[0085] In some embodiments of this application, the updated data fusion model specifically involves: correcting the water requirement weights based on the target crop water requirement satisfaction index;

[0086] A calculation model for calculating solar energy supply capacity in the future time period based on the correction of the mismatch between solar energy supply capacity and irrigation energy requirements.

[0087] Specifically, soil moisture response data collected before and after irrigation are compared with the target crop's water requirements to determine whether the actual change in soil moisture achieves the theoretical irrigation effect. If there is a significant deviation, it is identified as "insufficient water demand response" or "over-irrigation." Simultaneously, real-time electricity consumption data recorded throughout the irrigation process is analyzed. Combined with irrigation pump load curves, flow output, and energy consumption linearity characteristics, abnormal fluctuations in energy consumption per unit of water are calculated to determine if there are issues such as low energy efficiency, decreased equipment efficiency, or unreasonable energy supply path settings. Based on these two assessments, the weights used in the original data fusion model for predicting water demand are adjusted. The parameters used for estimating solar energy supply capacity and the comprehensive evaluation weights used for strategy evaluation are dynamically adjusted. For example, if water demand is insufficient for several consecutive irrigation cycles, the crop stage sensitivity coefficient and evaporation factor weights are appropriately increased. If electricity consumption is found to be consistently high, the energy consumption function per unit water volume is modified or the scheduling priority of irrigation mode is adjusted. Finally, the model is driven to learn by real-time feedback data, enabling the data fusion model to continuously adapt to different crop types, meteorological fluctuations, soil conditions and equipment status, and realize the intelligent evolution and accurate recommendation of subsequent energy supply strategies and irrigation mode combinations.

[0088] It should be noted that the system collects data on soil moisture changes and actual electricity consumption before and after irrigation to provide quantitative feedback on irrigation results. This feedback is then used to correct parameters in the model regarding water demand estimation, energy efficiency, and strategy selection. This establishes a closed-loop control path throughout the entire process of "perception-execution-evaluation-optimization," significantly improving the system's self-regulation capabilities.

[0089] See Figure 2 As shown, this embodiment of the invention provides a solar irrigation system based on data fusion, comprising:

[0090] The data acquisition module is configured to collect environmental data, soil data, crop growth stage data, irrigation water data, solar energy data, and electricity consumption data.

[0091] The data preprocessing module is configured to preprocess environmental data, soil data, crop growth stage data, irrigation water data, solar energy data, and electricity consumption data to obtain first environmental data, first soil data, first crop growth stage data, first irrigation water data, first solar energy data, and first electricity consumption data.

[0092] The water demand prediction module is configured to predict the water demand of the target crop within a future time period based on data from the first crop growth stage, combined with first environmental data and first soil data.

[0093] The energy supply analysis module is configured to obtain the solar energy supply capacity and irrigation energy requirements for a future time period based on the first solar energy data and the first electricity consumption data;

[0094] The strategy decision-making module is configured to select different energy supply strategies based on the matching relationship between solar energy supply capacity and irrigation energy requirements. Based on the energy supply strategies, combined with data from the first crop growth stage and the target crop's water requirement, different irrigation modes are selected.

[0095] The execution control module is configured to comprehensively evaluate the combination scheme of energy supply strategy and irrigation mode based on preset values, and select the combination scheme of energy supply strategy and irrigation mode with the highest evaluation.

[0096] The status monitoring module is configured to record real-time power consumption data, actual water output data, and soil moisture response data when executing the combined scheme;

[0097] The model update module is configured to update the data fusion model based on soil moisture response data before and after irrigation and real-time electricity consumption data, and to adaptively optimize the combination scheme of energy supply strategy and irrigation mode.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A solar irrigation method based on data fusion, characterized by, The application relates to a solar energy and energy storage combined irrigation energy supply strategy and method. The application comprises the following steps: Collecting environmental data, soil data, crop growth stage data, irrigation water quantity data, solar energy data and power consumption data; Pretreating the environmental data, soil data, crop growth stage data, irrigation water quantity data, solar energy data and power consumption data to obtain first environmental data, first soil data, first crop growth stage data, first irrigation water quantity data, first solar energy data and first power consumption data; Based on the first crop growth stage data, the first environmental data and the first soil data are combined to predict the target crop water requirement in a future time period; According to the first solar energy data and the first power consumption data, the solar energy supply capacity and the energy required for irrigation in the future time period are obtained; According to the first photovoltaic system power generation power in the first solar energy data, the remaining release electric quantity in the first photovoltaic system energy storage state is estimated, and the solar energy supply capacity in the future time period is calculated; the energy required for irrigation is calculated in combination with the first power consumption data; According to the matching relationship between the solar energy supply capacity and the energy required for irrigation, different energy supply strategies are selected; When the solar energy supply capacity is greater than the energy required for irrigation, a pure solar energy irrigation energy supply strategy is selected; when the solar energy supply capacity is less than the energy required for irrigation, but the remaining release electric quantity in the first photovoltaic system energy storage state is greater than the energy required for irrigation, a solar energy and energy storage combined irrigation energy supply strategy is selected; when the solar energy supply capacity and the remaining release electric quantity in the first photovoltaic system energy storage state are both less than the energy required for irrigation, grid energy is called, and a grid combined irrigation energy supply strategy is selected; Based on the energy supply strategy, the first crop growth stage data and the target crop water requirement are combined to select different irrigation modes; The energy supply strategy and the irrigation mode combination scheme are comprehensively evaluated based on preset values, and the energy supply strategy and the irrigation mode combination scheme with the highest evaluation are selected; Real-time power consumption data, actual water discharge data and soil moisture response data are recorded in real time when the combination scheme is executed; 2. A solar irrigation method based on data fusion as claimed in claim 1, wherein, According to the soil moisture response data and the real-time power consumption data before and after irrigation, the data fusion model is updated, and the energy supply strategy and the irrigation mode combination scheme are adaptively optimized. The environmental data comprises air temperature, air humidity, wind speed, precipitation, evaporation and solar radiation intensity; The soil data comprises soil temperature, soil humidity, salinity and permeation rate; The solar energy data comprises photovoltaic system power generation power and photovoltaic system energy storage state; The power consumption data comprises historical power consumption power and real-time power consumption power of the irrigation system; 3. A data fusion based solar irrigation method as claimed in claim 2, wherein, The crop growth stage data comprises crop type, crop planting time and crop growth stage.

4. A solar irrigation method based on data fusion as claimed in claim 3, wherein, The pretreatment comprises time alignment, abnormality elimination and multi-dimensional normalization processing of the environmental data, soil data, crop growth stage data, irrigation water quantity data, solar energy data and power consumption data. The target crop water requirement in the future time period is predicted according to the first evaporation in the first environmental data, the first soil humidity in the first soil data and the first crop growth stage adjustment water weight in the first crop growth stage data, and the water requirement is corrected in combination with the first precipitation.

5. A data fusion based solar irrigation method as claimed in claim 4, wherein, The selecting different irrigation modes comprises a low-pressure irrigation mode, a periodic irrigation mode and a load-regulated time-sharing irrigation mode. Unit irrigation water quantity, unit electricity consumption data and target crop water requirement satisfaction index under different irrigation modes are established.

6. A data fusion based solar irrigation method as claimed in claim 5, wherein, The selected evaluation highest energy supply strategy and irrigation mode combination scheme specifically comprises: using a weighted algorithm to calculate the unit irrigation water quantity, unit electricity consumption data and target crop water requirement satisfaction index, and calculating the evaluation highest energy supply strategy and irrigation mode combination scheme.

7. A data fusion based solar irrigation method as claimed in claim 6, wherein, The updating data fusion model specifically comprises: correcting the water requirement weight based on the target crop water requirement satisfaction index; A calculation model of solar energy supply capacity in a future time period is calculated based on the matching deviation correction of solar energy supply capacity and irrigation required energy.

8. A data fusion based solar irrigation system, implemented in a data fusion based solar irrigation method as claimed in any one of claims 1 to 7, characterized in that, The system comprises: A data acquisition module configured to acquire environmental data, soil data, crop growth stage data, irrigation water quantity data, solar energy data and electricity consumption data; A data preprocessing module configured to preprocess the environmental data, soil data, crop growth stage data, irrigation water quantity data, solar energy data and electricity consumption data to obtain first environmental data, first soil data, first crop growth stage data, first irrigation water quantity data, first solar energy data and first electricity consumption data; A water requirement prediction module configured to predict the target crop water requirement in a future time period based on the first crop growth stage data, combined with the first environmental data and the first soil data; An energy supply analysis module configured to obtain the solar energy supply capacity and the irrigation required energy in a future time period according to the first solar energy data and the first electricity consumption data; A strategy decision module configured to select different energy supply strategies according to the matching relationship between the solar energy supply capacity and the irrigation required energy, and select different irrigation modes based on the energy supply strategy, combined with the first crop growth stage data and the target crop water requirement; An execution control module configured to comprehensively evaluate the energy supply strategy and irrigation mode combination scheme based on a preset value, and select the evaluation highest energy supply strategy and irrigation mode combination scheme; A state monitoring module configured to record real-time electricity consumption data, actual water output data and soil moisture response data in real time when the combination scheme is executed; A model updating module configured to update the data fusion model according to the soil moisture response data and the real-time electricity consumption data before and after irrigation, and to adaptively optimize the energy supply strategy and irrigation mode combination scheme.

Images