Optimal scheduling method and system for water network regulation and storage engineering

Abstract

The application discloses an optimal scheduling method and system for water network storage engineering, relates to the technical field of water network storage engineering, and comprises a collection module, a preprocessing module, a prediction module, a generation module, an evaluation module and a feedback module. The system combines the real-time operation state of engineering with multi-target optimization logic to generate a candidate scheduling scheme, selects an optimal scheme by evaluating water resource utilization rate, engineering operation stability and cost consumption, effectively integrates multi-source real-time data, realizes dynamic adjustment and accurate prediction, constitutes a collaborative scheduling mechanism across basins and engineering, ensures optimal operation of engineering at all times, effectively improves water resource utilization rate, engineering operation stability, reduces cost, enhances scheduling adaptability and reliability, and effectively plays the overall benefit of the water network through the efficient emergency response capability of the overall storage system when a single water source or local engineering is abnormal.

Description

Technical Field

[0001] This invention relates to the field of water network regulation and storage engineering technology, specifically to an optimized scheduling method and system for water network regulation and storage engineering. Background Technology

[0002] As a core infrastructure for regional water resource allocation and water security, water network regulation and storage projects play a crucial role in coordinating multiple water sources such as rivers, lakes, and reservoirs to achieve multiple objectives, including flood control and disaster reduction, urban and rural water supply, and ecological water replenishment. With the acceleration of urbanization and the frequent occurrence of extreme weather events, the contradiction between water supply and demand in the region is becoming increasingly prominent, placing higher demands on the scheduling efficiency and flexibility of water network regulation and storage projects.

[0003] Currently, the industry mostly uses experience-based scheduling modes or simple mathematical models based on historical data for scheduling. Although these can meet basic operational needs, information technologies such as the Internet of Things and big data are gradually being introduced to try to improve the real-time performance and scientific nature of scheduling, laying the foundation for the subsequent research and development of optimized scheduling systems.

[0004] However, current water network regulation and storage engineering scheduling technologies in the industry still have shortcomings. Existing scheduling systems have weak data fusion capabilities, cannot effectively integrate multi-source real-time data, and are difficult to achieve dynamic adjustment and accurate prediction. Furthermore, they lack cross-basin and cross-project collaborative scheduling mechanisms. When a single water source or local project experiences an anomaly, the overall regulation and storage system's emergency response capability is insufficient, failing to fully realize the overall benefits of the water network.

[0005] To address the problems existing in the above-mentioned technologies, our research team proposes an optimized scheduling method and system for water network regulation and storage projects. Summary of the Invention

[0006] In order to overcome the shortcomings of the prior art, the purpose of this invention is to provide an optimized scheduling method and system for water network regulation and storage projects.

[0007] On one hand, the present invention provides an optimized scheduling system for water network regulation and storage projects, comprising the following modules:

[0008] The data acquisition module is used to collect real-time water volume and water quality parameters of the water source belonging to the water network regulation and storage project, real-time pressure and flow of each node of the pipeline network, real-time volume and water level of the water storage body, and real-time meteorological parameters of the area covered by the project.

[0009] The preprocessing module receives data collected by the acquisition module and performs outlier identification, redundancy removal, and format standardization on the data.

[0010] The prediction module is used to acquire preprocessed data and apply the preprocessed data to predict the water demand and water storage demand in the water network coverage area.

[0011] The generation module is used to obtain the prediction results from the prediction module. Based on the prediction results, it integrates the real-time operation status of the water network regulation and storage project with multi-objective optimization logic to generate several candidate optimization scheduling schemes.

[0012] The evaluation module is used to evaluate the water resource utilization rate, engineering operation stability and cost consumption of each candidate optimization scheduling scheme.

[0013] The feedback module is used to obtain the evaluation results, select the most efficient scheduling plan and send it to the water network storage project for execution, collect real-time data of the plan execution to form a plan execution message, and then send the message back to the preset receiving end.

[0014] Furthermore, the parameters collected by the acquisition module include water quality parameters such as pH value, dissolved oxygen concentration, turbidity, and chemical oxygen demand, and meteorological parameters such as rainfall, evaporation, temperature, and relative humidity.

[0015] The acquisition frequency of the acquisition module is dynamically adjusted according to the real-time operation status of the water network regulation and storage project. When the water level of the storage body deviates from the preset normal range or the pressure of the pipeline node exceeds the preset stable range, the acquisition module automatically increases the acquisition frequency of the corresponding parameter.

[0016] Furthermore, the outlier identification logic in the preprocessing module is as follows:

[0017] For any real-time acquired parameter, calculate the mean and standard deviation of the historical acquired data for that parameter within a preset time window, and then calculate the deviation of that parameter. , This represents the collected value of the parameter at time i. This represents the average of historically collected data. Indicates the standard deviation of historically collected data;

[0018] like Greater than the preset deviation coefficient, and If it is not within the allowable range for the corresponding project, then it is judged. Outliers were identified and removed.

[0019] The redundancy removal involves calculating the Pearson correlation coefficient between any two acquired parameters. ,like If the data exceeds the preset threshold, the parameter with the higher data collection frequency will be retained, and redundant data of the other parameter will be removed.

[0020] The format standardization process involves converting all collected parameters into a preset engineering data format, including: standardization of parameter name encoding, data units, and data precision.

[0021] Furthermore, the prediction module uses the following formula to predict water demand in the water network coverage area:

[0022] ;

[0023] In the formula: Let t represent the predicted water demand for the time period. The historical average water consumption for the same period corresponding to time period t; These are the influence coefficients for rainfall, temperature, and population activity intensity. Let t be the predicted rainfall for time period t; The predicted temperature for time period t; The population activity intensity index for time period t;

[0024] Water storage demand forecast: based on The current real-time volume of the water storage body and the inflow volume corresponding to the predicted rainfall in time period t are used to calculate the theoretical volume of the water storage body after time period t ends. If the theoretical volume exceeds the preset safe volume range of the water storage body, a regulation demand signal is generated. The signal strength is set to be positively correlated with the degree to which the theoretical volume deviates from the preset safe volume range.

[0025] in, , , All data originates from the data acquisition module. ∈[0,1], determined with the help of public facility operation data and traffic flow data in the coverage area, where 0 represents no population activity and 1 represents the maximum activity intensity. ∈[-1, 0], and its value is negatively correlated with the amount of rainfall: the greater the rainfall, the closer the value is to -1, and the stronger the inhibitory effect on water demand; the smaller the rainfall, the closer the value is to 0, and the weaker the inhibitory effect on water demand. The value of ∈[0,1] is positively correlated with temperature: the higher the temperature, the closer the value is to 1, and the stronger the effect on promoting water demand; the lower the temperature, the closer the value is to 0, and the weaker the effect on promoting water demand. The value of ∈[0,1] is positively correlated with the intensity of population activity: the greater the intensity of population activity, such as during peak hours on weekdays, the closer the value is to 1, and the stronger the effect on water demand; the smaller the intensity of population activity, such as during late night hours, the closer the value is to 0, and the weaker the effect on water demand.

[0026] Furthermore, the objective of the multi-objective optimization logic in the generation module is:

[0027] Maximize water resource utilization, maximize engineering operational stability, and minimize cost consumption;

[0028] The multi-objective optimization logic performs multi-objective collaborative optimization by quantifying the comprehensive optimization index:

[0029] ;

[0030] In the formula: To comprehensively optimize the index; These are the weighting coefficients for water resource utilization rate, engineering operation stability, and cost consumption. This is a predicted value for water resource utilization rate; This is the predicted value of the engineering operation stability index; This represents the predicted cost of the project per unit of time.

[0031] The above formula revolves around the core objectives of maximizing water resource utilization, maximizing operational stability, and minimizing cost consumption in water network regulation and storage projects. It integrates the predicted values ​​of water resource utilization, operational stability, and unit time cost consumption into a unified comprehensive optimization index. Furthermore, it selects schemes with the comprehensive optimization index falling within a preset excellent range as candidates to ensure scheme quality. Subsequently, it can also use the actual performance parameters output by the evaluation module to provide feedback and correction. The prediction models of S and C form a closed-loop optimization logic of prediction-generation-evaluation-correction.

[0032] The generation module, based on preset engineering operation constraints, including pipeline node pressure, water level in the reservoir, and pump operating power, selects different combinations of weight coefficients within the feasible region and calculates the comprehensive optimization index under the corresponding weight combinations. Filter out Schemes whose values ​​are within a preset good range are used to form several candidate optimized scheduling schemes, and the number of candidate schemes is not less than three.

[0033] in, All are positive numbers and their sum is 1, and the allocation is dynamically adjusted according to the scheduling priority of the water network regulation and storage project. ∈[0,1], estimated based on the water demand and available water resources output by the prediction module. ∈[0,1], estimated based on the preset allowable fluctuation range of pipeline node pressure and the safe range of water level in the reservoir. The unit is yuan / hour, which is estimated based on the rated power of the water pump, the energy consumption of the gate regulation, and historical maintenance cost data.

[0034] The generation module pushes candidate optimized scheduling schemes to the evaluation module for actual performance evaluation. The evaluation results are used to select the optimal scheme in the subsequent process. Furthermore, the actual performance parameters output by the evaluation module—namely, water resource utilization rate, operational stability index, and actual cost consumption—will be fed back into the generation module to correct errors in the next optimization calculation. , , Prediction model parameters.

[0035] Furthermore, the evaluation module's performance evaluation of each candidate optimized scheduling scheme includes:

[0036] Water resource utilization rate:

[0037] ;

[0038] The above formula uses the ratio of actual water usage to total available water resources as its core logic. It clarifies that the actual water supply is the total amount of water supplied by the project to the covered area, while the total available water resources innovatively integrate the real-time water volume of the water source and the adjustable water volume of the storage body. This design fully aligns with the core function of water network regulation and storage projects. It not only considers the immediately available water source volume but also incorporates the regulation potential of the storage body, avoiding misjudgments caused by calculating the available amount solely based on the real-time water source volume. It can more realistically and comprehensively reflect the actual utilization efficiency of water resources and provide accurate quantitative basis for the effectiveness evaluation of subsequent scheduling schemes.

[0039] Operational stability index:

[0040] ;

[0041] The above formula constructs a stability quantification model from two key dimensions of the operation of the water network regulation and storage project: pipeline pressure and water level of the storage body. It reflects the overall stability through the comprehensive calculation of the pressure deviation of pipeline nodes and the water level deviation of the monitoring points of the storage body. It covers the two core indicators of pipeline water supply pressure and water level of the storage body. Furthermore, by calculating the average deviation of multiple nodes and multiple monitoring points, it avoids the interference of local abnormal data on the judgment of overall stability, and realizes a comprehensive and objective quantification of the stability of the project operation.

[0042] Cost consumption:

[0043] ;

[0044] In the formula: This represents the actual water supply to the coverage area after the candidate scheme is implemented; This represents the total available water resources during the implementation of the candidate scheme; This represents the total number of pipeline nodes. The actual pressure of the i-th node in the pipeline network when the candidate scheme is implemented; The design rated pressure for this node; This represents the total number of monitoring points in the water storage body. The actual water level at the j-th monitoring point of the reservoir when the candidate scheme is implemented; This is the design normal water level for this monitoring point; This refers to the energy consumption cost of the water pumps during the implementation of the candidate solution; The pipeline maintenance cost during the implementation of the candidate scheme;

[0045] First, for each monitoring node in the pipeline network, the difference between the maximum and minimum actual pressure at that node during the execution of the candidate scheme is calculated as the pressure fluctuation amplitude of that node. Second, based on the pipe diameter, flow rate, and importance of the pipeline segment to which each node belongs, a preset weight value is established. The larger the pipe diameter, the higher the flow rate, and the more critical the location of the pipeline segment, the greater the weight value of the corresponding node. Combined with the pressure fluctuation amplitude of each node, the average pressure fluctuation level of the entire pipeline network is calculated. Third, for different segments of the pipeline network, a preset maintenance cost benchmark coefficient is established based on their material (such as ductile iron pipe, steel pipe, plastic pipe, etc.), laying environment (such as direct underground burial, overhead laying, etc.), and service life. The weaker the anti-aging performance of the material, the stronger the corrosiveness of the laying environment, and the longer the service life of the pipeline segment, the higher the benchmark coefficient value is. Finally, the average pressure fluctuation level of the entire pipeline network, the maintenance cost benchmark coefficient of the corresponding pipeline segment, and the actual execution time of the candidate scheme are multiplied to obtain the pipeline network maintenance cost during the execution of the candidate scheme.

[0046] in, The sum of the real-time water volume from the water source and the adjustable water volume of the storage tank is taken. The adjustable water volume of the storage tank is the difference between the current volume of the storage tank and the preset minimum safe volume. The product of the water pump's operating power, operating time, and unit electricity price. It is calculated based on the fluctuation range of pipeline operating pressure and the preset maintenance cost coefficient.

[0047] Furthermore, the scheme execution message generated by the feedback module includes:

[0048] The execution start and end timestamps of the plan, the real-time operating parameters of each execution unit, the cumulative actual water supply during the execution period, the change in water storage volume, the water quality change trend data of key nodes of the water source and pipeline network, and abnormal event records;

[0049] The execution unit includes a water pump, a gate, and a water purification device. Real-time operating parameters include the water pump's operating power, the gate's opening degree, and the purification device's processing flow rate.

[0050] Furthermore, during the operation phase of the feedback module, in the process of executing the optimal scheduling scheme, the feedback module synchronously calculates the deviation between the execution data and the prediction data output by the prediction module. If any deviation value continues to exceed the preset deviation threshold for a period of time that reaches the preset time threshold, the prediction module is triggered to re-predict demand based on the latest real-time data, the generation module regenerates candidate optimized scheduling schemes based on the new prediction results, and the evaluation module re-evaluates and selects a new optimal scheme to complete the scheduling scheme update, so that the water network regulation and storage project is always in the optimal operating state.

[0051] The deviation values ​​include deviations in water supply, water level changes, and pressure.

[0052] Furthermore, the acquisition module is interconnected with a preprocessing module via a wireless network, the preprocessing module is interconnected with a prediction module via a wireless network, the prediction module is interconnected with a generation module and an evaluation module via a wireless network, and the evaluation module is interconnected with a feedback module via a wireless network.

[0053] On the other hand, the present invention provides an optimized scheduling method for water network regulation and storage projects, which is executed using the optimized scheduling system for water network regulation and storage projects, and includes the following steps:

[0054] S10. The data acquisition module collects data on water sources, pipelines, water storage bodies, and meteorological parameters of the water network storage and regulation project. When the water level of the water storage body or the pressure of the pipeline is abnormal, the acquisition frequency of the corresponding parameters is automatically increased.

[0055] S20. The preprocessing module removes outliers, filters redundant parameters, and standardizes the format of the collected data, unifying parameter coding, units, and precision.

[0056] S30. The prediction module predicts water demand and calculates the theoretical volume of the water storage body. If the demand exceeds the safe range, it generates a regulation and storage demand signal.

[0057] S40. The generation module integrates the engineering status and multi-objective optimization logic, selects weight combinations based on operational constraints to calculate the optimization index, and screens no less than three candidate solutions.

[0058] S50, the evaluation module calculates the water resource utilization rate, operational stability index and cost consumption of each candidate scheme to complete the performance evaluation;

[0059] S60. The feedback module issues the optimal solution for execution and sends back the running data message. When the deviation between the executed and predicted data exceeds the limit and timeout occurs, the solution is updated again.

[0060] The beneficial effects of this invention are:

[0061] 1. The optimized scheduling system for water network regulation and storage projects of this invention collects real-time data on water source quantity and quality, pipeline node pressure and flow, water storage volume and water level, and meteorological parameters of the covered area through a data acquisition module. It can also dynamically adjust the data acquisition frequency based on the real-time operating status of the project, ensuring data timeliness and relevance. Data quality is improved through outlier identification, redundancy removal, and format standardization, providing support for accurate prediction of water demand and water storage needs. Candidate scheduling schemes are generated by combining the real-time operating status of the project with multi-objective optimization logic. The optimal scheme is selected by evaluating water resource utilization, project operational stability, and cost consumption. This effectively integrates multi-source real-time data, achieving dynamic adjustment and accurate prediction, and forming a cross-basin, cross-project collaborative scheduling mechanism.

[0062] 2. The optimized scheduling method for water network regulation and storage projects of this invention selects the optimal solution through a data acquisition module, a preprocessing module, a prediction module, a generation module, an evaluation module, and a feedback module. During execution, the deviation between the executed data and the predicted data is calculated simultaneously. When the deviation exceeds the threshold and continues to reach the limit, a new prediction is made and a new solution is generated to ensure that the project always operates optimally. This effectively improves water resource utilization, project operation stability, reduces costs, and enhances scheduling adaptability and reliability. When a single water source or local project experiences an anomaly, the efficient emergency response capability of the overall regulation and storage system effectively leverages the overall benefits of the water network. Attached Figure Description

[0063] Figure 1 This is a schematic diagram of the optimized scheduling system for water network regulation and storage projects in Example 1;

[0064] Figure 2 This is a flowchart illustrating the optimized scheduling method for water network regulation and storage projects in Example 2. Detailed Implementation

[0065] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention, but are not intended to limit the present invention.

[0066] Example 1

[0067] Please see Figure 1 An optimized scheduling system for water network regulation and storage projects includes the following modules:

[0068] The data acquisition module is used to collect real-time water volume and water quality parameters of the water source belonging to the water network regulation and storage project, real-time pressure and flow of each node of the pipeline network, real-time volume and water level of the water storage body, and real-time meteorological parameters of the area covered by the project.

[0069] The parameter data includes water quality parameters such as pH value, dissolved oxygen concentration, turbidity and chemical oxygen demand, and meteorological parameters such as rainfall, evaporation, temperature and relative humidity.

[0070] The acquisition frequency of the acquisition module is dynamically adjusted according to the real-time operation status of the water network regulation and storage project. When the water level of the storage body deviates from the preset normal range or the pressure of the pipeline node exceeds the preset stable range, the acquisition module automatically increases the acquisition frequency of the corresponding parameter.

[0071] The preprocessing module receives data collected by the acquisition module and performs outlier identification, redundancy removal, and format standardization on the data.

[0072] The outlier identification logic is as follows: For any real-time acquired parameter, calculate the mean and standard deviation of the historical acquired data for that parameter within a preset time window, and then calculate the deviation of that parameter. , This represents the collected value of the parameter at time i. This represents the average of historically collected data. Indicates the standard deviation of historically collected data;

[0073] like Greater than the preset deviation coefficient, and If it is not within the allowable range for the corresponding project, then it is judged. Outliers were identified and removed.

[0074] The redundancy removal involves calculating the Pearson correlation coefficient between any two acquired parameters. ,like If the data exceeds the preset threshold, the parameter with the higher data collection frequency will be retained, and redundant data of the other parameter will be removed.

[0075] The format standardization process involves converting all collected parameters into a preset engineering data format, including: standardization of parameter name encoding, data units, and data precision.

[0076] The prediction module is used to acquire preprocessed data and apply the preprocessed data to predict the water demand and water storage demand in the water network coverage area.

[0077] The prediction module uses the following formula to predict water demand in the water network coverage area:

[0078] ;

[0079] In the formula: Let t represent the predicted water demand for the time period. The historical average water consumption for the same period corresponding to time period t; These are the influence coefficients for rainfall, temperature, and population activity intensity. Let t be the predicted rainfall for time period t; The predicted temperature for time period t; The population activity intensity index for time period t;

[0080] The above formula uses the historical average water consumption for the same period corresponding to time t as the baseline, fully considers the core influencing factors of water demand in the water network coverage area, and incorporates rainfall, temperature and population activity intensity into the prediction model. The moderating effect of each factor on water demand is quantified by three coefficients. This multi-factor collaborative design not only relies on historical data to ensure the stability of the prediction, but also achieves accurate adaptation to changes in actual water demand through dynamic coefficients and quantitative indicators, avoiding the one-sidedness of single-factor prediction.

[0081] Water storage demand forecast: based on The current real-time volume of the water storage body and the inflow volume corresponding to the predicted rainfall in time period t are used to calculate the theoretical volume of the water storage body after time period t ends. If the theoretical volume exceeds the preset safe volume range of the water storage body, a regulation demand signal is generated. The signal strength is set to be positively correlated with the degree to which the theoretical volume deviates from the preset safe volume range.

[0082] in, , , All data originates from the data acquisition module. ∈[0,1], determined with the help of public facility operation data and traffic flow data in the coverage area, where 0 represents no population activity and 1 represents the maximum activity intensity. ∈[-1, 0], and its value is negatively correlated with the amount of rainfall: the greater the rainfall, the closer the value is to -1, and the stronger the inhibitory effect on water demand; the smaller the rainfall, the closer the value is to 0, and the weaker the inhibitory effect on water demand. The value of ∈[0,1] is positively correlated with temperature: the higher the temperature, the closer the value is to 1, and the stronger the effect on promoting water demand; the lower the temperature, the closer the value is to 0, and the weaker the effect on promoting water demand. The value of ∈[0,1] is positively correlated with the intensity of population activity: the greater the intensity of population activity, such as during peak hours on weekdays, the closer the value is to 1, and the stronger the effect on water demand; the smaller the intensity of population activity, such as during late night hours, the closer the value is to 0, and the weaker the effect on water demand.

[0083] The generation module is used to obtain the prediction results from the prediction module. Based on the prediction results, it integrates the real-time operation status of the water network regulation and storage project with multi-objective optimization logic to generate several candidate optimization scheduling schemes.

[0084] The objectives of the multi-objective optimization logic are: maximizing water resource utilization, maximizing engineering operation stability, and minimizing cost consumption;

[0085] The multi-objective optimization logic performs multi-objective collaborative optimization by quantifying the comprehensive optimization index:

[0086] ;

[0087] In the formula: To comprehensively optimize the index; These are the weighting coefficients for water resource utilization rate, engineering operation stability, and cost consumption. This is a predicted value for water resource utilization rate; This is the predicted value of the engineering operation stability index; This represents the predicted cost of the project per unit of time.

[0088] The above formula revolves around the core objectives of maximizing water resource utilization, maximizing operational stability, and minimizing cost consumption in water network regulation and storage projects. It integrates the predicted values ​​of water resource utilization, operational stability, and unit time cost consumption into a unified comprehensive optimization index. Furthermore, it selects schemes with the comprehensive optimization index falling within a preset excellent range as candidates to ensure scheme quality. Subsequently, it can also use the actual performance parameters output by the evaluation module to provide feedback and correction. The prediction models of S and C form a closed-loop optimization logic of prediction-generation-evaluation-correction.

[0089] The generation module, based on preset engineering operation constraints, including pipeline node pressure, reservoir water level, and pump operating power, selects different combinations of weighting coefficients within the feasible region and calculates the comprehensive optimization index under the corresponding weighting combinations. Filter out Schemes whose values ​​are within a preset good range are used to form several candidate optimized scheduling schemes, and the number of candidate schemes is not less than three.

[0090] in, All are positive numbers and their sum is 1, and the allocation is dynamically adjusted according to the scheduling priority of the water network regulation and storage project. ∈[0,1], estimated based on the water demand and available water resources output by the prediction module. ∈[0,1], estimated based on the preset allowable fluctuation range of pipeline node pressure and the safe range of water level in the reservoir. The unit is yuan / hour, which is estimated based on the rated power of the water pump, the energy consumption of the gate regulation, and historical maintenance cost data.

[0091] The generation module pushes candidate optimized scheduling schemes to the evaluation module for actual performance evaluation. The evaluation results are used to select the optimal scheme in the subsequent process. Furthermore, the actual performance parameters output by the evaluation module—namely, water resource utilization rate, operational stability index, and actual cost consumption—will be fed back into the generation module to correct errors in the next optimization calculation. , , Prediction model parameters.

[0092] The evaluation module is used to evaluate the water resource utilization rate, engineering operation stability and cost consumption of each candidate optimization scheduling scheme.

[0093] The evaluation module assesses the performance of each candidate optimized scheduling scheme, including:

[0094] Water resource utilization rate:

[0095] ;

[0096] The above formula uses the ratio of actual water usage to total available water resources as its core logic. It clarifies that the actual water supply is the total amount of water supplied by the project to the covered area, while the total available water resources innovatively integrate the real-time water volume of the water source and the adjustable water volume of the storage body. This design fully aligns with the core function of water network regulation and storage projects. It not only considers the immediately available water source volume but also incorporates the regulation potential of the storage body, avoiding misjudgments caused by calculating the available amount solely based on the real-time water source volume. It can more realistically and comprehensively reflect the actual utilization efficiency of water resources and provide accurate quantitative basis for the effectiveness evaluation of subsequent scheduling schemes.

[0097] Operational stability index:

[0098] ;

[0099] The above formula constructs a stability quantification model from two key dimensions of the operation of the water network regulation and storage project: pipeline pressure and water level of the storage body. It reflects the overall stability through the comprehensive calculation of the pressure deviation of pipeline nodes and the water level deviation of the monitoring points of the storage body. It covers the two core indicators of pipeline water supply pressure and water level of the storage body. Furthermore, by calculating the average deviation of multiple nodes and multiple monitoring points, it avoids the interference of local abnormal data on the judgment of overall stability, and realizes a comprehensive and objective quantification of the stability of the project operation.

[0100] Cost consumption:

[0101] ;

[0102] In the formula: This represents the actual water supply to the coverage area after the candidate scheme is implemented; This represents the total available water resources during the implementation of the candidate scheme; This represents the total number of pipeline nodes. The actual pressure of the i-th node in the pipeline network when the candidate scheme is implemented; The design rated pressure for this node; This represents the total number of monitoring points in the water storage body. The actual water level at the j-th monitoring point of the reservoir when the candidate scheme is implemented; This is the design normal water level for this monitoring point; This refers to the energy consumption cost of the water pumps during the implementation of the candidate solution; The pipeline maintenance cost during the implementation of the candidate scheme;

[0103] in, The sum of the real-time water volume from the water source and the adjustable water volume of the storage tank is taken. The adjustable water volume of the storage tank is the difference between the current volume of the storage tank and the preset minimum safe volume. The product of the water pump's operating power, operating time, and unit electricity price. It is calculated based on the fluctuation range of pipeline operating pressure and the preset maintenance cost coefficient.

[0104] First, for each monitoring node in the pipeline network, the difference between the maximum and minimum actual pressure at that node during the execution of the candidate scheme is calculated as the pressure fluctuation amplitude of that node. Second, based on the pipe diameter, flow rate, and importance of the pipeline segment to which each node belongs, a preset weight value is established. The larger the pipe diameter, the higher the flow rate, and the more critical the location of the pipeline segment, the greater the weight value of the corresponding node. Combined with the pressure fluctuation amplitude of each node, the average pressure fluctuation level of the entire pipeline network is calculated. Third, for different segments of the pipeline network, a preset maintenance cost benchmark coefficient is established based on their material (such as ductile iron pipe, steel pipe, plastic pipe, etc.), laying environment (such as direct underground burial, overhead laying, etc.), and service life. The weaker the anti-aging performance of the material, the stronger the corrosiveness of the laying environment, and the longer the service life of the pipeline segment, the higher the benchmark coefficient value is. Finally, the average pressure fluctuation level of the entire pipeline network, the maintenance cost benchmark coefficient of the corresponding pipeline segment, and the actual execution time of the candidate scheme are multiplied to obtain the pipeline network maintenance cost during the execution of the candidate scheme.

[0105] The feedback module is used to obtain the evaluation results, select the most efficient scheduling plan and send it to the water network storage project for execution, collect real-time data of the plan execution to form a plan execution message, and then send the message back to the preset receiving end.

[0106] The generated scheme execution message includes:

[0107] The execution start and end timestamps of the plan, the real-time operating parameters of each execution unit, the cumulative actual water supply during the execution period, the change in water storage volume, the water quality change trend data of key nodes of the water source and pipeline network, and abnormal event records;

[0108] The execution unit includes a water pump, a gate, and a water purification device. Real-time operating parameters include the water pump's operating power, the gate's opening degree, and the purification device's processing flow rate.

[0109] Furthermore, during the operation phase of the feedback module, in the process of executing the optimal scheduling scheme, the feedback module synchronously calculates the deviation between the execution data and the prediction data output by the prediction module. If any deviation value continues to exceed the preset deviation threshold for a period of time that reaches the preset time threshold, the prediction module is triggered to re-predict demand based on the latest real-time data, the generation module regenerates candidate optimized scheduling schemes based on the new prediction results, and the evaluation module re-evaluates and selects a new optimal scheme to complete the scheduling scheme update, so that the water network regulation and storage project is always in the optimal operating state.

[0110] The deviation values ​​include deviations in water supply, water level changes, and pressure.

[0111] The acquisition module is interconnected with the preprocessing module via a wireless network. The preprocessing module is interconnected with the prediction module via a wireless network. The prediction module is interconnected with the generation module and the evaluation module via a wireless network. The evaluation module is interconnected with the feedback module via a wireless network.

[0112] In this embodiment, the acquisition module collects real-time water quantity and quality of the water source belonging to the water network regulation and storage project, real-time pressure and flow of each node in the pipeline network, real-time volume and water level of the water storage body, and real-time meteorological parameters of the project coverage area. The preprocessing module runs after receiving the data collected by the acquisition module, and performs outlier identification, redundancy removal, and format standardization on the data. Then, the prediction module applies the standardized data to predict the water demand and water storage demand of the water network coverage area. The generation module further obtains the prediction results from the prediction module, and based on the prediction results, integrates the real-time operating status of the water network regulation and storage project with multi-objective optimization logic to generate several candidate optimized scheduling schemes. The evaluation module evaluates the water resource utilization rate, project operation stability, and cost consumption of each candidate optimized scheduling scheme. Finally, the feedback module obtains the evaluation results, selects the most efficient scheduling scheme, sends it to the water network regulation and storage project for execution, collects real-time data of scheme execution to form a scheme execution message, and then feeds the message back to the preset receiving end.

[0113] The system described in the above embodiments can accurately collect data related to water sources, pipe networks, water storage bodies, and meteorology, optimize data quality, accurately predict water demand and water storage capacity requirements, generate multiple candidate scheduling schemes, and select the optimal one for execution. This not only improves water resource utilization and enhances the stability of engineering operations but also reduces costs. Furthermore, it can dynamically monitor execution deviations, update the scheme in a timely manner, and continuously ensure a stable and reliable water supply in the covered area.

[0114] Example 2

[0115] Based on Example 1, this example refers to... Figure 2The optimized scheduling system used for water network regulation and storage projects in Example 1 will be further described in detail.

[0116] An optimized scheduling method for water network regulation and storage projects, executed using the optimized scheduling system for water network regulation and storage projects, includes the following steps:

[0117] S10. The data acquisition module collects data on water sources, pipelines, water storage bodies, and meteorological parameters of the water network storage and regulation project. When the water level of the water storage body or the pressure of the pipeline is abnormal, the acquisition frequency of the corresponding parameters is automatically increased.

[0118] S20. The preprocessing module removes outliers, filters redundant parameters, and standardizes the format of the collected data, unifying parameter coding, units, and precision.

[0119] S30. The prediction module predicts water demand and calculates the theoretical volume of the water storage body. If the demand exceeds the safe range, it generates a regulation and storage demand signal.

[0120] S40. The generation module integrates the engineering status and multi-objective optimization logic, selects weight combinations based on operational constraints to calculate the optimization index, and screens no less than three candidate solutions.

[0121] S50, the evaluation module calculates the water resource utilization rate, operational stability index and cost consumption of each candidate scheme to complete the performance evaluation;

[0122] S60. The feedback module issues the optimal solution for execution and sends back the running data message. When the deviation between the executed and predicted data exceeds the limit and timeout occurs, the solution is updated again.

[0123] In summary, the system and method described in the above embodiments can collect real-time data on water source quantity and quality, pipeline node pressure and flow, water storage volume and level, and meteorological parameters of the covered area during the execution of the water network regulation and storage project. They can also dynamically adjust the data collection frequency based on the real-time operating status of the project, ensuring data timeliness and relevance. Data quality is improved through outlier identification, redundancy removal, and format standardization, providing support for accurate prediction of water demand and water storage needs. Candidate scheduling schemes are generated by combining the real-time operating status of the project with multi-objective optimization logic. The optimal scheme is selected by evaluating water resource utilization, project operational stability, and cost consumption. During execution, the deviation between the executed data and the predicted data is calculated simultaneously. If the deviation exceeds a threshold and continues to reach the limit, a new prediction is made and a new scheme is generated, ensuring the project always operates optimally. This effectively improves water resource utilization, project operational stability, reduces costs, and enhances scheduling adaptability and reliability.

[0124] Although the present invention has been described in detail above with general descriptions and specific embodiments, the scope of protection of the present invention is not limited thereto. Modifications or improvements can be made to the present invention, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. An optimized scheduling system for water network regulation and storage projects, characterized in that, include: The data acquisition module is used to collect real-time water volume and water quality parameters of the water source belonging to the water network regulation and storage project, real-time pressure and flow of each node of the pipeline network, real-time volume and water level of the water storage body, and real-time meteorological parameters of the area covered by the project. The preprocessing module receives data collected by the acquisition module and performs outlier identification, redundancy removal, and format standardization on the data. The prediction module is used to acquire preprocessed data and apply the preprocessed data to predict the water demand and water storage demand in the water network coverage area. The prediction module uses the following formula to predict water demand in the water network coverage area: ； In the formula: Let t represent the predicted water demand for the time period. The historical average water consumption for the same period corresponding to time period t; These are the influence coefficients for rainfall, temperature, and population activity intensity. Let t be the predicted rainfall for time period t; The predicted temperature for time period t; The population activity intensity index for time period t; Water storage demand forecast: based on The current real-time volume of the water storage body and the inflow volume corresponding to the predicted rainfall in time period t are used to calculate the theoretical volume of the water storage body after time period t ends. If the theoretical volume exceeds the preset safe volume range of the water storage body, a regulation demand signal is generated. The signal strength is set to be positively correlated with the degree to which the theoretical volume deviates from the preset safe volume range. in, , , All data originates from the data acquisition module; The generation module is used to obtain the prediction results from the prediction module. Based on the prediction results, it integrates the real-time operation status of the water network regulation and storage project with multi-objective optimization logic to generate several candidate optimization scheduling schemes. The objective of the multi-objective optimization logic in the generation module is: Maximize water resource utilization, maximize engineering operational stability, and minimize cost consumption; The multi-objective optimization logic performs multi-objective collaborative optimization by quantifying the comprehensive optimization index: ； In the formula: To comprehensively optimize the index; These are the weighting coefficients for water resource utilization rate, engineering operation stability, and cost consumption. This is a predicted value for water resource utilization rate; This is the predicted value of the engineering operation stability index; This represents the predicted cost of the project per unit of time. The generation module, based on preset engineering operation constraints, including pipeline node pressure, water level in the reservoir, and pump operating power, selects different combinations of weight coefficients within the feasible region and calculates the comprehensive optimization index under the corresponding weight combinations. Filter out Schemes whose values ​​are within a preset good range are used to form several candidate optimized scheduling schemes, and the number of candidate schemes is not less than three. in, All are positive numbers and their sum is 1, and the allocation is dynamically adjusted according to the scheduling priority of the water network regulation and storage project. ∈[0,1], estimated based on the water demand and available water resources output by the prediction module. ∈[0,1], estimated based on the preset allowable fluctuation range of pipeline node pressure and the safe range of water level in the reservoir. The unit is yuan / hour, and it is estimated based on the rated power of the water pump, the energy consumption of the gate regulation, and historical maintenance cost data. The evaluation module is used to evaluate the water resource utilization rate, engineering operation stability and cost consumption of each candidate optimization scheduling scheme. The feedback module is used to obtain the evaluation results, select the most efficient scheduling plan and send it to the water network storage project for execution, collect real-time data of plan execution to form a plan execution message, and then send the message back to the preset receiving end. During the operation phase of the feedback module, in the process of executing the optimal scheduling scheme, the feedback module synchronously calculates the deviation between the execution data and the prediction data output by the prediction module. If any deviation value exceeds the preset deviation threshold for a period of time that reaches the preset time threshold, the prediction module is triggered to re-predict demand based on the latest real-time data. The generation module regenerates the candidate optimized scheduling scheme based on the new prediction results. The evaluation module re-evaluates and selects a new optimal scheme to complete the scheduling scheme update, so that the water network regulation and storage project is always in the optimal operating state. The deviation values ​​include deviations in water supply, water level changes, and pressure.

2. The optimized scheduling system for water network regulation and storage projects according to claim 1, characterized in that, The data collected by the acquisition module includes water quality parameters such as pH value, dissolved oxygen concentration, turbidity and chemical oxygen demand, and meteorological parameters such as rainfall, evaporation, temperature and relative humidity. The acquisition frequency of the acquisition module is dynamically adjusted according to the real-time operation status of the water network regulation and storage project. When the water level of the storage body deviates from the preset normal range or the pressure of the pipeline node exceeds the preset stable range, the acquisition module automatically increases the acquisition frequency of the corresponding parameter.

3. The optimized scheduling system for water network regulation and storage projects according to claim 1, characterized in that, The outlier identification in the preprocessing module specifically includes: For any real-time acquired parameter, calculate the mean and standard deviation of the historical acquired data for that parameter within a preset time window, and then calculate the deviation of that parameter. , This represents the collected value of the parameter at time i. This represents the average of historically collected data. Indicates the standard deviation of historically collected data; like Greater than the preset deviation coefficient, and If it is not within the allowable range for the corresponding project, then it is judged. Outliers were identified and removed. The redundancy removal involves calculating the Pearson correlation coefficient between any two acquired parameters. ,like If the data exceeds the preset threshold, the parameter with the higher data collection frequency will be retained, and redundant data of the other parameter will be removed. The format standardization process involves converting all collected parameters into a preset engineering data format, including: standardization of parameter name encoding, data units, and data precision.

4. The optimized scheduling system for water network regulation and storage projects according to claim 1, characterized in that, The evaluation module assesses the effectiveness of each candidate optimized scheduling scheme, including: Water resource utilization rate: ； Operational stability index: ； Cost consumption: ； In the formula: This represents the actual water supply to the coverage area after the candidate scheme is implemented; This represents the total available water resources during the implementation of the candidate scheme; This represents the total number of pipeline nodes. The actual pressure of the i-th node in the pipeline network when the candidate scheme is implemented; The design rated pressure for this node; This represents the total number of monitoring points in the water storage body. The actual water level at the j-th monitoring point of the reservoir when the candidate scheme is implemented; This is the design normal water level for this monitoring point; This refers to the energy consumption cost of the water pumps during the implementation of the candidate solution; The pipeline maintenance cost during the implementation of the candidate scheme; in, The sum of the real-time water volume from the water source and the adjustable water volume of the storage tank is taken. The adjustable water volume of the storage tank is the difference between the current volume of the storage tank and the preset minimum safe volume. The product of the water pump's operating power, operating time, and unit electricity price. It is calculated based on the fluctuation range of pipeline operating pressure and the preset maintenance cost coefficient.

5. The optimized scheduling system for water network regulation and storage projects according to claim 1, characterized in that, The scheme execution message generated by the feedback module includes: The execution start and end timestamps of the plan, the real-time operating parameters of each execution unit, the cumulative actual water supply during the execution period, the change in water storage volume, the water quality change trend data of key nodes of the water source and pipeline network, and abnormal event records; The execution unit includes a water pump, a gate, and a water purification device. Real-time operating parameters include the water pump's operating power, the gate's opening degree, and the purification device's processing flow rate.

6. The optimized scheduling system for water network regulation and storage projects according to claim 1, characterized in that, The acquisition module is interconnected with a preprocessing module via a wireless network. The preprocessing module is interconnected with a prediction module via a wireless network. The prediction module is interconnected with a generation module and an evaluation module via a wireless network. The evaluation module is interconnected with a feedback module via a wireless network.

7. An optimized scheduling method for water network regulation and storage projects, characterized in that, The method is executed using the optimized scheduling system for water network regulation and storage projects as described in any one of claims 1-6, and includes the following steps: S10. The data acquisition module collects data on water sources, pipelines, water storage bodies, and meteorological parameters of the water network regulation and storage project. When the water level of the water storage body or the pressure of the pipeline is abnormal, the acquisition frequency of the corresponding parameters is automatically increased. S20. The preprocessing module removes outliers, filters redundant parameters, and standardizes the format of the collected data, unifying parameter coding, units, and precision. S30. The prediction module predicts water demand and calculates the theoretical volume of the water storage body. If the demand exceeds the safe range, it generates a regulation and storage demand signal. S40. The generation module integrates the engineering status and multi-objective optimization logic, selects weight combinations based on operational constraints to calculate the optimization index, and screens no less than three candidate solutions. S50, the evaluation module calculates the water resource utilization rate, operational stability index and cost consumption of each candidate scheme to complete the performance evaluation; S60. The feedback module issues the optimal solution for execution and sends back the running data message. When the deviation between the executed and predicted data exceeds the limit and timeout occurs, the solution is updated again.

Images