Cloud-based water supply network real-time management system

Abstract

The invention relates to the technical field of resource management, in particular to a cloud-based water supply network real-time management system, which comprises a dynamic optimization module for acquiring real-time data of a sensor through a cloud end, extracting water network pressure, flow and pump speed, establishing a dynamic optimization framework, analyzing a relationship between an operation mode and the real-time data, dynamically updating model parameters, and establishing a dynamic optimization model; and forming dynamic optimization model output. According to the method, the sensor data is acquired and analyzed in real time, the pressure, the flow and the pump speed of the water network are accurately regulated and controlled, and a dynamic optimization framework is established, so that model parameters can be updated according to the real-time data, the adjustment speed and the accuracy of a water supply strategy are greatly improved, in addition, parameter combination is more optimized through global search, and the accuracy of the system is improved. The water supply efficiency and adaptability are effectively improved, the feasibility of a solution and the emergency response capability of the system are enhanced through refining processing of integer and nonlinear targets, and the optimized topological structure adjustment can effectively prevent and cope with emergency situations in a water network.

Description

Technical Field

[0001] The present invention relates to the technical field of resource management, and particularly to a cloud-based real-time management system for a water supply network. Background Art

[0002] The technical field of resource management mainly focuses on effectively planning, allocating, using, and protecting natural and artificial resources. In modern times, with the rapid development of technology, especially the application of information technology and cloud computing, the technical field of resource management has developed highly complex and automated systems. These systems can monitor the status of resources in real time, predict demand changes, and optimize resource allocation and utilization efficiency accordingly. In multiple important fields such as energy, water resources, and logistics, the application of this technology has helped improve resource utilization efficiency, reduce waste, and enhance sustainable environmental management.

[0003] Among them, a cloud-based real-time management system for a water supply network refers to a system that uses cloud computing technology to monitor and manage a water supply network. This system enables water utility managers to receive water network data in real time via the Internet, monitor indicators such as water quality and water pressure, and promptly discover and solve problems in water supply. Its main uses include but are not limited to predicting and adjusting water supply strategies, optimizing the water supply process, reducing resource waste, and enhancing the ability to respond to sudden water-related events. Through real-time data analysis and cloud resource sharing, this system improves the intelligence and automation level of the water supply network and provides users with more reliable and efficient water supply services.

[0004] Existing technologies usually lack efficient real-time data analysis capabilities, resulting in slow responses when dealing with rapidly changing water supply demands and being unable to optimize water supply strategies in real time. This lack of flexibility may cause resource waste or insufficient water supply during peak periods. The lack of in-depth analysis of the water network structure makes it difficult to promptly identify and handle key nodes and vulnerable connections, weakening the system's ability to handle emergencies. These technical limitations may lead to water supply interruptions or quality degradation in case of emergencies, affecting the overall reliability of the service and user satisfaction. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art and propose a cloud-based real-time management system for a water supply network.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: A cloud-based real-time management system for a water supply network includes:

[0007] The dynamic optimization module obtains real-time sensor data through the cloud, extracts water network pressure, flow rate, and pump speed, establishes a dynamic optimization framework, analyzes the relationship between the operation mode and real-time data, dynamically updates the model parameters, and forms the output of a dynamic optimization model;

[0008] The genetic optimization module calls the output of the dynamic optimization model, sets the initial values of the pump speed and valve status, performs a global search, evaluates the matching degree of different parameter combinations, records the results of each search, and generates an optimization plan for key parameters;

[0009] The MINLP refinement module uses the optimization plan for key parameters to process the constraint conditions and optimization objectives, performs the refinement of integer constraints and non-linear objectives, checks the feasibility of the solutions, records the results of each refinement, and generates an optimized result for feasible solutions;

[0010] The topology analysis module constructs a water network diagram based on the optimized result of feasible solutions, calculates the node centrality and connectivity, performs the analysis of fluidity and pressure changes, identifies key nodes and vulnerable connections, records the analysis results, and generates the results of network structure characteristics;

[0011] The adaptive adjustment module analyzes the requirements for structure adjustment based on the results of network structure characteristics, optimizes the topological structure, performs node reconfiguration and connection optimization, records the implementation process of the adjustment, and generates the implementation results of water network control.

[0012] The output of the dynamic optimization model includes water network pressure, flow rate, and pump speed. The optimization plan for key parameters includes pump speed, valve status, and parameter combinations. The optimized result of feasible solutions includes constraint conditions, optimization objectives, and feasible solutions. The results of network structure characteristics include node centrality, connectivity, and key nodes. The implementation results of water network control include topological structure optimization, node reconfiguration, and connection optimization.

[0013] As a further solution of the present invention, the specific steps for obtaining the dynamic optimization framework are as follows:

[0014] Call the real-time sensor data of the water network system through cloud services, obtain the water network pressure, flow rate, and pump speed, screen and verify the measurement accuracy of each sensor, and establish an initial data set;

[0015] Based on the initial data set, perform the relationship analysis between the water network pressure, flow rate, and pump speed, process the data using linear algebra operations, and generate a relationship matrix;

[0016] Use the relationship matrix to construct a dynamic adjustment logic, and perform real-time adjustment of the model parameters in combination with the changes in the real-time data stream. The formula is as follows:

[0017]

[0018] Calculate the current output parameters and generate a dynamic optimization framework;

[0019] where P newrepresents the newly calculated output parameters of the water network system, β0 represents the constant term used to adjust the baseline output level, β1 represents the weight coefficient of the water network pressure on the output, reflecting the sensitivity of the pressure change to the output parameters, β2 represents the weight coefficient of the water flow rate on the output, indicating the magnitude of the influence of the flow rate change on the output parameters, P pressure represents the pressure value of the current water network, α1 is the time decay coefficient, reflecting the decay speed of the system response with time change, t represents the time from the system startup to the current time, P flow is the flow rate value of the current water network, P pump represents the numerical value of the current pump speed.

[0020] As a further solution of the present invention, the obtaining steps of the output of the dynamic optimization model are specifically as follows:

[0021] Retrieve the current model parameters from the dynamic optimization framework, analyze the key variables in combination with real-time sensor data, identify the parameters that mainly affect the model output, and generate the key parameter analysis results;

[0022] Assign weights to each parameter in the key parameter analysis results, calculate its contribution to the model output using a quantitative method, integrate the data, and generate a weighted relationship matrix;

[0023] Apply the weighted relationship matrix and real-time data to update the weight coefficients and adjustment coefficients, using the formula:

[0024]

[0025] Generate the output of the dynamic optimization model;

[0026] where, w0 represents the base offset used to adjust the baseline level of the model output, w i is the weight of the i-th parameter, affecting the criticality of the parameter in the model output, X i is the real-time data of the i-th parameter, directly obtained from the dynamic optimization framework, reflecting the numerical value under the current environmental or operating conditions, v j is the adjustment coefficient of the j-th parameter, used to fine-tune the sensitivity of the model to the j-th auxiliary data Y j of, Y j is the auxiliary data of the associated parameter.

[0027] As a further solution of the present invention, the obtaining steps of the key parameter optimization scheme are specifically as follows:

[0028] Retrieve data from the output of the dynamic optimization model, set the initial parameter values of the pump speed and valve status, perform system simulation, and generate the initial simulation results;

[0029] Using a global search algorithm, analyze the initial simulation results, evaluate the performance of different combinations of pump speeds and valve settings, and generate a performance matching result through system performance evaluation;

[0030] Based on the performance matching result, use a mathematical model formula to perform data analysis. The formula is:

[0031]

[0032] Select the optimal solution from multiple parameter combinations to generate an optimized key parameter solution;

[0033] Among them, S opt represents the score of the optimal solution, which is used to select the optimal parameter combination. e represents the base of the natural logarithm, which is a constant. k i represents the critical weight of the i-th parameter, reflecting the influence of each parameter on the total score. x i is the actual value of the current i-th parameter, and x i,opt is the ideal or target value of the i-th parameter. (x i -x i,opt ) 2 Calculates the square of the deviation between the current parameter value and the ideal value, which is used to amplify the impact of deviating from the ideal state.

[0034] As a further solution of the present invention, the specific steps for obtaining the optimized feasible solution are as follows:

[0035] According to the optimized key parameter solution, perform initialization settings for integer constraints and non-linear objectives, call the preliminary refinement of model parameters, and perform basic verification of constraint conditions to generate a preliminary refinement result;

[0036] Call the preliminary refinement result, perform multi-dimensional analysis of constraint conditions, judge the satisfaction degree of integer constraints and the approximation degree of non-linear objectives, perform comparative analysis of results, and generate an analysis result of constraint satisfaction;

[0037] Based on the analysis result of constraint satisfaction, use the formula:

[0038]

[0039] Calculate the adaptability of the combination of constraints and target parameters, select the optimal parameter settings, and generate an optimized feasible solution;

[0040] Among them, w i represents the weight coefficient of the i-th constraint condition, which is used to adjust the influence of different constraint conditions on the optimization result. k i represents the adjustment coefficient of the i-th constraint condition, which is used to adjust the sensitivity of the constraint value in the formula and affect the response intensity of the objective function to the deviation of the constraint value from the target. ci represents the current constraint value, t i represents the target value of the i-th constraint condition.

[0041] As a further solution of the present invention, the steps for obtaining the network structure feature results are specifically as follows:

[0042] According to the feasible solution optimization result, construct a water network diagram, perform basic data collection of nodes and connection relationships, calculate the basic connectivity between nodes, and generate a preliminary network diagram result;

[0043] Call the preliminary network diagram result, calculate the node centrality, analyze the key importance of Mig nodes in the network, perform connectivity analysis based on the key importance index, and generate a node centrality analysis result;

[0044] Based on the node centrality analysis result, perform analysis of fluidity and pressure changes, identify key nodes and vulnerable connections, and use the formula:

[0045]

[0046] Calculate the degree of influence of fluidity on key nodes, identify key nodes, and generate network structure feature results;

[0047] where f j represents the flow rate, P j represents the node pressure, D j represents the connection vulnerability, C crit represents the comprehensive influence degree of key nodes.

[0048] As a further solution of the present invention, the steps for obtaining the water network control implementation results are specifically as follows:

[0049] Based on the network structure feature results, analyze the topological requirements of the existing water network, determine the key areas for structural adjustment, and generate a structural adjustment requirement analysis result;

[0050] Utilize the structural adjustment requirement analysis result to design a topological structure optimization strategy, perform node reconfiguration and connection optimization, improve the overall performance of the system through adjustment methods, and generate a node and connection optimization record;

[0051] Combine the node and connection optimization record, and use the formula:

[0052]

[0053] Evaluate the implementation of water network control, emphasize the influence of the number of connections through a logarithmic function, and generate water network control implementation results;

[0054] where R adjRepresents the implementation result of the adjusted water network control, N k Indicates the connection number of the k-th node, γ k Is the node criticality coefficient, p represents the total number of nodes in the network, and is used to summarize the contributions of all nodes.

[0055] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0056] In the present invention, by obtaining and analyzing sensor data in real time, the pressure, flow rate, and pump speed of the water network are precisely regulated. The establishment of the dynamic optimization framework enables the model parameters to be updated according to real-time data, greatly improving the adjustment speed and accuracy of the water supply strategy. In addition, the global search makes the parameter combination more optimized, effectively improving the water supply efficiency and adaptability. The refined processing of integer and non-linear objectives further enhances the feasibility of the solution and the emergency response ability of the system, and the optimized topological structure adjustment can effectively prevent and respond to emergencies in the water network. Brief Description of the Drawings

[0057] Figure 1 Is the system flowchart of the present invention;

[0058] Figure 2 Is the flowchart of the acquisition steps of the dynamic optimization framework of the present invention;

[0059] Figure 3 Is the flowchart of the acquisition steps of the output of the dynamic optimization model of the present invention;

[0060] Figure 4 Is the flowchart of the acquisition steps of the key parameter optimization scheme of the present invention;

[0061] Figure 5 Is the flowchart of the acquisition steps of the optimization result of the feasible solution of the present invention;

[0062] Figure 6 Is the flowchart of the acquisition steps of the network structure feature result of the present invention;

[0063] Figure 7 Is the flowchart of the acquisition steps of the implementation result of the water network control of the present invention. Detailed Description of the Preferred Embodiment

[0064] In order to make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0065] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0066] Embodiment 1

[0067] Please refer to Figure 1 , a cloud-based real-time management system for a water supply network includes:

[0068] The dynamic optimization module obtains real-time sensor data through the cloud, extracts water network pressure, flow rate, and pump speed, establishes a dynamic optimization framework, analyzes the relationship between the operation mode and real-time data, dynamically updates the model parameters, and forms the output of the dynamic optimization model;

[0069] The genetic optimization module calls the output of the dynamic optimization model, sets the initial values of the pump speed and valve status, performs a global search, evaluates the matching degree of different parameter combinations, records the results of each search, and generates an optimization plan for key parameters;

[0070] The MINLP refinement module uses the optimization plan for key parameters, processes the constraint conditions and optimization objectives, performs the refinement of integer constraints and non-linear objectives, checks the feasibility of the solutions, records the results of each refinement, and generates the optimization results of feasible solutions;

[0071] The topology analysis module constructs a water network diagram based on the optimization results of feasible solutions, calculates the node centrality and connectivity, performs the analysis of fluidity and pressure changes, identifies key nodes and vulnerable connections, records the analysis results, and generates the results of network structure characteristics;

[0072] The adaptive adjustment module analyzes the requirements for structural adjustment based on the results of network structure characteristics, performs topological structure optimization, executes node reconfiguration and connection optimization, records the implementation process of the adjustment, and generates the implementation results of water network management and control.

[0073] The output of the dynamic optimization model includes water network pressure, flow rate, and pump speed; the optimization plan for key parameters includes pump speed, valve status, and parameter combinations; the optimization results of feasible solutions include constraint conditions, optimization objectives, and feasible solutions; the results of network structure characteristics include node centrality, connectivity, and key nodes; the implementation results of water network management and control include topological structure optimization, node reconfiguration, and connection optimization.

[0074] Please refer to Figure 2, the steps to obtain the dynamic optimization framework are specifically as follows:

[0075] Retrieve the real-time sensor data of the water network system through cloud services, obtain the water network pressure, flow rate, and pump speed, screen and verify the measurement accuracy of each sensor, and establish an initial dataset;

[0076] Retrieve the real-time sensor data of the water network system through cloud services, obtain the water network pressure, flow rate, and pump speed. First, verify the sensor data to ensure the accuracy and consistency of the data. Second, eliminate outliers. Finally, integrate the valid data to form an initial dataset, which will be used for subsequent analysis and modeling processing.

[0077] Based on the initial dataset, analyze the relationships among the water network pressure, flow rate, and pump speed, process the data using linear algebra operations, and generate a relationship matrix;

[0078] Based on the initial dataset, analyze the relationships among the water network pressure, flow rate, and pump speed. First, apply the linear regression method to process the data to determine the relationships between each variable. Then, calculate the correlation coefficient of the linear regression model to evaluate the correlation between each parameter. Finally, form a relationship matrix to provide a basis for subsequent model parameter updates.

[0079] Using the relationship matrix, construct a dynamic adjustment logic, and adjust the model parameters in real-time in combination with the changes in the real-time data stream. Use the formula:

[0080]

[0081] Calculate the current output parameters to generate a dynamic optimization framework;

[0082] Among them, P new represents the newly calculated output parameter of the water network system, β0 represents the constant term, which is used to adjust the baseline output level, β1 represents the weight coefficient of the water network pressure on the output, reflecting the sensitivity of the pressure change to the output parameter, β2 represents the weight coefficient of the water flow rate on the output, indicating the magnitude of the influence of the flow rate change on the output parameter, P pressure represents the current pressure value of the water network, α1 is the time decay coefficient, reflecting the decay speed of the system response with time change, t represents the time from the system startup to the current, P flow is the current flow rate value of the water network, P pump represents the numerical value of the current pump speed.

[0083] Formula:

[0084]

[0085] The advantage of the formula is that by combining factors such as pressure, flow rate, and pump speed, the output parameters can be dynamically adjusted to respond to changes in real-time data streams, enhancing system matching.

[0086] Detailed explanation of the formula and the derivation process of formula calculation:

[0087] In the formula, P new is the newly calculated output parameter, β0 represents the constant term, obtained from the average value of previous data and set to 50, β1 and β2 respectively represent the weights of pressure and flow rate on the output, obtained through data analysis and set to 0.4 and 0.6 respectively, P pump represents the pump speed, measured as 10, α1 is the adjustment coefficient, obtained from the fluctuations of previous data and set to 0.01, t is the time variable, set to 10 seconds.

[0088] The calculation process is as follows:

[0089] 1. Calculate

[0090] 2. Calculate exp(-α1·t) = exp(-0.01·10) ≈ 0.9048;

[0091] 3. Substitute the result into the formula:

[0092] P new = 50 + 0.4·P pressure + 0.6·P flow + 10·0.9048

[0093] Set P pressure to 80, P flow to 120, and obtain:

[0094] The result shows that the current output parameter is 163.048, reflecting the system state adjusted according to real-time data, and becoming the basis for subsequent decision-making and optimization.

[0095] Please refer to Figure 3 for the specific steps to obtain the output of the dynamic optimization model:

[0096] Retrieve the current model parameters from the dynamic optimization framework, analyze the key variables in combination with real-time sensor data, identify the parameters that mainly affect the model output, and generate the analysis results of key parameters;

[0097] Retrieve the current model parameters from the dynamic optimization framework, combine the real-time sensor data for data cleaning, eliminate the outliers beyond the normal range, analyze the impact of key variables on the model output, conduct statistics on the real-time data of each parameter to obtain an effective data set, group the data set and calculate the average values of multiple groups, and then determine the parameters that critically affect the model output. Calculate the weight coefficients of the parameters based on the correlation between the parameters, and integrate the data to generate the analysis results of the key parameters.

[0098] Assign weights to each parameter in the analysis results of the key parameters, use quantitative methods to calculate its contribution to the model output, and integrate the data to generate a weighted relationship matrix;

[0099] Assign weights to each parameter in the analysis results of the key parameters. When setting the weight parameters, evaluate according to the previous influence degree of the parameters on the model output, select the corresponding data for comparative analysis, dynamically adjust the weights in combination with the actual monitoring data, and ensure the rationality of the weight assignment by comparing the performances of multiple parameters in different scenarios, and generate a weighted relationship matrix.

[0100] Apply the weighted relationship matrix and real-time data to update the weight coefficients and adjustment coefficients, using the formula:

[0101]

[0102] Generate the output of the dynamic optimization model;

[0103] Among them, w0 represents the base offset, which is used to adjust the baseline level of the model output, and w i is the weight of the i-th parameter, which affects the criticality of the parameter in the model output, and X i is the real-time data of the i-th parameter, which is directly obtained from the dynamic optimization framework and reflects the value under the current environmental or operating conditions, and v j is the adjustment coefficient of the j-th parameter, which is used to fine-tune the sensitivity of the model to the j-th auxiliary data Y j and Y j is the auxiliary data of the associated parameter.

[0104] Formula:

[0105]

[0106] The advantage of the formula is that by combining real-time data and weight parameters, it can dynamically adjust the model output and reflect the matching of the model to environmental changes.

[0107] Detailed explanation of the formula and the derivation process of the formula calculation:

[0108] In the formula, set the base offset \(w_0 = 10\), the key parameters \(X_1 = 5\), \(X_2 = 3\), the weights \(w_1 = 0.4\), \(w_2 = 0.6\), and the adjustment coefficient \(v_1 = 0.5\), and the auxiliary parameter \(Y_1 = 2\); first calculate

[0109]

[0110] Then calculate the weighted sum:

[0111]

[0112] Next, calculate the non - linear part:

[0113]

[0114] Therefore, the calculation formula is:

[0115]

[0116] The result shows that the value output by the model is 26.131, reflecting the state of the dynamic optimization model in the current environment, which is closely related to the step results, indicating that under the current parameter configuration, the model can output the optimal decision with this value.

[0117] Please refer to Figure 4 , the steps to obtain the key parameter optimization scheme are specifically as follows:

[0118] Retrieve data from the output of the dynamic optimization model, set the initial parameter values of the pump speed and valve state, perform system simulation, and generate the initial simulation results;

[0119] Retrieve data from the output of the dynamic optimization model. The data is collected by multiple sensors at different valve positions and pump speeds to ensure the diversity and coverage of the data. Through the preliminary analysis of the data, the initial parameter values of the pump speed and valve state are set. The parameter values are optimized according to past operation data and the preset system response curve to ensure that they can reflect the requirements of the actual working conditions. The system simulation is carried out through a defined set of simulation processes, including the integration of fluid dynamics models and thermodynamic models. The results of the simulation will directly affect the subsequent parameter adjustment and system performance evaluation. The generated initial simulation results provide a benchmark for comparing the system responses under different parameter settings.

[0120] Use the global search algorithm to analyze the initial simulation results, evaluate the performance of different combinations of pump speeds and valve settings, and generate the performance matching degree results through system performance evaluation;

[0121] Using a global search algorithm, by traversing all estimated parameter combinations, evaluating the system performance of each combination under given conditions, capturing the optimal pump speed and valve position settings. The global search algorithm relies on the previously generated initial simulation results as input, combines the constraints in actual operation and the performance limitations of the equipment for optimization. The algorithm compares the performance of different parameter combinations, screens out the parameter combinations that can achieve the highest efficiency and optimal output. In this process, the feasibility and economy of multiple combinations are evaluated. Through system performance evaluation, the matching degree of each combination is obtained. These matching degree results assist in analyzing the performance of various settings in actual applications and the parameters that need to be adjusted.

[0122] Based on the performance matching degree results, using a mathematical model formula, perform data analysis, using the formula:

[0123]

[0124] Select the optimal solution from multiple parameter combinations to generate an optimized solution for key parameters;

[0125] Among them, S opt represents the score of the optimal solution, used to select the optimal parameter combination. e represents the base of the natural logarithm, which is a constant. k i represents the critical weight of the i-th parameter, reflecting the influence of each parameter on the total score. x i is the actual value of the current i-th parameter. x i,opt is the ideal or target value of the i-th parameter. (x i - x i,opt ) 2 Calculates the square of the deviation between the current parameter value and the ideal value, used to magnify the influence of deviating from the ideal state.

[0126] Formula:

[0127]

[0128] The benefit of the formula is that by referring to the square of the deviation between each parameter and its optimal value, weighted by its criticality, this way strengthens the sensitivity to the selection of optimal parameters and can effectively screen out the parameter combinations that contribute the most to the system performance.

[0129] Detailed explanation of the formula and the derivation process of formula calculation:

[0130] Referring to a system, there are three parameters set: pump speed x1, valve position x2, and temperature x3. The set optimal values are x 1,opt = 3000 rpm, x 2,opt = 50%, x 3,opt= 350K. The current actual values are x1 = 2950 rpm, x2 = 45%, x3 = 345K, with weights k1 = 0.5, k2 = 0.3, k3 = 0.2. Substitute into the formula:

[0131]

[0132] The calculated S opt value will indicate the proximity of the current parameter settings to the ideal settings, and optimizing the parameters can significantly improve the system efficiency.

[0133] The results show that there is a small - range deviation between the current parameter settings and the optimal settings. Performance optimization is carried out through fine - tuning to enhance the output efficiency and stability of the system.

[0134] Please refer to Figure 5 , and the specific steps to obtain the optimized results of the feasible solutions are as follows:

[0135] According to the key parameter optimization plan, perform the initialization settings of integer constraints and non - linear objectives, call the preliminary refinement of the model parameters, conduct the basic verification of the constraint conditions, and generate the preliminary refinement results;

[0136] When initializing the system settings, first set the integer constraints and non - linear objectives according to the obtained key parameter optimization plan. Conduct the preliminary refinement by calling the parameters of the model, which involves the basic verification of multiple constraint conditions inside the system, including detecting whether the integer constraints meet the required conditions and conducting a preliminary evaluation of the non - linear objectives, including inputting multiple types of data indicators and analyzing their satisfaction degrees. This includes not only the input of numerical values but also the screening of the data distribution, verifying the accuracy and effectiveness of the data, laying a foundation for further in - depth analysis.

[0137] Call the preliminary refinement results, perform the multi - dimensional analysis of the constraint conditions, judge the satisfaction degree of the integer constraints and the approximation degree of the non - linear objectives, conduct the comparative analysis of the results, and generate the analysis results of the constraint satisfaction degree;

[0138] Following the preliminary settings, the system enters the multi - dimensional analysis stage of the constraint conditions. This stage focuses on the verification of the satisfaction degree of the integer constraints and the approximation degree of the non - linear objectives. Adopt data - processing techniques to refine and optimize the model parameters. Through the comparative analysis method, evaluate the effects of each parameter combination to ensure that each parameter adjustment can meet the integer constraints while approaching the preset non - linear objective to the greatest extent, generating the analysis results of the constraint satisfaction degree. These results will be recorded and used to evaluate the effectiveness of multiple parameter settings, providing a scientific basis for the selection of the optimization plan.

[0139] Based on the analysis results of the constraint satisfaction degree, use the formula:

[0140]

[0141] Calculate the suitability of the computational constraints and the combination of target parameters, select the optimal parameter settings, and generate a feasible solution optimization result;

[0142] Among them, w i represents the weight coefficient of the i-th constraint condition, used to adjust the influence of the differential constraint condition in the optimization result, k i represents the adjustment coefficient of the i-th constraint condition, used to adjust the sensitivity of the constraint value in the formula, and affects the response intensity of the objective function to the deviation of the constraint value from the target, c i represents the current constraint value, t i represents the target value of the i-th constraint condition.

[0143] Formula:

[0144]

[0145] The benefit of the formula is to optimize the adaptability and flexibility of the parameter settings by combining weights and square root operations for more precise constraint objectives.

[0146] Detailed explanation of the formula and the derivation process of the formula calculation:

[0147] In the formula, R opt represents the optimization result, w i is the weight coefficient, k i is the adjustment coefficient, c i is the current constraint value, t i is the target constraint value. First, monitor and collect data to obtain the weight coefficient. Assume that through previous data regression analysis, w1 = 0.3, w2 = 0.5, and w3 = 0.2 are obtained. Second, collect c i and t i , set the current constraint values c1 = 100, c2 = 80, c3 = 60, and the target constraint values t1 = 90, t2 = 70, t3 = 50. Next, the adjustment coefficient k i is obtained through simulation of the constraint environment, and k1 = 1, k2 = 2, and k3 = 3 are set.

[0148] Substitute the parameters into the formula for calculation:

[0149]

[0150] Calculate step by step to obtain:

[0151]

[0152] The result shows that the combined result of the optimized parameters is 0.272, indicating the degree of optimization and the closeness to the target under the current constraints.

[0153] Please refer to Figure 6 , and the steps for obtaining the network structure feature results are specifically as follows:

[0154] Based on the feasible solution optimization results, construct a water network diagram, perform basic data collection of nodes and connection relationships, calculate the basic connectivity between nodes, and generate preliminary network diagram results;

[0155] When constructing a water network diagram through GIS based on the data of the feasible solution optimization results, first locate the known nodes. Each node is input into the system according to its geographical coordinates and connection data. In this way, the placement of each node is ensured. The connectivity of the nodes depends on their geographical proximity and previous connection data. The data is imported from the database of the water authority into GIS. Each connection not only represents a physical connection but also simulates the water flow direction and estimated pressure points. The pressure point data is calculated based on past flow and pressure records. Through this method, a diagram reflecting the real water network can be created, and this process ensures the high accuracy and operability of the network diagram.

[0156] Call the preliminary network diagram results, calculate the node centrality, analyze the key importance of the nodes in the network, perform connectivity analysis based on the key importance indicators, and generate node centrality analysis results;

[0157] After completing the construction of the water network diagram, the calculation of node centrality is based on the centrality theory in graph theory. The number of connections and the flow of each node are calculated through network analysis. The centrality of each node is evaluated based on the number of nodes it is connected to and the magnitude of the flow of these connections. Nodes with high centrality mean they play a key role in the water network, which are key distribution points or nodes with large flows. The mobility analysis is performed using flow simulation. The input parameters include the centrality data of the nodes, flow data, and the pressure changes monitored in real time. Simulate the flow and pressure distribution of water in the network, and output the mobility and pressure status of each node to determine which nodes become vulnerable points under the target conditions.

[0158] Based on the node centrality analysis results, perform an analysis of mobility and pressure changes, judge key nodes and vulnerable connections, and use the formula:

[0159]

[0160] Calculate the degree of influence of mobility on key nodes, identify key nodes, and generate network structure feature results;

[0161] where f j represents the flow rate, P j represents the node pressure, D j represents the connection vulnerability, C critRepresents the comprehensive influence degree of key nodes.

[0162] Formula:

[0163]

[0164] The advantage of the formula is that by introducing three key parameters, namely flow volume, node pressure, and connection vulnerability, the accuracy of identifying key nodes is improved.

[0165] Detailed explanation of the formula and the derivation process of formula calculation:

[0166] Flow volume f j Obtained through the flow monitoring of multiple nodes in the network. The monitoring results show that the flow volume of node 1 is 50 units and that of node 2 is 70 units. Node pressure P j Recorded in real time by the monitoring device. The results are that the pressure of node 1 is 1.5 units and that of node 2 is 2.0 units. Connection vulnerability D j Obtained based on the comprehensive evaluation of connection strength and previous failure records. The connection vulnerability between node 1 and node 2 is 0.8.

[0167] Substitute the values into the formula:

[0168]

[0169] The calculation steps are as follows:

[0170] 1. Calculate the square root of the connection vulnerability:

[0171] 2. Calculate the value of each term:

[0172] For node 1:

[0173] For node 2:

[0174] 3. Sum: C crit =39.5 + 73.8 ≈ 113.3

[0175] The results show that the critical value of the key nodes in the network is 113.3, indicating the key role of fluidity and pressure in the overall network structure.

[0176] Please refer to Figure 7 , and the specific steps for obtaining the implementation results of water network management and control are as follows:

[0177] Based on the results of network structure characteristics, analyze the topological requirements of the existing water network, determine the key areas for structural adjustment, and generate the analysis results of structural adjustment requirements;

[0178] Based on the results of the network structure characteristics, through systematic analysis, the key areas that need to be adjusted in the water network are determined. This process includes the evaluation of the efficiency of existing nodes and the prediction of flow requirements. Referring to the complexity of the water network and the changing environmental conditions, a dynamic adjustment strategy is adopted. The strategy is based on previous data and prediction models. The identification of the structural adjustment requirements is not based on a single data point, but a comprehensive decision-making process, ensuring the effectiveness and practicality of the adjustment strategy. The results of the structural adjustment requirements analysis are generated, which are crucial for subsequent optimization activities.

[0179] Using the results of the structural adjustment requirements analysis, design a topology optimization strategy, perform node reconfiguration and connection optimization, and improve the overall performance of the system through adjustment methods to generate node and connection optimization records;

[0180] Using the data obtained from the structural adjustment requirements analysis, a topology optimization strategy is designed. This strategy includes node reconfiguration and connection optimization. During the optimization process, the interaction between nodes and the impact on system performance are referred to. The connections and configurations of each node are adjusted through a data-driven method to improve the efficiency and response speed of the entire water network. This process involves calculations and model adjustments to ensure that the optimization measures can be implemented under real conditions. The optimization records provide a basis for the continuous improvement of the system.

[0181] Combined with the node and connection optimization records, use the formula:

[0182]

[0183] Conduct a control implementation evaluation of the water network, emphasize the impact of the number of connections through a logarithmic function, and generate the water network control implementation results;

[0184] Among them, R adj represents the control implementation result of the adjusted water network, N k represents the number of connections of the kth node, γ k is the node criticality coefficient, and p represents the total number of nodes in the network, which is used to summarize the contributions of all nodes.

[0185] Formula:

[0186]

[0187] The benefit of the formula is that it emphasizes the non-linear impact of the number of node connections through a logarithmic function, so that even a small change in the number of connections will significantly affect the adjustment weight of the node, thereby guiding the network optimization strategy.

[0188] Detailed explanation of the formula and the derivation process of the formula calculation:

[0189] Set N1 = 3, N2 = 5, γ1 = 0.5, γ2 = 1.5.

[0190] R adj = 0.5·log(1 + 3) + 1.5·log(1 + 5) = 0.5·1.386 + 1.5·1.792 = 0.693 + 2.688 = 3.381

[0191] The results show that the node reconfiguration and connection optimization strategies can effectively improve the overall network performance, providing a quantitative basis for the evaluation of the system's control implementation.

[0192] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as the technical solution content of the present invention is not departed from, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A cloud-based real-time management system for a water supply network, characterized in that, The system includes: The dynamic optimization module obtains real-time sensor data through the cloud, extracts the water network pressure, flow rate, and pump speed, establishes a dynamic optimization framework, analyzes the relationship between the operation mode and real-time data, dynamically updates the model parameters, and forms the output of the dynamic optimization model; The genetic optimization module calls the output of the dynamic optimization model, sets the initial values of the pump speed and valve status, performs a global search, evaluates the matching degree of different parameter combinations, records the results of each search, and generates an optimization scheme for key parameters; The MINLP refinement module uses the optimization scheme for key parameters to process the constraint conditions and optimization objectives, performs the refinement of integer constraints and non-linear objectives, checks the feasibility of the solutions, records the results of each refinement, and generates an optimized result of feasible solutions; The topology analysis module constructs a water network diagram based on the optimized result of feasible solutions, calculates the node centrality and connectivity, performs the analysis of fluidity and pressure changes, identifies key nodes and vulnerable connections, records the analysis results, and generates the results of network structure characteristics; The adaptive adjustment module analyzes the structural adjustment requirements based on the results of network structure characteristics, performs topology structure optimization, executes node reconfiguration and connection optimization, records the implementation process of the adjustment, and generates the implementation results of water network control; 2. The real-time management system for a cloud-based water supply network according to claim 1, characterized in that The output of the dynamic optimization model includes the water network pressure, flow rate, and pump speed. The optimization scheme for key parameters includes the pump speed, valve status, and parameter combination. The optimized result of feasible solutions includes the constraint conditions, optimization objectives, and feasible solutions. The results of network structure characteristics include the node centrality, connectivity, and key nodes. The implementation results of water network control include topology structure optimization, node reconfiguration, and connection optimization.

3. The real-time management system for a cloud-based water supply network according to claim 2, wherein, The specific steps for obtaining the dynamic optimization framework are as follows: Call the real-time sensor data of the water network system through the cloud service, obtain the water network pressure, flow rate, and pump speed, screen and verify the measurement accuracy of each sensor, and establish an initial data set; Based on the initial data set, perform the relationship analysis among the water network pressure, flow rate, and pump speed, process the data using linear algebra operations, and generate a relationship matrix; Use the relationship matrix to construct a dynamic adjustment logic, perform real-time adjustment of the model parameters in combination with the changes in the real-time data stream, and adopt the formula: Calculate the current output parameters and generate a dynamic optimization framework; Among them, P new represents the newly calculated output parameter of the water network system, β0 represents the constant term used to adjust the baseline output level, β1 represents the weight coefficient of the water network pressure on the output, reflecting the sensitivity of the pressure change to the output parameter, β2 represents the weight coefficient of the water flow rate on the output, indicating the magnitude of the influence of the flow rate change on the output parameter, P pressure represents the pressure value of the current water network, α1 is the time decay coefficient, reflecting the decay rate of the system response with time change, t represents the time from the start of the system to the current time, P flow is the flow rate value of the current water network, P pump represents the numerical value of the current pump speed.

4. The cloud-based real-time management system for a water supply network according to claim 3, wherein The specific steps for obtaining the output of the dynamic optimization model are as follows: Retrieve the current model parameters from the dynamic optimization framework, analyze the key variables in combination with the real-time sensor data, identify the parameters that mainly affect the model output, and generate the analysis results of key parameters; Assign weights to each parameter in the analysis results of key parameters, calculate its contribution degree to the model output using a quantitative method, integrate the data, and generate a weighted relationship matrix; Apply the weighted relationship matrix and real-time data to update the weight coefficients and adjustment coefficients, and adopt the formula: Generate the output of the dynamic optimization model; Among them, w0 represents the base offset, which is used to adjust the baseline level of the model output, and w i is the weight of the i-th parameter, which affects the criticality of the parameter in the model output. X i is the real-time data of the i-th parameter, which is directly obtained from the dynamic optimization framework and reflects the value under the current environment or operating conditions. v j is the adjustment coefficient of the j-th parameter, which is used to fine-tune the sensitivity of the model to the j-th auxiliary data Y j . Y j is the auxiliary data related to the parameter.

5. The cloud-based real-time management system for a water supply network according to claim 4, wherein The specific steps for obtaining the optimization scheme for key parameters are as follows: Retrieve data from the output of the dynamic optimization model, set the initial parameter values of the pump speed and valve status, perform system simulation, and generate the initial simulation results; Using a global search algorithm, analyze the initial simulation results, evaluate the performance of different combinations of pump speeds and valve settings, and generate a performance matching result through system performance evaluation; Based on the performance matching result, use a mathematical model formula to perform data analysis, using the formula: Select the optimal solution from multiple parameter combinations to generate an optimized key parameter solution; Among them, S opt represents the score of the optimal solution, which is used to select the optimal parameter combination. e represents the base of the natural logarithm, which is a constant, and k i represents the critical weight of the i-th parameter, reflecting the influence of each parameter on the total score. x i is the actual value of the current i-th parameter, and x i,opt is the ideal or target value of the i-th parameter. (x i - x i,opt ) 2 calculates the square of the deviation between the current parameter value and the ideal value, which is used to amplify the influence of deviating from the ideal state.

6. The cloud-based real-time management system for a water supply network according to claim 5, wherein The specific steps for obtaining the optimized feasible solution result are as follows: According to the optimized key parameter solution, perform initial settings for integer constraints and non-linear objectives, call the preliminary refinement of model parameters, and perform basic verification of constraint conditions to generate a preliminary refinement result; Call the preliminary refinement result, perform multi-dimensional analysis of constraint conditions, judge the satisfaction degree of integer constraints and the approximation degree of non-linear objectives, perform comparative analysis of results, and generate a constraint satisfaction analysis result; Based on the constraint satisfaction analysis result, use the formula: Calculate the adaptability of the combination of constraints and target parameters, select the optimal parameter settings, and generate an optimized feasible solution result; Among them, w i represents the weight coefficient of the i-th constraint condition, used to adjust the influence of the differential constraint condition on the optimization result, k i represents the adjustment coefficient of the i-th constraint condition, used to adjust the sensitivity of the constraint value in the formula, and affects the response intensity of the objective function to the deviation of the constraint value from the target, c i represents the current constraint value, t i represents the target value of the i-th constraint condition.

7. The cloud-based real-time water supply network management system according to claim 6, characterized in that, The specific steps for obtaining the network structure feature result are as follows: According to the optimized feasible solution result, construct a water network diagram, collect basic data on nodes and connection relationships, calculate the basic connectivity between nodes, and generate a preliminary network diagram result; Call the preliminary network diagram result, calculate the node centrality, analyze the key importance of nodes in the network, and perform connectivity analysis based on key importance indicators to generate a node centrality analysis result; Based on the node centrality analysis result, perform analysis of fluidity and pressure changes, judge key nodes and vulnerable connections, using the formula: Calculate the degree of influence of fluidity on key nodes, identify key nodes, and generate a network structure feature result; Among them, f j represents the flow rate, P j represents the node pressure, D j represents the connection vulnerability, C crit represents the comprehensive influence degree of critical nodes.

8. The cloud-based real-time water supply network management system according to claim 7, wherein The specific steps for obtaining the water network control implementation result are as follows: Based on the network structure feature result, analyze the topological requirements of the existing water network, determine the key areas for structural adjustment, and generate a structural adjustment requirement analysis result; Use the structural adjustment requirement analysis result to design a topological structure optimization strategy, perform node reconfiguration and connection optimization, and improve the overall performance of the system through adjustment methods to generate a node and connection optimization record; Combined with the node and connection optimization record, use the formula: Conduct a control implementation evaluation of the water network, emphasize the impact of the number of connections through a logarithmic function, and generate a water network control implementation result; Among them, R adj represents the implementation result of the adjusted water network control, N k represents the number of connections of the k-th node, γ k is the node criticality coefficient, and p represents the total number of nodes in the network, which is used to summarize the contributions of all nodes.

Images