Canal ecological water resources allocation method based on feedback mechanism

Abstract

The present invention specifically relates to a canal ecological water resource allocation method based on a feedback mechanism. In the rainy season, when a water level gauge detects a rise in the canal water level, the upstream sluice gate is closed or the opening degree is reduced to control the canal water level within a safe range, the switch status of the sluice gate and the regulating gate is adjusted, and the water resource distribution in the basin is regulated to avoid excessive water accumulation in local areas. The working status of the sluice gate and the pump station is automatically adjusted based on real-time monitoring data. The sluice gate is automatically closed when the water level is too high to reduce the downstream flood control pressure. In the dry season, when the water level gauge shows that the water level has dropped to near or below the ecological flow guarantee water level, the upstream sluice gate is opened to increase the canal flow, or the pump station is started to extract water from groundwater, lakes or water storage facilities and inject it into the canal. The water level and flow are automatically monitored. Once it falls below the ecological flow threshold, the sluice gate or pump station is automatically opened to replenish water. In neither the rainy nor the dry season, the water resource allocation of the canal is intelligently adjusted according to the weather forecast data in combination with the weather forecast data.

Description

Technical Field

[0001] The present invention belongs to the field of resource allocation, and in particular relates to a canal ecological water resource allocation method based on a feedback mechanism. Background Art

[0002] Existing methods for allocating ecological water resources for the canal extensively utilize modern information technology, such as remote sensing, IoT sensor networks, and big data analytics. These methods collect real-time water level, flow, water quality, and other water information, and combine it with meteorological forecast data for in-depth analysis. This approach aims to flexibly and rapidly adjust water resource allocation strategies by monitoring water status and future weather trends in real time. This ensures that the canal provides sufficient ecological flow across different seasons and under extreme climate conditions, thereby maintaining the stability and health of the canal's aquatic ecosystem.

[0003] Especially in terms of ecological flow assurance, modern allocation methods strive to maintain the necessary minimum flow in each section of the canal throughout the year and in different seasons through refined management, in order to support the reproduction and growth of aquatic plant and animal populations and maintain the integrity of the ecological chain. However, because the canal's water resources are significantly affected by natural factors such as seasonal precipitation and evaporation, especially the rainy season, which can cause a sharp rise in water levels and lead to flood risks, and the dry season, which can easily lead to a rapid drop in water levels, threatening ecological water requirements. Therefore, accurately controlling and balancing these seasonal differences poses a great challenge to existing water resource allocation methods.

[0004] The reality is that despite the application of numerous advanced technologies to canal water resource management, many existing allocation plans still exhibit limitations when faced with complex and changing weather conditions and highly uncertain ecological demands. On the one hand, the lack of detailed simulations of hydrological processes and accurate predictions of future changes makes it difficult to accurately match the spatiotemporal distribution of water resources with ecological demands. On the other hand, some regulatory measures may fail to fully consider the diversity and complexity of ecosystems and the interactions between different river sections. This makes it difficult to achieve both uniform and sufficient allocation of canal ecological water resources under extreme climatic conditions, making it prone to localized oversaturation or drought-induced shortages. Summary of the Invention

[0005] The purpose of the present invention is to provide a canal ecological water resources allocation method based on a feedback mechanism to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] The present invention provides a canal ecological water resource allocation method based on a feedback mechanism, comprising the steps of:

[0008] During the rainy season: When the water level gauge detects rising canal water levels, it closes or reduces the opening of upstream sluice gates to keep the canal water level within a safe range. It also adjusts the opening and closing status of sluice gates and regulating gates to regulate water resource distribution within the basin and prevent excessive waterlogging in some areas. Real-time monitoring data automatically adjusts the operating status of sluice gates and pumping stations, automatically closing sluice gates when water levels are too high, alleviating downstream flood control pressure.

[0009] During the dry season: When the water level gauge indicates that the water level has dropped to or below the ecological flow guarantee level, the upstream sluice gates are opened to increase the canal flow, or the pumping stations are activated to extract water from groundwater, lakes, or water storage facilities and inject it into the canal. The water level and flow are automatically monitored, and once it falls below the ecological flow threshold, the sluice gates or pumping stations are automatically opened to replenish water.

[0010] In neither rainy nor dry seasons, the water resource allocation of the canal is intelligently adjusted based on weather forecast data.

[0011] Furthermore, combined with weather forecast data, the canal’s water resource allocation is intelligently adjusted based on the weather forecast data. The specific process includes: predicting canal water level and flow changes based on a time series analysis model;

[0012] Integrate real-time hydrological monitoring data;

[0013] Obtain historical hydrological record data for model training and validation;

[0014] Synchronous access to weather forecast data, including rainfall and temperature in the next few hours to days;

[0015] Check and process missing values, and fill in missing hydrological monitoring data through interpolation and average filling;

[0016] Correct outliers to identify and address data points that deviate significantly from the normal range;

[0017] Standardize or normalize the data to ensure that different variables are on the same scale;

[0018] Convert weather forecast data into features related to water level and flow;

[0019] Construct hysteresis characteristics based on the impact of water level and flow changes in historical periods on current conditions;

[0020] Use the LSTM model to prepare training sets, validation sets, and test sets, and divide the time series data into time windows;

[0021] Build a multi-layer LSTM structure and set the input and output dimensions;

[0022] Train the model and adjust hyperparameters;

[0023] The selected LSTM model is trained using historical data, and the model parameters are optimized to minimize the prediction error. The trained model is then input with the latest real-time hydrological data and meteorological forecast data to predict future canal water levels and flows.

[0024] Furthermore, real-time hydrological monitoring data includes water level and flow information at various monitoring points on the canal.

[0025] Furthermore, the characteristics related to water level and flow include accumulated rainfall and temperature difference.

[0026] Furthermore, we set the input dimension to contain features of multiple time steps and the output dimension to contain the predicted target variable.

[0027] Furthermore, hyperparameters including learning rate, number of hidden layer units, batch size, and number of recurrent layers are tuned.

[0028] Furthermore, combined with weather forecast data, the canal's water resource allocation is intelligently adjusted based on the weather forecast data. The specific process includes:

[0029] Based on the prediction of future canal water level and flow, the uniformity of canal ecological water resource allocation is calculated to evaluate the uniformity of ecological flow distribution;

[0030] The following variables are used to calculate the uniformity of the canal's ecological water resources allocation:

[0031] Q i (t): represents the predicted flow value of the i-th river section in the future time period t;

[0032] E i : represents the ecological water demand of the i-th river section;

[0033] T: the length of the future forecast period, such as days or months;

[0034] N: total number of canal sections; calculate the mean flow rate of each section

[0035] Calculate the flow uniformity index, coefficient of variation V Q ,

[0036] Calculate the ecological water demand satisfaction of each river section like Then the satisfaction is 1, otherwise it is calculated proportionally;

[0037] Calculate the uniformity index U of ecological water demand satisfaction E :

[0038]

[0039] A composite index U is constructed by integrating flow uniformity and ecological water demand satisfaction: U = w_1*V Q +w_2*U E Among them, w_1 and w_2 are weight factors, which are determined according to the relative importance of ecological demand and flow uniformity; then the uniformity of ecological flow distribution is evaluated by the uniformity of canal ecological water resources allocation, which closes the loop feedback of water resources allocation in rainy and dry seasons.

[0040] Furthermore, the uniformity of ecological flow distribution is evaluated based on the uniformity of the canal's ecological water resource allocation, and closed-loop feedback is performed on the allocation of water resources in the rainy season and the dry season. Specifically, if the composite indicator constructed by the comprehensive flow uniformity and the ecological water demand satisfaction does not meet the threshold requirement, closed-loop feedback is performed on the allocation of water resources in the rainy season and the dry season; otherwise, closed-loop feedback on the allocation of water resources in the rainy season and the dry season is not required.

[0041] Beneficial effects: Compared with the background technology, this application significantly improves the adaptability and regulatory efficiency of the canal's ecological water resources in the rainy and dry seasons, effectively solves the problem of uneven water resource allocation caused by weather changes, and realizes the efficient utilization of water resources and the refined guarantee of ecological flow. DETAILED DESCRIPTION

[0042] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0043] This application discloses a canal ecological water resource allocation method based on a feedback mechanism, comprising the following steps:

[0044] During the rainy season:

[0045] When the water level gauge detects a rise in the canal water level, the dispatching center closes or reduces the opening of upstream sluice gates to control the canal water level within a safe range and prevent excessive water levels from damaging the ecological environment and facilities around the canal. At the same time, water storage facilities (such as reservoirs and ponds) are used to store water, making full use of the abundant water resources reserved during the rainy season.

[0046] Sluice and throttle control:

[0047] Adjust the opening and closing status of sluice gates and control gates based on real-time hydrological information to regulate water resource distribution within the basin and avoid excessive waterlogging in some areas;

[0048] Real-time monitoring data automatically adjusts the working status of sluices and pumping stations. For example, when the water level is too high, the sluice gates are automatically closed to reduce the pressure of flood control downstream. In the dry season:

[0049] When the water level gauge shows that the water level has dropped to near or below the ecological flow guarantee level, the dispatching center should open the upstream sluice gate to increase the canal flow, or start the pumping station to extract water from groundwater, lakes or water storage facilities and inject it into the canal;

[0050] If the natural water source is insufficient to maintain ecological flow, the pumping station needs to adjust the operating power and pumping volume as needed based on feedback from the water level gauge and flow meter to ensure that the canal branch does not dry up;

[0051] Automatically monitor water levels and flows, and automatically open sluice gates or pump stations to replenish water once they fall below the ecological flow threshold;

[0052] In the non-rainy and non-dry seasons, the water resource allocation of the canal is intelligently adjusted based on weather forecast data:

[0053] The specific process is:

[0054] The specific process of predicting canal water level and flow changes based on time series analysis model:

[0055] Integrate real-time hydrological monitoring data, including but not limited to water level and flow information at various monitoring points on the canal;

[0056] Obtain historical hydrological record data for model training and validation;

[0057] Synchronous access to weather forecast data, including rainfall and temperature in the next few hours to days;

[0058] Check and process missing values, and fill in missing hydrological monitoring data through interpolation and average filling;

[0059] Correct outliers to identify and address data points that deviate significantly from the normal range;

[0060] Standardize or normalize the data to ensure that different variables are on the same scale;

[0061] Convert weather forecast data into features related to water level and flow, such as accumulated rainfall and temperature difference;

[0062] Construct hysteresis characteristics based on the impact of water level and flow changes in historical periods on current conditions;

[0063] Use the LSTM model (Long Short-Term Memory Network) to predict future canal water levels and flows: Prepare training, validation, and test sets, and divide the time series data into time windows; Build a multi-layer LSTM structure, set the input dimension (including features of multiple time steps) and the output dimension (predicting the target variable); Train the model and adjust hyperparameters such as the learning rate, number of hidden layer units, batch size, and number of recurrent layers; Use historical data to train the selected LSTM model and optimize the model parameters to minimize prediction error; Use the trained model to input the latest real-time hydrological data and meteorological forecast data to predict future canal water levels and flows;

[0064] Based on the prediction of future canal water level and flow, the uniformity of canal ecological water resource allocation is calculated to evaluate the uniformity of ecological flow distribution;

[0065] The following variables are used to calculate the uniformity of the canal's ecological water resources allocation:

[0066] Q i (t): represents the predicted flow value of the i-th river section in the future time period t;

[0067] E i : represents the ecological water demand of the i-th river section;

[0068] T: the length of the future forecast period, such as days or months;

[0069] N: total number of canal sections; calculate the mean flow rate for each section

[0070] Calculate the flow uniformity index, coefficient of variation V Q ,

[0071] Calculate the ecological water demand satisfaction of each river section like Then the satisfaction is 1, otherwise it is calculated proportionally;

[0072] Calculate the uniformity index U for the satisfaction of ecological water demand E :

[0073]

[0074] A composite index U is constructed by integrating flow uniformity and ecological water demand satisfaction: U = w_1*V Q +w_2*U E Where w_1 and w_2 are weight factors, which are determined based on the relative importance of ecological needs and flow uniformity;

[0075] Then, the uniformity of the canal's ecological water resource allocation is used to evaluate the uniformity of the ecological flow distribution, and closed-loop feedback is provided on the allocation of water resources in the rainy season and the dry season; if the composite indicator constructed by the comprehensive flow uniformity and the ecological water demand satisfaction does not meet the threshold requirements, closed-loop feedback is provided on the allocation of water resources in the rainy season and the dry season; otherwise, closed-loop feedback on the allocation of water resources in the rainy season and the dry season is not required.

[0076] The progress and advantages of this application over the existing technology are reflected in the following aspects: 1. Refined dynamic regulation: The technical solution of this application introduces real-time monitoring data and weather forecast data, combined with the feedback information of the water level meter and flow meter, to achieve refined and automated regulation of the canal water level and flow, and improve the accuracy and timeliness of water resource allocation. 2. Rainy season water resource utilization and flood control: In response to the risk of floods in the rainy season, this application proposes to close or reduce the opening degree of the upstream sluice gate when the water level rises, and use water storage facilities to store water resources, which not only ensures the safety of the ecological environment and facilities around the canal, but also effectively utilizes the abundant water resources in the rainy season. 3. Dry season ecological flow guarantee: In the dry season, when the water level drops to close to or below the ecological flow guarantee water level, this method can promptly open the upstream sluice gate to increase the flow or start the pump station to supplement the water source to ensure that the ecological flow is met. At the same time, the operating power and pumping volume of the pump station can be dynamically adjusted according to real-time monitoring data, reducing the risk of canal branches drying up. 4. Intelligent prediction and configuration: An LSTM model based on time series analysis is adopted. By integrating, processing and analyzing real-time hydrological monitoring data, historical hydrological record data and meteorological forecast data, accurate predictions of future canal water levels and flows are achieved, providing a scientific basis for water resource allocation. 5. Assessment of the uniformity of ecological water resource allocation: This application innovatively proposes a method for calculating the uniformity of the canal's ecological water resource allocation. Taking into account the two core indicators of flow uniformity and ecological water demand satisfaction, a composite evaluation index U is constructed to ensure the uniformity of the canal's ecological flow distribution, making up for the problem that existing technologies have paid insufficient attention to the uniformity of water resource allocation. 6. Closed-loop feedback mechanism: This scheme emphasizes the role of closed-loop feedback. According to the assessment results of the canal's ecological water resource allocation uniformity, the water resource allocation strategy in the rainy and dry seasons is adjusted in real time to ensure that under various climatic conditions, the canal can achieve effective protection of ecological flow and balanced allocation of water resources. To sum up, compared with the background technology, this application significantly improves the adaptability and regulatory efficiency of the canal's ecological water resources in the rainy and dry seasons, effectively solves the problem of uneven water resource allocation caused by weather changes, and realizes the efficient utilization of water resources and the refined guarantee of ecological flow.

[0077] The embodiments that require protection in this application include:

[0078] The canal ecological water resource allocation method based on a feedback mechanism includes the following steps: During the rainy season: when the water level gauge detects a rise in the canal water level, it closes or reduces the opening of the upstream sluice gate to control the canal water level within a safe range, adjusts the opening and closing status of the sluice gate and regulating gate, regulates the distribution of water resources within the basin, and avoids excessive waterlogging in some areas; real-time monitoring data automatically adjusts the working status of the sluice gate and pump station, and automatically closes the sluice gate when the water level is too high, reducing the pressure on downstream flood control;

[0079] During the dry season: When the water level gauge indicates that the water level has dropped to or below the ecological flow guarantee level, the upstream sluice gates are opened to increase the canal flow, or the pumping stations are activated to extract water from groundwater, lakes, or water storage facilities and inject it into the canal. The water level and flow are automatically monitored, and once it falls below the ecological flow threshold, the sluice gates or pumping stations are automatically opened to replenish water.

[0080] In neither rainy nor dry seasons, the water resource allocation of the canal is intelligently adjusted based on weather forecast data.

[0081] Preferably, the water resource allocation of the canal is intelligently adjusted based on the weather forecast data in combination with the weather forecast data, and the specific process includes: predicting the changes in the canal water level and flow based on the time series analysis model;

[0082] Integrate real-time hydrological monitoring data;

[0083] Obtain historical hydrological record data for model training and validation;

[0084] Synchronous access to weather forecast data, including rainfall and temperature in the next few hours to days;

[0085] Check and process missing values, and fill in missing hydrological monitoring data through interpolation and average filling;

[0086] Correct outliers to identify and address data points that deviate significantly from the normal range;

[0087] Standardize or normalize the data to ensure that different variables are on the same scale;

[0088] Convert weather forecast data into features related to water level and flow;

[0089] Construct hysteresis characteristics based on the impact of water level and flow changes in historical periods on current conditions;

[0090] Use the LSTM model to prepare training sets, validation sets, and test sets, and divide the time series data into time windows;

[0091] Build a multi-layer LSTM structure and set the input and output dimensions;

[0092] Train the model and adjust hyperparameters;

[0093] The selected LSTM model is trained using historical data, and the model parameters are optimized to minimize the prediction error. The trained model is then input with the latest real-time hydrological data and meteorological forecast data to predict future canal water levels and flows.

[0094] Preferably, real-time hydrological monitoring data includes water level and flow information at each monitoring point in the canal. Features related to water level and flow include accumulated rainfall and temperature difference. The input dimension is set to include features with multiple time steps, and the output dimension is set to include the predicted target variable. Hyperparameters to adjust include the learning rate, number of hidden units, batch size, and number of recurrent layers.

[0095] Preferably, the water resource allocation of the canal is intelligently adjusted according to the weather forecast data in combination with the weather forecast data. The specific process includes:

[0096] Based on the prediction of future canal water level and flow, the uniformity of canal ecological water resource allocation is calculated to evaluate the uniformity of ecological flow distribution;

[0097] The following variables are used to calculate the uniformity of the canal's ecological water resources allocation:

[0098] Q i (t): represents the predicted flow value of the i-th river section in the future time period t;

[0099] E i : represents the ecological water demand of the i-th river section;

[0100] T: the length of the future forecast period, such as days or months;

[0101] N: total number of canal sections; calculate the mean flow rate for each section

[0102] Calculate the flow uniformity index, coefficient of variation V Q ,

[0103] Calculate the ecological water demand satisfaction of each river section like Then the satisfaction is 1, otherwise it is calculated proportionally;

[0104] Calculate the uniformity index U for the satisfaction of ecological water demand E :

[0105]

[0106] A composite index U is constructed by integrating flow uniformity and ecological water demand satisfaction: U = w_1*V Q +w_2*U EWhere w_1 and w_2 are weighting factors, determined based on the relative importance of ecological demand and flow uniformity. The uniformity of the canal's ecological water resource allocation is then used to assess the uniformity of ecological flow distribution, providing closed-loop feedback on the allocation of water resources between the rainy and dry seasons. Specifically, if the composite indicator constructed by integrating flow uniformity and ecological water demand satisfaction does not meet the threshold requirement, closed-loop feedback on the allocation of water resources between the rainy and dry seasons is performed; otherwise, closed-loop feedback on the allocation of water resources between the rainy and dry seasons is not required.

[0107] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium can be at least one of the following media: read-only memory (English: Read-only Memory, abbreviated: ROM), RAM, magnetic disk or optical disk, etc., various media that can store program codes.

[0108] The present application also discloses an electronic device, comprising a computer-readable storage medium, wherein the storage medium is used to store a computer program, and the computer program is used to execute the data processing steps of the above embodiment.

[0109] The above is merely one specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A canal ecological water resources allocation method based on feedback mechanism, characterized in that: Including steps: During the rainy season: When the water level gauge detects rising canal water levels, it closes or reduces the opening of upstream sluice gates to keep the canal water level within a safe range. It also adjusts the opening and closing status of sluice gates and regulating gates to regulate water resource distribution within the basin and prevent excessive waterlogging in some areas. Real-time monitoring data automatically adjusts the operating status of sluice gates and pumping stations, automatically closing sluice gates when water levels are too high, alleviating downstream flood control pressure. During the dry season: When the water level gauge indicates that the water level has dropped to or below the ecological flow guarantee level, the upstream sluice gates are opened to increase the canal flow, or the pumping stations are activated to extract water from groundwater, lakes, or water storage facilities and inject it into the canal. The water level and flow are automatically monitored, and once it falls below the ecological flow threshold, the sluice gates or pumping stations are automatically opened to replenish water. In the non-rainy and non-dry seasons, the water resource allocation of the canal is intelligently adjusted based on weather forecast data; the specific process includes: predicting the changes in canal water level and flow based on time series analysis models; Integrate real-time hydrological monitoring data; Obtain historical hydrological record data for model training and validation; Synchronous access to weather forecast data, including rainfall and temperature in the next few hours to days; Check and process missing values, and fill in missing hydrological monitoring data through interpolation and average filling; Correct outliers to identify and address data points that deviate significantly from the normal range; Standardize or normalize the data to ensure that different variables are on the same scale; Convert weather forecast data into features related to water level and flow; Construct hysteresis characteristics based on the impact of water level and flow changes in historical periods on current conditions; Use the LSTM model to prepare training sets, validation sets, and test sets, and divide the time series data into time windows; Build a multi-layer LSTM structure and set the input and output dimensions; Train the model and adjust hyperparameters; The selected LSTM model is trained using historical data, and the model parameters are optimized to minimize the prediction error. The trained model is then input with the latest real-time hydrological data and meteorological forecast data to predict future canal water levels and flows.

2. The canal ecological water resource allocation method based on feedback mechanism according to claim 1 is characterized in that: Real-time hydrological monitoring data, including water level and flow information at each monitoring point on the canal.

3. The canal ecological water resource allocation method based on feedback mechanism according to claim 2 is characterized in that: Characteristics related to water level and flow include accumulated rainfall and temperature difference.

4. The canal ecological water resource allocation method based on feedback mechanism according to claim 3 is characterized in that: Set the input dimension to contain features over multiple time steps and the output dimension to contain the predicted target variable.

5. The canal ecological water resource allocation method based on feedback mechanism according to claim 4 is characterized in that: The hyperparameters to be adjusted include learning rate, number of hidden layer units, batch size, and number of recurrent layers.

Images