A canal system water gate collaborative scheduling method and system based on supply and demand water prediction

Abstract

The present application relates to a kind of canal system water gate collaborative scheduling method and system based on supply and demand water prediction, belong to water conservancy engineering intelligent scheduling technical field.Pass through the supply and demand water quantity prediction model of multi-time scale of multi-source data fusion construction, and output water demand prediction result, and the water supply of water source;According to the water supply of each period, water demand carries out supply and demand balance analysis;Construction irrigation area water resources scheduling model, formulate irrigation area water resources scheduling scheme;With the minimum channel water loss, multi-water gate collaborative scheduling as goal establishes irrigation area global water distribution coordination model, the sum of each branch canal and following channel water distribution is approximately equal to water distribution main canal design flow, water distribution flow is evenly used as constraint condition, carries out global optimization to collaborative scheduling strategy.The present application realizes the dynamic collaborative scheduling of multiple water gates in the region by multi-source data fusion, accurate prediction of water demand, inflow prediction and multi-objective collaborative optimization algorithm, improves water resources utilization efficiency and scheduling reliability.

Description

Technical Field

[0001] This invention relates to a method and system for coordinated scheduling of canal sluice gates based on water supply and demand forecasting, belonging to the field of intelligent scheduling technology for water conservancy projects. Background Technology

[0002] Water resource allocation is a crucial aspect of irrigation district management, directly impacting irrigation efficiency and water use effectiveness. Sluice gates, as core control facilities in water conservancy projects, perform multiple functions including irrigation, water supply, navigation, and ecological flow regulation, serving as key engineering facilities for controlling water levels and distributing flow. In traditional irrigation district management models, water resource allocation relies heavily on manual experience-based decisions, lacking data support. This leads to difficulties in matching water allocation volume, timing, and sluice gate operation with actual crop needs. Such experience-based allocation easily results in irrigation delays, supply-demand mismatches, and disordered processes, affecting crop growth and exacerbating water waste and supply-demand imbalances.

[0003] With the development of IoT, big data and AI technologies, the system gathers rainfall and soil moisture information from irrigation areas, identifies the current degree of land drought, current rainfall, and future rainfall, manages crop planting types and growth stages in irrigation areas, determines the water requirements of crops, considers various factors to determine water demand, predicts water inflow to irrigation areas, and uses water supply and demand prediction models, water resource scheduling and other water-related models to provide the best solution for the coordinated operation of sluice gates in the canal system. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method and system for coordinated scheduling of canal sluice gates based on water supply and demand prediction. Through multi-source data fusion, accurate water demand prediction, water inflow prediction and multi-objective collaborative optimization algorithm, dynamic coordinated scheduling of multiple sluice gates in the region is realized, thereby improving water resource utilization efficiency and scheduling reliability.

[0005] The technical solution adopted in this invention is as follows: A method for coordinated scheduling of canal system sluice gates based on water supply and demand forecasting includes the following steps: S1. Collect multi-source data from the irrigation area and preprocess it; S2. Based on historical and real-time data, as well as the crop planting structure and crop irrigation quota data of the irrigation area, construct a multi-time-scale water supply and demand prediction model, and output the regional and type water demand prediction results for future time periods, as well as the available water supply of the water source. S3. Conduct a supply and demand balance analysis based on the available water supply and demand for each time period to determine whether to "determine demand based on supply" or "supply water as needed"; S4. Construct a water resource scheduling model for the irrigation district and formulate a water resource scheduling plan for the irrigation district: First, based on the topological relationship map of the irrigation district, obtain the data of the main canals and branch canals associated with water users. Then, calculate the water demand and water demand period information of the coverage area of ​​each main and branch canal as input. Use the elevation information of the main canal to construct the irrigation district canal system water transmission and distribution optimization decision model, and obtain the water transmission and distribution volume and duration information of the main and branch canals. Based on the water supply and demand forecast results of the irrigation area, the total water diversion flow and water volume for each time period are determined, and water allocation priority is set according to the location of the water user, as well as the application time, crop planting structure and urgency. Then, the main and branch canals required for water distribution to water users, as well as the associated sluice gates, are analyzed. Water is released from the source sluice gate and multiple sluice gates along the line are opened in sequence to coordinate multiple sluice gates. The water level, flow rate, and sluice gate opening are monitored at all times to ensure that the canals do not overflow during the scheduling process and that the sluice gates are opened and closed within a safe range. S5. To establish a coordinated water distribution model for the entire irrigation area with the goal of minimizing water conveyance loss in the canals and coordinating the scheduling of multiple sluice gates, a global optimization of the coordinated scheduling strategy is performed, with the constraints that the sum of the water distribution volume of each branch canal and the downstream canals is approximately equal to the design flow of the main water distribution canal and that the water distribution flow is uniform. S6. Distribute the collaborative scheduling strategy to each sluice gate for execution, and continuously optimize the model parameters through real-time data feedback.

[0006] The multi-source data mentioned in step S1 of the above method includes meteorological, hydrological, soil moisture, water demand, and engineering data.

[0007] In step S2, the set of factors related to crop water demand in the irrigation area is used as input. The mathematical statistics, multiple regression, and BP (Back Propagation) neural network methods are used to construct a dynamically updated dataset as training samples. The model parameters are continuously optimized through an adaptive mechanism. After multiple rounds of model training and cross-validation, a water supply and demand prediction model with both interpretability and high accuracy is finally constructed.

[0008] In step S3, the available water volume analysis is based on the analysis of the total amount of water that can be drawn from the water source, the water inflow process, and the water supply capacity of the canals to determine the available water volume for each time period; the irrigation water demand analysis uses the monitoring data obtained from the irrigation area monitoring points, combined with the water demand information of each water user, and integrates it with drought monitoring data and crop planting structure extracted data to achieve a judgment on the supply and demand balance of the irrigation area.

[0009] In step S3, for "supply-driven demand", under the premise that the available water supply is certain, it is analyzed whether the available water supply can meet the irrigation needs of crops throughout the year or within a certain irrigation season. If it cannot meet the water requirements of crops, the irrigation system is adjusted and the planting structure is optimized so that the available water supply can meet the irrigation needs of crops. If it can meet the needs, there is no need to change the planting structure. For "demand-driven water supply", under the conditions that the water source project has sufficient regulation capacity, sufficient water supply, and sufficient water transmission capacity of the water transmission and distribution project, water is supplied according to the water requirements of crops in the irrigation area.

[0010] In step S5, the objective function of the model is determined as follows: , in The sum of the water distribution volume, , , These are the required water volumes for each distribution channel. Water transport losses in upstream and downstream channels during the cycle, in meters. 3 , The permeability coefficients of the upper and lower canal beds; T represents the rotation period. Indicates the water distribution period; The permeability index of the upper and lower canal beds; For the lower-level channel serial number; The length of water conveyance in the upstream and downstream channels; For the water delivery time of upstream and downstream channels; Water flow rate (m) for upstream and downstream channels 3 / s; Input parameters: water demand forecast, current opening of each sluice gate, flow data, river topology, upstream and downstream connections, length, roughness, and scheduling constraints (such as minimum ecological flow, maximum gate opening, and flood control level threshold). Optimization objectives: To ensure the multi-objective optimization function and guarantee water supply for water users: minimize the deviation between water demand and actual water supply; energy consumption optimization objective: minimize the total energy consumption of sluice gate opening and closing mechanism; water level stability objective: minimize upstream and downstream water level fluctuations; ecological constraints: ensure that the flow rate at key sections is greater than or equal to the ecological base flow rate.

[0011] Solution Algorithm: Combining the discrete characteristics of sluice gate scheduling, the scheduling strategy is globally optimized, and the opening instructions of each sluice gate in different time periods for the next 24 hours are output.

[0012] A canal system sluice gate collaborative scheduling system based on water supply and demand forecasting includes a multi-source data acquisition and preprocessing module, a water supply and demand forecasting module, a water supply and demand balance analysis module, an irrigation district water resource scheduling module, a collaborative scheduling strategy optimization module, a scheduling strategy issuance and execution module, and a real-time data feedback and model optimization module. The multi-source data acquisition and preprocessing module includes a data acquisition unit and a preprocessing unit, which collects all elements of water demand and water inflow related to the irrigation area, and performs cleaning, fusion and standardization processing. The water supply and demand forecasting module constructs a multi-time-scale water supply and demand forecasting model based on historical and real-time data, and outputs regional and type-specific water demand forecasts and water supply forecasts for future time periods. The supply and demand balance analysis module performs supply and demand balance analysis based on the available water supply and demand in each time period to determine whether to "determine demand based on supply" or "supply water as needed"; The irrigation district water resource scheduling module includes an irrigation district canal system water transmission and distribution optimization decision-making module, a water distribution priority determination module, and a multi-sluice gate safety coordination module. The irrigation district canal system water transmission and distribution optimization decision-making module constructs an irrigation district canal system water transmission and distribution optimization decision-making model to obtain information on the water transmission and distribution volume and duration of main and branch canals. The water distribution priority determination module determines the total water diversion flow and time period water volume based on the irrigation district water supply and demand forecast results, and sets the water distribution priority according to the location of water users, application time, crop planting structure, and urgency. The multi-sluice gate safety coordination module analyzes the main and branch canals and associated sluice gates required by water users for water distribution, and coordinates the multi-sluice gates by opening the water source sluice gate and opening multiple sluice gates along the line in sequence. It monitors the water level, flow rate, and sluice gate opening degree of the canals at all times to ensure that the canals do not overflow and that the sluice gate opening and closing are within the safe range during the scheduling process. The collaborative scheduling strategy optimization module establishes a water distribution coordination model for the entire irrigation area with the goal of minimizing channel water conveyance loss and coordinating the scheduling of multiple sluice gates. It uses the constraint that the sum of the water distribution volume of each branch canal and downstream canals is approximately equal to the design flow of the main water distribution canal and that the water distribution flow is uniform to perform global optimization of the collaborative scheduling strategy. The scheduling strategy distribution and execution module distributes the coordinated scheduling strategy to each sluice gate for execution; The real-time data feedback and model optimization module continuously optimizes model parameters through real-time data feedback.

[0013] The beneficial effects of this invention are: (1) By integrating multi-source data and water supply and demand professional models, the accuracy of water demand prediction is greatly improved compared with traditional statistical methods, effectively reducing the problems of "water oversupply" or "water undersupply". (2) By achieving dynamic coordination of regional sluice gate groups through multi-objective optimization, the energy consumption of ineffective water supply can be reduced, while ensuring that the ecological flow meets the standards and taking into account the gate opening, making the scheduling strategy smoother, reducing the wear of the gate mechanical structure, and extending the service life of the equipment. (3) By using water supply and demand prediction models and water resource scheduling models, a closed-loop management system is formed for water demand, water supply, water distribution, and water distribution feedback optimization. The prediction-pre-action mode fundamentally changes the logical timing of scheduling. By accurately matching supply and demand, the system minimizes water wastage caused by improper scheduling and improves water resource utilization efficiency. Combined with real-time feedback and model self-updating mechanism, the system can quickly adjust scheduling strategies according to scenarios such as sudden weather changes and surges in water demand. The response time is ≤30 minutes, which has good economic and social benefits. Attached Figure Description

[0014] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0015] The present invention will be further described below with reference to specific embodiments.

[0016] Example 1: A method for coordinated scheduling of canal system sluice gates based on water supply and demand forecasting, comprising the following steps: S1. Collect multi-source data from the irrigation district and preprocess it: Real-time collection of all relevant data in the irrigation area, including rainfall, soil moisture, engineering conditions, and water conditions, followed by cleaning, fusion, and standardization, to provide data support for subsequent forecasting and scheduling.

[0017] Multi-source data includes meteorological, hydrological, soil moisture, water demand, and engineering data.

[0018] Meteorological data: Rainfall, evaporation, temperature, wind speed, etc. are obtained through weather stations, rain gauges, satellite remote sensing, or third-party APIs; Hydrological data: Obtain water level, flow rate, and water quality of rivers / channels through hydrological stations, water level gauges, and flow meters; Soil moisture data: Obtain data from soil moisture stations distributed throughout the irrigation district, including soil moisture content data; Water demand data: Based on the type of crops planted by water users and the irrigation quota, the water demand of different crops at different growth stages is automatically determined. Operational data: Real-time operating parameters such as the opening degree, hoist status, and energy consumption of each sluice gate are obtained through PLC controllers or IoT terminals; Data preprocessing: Linear interpolation and random forest interpolation are used to impute missing values, detect outliers, and align time series data on the original data. Timestamps are standardized to the minute level, and a standardized dataset is output.

[0019] S2. Based on historical and real-time data, as well as the crop planting structure and irrigation quota data of the irrigation area, a multi-time-scale water supply and demand prediction model is constructed, and the prediction results of water demand by region and type for future time periods, as well as the available water supply from the water source, are output: Based on historical and real-time data, a multi-timescale water supply and demand forecasting model is constructed, outputting regional and type-specific water demand forecasts for the next 72 hours.

[0020] Using relevant factors of the irrigation district as input, and relying on historical and real-time data, this study integrates multi-source information such as meteorological, soil, crop growth, and soil moisture data, as well as data on the total amount of water that can be drawn from the water source, the water inflow process, and the water supply capacity of the canals. It also incorporates localized parameters such as crop planting structure, irrigation quotas, and crop coefficients within the irrigation district. By comprehensively utilizing mathematical statistics, multiple regression, and backpropagation (BP) neural network methods, a dynamically updated dataset is constructed as training samples, and model parameters are continuously optimized through an adaptive mechanism. After multiple rounds of model training and cross-validation, a water supply and demand prediction model with both interpretability and high accuracy is finally constructed, providing scientific support for the optimal allocation of water resources and irrigation decisions in the irrigation district.

[0021] S3. Conduct a supply-demand balance analysis based on the available water supply and demand for each time period to determine whether to adopt a "supply-driven demand" or "demand-driven water supply" approach: (1) Water supply analysis: Based on the analysis of the total amount of water that can be drawn from the water source, the water inflow process, and the water supply capacity of the channel, the water supply volume for each period is determined; (2) Irrigation water demand analysis: By using the monitoring data of the irrigation area monitoring points, combined with the water demand information of each water user, and at the same time merging with drought monitoring and crop planting structure data, the water demand perception and prediction of the irrigation area can be realized. (3) Supply and demand balance analysis: Based on the water source situation, there are two situations: "supply determines demand" and "supply water according to demand". "Supply-driven demand": Given a fixed water supply, analyze whether the available water can meet the irrigation needs of crops throughout the year or within a specific irrigation season. If it cannot, adjust the irrigation system and optimize the planting structure to ensure the available water meets the crop's irrigation needs. If it does, no change to the planting structure is necessary. "On-demand water supply": Under the conditions of sufficient water source regulation capacity, adequate water supply volume, and sufficient water transmission capacity, supply water according to the water requirements of crops in the irrigation area.

[0022] S4. Construct a water resource scheduling model for the irrigation district and formulate a water resource scheduling plan for the irrigation district: Based on the water supply and demand forecast results of the irrigation area, and combined with water condition monitoring data such as the remotely controlled sluice gate project of the irrigation area's main and branch canals, a water resource scheduling model for the irrigation area is constructed. Water resource scheduling schemes for the irrigation area under different water resource allocation schemes are formulated to scientifically allocate water in the irrigation area and realize the generation of water resource scheduling schemes, simulation demonstration of the water resource scheduling process, and analysis and evaluation.

[0023] Taking into account the needs of minimizing water transmission and distribution losses and ensuring stable water flow in the irrigation area, this study explores suitable optimization objectives for water transmission and distribution in the irrigation area's canal system. Using information such as water demand and time periods for each branch canal's coverage area as input, an optimization decision-making model for the irrigation area's canal system's water transmission and distribution is constructed. This model yields information such as the water transmission and distribution volume and duration of the main and branch canals, providing an optimization decision-making method for the scheduling of water transmission and distribution in the irrigation area's canal system. Constraints in the water resource scheduling component include main canal flow constraints, surface water supply constraints, water balance constraints, and time constraints.

[0024] Based on the water supply and demand forecasts for the irrigation district, the total water diversion flow and the water volume for each time period are determined. Water allocation priorities are set according to the location of water users, the application time, crop planting structure, and urgency.

[0025] The system analyzes the main and branch canals and associated sluice gates required for water distribution to water users. It coordinates the opening of multiple sluice gates by opening the sluice gate at the water source and opening multiple sluice gates along the line in sequence. It monitors the water level, flow rate, and sluice gate opening at all times to ensure that the canals do not overflow and that the sluice gates are opened and closed within a safe range during the scheduling process.

[0026] A coordinated water distribution model for the entire irrigation district was established with the goal of minimizing water conveyance loss in the channels and coordinating the scheduling of multiple sluice gates. The model takes the sum of the water distribution volume of each branch canal and downstream channels as approximately equal to the design flow of the main water distribution canal and the uniformity of the water distribution flow as constraints.

[0027] The objective function of the model is determined as follows: , The sum of the water distribution volume, , , These are the required water volumes for each distribution channel. Water transport losses in upstream and downstream channels during the cycle, in meters. 3 , The permeability coefficients of the upper and lower canal beds; T represents the rotation period. Indicates the water distribution period; The permeability index of the upper and lower canal beds; For the lower-level channel serial number; The length of water conveyance in the upstream and downstream channels; For the water delivery time of upstream and downstream channels; Water flow rate (m) for upstream and downstream channels 3 / s; Input parameters: water demand forecast, current opening of each sluice gate, flow data, river topology, upstream and downstream connections, length, roughness, and scheduling constraints (such as minimum ecological flow, maximum gate opening, and flood control level threshold). Optimization objectives: To ensure the multi-objective optimization function and guarantee water supply for water users: minimize the deviation between water demand and actual water supply; energy consumption optimization objective: minimize the total energy consumption of sluice gate opening and closing mechanism; water level stability objective: minimize upstream and downstream water level fluctuations; ecological constraints: ensure that the flow rate at key sections is greater than or equal to the ecological base flow rate.

[0028] Solution Algorithm: Combining the discrete characteristics of sluice gate scheduling, the scheduling strategy is globally optimized, and the opening instructions of each sluice gate in different time periods for the next 24 hours are output.

[0029] S5. To establish a coordinated water distribution model for the entire irrigation area with the goal of minimizing water conveyance loss in the canals and coordinating the scheduling of multiple sluice gates, a global optimization of the coordinated scheduling strategy is performed, with the constraints that the sum of the water distribution volume of each branch canal and the downstream canals is approximately equal to the design flow of the main water distribution canal and that the water distribution flow is uniform.

[0030] S6. Distribute the collaborative scheduling strategy to each sluice gate for execution, and continuously optimize the model parameters through real-time data feedback.

[0031] The collaborative scheduling strategy is distributed to each sluice gate for execution, and model parameters are continuously optimized through real-time data feedback. The command issuing unit sends scheduling commands to the PLC controllers of each sluice gate via MQTT protocol or industrial Ethernet, supporting remote manual / automatic switching of control modes. Performance evaluation unit: Real-time monitoring of indicators such as water supply, water level, and energy consumption; calculation of actual execution error of scheduling strategies, water supply completion rate, and energy consumption exceedance rate; Model update unit: Based on historical scheduling prediction errors, actual scheduling effects and other data, the parameters of the water demand prediction model and the collaborative scheduling model are updated regularly to improve the system's adaptability.

[0032] Example 2 A canal system sluice gate collaborative scheduling system based on water supply and demand forecasting includes a multi-source data acquisition and preprocessing module, a water supply and demand forecasting module, a water supply and demand balance analysis module, an irrigation district water resource scheduling module, a collaborative scheduling strategy optimization module, a scheduling strategy issuance and execution module, and a real-time data feedback and model optimization module.

[0033] The multi-source data acquisition and preprocessing module includes a data acquisition unit and a preprocessing unit, which collects all elements of water demand and water inflow related to the irrigation area, and performs cleaning, fusion and standardization processing. The water supply and demand forecasting module constructs a multi-timescale water supply and demand forecasting model based on historical and real-time data, and outputs regional and type-specific water demand forecasts and water supply forecasts for future time periods.

[0034] The supply and demand balance analysis module performs supply and demand balance analysis based on the available water supply and demand in each time period to determine whether to "determine demand based on supply" or "supply water as needed"; The irrigation district water resource scheduling module includes an irrigation district canal system water transmission and distribution optimization decision-making module, a water distribution priority determination module, and a multi-sluice gate safety coordination module. The irrigation district canal system water transmission and distribution optimization decision-making module constructs an irrigation district canal system water transmission and distribution optimization decision-making model to obtain information on the water transmission and distribution volume and duration of main and branch canals. The water distribution priority determination module determines the total water diversion flow and time period water volume based on the irrigation district water supply and demand forecast results, and sets the water distribution priority according to the location of water users, application time, crop planting structure, and urgency. The multi-sluice gate safety coordination module analyzes the main and branch canals and associated sluice gates required by water users for water distribution, and coordinates the multi-sluice gates by opening the water source sluice gate and opening multiple sluice gates along the line in sequence. It monitors the water level, flow rate, and sluice gate opening degree of the canals at all times to ensure that the canals do not overflow and that the sluice gate opening and closing are within the safe range during the scheduling process. The collaborative scheduling strategy optimization module establishes a water distribution coordination model for the entire irrigation area with the goal of minimizing channel water conveyance loss and coordinating the scheduling of multiple sluice gates. It uses the constraint that the sum of the water distribution volume of each branch canal and downstream canals is approximately equal to the design flow of the main water distribution canal and that the water distribution flow is uniform to perform global optimization of the collaborative scheduling strategy. The scheduling strategy distribution and execution module distributes the coordinated scheduling strategy to each sluice gate for execution; The real-time data feedback and model optimization module continuously optimizes model parameters through real-time data feedback.

[0035] The above is a further description of the present invention in conjunction with specific embodiments, and the scope of protection of the present invention is not limited thereto.

Claims

1. A method for coordinated scheduling of canal system sluice gates based on water supply and demand forecasting, characterized in that, The steps include the following: S1. Collect multi-source data from the irrigation area and preprocess it; S2. Based on historical and real-time data, as well as the crop planting structure and crop irrigation quota data of the irrigation area, construct a multi-time-scale water supply and demand prediction model, and output the regional and type water demand prediction results for future time periods, as well as the available water supply of the water source. S3. Conduct a supply and demand balance analysis based on the available water supply and demand for each time period to determine whether to "determine demand based on supply" or "supply water as needed"; S4. Construct a water resource scheduling model for the irrigation district and formulate a water resource scheduling plan for the irrigation district: First, based on the topological relationship map of the irrigation district, obtain the data of the main canals and branch canals associated with water users. Then, calculate the water demand and water demand period information of the coverage area of ​​each main and branch canal as input. Use the elevation information of the main canal to construct the irrigation district canal system water transmission and distribution optimization decision model, and obtain the water transmission and distribution volume and duration information of the main and branch canals. Based on the water supply and demand forecast results of the irrigation area, the total water diversion flow and water volume for each time period are determined, and water allocation priority is set according to the location of the water user, as well as the application time, crop planting structure and urgency. Then, the main and branch canals required for water distribution to water users, as well as the associated sluice gates, are analyzed. Water is released from the source sluice gate and multiple sluice gates along the line are opened in sequence to coordinate multiple sluice gates. The water level, flow rate, and sluice gate opening are monitored at all times to ensure that the canals do not overflow during the scheduling process and that the sluice gates are opened and closed within a safe range. S5. To establish a coordinated water distribution model for the entire irrigation area with the goal of minimizing water conveyance loss in the canals and coordinating the scheduling of multiple sluice gates, a global optimization of the coordinated scheduling strategy is performed, with the constraints that the sum of the water distribution volume of each branch canal and the downstream canals is approximately equal to the design flow of the main water distribution canal and that the water distribution flow is uniform. S6. Distribute the collaborative scheduling strategy to each sluice gate for execution, and continuously optimize the model parameters through real-time data feedback.

2. The method for coordinated scheduling of canal system sluice gates based on water supply and demand forecasting according to claim 1, characterized in that, The multi-source data mentioned in step S1 includes meteorological, hydrological, soil moisture, water demand, and engineering data.

3. The method for coordinated scheduling of canal system sluice gates based on water supply and demand forecasting according to claim 1, characterized in that, In step S2, the set of factors related to crop water demand in the irrigation area is used as input. The mathematical statistics, multiple regression, and BP neural network methods are used to construct a dynamically updated dataset as training samples. The model parameters are continuously optimized through an adaptive mechanism. After multiple rounds of model training and cross-validation, the water supply and demand prediction model is finally constructed.

4. The method for coordinated scheduling of canal system sluice gates based on water supply and demand forecasting according to claim 1, characterized in that, In step S3, the available water volume analysis is based on the analysis of the total amount of water that can be drawn from the water source, the water inflow process, and the water supply capacity of the canals to determine the available water volume for each time period; the irrigation water demand analysis uses the monitoring data obtained from the irrigation area monitoring points, combined with the water demand information of each water user, and integrates it with drought monitoring data and crop planting structure extracted data to achieve a judgment on the supply and demand balance of the irrigation area.

5. The method for coordinated scheduling of canal system sluice gates based on water supply and demand forecasting according to claim 1, characterized in that, In step S3, for "supply-driven demand", under the premise that the available water supply is certain, it is analyzed whether the available water supply can meet the irrigation needs of crops throughout the year or within a certain irrigation season. If it cannot meet the water requirements of crops, the irrigation system is adjusted and the planting structure is optimized so that the available water supply can meet the irrigation needs of crops. If it can meet the needs, there is no need to change the planting structure. For "demand-driven water supply", under the conditions that the water source project has sufficient regulation capacity, sufficient water supply, and sufficient water transmission capacity of the water transmission and distribution project, water is supplied according to the water requirements of crops in the irrigation area.

6. The method for coordinated scheduling of canal system sluice gates based on water supply and demand forecasting according to claim 1, characterized in that, In step S5, the objective function of the model is determined as follows: ， The sum of the water distribution volume, , , These are the required water volumes for each distribution channel. Water transport losses in upstream and downstream channels during the cycle, in meters. 3 , The permeability coefficients of the upper and lower canal beds; T represents the rotation period. Indicates the water distribution period; The permeability index of the upper and lower canal beds; For the lower-level channel serial number; The length of water conveyance in the upstream and downstream channels; For the water delivery time of upstream and downstream channels; Water flow rate (m) for upstream and downstream channels 3 / s; Input parameters: water demand forecast, current opening of each sluice gate, flow data, river topology, upstream and downstream connection relationship, length, roughness, and scheduling constraints; Optimization objectives: To ensure the multi-objective optimization function and guarantee water supply for water users: minimize the deviation between water demand and actual water supply; energy consumption optimization objective: minimize the total energy consumption of sluice gate opening and closing mechanisms; water level stability objective: minimize upstream and downstream water level fluctuations; ecological constraints: ensure that the flow rate at key sections is greater than or equal to the ecological baseline flow rate. Solution Algorithm: Combining the discrete characteristics of sluice gate scheduling, the scheduling strategy is globally optimized, and the opening instructions of each sluice gate in different time periods for the next 24 hours are output.

7. A canal system sluice gate coordinated scheduling system based on water supply and demand forecasting, characterized in that, It includes modules for multi-source data acquisition and preprocessing, water supply and demand forecasting, supply and demand balance analysis, irrigation district water resource scheduling, collaborative scheduling strategy optimization, scheduling strategy issuance and execution, and real-time data feedback and model optimization. The multi-source data acquisition and preprocessing module includes a data acquisition unit and a preprocessing unit, which collects all elements of water demand and water inflow related to the irrigation area, and performs cleaning, fusion and standardization processing. The water supply and demand forecasting module constructs a multi-time-scale water supply and demand forecasting model based on historical and real-time data, and outputs regional and type-specific water demand forecasts and water supply forecasts for future time periods. The supply and demand balance analysis module performs supply and demand balance analysis based on the available water supply and demand in each time period to determine whether to "determine demand based on supply" or "supply water as needed"; The irrigation district water resources scheduling module includes an irrigation district canal system water transmission and distribution optimization decision-making module, a water distribution priority determination module, and a multi-sluice gate safety coordination module. The irrigation district canal system water transmission and distribution optimization decision-making module constructs an irrigation district canal system water transmission and distribution optimization decision-making model to obtain information on the water transmission and distribution volume and duration of main and branch canals. The water distribution priority determination module determines the total water diversion flow and time period water volume based on the irrigation district water supply and demand forecast results, and sets the water distribution priority according to the location of water users, application time, crop planting structure, and urgency. The multi-sluice gate safety coordination module analyzes the main and branch canals required for water distribution by water users, as well as the associated sluice gates. It coordinates the multi-sluice gates by opening the water source sluice gate and opening multiple sluice gates along the line in sequence. It monitors the water level, flow rate, and gate opening degree of the canals at all times to ensure that the canals do not overflow during the scheduling process and that the gate opening and closing are within the safe range. The collaborative scheduling strategy optimization module establishes a water distribution coordination model for the entire irrigation area with the goal of minimizing channel water conveyance loss and coordinating the scheduling of multiple sluice gates. It uses the constraint that the sum of the water distribution volume of each branch canal and downstream canals is approximately equal to the design flow of the main water distribution canal and that the water distribution flow is uniform to perform global optimization of the collaborative scheduling strategy. The scheduling strategy distribution and execution module distributes the coordinated scheduling strategy to each sluice gate for execution; The real-time data feedback and model optimization module continuously optimizes model parameters through real-time data feedback.

Images