Irrigation pipe network water distribution optimization system based on regional water supply and demand analysis and prediction

Abstract

The invention relates to the technical field of agricultural irrigation, in particular to an irrigation pipe network water distribution optimization system based on regional water supply and demand analysis and prediction, which comprises a regional water supply and demand prediction module, an irrigation pipe network state monitoring module, a data integration analysis module and an optimization scheduling module, wherein the regional water demand prediction module is used for collecting multi-dimensional data of a target region and generating a water demand prediction result of each region through analysis; the irrigation pipe network state monitoring module is used for collecting pipe network data in real time; the data integration analysis module is used for generating an irrigation water source distribution optimization scheme; and the optimal scheduling module is used for scheduling distribution of irrigation water sources. According to the invention, by accurately predicting the regional water demand, monitoring the state of the irrigation pipe network in real time and utilizing an intelligent optimization algorithm to distribute and dispatch the water source, the utilization efficiency of the water resource is effectively improved, the waste is reduced, and the irrigation demand of each region is ensured to be reasonably met.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural irrigation, and in particular to an irrigation pipe network water distribution optimization system based on regional water supply and demand analysis and prediction. Background Art

[0002] In the traditional irrigation management model, the allocation of water resources often relies on human judgment and experience, lacks systematicity and precision, and leads to waste and irrational allocation of water resources. This extensive management method is difficult to cope with complex changes in water supply and demand, especially in the context of changing climate and diverse crop types. The scheduling and optimization of irrigation water sources face huge challenges. How to accurately allocate water resources according to the actual water demand of the region to ensure the stability and sustainability of agricultural production has become a technical problem that needs to be solved urgently.

[0003] In the existing technology, although some studies and solutions have proposed optimization scheduling methods based on water demand and water supply capacity, there are still some shortcomings; for example, the existing methods usually only consider a single factor, such as crop demand or meteorological data, and ignore the real-time status monitoring of the irrigation system, soil moisture and the combined effect of multiple factors, resulting in inaccurate water demand forecasting and water source allocation; in addition, the existing technology often lacks an effective real-time data collection and processing mechanism, and fails to dynamically adjust the water supply strategy during the operation of the irrigation network, resulting in uneven distribution and waste of water resources. Summary of the invention

[0004] Based on the above objectives, the present invention provides an irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction.

[0005] An irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction includes a regional water demand prediction module, an irrigation network status monitoring module, a data integration analysis module, and an optimization scheduling module; wherein:

[0006] Regional water demand forecasting module: used to collect historical meteorological data, soil moisture, crop types and multi-dimensional data of growth stages in the target area, and analyze the multi-dimensional data of the target area through the support vector machine algorithm to generate water demand forecast results for each area;

[0007] Irrigation pipe network status monitoring module: used to collect pipe network data in real time, including the flow, pressure and pipeline status of the pipe network, and feed back the monitored real-time pipe network data to the data integration and analysis module;

[0008] Data integration and analysis module: used to receive the water demand forecast data from the regional water demand forecast module and the real-time pipe network data from the irrigation pipe network status monitoring module. Through big data analysis technology, it matches and analyzes the water demand of each region with the water supply capacity of the pipe network, identifies mismatches or potential optimization points in water resource allocation, and generates an irrigation water source allocation optimization plan;

[0009] Optimization scheduling module: used to schedule the distribution of irrigation water according to the irrigation water distribution optimization plan provided by the data integration analysis module.

[0010] Optionally, the regional water demand prediction module includes a data acquisition unit, a data processing unit and a support vector machine analysis unit; wherein:

[0011] Data collection unit: used to collect historical meteorological data, soil moisture, crop types and multi-dimensional data of their growth stages in the target area;

[0012] The data acquisition unit comprises:

[0013] Meteorological data acquisition subunit: used to obtain historical and real-time meteorological parameters such as temperature, precipitation, wind speed, and relative humidity through weather stations or remote sensors;

[0014] Soil moisture collection subunit: uses soil moisture sensors to monitor and record soil moisture data at different depths and locations;

[0015] Crop information collection subunit: used to collect crop types, planting areas, planting density and data on each growth stage through agricultural management systems or field surveys;

[0016] Data processing unit: used to pre-process the multi-dimensional data collected by the data collection unit, including data cleaning, missing value filling and data normalization, to ensure the integrity and consistency of the data;

[0017] Support vector machine analysis unit: Use the support vector machine algorithm to analyze the pre-processed multi-dimensional data, build a regional water demand forecasting model, and generate water demand forecast results for each region;

[0018] The support vector machine analysis unit comprises:

[0019] Model training subunit: Use the historical meteorological data, soil moisture, crop types and growth stage multi-dimensional data collected by the data collection unit to train the support vector machine model, optimize the model parameters, and train to obtain a regional water demand prediction model;

[0020] Model prediction subunit: Use the trained regional water demand prediction model to predict future water demand and output the water demand for each region.

[0021] Optionally, the model training subunit specifically includes:

[0022] Data preparation: Use the historical meteorological data, soil moisture, crop types and growth stage multi-dimensional data collected by the data collection unit to build a training set;

[0023] Feature selection and preprocessing: Standardize the input data. By standardizing, the mean of each feature is adjusted to zero and the variance is adjusted to one.

[0024] Support vector machine algorithm: In the regression problem, the support vector regression algorithm is used to find the optimal hyperplane for fitting, with the goal of minimizing the regression error;

[0025] Optimize objective function: The goal of the model is to minimize the following loss function while optimizing the complexity and training error of the model;

[0026] Calculate support vectors: Through the optimization process, calculate the support vectors, which are the sample points closest to the regression hyperplane; let the support vector be x sv , then the regional water demand prediction model expression is:

[0027] f(x i )=∑ j∈SV α j y j K(x i , x j )+b, where f(x i ) is the water demand forecast result for region i, α j is the Lagrange multiplier corresponding to the support vector; y j is the actual water demand of support vector j; K(x i , x j ) is the kernel function; SV represents the set of support vectors, and b is the bias term.

[0028] Optionally, the irrigation network status monitoring module includes a sensor deployment unit, a data acquisition unit and a data transmission and storage unit; wherein:

[0029] Sensor deployment unit: used to deploy flow sensors, pressure sensors and pipeline status monitoring equipment to ensure comprehensive monitoring of the flow, pressure and pipeline status of the irrigation network;

[0030] The sensor arrangement unit comprises:

[0031] Flow sensor layout subunit: used to install flow sensors at the entrance of the irrigation pipe network and each branch point to measure the water flow in the pipe network in real time;

[0032] Pressure sensor layout subunit: used to install pressure sensors at each pump station and branch point to measure the water pressure in the pipe network in real time;

[0033] Pipeline status monitoring equipment installation subunit: used to install pipeline status monitoring equipment at the entrance, branch point and pump station of the irrigation pipe network, detect the integrity, leakage and wear of the pipeline in real time, and generate pipeline status parameters;

[0034] Data acquisition unit: used to collect flow data, pressure data and pipeline status data of the irrigation pipe network in real time through the flow sensor, pressure sensor and pipeline status monitoring equipment installed by the sensor deployment unit; wherein the data acquisition frequency of the flow sensor and the pressure sensor is once per minute, and the data acquisition frequency of the pipeline status monitoring equipment is once per hour;

[0035] Data transmission unit: used to transmit the collected flow data, pressure data and pipeline status data to the data integration and analysis module through wired or wireless communication.

[0036] Optionally, the data integration analysis module includes a data receiving unit, a data processing unit, a matching analysis unit and an optimization solution generation unit; wherein:

[0037] Data receiving unit: used to receive water demand forecast data from the regional water demand forecast module and real-time pipe network data from the irrigation pipe network status monitoring module, providing data support for subsequent analysis;

[0038] Data processing unit: used to pre-process the received water demand forecast data and real-time pipe network data to ensure data consistency;

[0039] The data processing unit comprises:

[0040] Data cleaning subunit: used to remove noise and outliers in the data;

[0041] Data format conversion subunit: used to convert data from different sources and formats into a unified data format;

[0042] Matching analysis unit: used to conduct in-depth analysis of the processed data using big data analysis technology;

[0043] The matching analysis unit comprises:

[0044] Demand and supply matching subunit: an algorithm is used to compare the water demand of each region with the water supply capacity of the pipe network to identify areas with imbalanced supply and demand;

[0045] Optimization point identification subunit: Based on the matching analysis results of the demand and water supply matching subunit, data mining technology is used to identify the water resource allocation points that can be optimized, including areas with insufficient or excessive water supply;

[0046] Optimization scheme generation unit: Based on the identification of water resource allocation points that can be optimized, the optimization algorithm is used to generate a specific irrigation water source allocation optimization scheme.

[0047] Optionally, the demand and water supply matching subunit includes:

[0048] Calculation of regional water demand and water supply capacity: Calculate the water demand Q of each region based on the regional water demand forecast data and the water supply capacity data of the pipe network. 需求 (t) and water supply capacity Q 供水 (t), where t represents the time point; the formulas are: Among them, N1 is the number of crop types in the area, M1 is the number of water supply points in the pipe network, and D 需求,i (t) is the water demand of the ith region at time t, D 供水,j (t) is the water supply capacity of the j-th water supply point at time t;

[0049] Demand and supply ratio calculation: Calculate the ratio of water demand to water supply capacity in each area, R(t), using the formula: If R(t)>1, it means that there is a water shortage problem in the region; if R(t)<1, it means that there is an excess of water in the region.

[0050] Optionally, the optimization point identification subunit includes:

[0051] Preliminary screening of water resource allocation points: Based on the demand-supply ratio R(t), identify areas with insufficient or excessive water supply; and mark these areas as preliminary screening objects for optimization point identification;

[0052] Optimization point screening: Screen out the water resource allocation points that need to be optimized. By setting the threshold δ, screen the characteristic data of the water shortage and surplus areas to find out the areas that meet the optimization criteria. The areas that meet the optimization criteria must meet the following conditions: |R(t)-1|>δ, where R(t) is the demand and water supply ratio of the area, and δ is the preset optimization threshold.

[0053] Optionally, the optimization scheme generating unit includes:

[0054] Determine the optimization objective function: Based on the identified water shortage and surplus areas, define the optimization objective function to minimize the waste of water resources in the irrigation water allocation process; the expression of the optimization objective function is: Among them, ΔQ 不足,iis the water shortage of the i-th water-deficient area, ΔQ 过剩,j is the excess water volume of the jth water-oversupplied area, N2 represents the number of water-undersupplied areas; M2 represents the number of water-oversupplied areas;

[0055] Set optimization constraints: Set corresponding constraints, including that the water supply of each area cannot exceed its maximum water supply capacity Q 供水,max , and the water demand of each area should be met; expressed as: Among them, Q 供水,i is the actual water supply in the ith area, Q 供水,max,i is the maximum water supply capacity of the i-th region, Q 需求,i is the water demand of the ith region;

[0056] Apply optimization algorithm: Use optimization algorithm based on linear programming to solve and obtain the best water resource allocation optimization plan to minimize the objective function and meet the constraints;

[0057] Generate optimization plan: Based on the calculation results of the optimization algorithm, generate a specific irrigation water allocation optimization plan, including the final water supply and scheduling time of each area, and the water resource allocation method between areas.

[0058] Optionally, the optimization scheduling module includes a solution receiving unit and a scheduling execution unit; wherein:

[0059] Solution receiving unit: used to receive the irrigation water source allocation optimization solution provided by the data integration and analysis module, and analyze the received optimization solution to provide basic data for subsequent scheduling execution;

[0060] The scheme receiving unit comprises:

[0061] Scheme analysis subunit: used to analyze the target area, water allocation and scheduling priority information in the optimization scheme to form standardized scheduling instructions;

[0062] Task allocation subunit: used to allocate the parsed dispatch instructions to different pipe network nodes and pump station equipment;

[0063] Scheduling execution unit: used to dynamically schedule the water source in the irrigation network according to the scheduling instructions provided by the scheme receiving unit;

[0064] The scheduling execution unit comprises:

[0065] Flow control subunit: adjusts the water flow of each pipe network node through real-time control of the flow regulating valve;

[0066] Pump station dispatch subunit: used to control pump station equipment, including starting, stopping and adjusting the operating power of the pump station.

[0067] Optionally, the solution parsing subunit includes:

[0068] Parse target area information: Extract target area information in the optimization plan, including the unique identifier R of each area i and its region name; among them, R i is the identifier of the i-th target area;

[0069] Analyze the water allocation information: Extract the water allocation Q for each target area from the optimization plan 分配,i , the calculation of the amount of water distributed is verified by the following formula: Q 分配,i =min(D i , Q 供水,max,i ), where Q 分配,i is the actual amount of water allocated to the i-th water-deficient area; D i is the water demand of the ith region; Q 供水,max,i is the maximum water supply capacity of the ith area;

[0070] Parse the scheduling priority information: Determine the scheduling priority P of each area based on the scheduling priority information in the optimization plan. i , the expression is: Among them, P i is the scheduling priority of the ith region; α, β, γ are weight coefficients; D i is the water demand of the ith area; Q 供水,max,i is the maximum water supply capacity of the ith area; S i is the soil moisture index of the ith region; T i is the crop growth stage index of the ith region;

[0071] Generate standardized dispatch instructions: Generate standardized dispatch instruction format, the instruction includes the target area identifier R i , water distribution Q 分配,i And the scheduling priority P i .

[0072] Beneficial effects of the present invention:

[0073] The present invention, through comprehensive analysis of multi-dimensional data such as historical meteorological data, soil moisture, crop types and their growth stages, can more accurately predict the water demand of each region, thereby providing refined water use guidance for the irrigation network and avoiding the waste of water resources caused by lack of experience and data in traditional irrigation management.

[0074] The present invention can identify potential optimization points and generate specific optimization plans through deep matching analysis of water demand and water supply capacity of the pipe network, so as to guide the irrigation pipe network system to adjust according to actual needs; this process greatly reduces human intervention and avoids problems such as improper scheduling or uneven water supply in traditional methods; through precise scheduling of water source distribution by optimization algorithm, it not only ensures that the water demand of each region is effectively met, but also minimizes the waste of water resources while ensuring the irrigation effect, thereby achieving the optimal allocation of water resources and maximizing irrigation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0076] Figure 1 A schematic diagram of an irrigation network water distribution optimization system according to an embodiment of the present invention;

[0077] Figure 2 Schematic diagram of a data integration analysis module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0078] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0079] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0080] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0081] like Figure 1-Figure 2 As shown, an irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction includes a regional water demand prediction module, an irrigation network status monitoring module, a data integration analysis module, and an optimization scheduling module; wherein:

[0082] Regional water demand forecasting module: used to collect historical meteorological data, soil moisture, crop types and multi-dimensional data of growth stages of the target area, and analyze the multi-dimensional data of the target area through the support vector machine (SVM) algorithm to generate water demand forecast results for each area, and transmit the forecast results to the data integration analysis module;

[0083] Irrigation network status monitoring module: used to collect real-time network data, including the flow, pressure and pipeline status of the network, and feed back the monitored real-time network data to the data integration and analysis module to provide basic data support for the operation status of the network;

[0084] Data integration and analysis module: used to receive the water demand forecast data from the regional water demand forecast module and the real-time pipe network data from the irrigation pipe network status monitoring module. Through big data analysis technology, it matches and analyzes the water demand of each region with the water supply capacity of the pipe network, identifies mismatches or potential optimization points in water resource allocation, and generates irrigation water source allocation optimization plans for reference by the optimization scheduling module.

[0085] Optimization and Scheduling Module: It is used to schedule the distribution of irrigation water sources according to the irrigation water source allocation optimization plan provided by the data integration and analysis module, to ensure that water resource waste is minimized while meeting the irrigation needs of each region, and to transmit the scheduling results to the irrigation network to implement accurate allocation of water resources.

[0086] The regional water demand prediction module includes a data acquisition unit, a data processing unit and a support vector machine analysis unit; wherein:

[0087] Data collection unit: used to collect historical meteorological data, soil moisture, crop types and multi-dimensional data of their growth stages in the target area;

[0088] The data acquisition unit includes:

[0089] Meteorological data acquisition subunit: used to obtain historical and real-time meteorological parameters such as temperature, precipitation, wind speed, and relative humidity through weather stations or remote sensors;

[0090] Soil moisture collection subunit: uses soil moisture sensors to monitor and record soil moisture data at different depths and locations;

[0091] Crop information collection subunit: used to collect crop types, planting areas, planting density and data on each growth stage through agricultural management systems or field surveys;

[0092] Data processing unit: used to pre-process the multi-dimensional data collected by the data collection unit, including data cleaning, missing value filling and data normalization, to ensure the integrity and consistency of the data;

[0093] Support vector machine analysis unit: Use the support vector machine algorithm to analyze the pre-processed multi-dimensional data, build a regional water demand forecasting model, and generate water demand forecast results for each region;

[0094] The support vector machine analysis unit includes:

[0095] Model training subunit: Use the historical meteorological data, soil moisture, crop types and growth stage multi-dimensional data collected by the data collection unit to train the support vector machine (SVM) model, optimize the model parameters, and train to obtain a regional water demand prediction model;

[0096] Model prediction subunit: Use the trained regional water demand prediction model to predict future water demand and output the water demand of each region; through systematic data collection, processing and analysis, the regional water demand prediction module can efficiently and accurately predict the water demand of each region; this not only improves the overall water distribution optimization capability of the system, but also effectively avoids the waste of water resources and the problem of unbalanced water supply, and promotes the refined management of agricultural irrigation and the sustainable use of water resources.

[0097] The model training subunit specifically includes:

[0098] Data preparation: Use the historical meteorological data, soil moisture, crop types and growth stage multi-dimensional data collected by the data acquisition unit to construct a training set; suppose the training data set is Among them, x i is the input feature vector, which contains multi-dimensional data such as meteorological data (such as temperature, precipitation, wind speed, etc.), soil moisture, crop information, etc.; i is the corresponding target variable, i.e., the water demand of region i; N is the number of training samples;

[0099] Feature selection and preprocessing: Standardize the input data. Through standardization, adjust the mean of each feature to zero and the variance to one, to ensure that the influence of features of different dimensions on the training process is relatively balanced; the standardization formula is: Among them, x ij is the jth eigenvalue of the i-th sample; x ij ′ is the standardized eigenvalue; is the mean of the jth feature; is the standard deviation of the jth feature;

[0100] Support vector machine algorithm: In the regression problem, the support vector regression algorithm is used to find the optimal hyperplane for fitting, with the goal of minimizing the regression error; let the regression function be f(x i ), then the calculation formula is: f(x i )=w T x i +b, where w is a weight vector, indicating the influence of each input feature; x i is the input feature vector; b is the bias term, which is used to adjust the position of the hyperplane;

[0101] Optimize the objective function: The goal of the model is to minimize the following loss function while optimizing the complexity and training error of the model, expressed as: Among them, w is the weight vector; C is the penalty parameter used to balance the training error and model complexity; ξ i is the slack variable for each sample, used to measure the regression error; N is the number of training samples; the objective function is minimized To control the complexity of the model, Control the training error to ensure that the model can fit the training data well;

[0102] Calculate support vectors: Through the optimization process, calculate the support vectors, which are the sample points closest to the regression hyperplane; let the support vector be x sv , then the regional water demand prediction model expression is:

[0103] f(x i )=∑ j∈SV α j y j K(x i , x j )+b, where f(x i ) is the water demand forecast result for region i, α j is the Lagrange multiplier corresponding to the support vector; y j is the actual water demand of support vector j; K(x i , x j) is the kernel function, including linear kernel, polynomial kernel and radial basis function kernel (RBF); SV represents the set of support vectors, and b is the bias term; through the above detailed training steps, the model training subunit can generate an accurate regional water demand prediction model based on multi-dimensional historical data, which not only improves the accuracy of water demand prediction, but also enhances the adaptability of the system in a dynamic environment, ensuring the efficient operation of the irrigation network and the rational allocation of water resources.

[0104] The irrigation network status monitoring module includes a sensor deployment unit, a data acquisition unit, and a data transmission and storage unit; wherein:

[0105] Sensor deployment unit: used to deploy flow sensors, pressure sensors and pipeline status monitoring equipment to ensure comprehensive monitoring of the flow, pressure and pipeline status of the irrigation network;

[0106] The sensor layout unit includes:

[0107] Flow sensor layout subunit: used to install flow sensors at the entrance of the irrigation pipe network and each branch point to measure the water flow in the pipe network in real time (unit: cubic meters per hour, m 3 / h);

[0108] Pressure sensor layout subunit: used to install pressure sensors at each pump station and branch point to measure the water pressure in the pipe network in real time (unit: Pascal, Pa);

[0109] Pipeline status monitoring equipment installation subunit: used to install pipeline status monitoring equipment at the entrance, branch point and pump station of the irrigation pipe network, detect the integrity, leakage and wear of the pipeline in real time, and generate pipeline status parameters;

[0110] Data acquisition unit: used for collecting flow data, pressure data and pipeline status data of the irrigation pipe network in real time through the flow sensor, pressure sensor and pipeline status monitoring equipment installed by the sensor deployment unit; the data collection frequency of the flow sensor and pressure sensor is once per minute, and the data collection frequency of the pipeline status monitoring equipment is once per hour;

[0111] Data transmission unit: used to transmit the collected flow data, pressure data and pipeline status data to the data integration and analysis module through wired or wireless communication; by deploying flow sensors, pressure sensors and pipeline status monitoring equipment at the entrance of the irrigation pipe network, each branch point and pump station, the irrigation pipe network status monitoring module can comprehensively and accurately collect the flow, pressure and pipeline status data of the pipe network in real time; this comprehensive monitoring method improves the system's real-time grasp of water flow and water pressure, and can promptly detect abnormal conditions in the pipe network.

[0112] The data integration analysis module includes a data receiving unit, a data processing unit, a matching analysis unit and an optimization solution generation unit; wherein:

[0113] Data receiving unit: used to receive water demand forecast data from the regional water demand forecast module and real-time pipe network data from the irrigation pipe network status monitoring module, providing data support for subsequent analysis;

[0114] Data processing unit: used to pre-process the received water demand forecast data and real-time pipe network data to ensure data consistency;

[0115] The data processing unit includes:

[0116] Data cleaning subunit: used to remove noise and outliers in the data to ensure data quality;

[0117] Data format conversion subunit: used to convert data from different sources and formats into a unified data format for subsequent analysis;

[0118] Matching analysis unit: used to conduct in-depth analysis of the processed data using big data analysis technology;

[0119] The matching analysis unit includes:

[0120] Demand and supply matching subunit: an algorithm is used to compare the water demand of each region with the water supply capacity of the pipe network to identify areas with imbalanced supply and demand;

[0121] Optimization point identification subunit: Based on the matching analysis results of the demand and water supply matching subunit, data mining technology is used to identify the water resource allocation points that can be optimized, including areas with insufficient or excessive water supply;

[0122] Optimization scheme generation unit: Based on the identification of water resource allocation points that can be optimized, the optimization algorithm is used to generate specific irrigation water source allocation optimization schemes to improve the efficiency of water resource utilization; through the design of the above units, the data integration analysis module can efficiently and accurately match regional water demand with the water supply capacity of the irrigation network, timely identify imbalances or potential optimization points in water resource allocation, and generate practical optimization schemes; this not only improves the efficiency of water resource utilization and reduces water resource waste, but also ensures that the irrigation needs of each region are fully met.

[0123] The demand and supply matching subunit includes:

[0124] Calculation of regional water demand and water supply capacity: Calculate the water demand Q of each region based on the regional water demand forecast data and the water supply capacity data of the pipe network. 需求 (t) and water supply capacity Q 供水 (t), where t represents the time point; the formulas are: Among them, N1 is the number of crop types in the area, M1 is the number of water supply points in the pipe network, and D 需求,i (t) is the water demand of the ith region at time t, D 供水,j (t) is the water supply capacity of the j-th water supply point at time t;

[0125] Demand and supply ratio calculation: Calculate the ratio of water demand to water supply capacity in each area, R(t), using the formula: If R(t)>1, it means that there is a water shortage problem in the region; if R(t)<1, it means that there is an oversupply of water in the region; through the above steps, the demand and water supply matching subunit can compare the water demand and water supply capacity of each region, identify the difference between supply and demand, and provide basic data for subsequent optimization point identification.

[0126] The optimization point identification subunit includes:

[0127] Preliminary screening of water resource allocation points: Based on the demand-supply ratio R(t), identify areas with insufficient or excessive water supply; and mark these areas as preliminary screening objects for optimization point identification;

[0128] Optimization point screening: Screen out the water resource allocation points that need to be optimized. By setting the threshold δ, screen the characteristic data of the water shortage and surplus areas to find out the areas that meet the optimization criteria. The areas that meet the optimization criteria must meet the following conditions: |R(r)-1|>δ, where R(t) is the demand and water supply ratio of the area, and δ is the preset optimization threshold. Through the above steps, the optimization point identification subunit can identify the water resource allocation points that need to be optimized and provide data support for subsequent water resource scheduling optimization.

[0129] The optimization solution generation unit includes:

[0130] Determine the optimization objective function: Based on the identified water shortage and surplus areas, define the optimization objective function to minimize the water waste in the irrigation water allocation process; the optimization objective function is expressed as minimizing the water gap ΔQ in the water shortage area and the water surplus ΔQ in the water surplus area 过剩 The difference between them; the expression of the optimization objective function is: Among them, ΔQ 不足,i is the water shortage of the i-th water-deficient area, ΔQ 过剩,j is the excess water volume of the jth water-oversupplied area, N2 represents the number of water-undersupplied areas; M2 represents the number of water-oversupplied areas;

[0131] Setting optimization constraints: In order to ensure that the irrigation water allocation plan minimizes waste while meeting demand, corresponding constraints need to be set. The constraints include that the water supply of each area cannot exceed its maximum water supply capacity Q供水,max , and the water demand of each area should be met; expressed as: Among them, Q 供水,i is the actual water supply in the ith area, Q 供水,max,i is the maximum water supply capacity of the i-th region, Q 需求,i is the water demand of the ith region;

[0132] Apply optimization algorithm: Use optimization algorithm based on linear programming to solve and obtain the best water resource allocation optimization plan to minimize the objective function and meet the constraints;

[0133] The linear programming algorithm has the form:

[0134] minc T x;

[0135] subject to: Ax≤b,x≥0, where x is the optimization variable vector, representing the actual water supply of each region; c is the objective function coefficient vector, representing the weight of water shortage and surplus; A is the constraint matrix, representing water supply capacity and demand constraints; b is the right-hand side vector of the constraint condition, representing the maximum water supply capacity of each region;

[0136] Generate optimization plan: According to the calculation results of the optimization algorithm, generate a specific irrigation water source allocation optimization plan, including the final water supply volume and scheduling time of each area, as well as the water resource allocation method between areas; through the above steps, the optimization plan generation unit can generate a scientific and reasonable irrigation water source allocation optimization plan to help optimize the water supply efficiency of the irrigation network and achieve optimal utilization of water resources.

[0137] The optimization scheduling module includes a scheme receiving unit and a scheduling execution unit; wherein:

[0138] Solution receiving unit: used to receive the irrigation water source allocation optimization solution provided by the data integration and analysis module, and analyze the received optimization solution to provide basic data for subsequent scheduling execution;

[0139] The solution receiving unit includes:

[0140] Scheme analysis subunit: used to analyze the target area, water allocation and scheduling priority information in the optimization scheme to form standardized scheduling instructions;

[0141] Task allocation subunit: used to allocate the parsed dispatching instructions to different pipe network nodes and pump station equipment to ensure that the instructions can be accurately executed;

[0142] Scheduling execution unit: used to dynamically schedule the water source in the irrigation network according to the scheduling instructions provided by the scheme receiving unit;

[0143] The scheduling execution unit includes:

[0144] Flow control subunit: adjusts the water flow of each pipe network node through real-time control of the flow regulating valve to ensure that the water source distribution meets the requirements of the optimization plan;

[0145] Pump station scheduling subunit: used to control pump station equipment, including starting, stopping and adjusting the operating power of the pump station to ensure that the water supply pressure and flow meet the requirements of the optimization plan; through the collaborative work of the above units, the optimization scheduling module can efficiently execute the irrigation water source allocation optimization plan provided by the data integration analysis module to achieve accurate scheduling of water source allocation.

[0146] The solution analysis subunit includes:

[0147] Parse target area information: Extract target area information in the optimization plan, including the unique identifier R of each area i and its region name; among them, R i is the identifier of the i-th target area;

[0148] Analyze the water allocation information: Extract the water allocation Q for each target area from the optimization plan 分配,i , ensuring that the amount of water allocated to each area meets its needs and does not exceed its maximum water supply capacity Q 供水,max,i , the calculation of the amount of water distributed is verified by the following formula: Q 分配,i =min(D i , Q 供水,max,i ), where Q 分配,i is the actual amount of water allocated to the i-th water-deficient area; D i is the water demand of the ith area; Q 供水,max,i is the maximum water supply capacity of the ith area;

[0149] Parse the scheduling priority information: Determine the scheduling priority P of each area based on the scheduling priority information in the optimization plan. i , the expression is: Among them, P i is the scheduling priority of the ith area; α, β, γ are weight coefficients, representing the water demand ratio respectively. The degree to which soil moisture and crop growth stage affect scheduling priority; D i is the water demand of the ith area; Q 供水,max,i is the maximum water supply capacity of the ith area; S i is the soil moisture index of the ith region; T i is the crop growth stage index of the i-th region; water demand ratio Reflects the ratio of regional water demand to water supply capacity. The larger the value, the higher the demand relative to water supply capacity and the higher the priority. Soil moisture index S i Reflects the moisture level of the soil. The lower the humidity, the drier the soil is. The crops need more water and have a higher priority. Crop growth stage index T i Reflects the growth stage of the crop. Crops in the vigorous growth stage require more water and have a higher priority.

[0150] Generate standardized dispatch instructions: Generate standardized dispatch instruction format, the instruction includes the target area identifier R i , water distribution Q 分配,i And the scheduling priority P i ; Standardized scheduling instructions are expressed as: Scheduling instructions i =(R i , Q 分配,i , P i ), where R i is the area identifier; Q 分配,i P is the amount of water to be distributed; i The scheduling priority.

[0151] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0152] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction, characterized in that: It includes regional water demand prediction module, irrigation network status monitoring module, data integration analysis module, and optimization scheduling module; among which: Regional water demand forecasting module: used to collect historical meteorological data, soil moisture, crop types and multi-dimensional data of growth stages in the target area, and analyze the multi-dimensional data of the target area through the support vector machine algorithm to generate water demand forecast results for each area; Irrigation pipe network status monitoring module: used to collect pipe network data in real time, including the flow, pressure and pipeline status of the pipe network, and feed back the monitored real-time pipe network data to the data integration and analysis module; Data integration and analysis module: used to receive the water demand forecast data from the regional water demand forecast module and the real-time pipe network data from the irrigation pipe network status monitoring module. Through big data analysis technology, it matches and analyzes the water demand of each region with the water supply capacity of the pipe network, identifies mismatches or potential optimization points in water resource allocation, and generates an irrigation water source allocation optimization plan; Optimization scheduling module: used to schedule the distribution of irrigation water according to the irrigation water distribution optimization plan provided by the data integration analysis module.

2. The irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction according to claim 1 is characterized in that: The regional water demand prediction module includes a data acquisition unit, a data processing unit and a support vector machine analysis unit; wherein: Data collection unit: used to collect historical meteorological data, soil moisture, crop types and multi-dimensional data of their growth stages in the target area; The data acquisition unit comprises: Meteorological data acquisition subunit: used to obtain historical and real-time meteorological parameters such as temperature, precipitation, wind speed, and relative humidity through weather stations or remote sensors; Soil moisture collection subunit: uses soil moisture sensors to monitor and record soil moisture data at different depths and locations; Crop information collection subunit: used to collect crop types, planting areas, planting density and data on each growth stage through agricultural management systems or field surveys; Data processing unit: used to pre-process the multi-dimensional data collected by the data collection unit, including data cleaning, missing value filling and data normalization, to ensure the integrity and consistency of the data; Support vector machine analysis unit: Use the support vector machine algorithm to analyze the pre-processed multi-dimensional data, build a regional water demand forecasting model, and generate water demand forecast results for each region; The support vector machine analysis unit comprises: Model training subunit: Use the historical meteorological data, soil moisture, crop types and growth stage multi-dimensional data collected by the data collection unit to train the support vector machine model, optimize the model parameters, and train to obtain a regional water demand prediction model; Model prediction subunit: Use the trained regional water demand prediction model to predict future water demand and output the water demand for each region.

3. The irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction according to claim 2 is characterized in that: The model training subunit specifically includes: Data preparation: Use the historical meteorological data, soil moisture, crop types and growth stage multi-dimensional data collected by the data collection unit to build a training set; Feature selection and preprocessing: Standardize the input data. By standardizing, the mean of each feature is adjusted to zero and the variance is adjusted to one. Support vector machine algorithm: In the regression problem, the support vector regression algorithm is used to find the optimal hyperplane for fitting, with the goal of minimizing the regression error; Optimize objective function: The goal of the model is to minimize the following loss function while optimizing the complexity and training error of the model; Calculate support vectors: Through the optimization process, calculate the support vectors, which are the sample points closest to the regression hyperplane; let the support vector be x sv , then the regional water demand prediction model expression is: f(x i )=∑ j∈SV α j y j K(x i , x j )+b, where f(x i ) is the water demand forecast result for region i, α j is the Lagrange multiplier corresponding to the support vector; y j is the actual water demand of support vector j; K(x i , x j ) is the kernel function; SV represents the set of support vectors, and b is the bias term.

4. The irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction according to claim 1 is characterized in that: The irrigation network status monitoring module includes a sensor deployment unit, a data acquisition unit and a data transmission and storage unit; wherein: Sensor deployment unit: used to deploy flow sensors, pressure sensors and pipeline status monitoring equipment to ensure comprehensive monitoring of the flow, pressure and pipeline status of the irrigation network; The sensor arrangement unit comprises: Flow sensor layout subunit: used to install flow sensors at the entrance of the irrigation pipe network and each branch point to measure the water flow in the pipe network in real time; Pressure sensor layout subunit: used to install pressure sensors at each pump station and branch point to measure the water pressure in the pipe network in real time; Pipeline status monitoring equipment installation subunit: used to install pipeline status monitoring equipment at the entrance, branch point and pump station of the irrigation pipe network, detect the integrity, leakage and wear of the pipeline in real time, and generate pipeline status parameters; Data acquisition unit: used to collect flow data, pressure data and pipeline status data of the irrigation pipe network in real time through the flow sensor, pressure sensor and pipeline status monitoring equipment installed by the sensor deployment unit; wherein the data acquisition frequency of the flow sensor and the pressure sensor is once per minute, and the data acquisition frequency of the pipeline status monitoring equipment is once per hour; Data transmission unit: used to transmit the collected flow data, pressure data and pipeline status data to the data integration and analysis module through wired or wireless communication.

5. The irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction according to claim 1, characterized in that: The data integration analysis module includes a data receiving unit, a data processing unit, a matching analysis unit and an optimization solution generation unit; wherein: Data receiving unit: used to receive water demand forecast data from the regional water demand forecast module and real-time pipe network data from the irrigation pipe network status monitoring module, providing data support for subsequent analysis; Data processing unit: used to pre-process the received water demand forecast data and real-time pipe network data to ensure data consistency; The data processing unit comprises: Data cleaning subunit: used to remove noise and outliers in the data; Data format conversion subunit: used to convert data from different sources and formats into a unified data format; Matching analysis unit: used to conduct in-depth analysis of the processed data using big data analysis technology; The matching analysis unit comprises: Demand and supply matching subunit: an algorithm is used to compare the water demand of each region with the water supply capacity of the pipe network to identify areas with imbalanced supply and demand; Optimization point identification subunit: Based on the matching analysis results of the demand and water supply matching subunit, data mining technology is used to identify the water resource allocation points that can be optimized, including areas with insufficient or excessive water supply; Optimization scheme generation unit: Based on the identification of water resource allocation points that can be optimized, the optimization algorithm is used to generate a specific irrigation water source allocation optimization scheme.

6. The irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction according to claim 5, characterized in that: The demand and water supply matching subunit includes: Calculation of regional water demand and water supply capacity: Calculate the water demand Q of each region based on the regional water demand forecast data and the water supply capacity data of the pipe network. 需求 (t) and water supply capacity Q 供水 (t), where t represents the time point; the formulas are: Among them, N1 is the number of crop types in the area, M1 is the number of water supply points in the pipe network, and D 需求,i (t) is the water demand of the ith region at time t, D 供水,j (t) is the water supply capacity of the j-th water supply point at time t; Demand and supply ratio calculation: Calculate the ratio of water demand to water supply capacity in each area, R(t), using the formula: If R(t)>1, it means that there is a water shortage problem in the region; if R(t)<1, it means that there is an excess of water in the region.

7. The irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction according to claim 6, characterized in that: The optimization point identification subunit comprises: Preliminary screening of water resource allocation points: Based on the demand-supply ratio R(t), identify areas with insufficient or excessive water supply; and mark these areas as preliminary screening objects for optimization point identification; Optimization point screening: Screen out the water resource allocation points that need to be optimized. By setting the threshold δ, screen the characteristic data of the water shortage and surplus areas to find out the areas that meet the optimization criteria. The areas that meet the optimization criteria must meet the following conditions: |R(t)-1|>δ, where R(t) is the demand and water supply ratio of the area, and δ is the preset optimization threshold.

8. The irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction according to claim 7, characterized in that: The optimization scheme generating unit comprises: Determine the optimization objective function: Based on the identified water shortage and surplus areas, define the optimization objective function to minimize the waste of water resources in the irrigation water allocation process; the expression of the optimization objective function is: Among them, ΔQ 不足,i is the water shortage of the i-th water-deficient area, ΔQ 过剩,j is the excess water volume of the jth water-oversupplied area, N2 represents the number of water-undersupplied areas; M2 represents the number of water-oversupplied areas; Set optimization constraints: Set corresponding constraints, including that the water supply of each area cannot exceed its maximum water supply capacity Q 供水,max , and the water demand of each area should be met; expressed as: Among them, Q 供水,i is the actual water supply in the ith area, Q 供水,max,i is the maximum water supply capacity of the i-th region, Q 需求,i is the water demand of the ith region; Apply optimization algorithm: Use optimization algorithm based on linear programming to solve and obtain the best water resource allocation optimization plan to minimize the objective function and meet the constraints; Generate optimization plan: Based on the calculation results of the optimization algorithm, generate a specific irrigation water allocation optimization plan, including the final water supply and scheduling time of each area, and the water resource allocation method between areas.

9. The irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction according to claim 1, characterized in that: The optimization scheduling module includes a solution receiving unit and a scheduling execution unit; wherein: Solution receiving unit: used to receive the irrigation water source allocation optimization solution provided by the data integration and analysis module, and analyze the received optimization solution to provide basic data for subsequent scheduling execution; The scheme receiving unit comprises: Scheme analysis subunit: used to analyze the target area, water allocation and scheduling priority information in the optimization scheme to form standardized scheduling instructions; Task allocation subunit: used to allocate the parsed dispatching instructions to different pipe network nodes and pump station equipment; Scheduling execution unit: used to dynamically schedule the water source in the irrigation network according to the scheduling instructions provided by the scheme receiving unit; The scheduling execution unit comprises: Flow control subunit: adjusts the water flow of each pipe network node through real-time control of the flow regulating valve; Pump station dispatch subunit: used to control pump station equipment, including starting, stopping and adjusting the operating power of the pump station.

10. The irrigation network water distribution optimization system based on regional water supply and demand analysis and prediction according to claim 9, characterized in that: The solution analysis subunit includes: Parse target area information: Extract target area information in the optimization plan, including the unique identifier R of each area i and its region name; among them, R i is the identifier of the i-th target area; Analyze the water allocation information: Extract the water allocation Q for each target area from the optimization plan 分配,i , the calculation of the amount of water distributed is verified by the following formula: Q 分配,i =min(D i , Q 供水,max,i ), where Q 分配,i is the actual amount of water allocated to the i-th water-deficient area; D i is the water demand of the ith area; Q 供水,max,i is the maximum water supply capacity of the ith area; Parse the scheduling priority information: Determine the scheduling priority P of each area based on the scheduling priority information in the optimization plan. i , the expression is: Among them, P i is the scheduling priority of the ith region; α, β, γ are weight coefficients; D i is the water demand of the ith area; Q 供水,max,i is the maximum water supply capacity of the ith area; S i is the soil moisture index of the ith region; T i is the crop growth stage index of the ith region; Generate standardized dispatch instructions: Generate standardized dispatch instruction format, the instruction includes the target area identifier R i , water distribution Q 分配,i And the scheduling priority P i .

Images