Water supply pipe network optimization scheduling method and system based on multi-model coupling

Abstract

The invention provides a water supply pipe network optimization scheduling method and system based on multi-model coupling, and the method comprises the steps: collecting the basic data of a regional pipe network, and building a water supply pipe network hydraulic model; obtaining a water supply network operation scheduling target, and establishing a water supply network scheduling scene model; historical monitoring data of a water supply network are acquired, a node water demand prediction model and a node water demand change curve prediction model are constructed by using a neural network algorithm, and node predicted water demand and a node water demand change curve during prediction are respectively output; constructing a water supply pipe network optimization scheduling model based on multi-model coupling, performing optimization by using an improved particle swarm algorithm, outputting a water supply pipe network optimization scheduling scheme, and introducing an optimization scheduling evaluation index to perform scheduling scheme evaluation; and constructing a water supply pipe network optimization scheduling scheme screening model, and obtaining an optimal water supply pipe network optimization scheduling scheme. According to the method, a multi-model coupling mode is adopted, the prediction error is effectively reduced, the optimization efficiency is improved, and intelligent and precise scheduling of the water supply pipe network is realized.

Description

Technical Field

[0001] The present invention belongs to the field of water supply network optimization scheduling, and specifically relates to a water supply network optimization scheduling method and system based on multi-model coupling. Background Art

[0002] With the continuous expansion of urban scale and the continuous increase of urban population, the scale and topological complexity of urban water supply network systems are also gradually increasing. The traditional experience-based manual scheduling method cannot achieve intelligent and precise regulation, which easily causes a lot of energy waste. There are often problems such as imbalance between supply and demand, insufficient water pressure during peak water use, excessive fluctuation of pipe network pressure, and increased probability of pipe network burst. It is difficult to adapt to the current water supply network scheduling needs. Therefore, it is very necessary to provide an intelligent and precise water supply network scheduling solution.

[0003] Chinese patent CN118644015A discloses a pipe network optimization scheduling system and method based on hydraulic model and neural network algorithm, which constructs a pipe network hydraulic model based on the collected water supply pipe network structure data, used to simulate and analyze the dynamic behavior of water flow in the pipe network, and constructs a scheduling model based on historical pipe network water supply data and neural network algorithm, learns and predicts future water demand and water supply mode, and improves the accuracy and efficiency of scheduling. Chinese patent CN115860192A discloses a water supply pipe network optimization scheduling method based on fuzzy neural network and genetic algorithm, which inputs the water supply flow and pressure parameters of each water plant water supply pump station into the trained neural network model, which is used to predict the flow and pressure values ​​of each measuring point in the water supply pipe network, and optimizes the water supply flow and pressure parameters of each water plant water supply pump station based on genetic algorithm. The above method only uses a single prediction model based on neural network, which leads to large prediction errors and high sampling frequency requirements, and the accuracy of the scheduling plan is difficult to guarantee. Summary of the invention

[0004] In view of the problems existing in the above-mentioned urban water supply network system and the limitations of the current method of obtaining the optimal scheduling plan for the water supply network, the present invention provides a water supply network optimal scheduling method and system based on multi-model coupling.

[0005] Based on the above purpose, the technical solution adopted by the present invention is as follows:

[0006] A water supply network optimization scheduling method based on multi-model coupling includes the following steps:

[0007] S1. Collect basic data of regional pipe network and establish hydraulic model of water supply pipe network;

[0008] S2. Obtain the water supply network operation scheduling target and establish a water supply network scheduling scenario model;

[0009] S3. Obtain the historical monitoring data of the water supply network, randomly divide the historical monitoring data of the water supply network into a training set and a validation set according to a ratio, use a neural network algorithm to construct a node water demand prediction model and a node water demand time-varying curve prediction model, which respectively output the predicted node water demand and the predicted node water demand time-varying curve, and use the training set to train the node water demand prediction model and the node water demand time-varying curve prediction model respectively to obtain the trained node water demand prediction model and the trained node water demand time-varying curve prediction model;

[0010] S4. Input the validation set into the trained node water demand prediction model and the trained node water demand time-varying curve prediction model respectively to generate a node water demand prediction result and a node water demand time-varying curve prediction result, set a water demand prediction evaluation index and a water demand time-varying curve evaluation index. If the prediction results meet the evaluation criteria, obtain the trained node water demand prediction model and the trained node water demand time-varying curve prediction model respectively and enter S5. If they do not meet the evaluation criteria, return to S3;

[0011] S5. Couple the water supply network hydraulic model, the water supply network scenario scheduling model, the node water demand prediction model and the node water demand time-varying curve prediction model to construct an optimized water supply network scheduling model based on multi-model coupling, and use an improved particle swarm algorithm to optimize the optimized water supply network scheduling model based on multi-model coupling to output an optimized water supply network scheduling plan;

[0012] The improved particle swarm algorithm is based on the standard particle swarm algorithm, including improving the inertia weight, adding a penalty function and restricting the particle speed and the particle position range;

[0013] The calculation formula for the improved inertia weight is: ;

[0014] In the formula, ω op represents the improved inertia weight, ω max represents the initial inertia weight, ω min represents the inertia weight at the maximum number of iterations, σ represents the density of feasible solutions in the particle swarm;

[0015] The expression of the penalty function is: ;

[0016] In the formula, f pe ( x) represents the penalty function, where the penalty coefficient , μ and γ represent non - negative parameters to be debugged, α and β are values not less than 1;

[0017] The specific range for restricting the particle velocity and particle position is as follows: ;

[0018] In the formula, v max and v min respectively represent the maximum velocity and minimum velocity of the particle, x max and x min respectively represent the maximum position and minimum position of the particle;

[0019] S6. Introduce an optimized scheduling evaluation index to evaluate the optimized scheduling plan of the water supply network. If it meets the optimized scheduling evaluation criteria, save the optimized scheduling plan of the water supply network and continue the iterative calculation. If it does not meet the optimized scheduling evaluation criteria, go to step S7;

[0020] S7. Construct a screening model for the optimized scheduling plan of the water supply network to obtain the optimal optimized scheduling plan of the water supply network.

[0021] Preferably, step S1 further includes: The basic data of the regional water supply network includes network GIS attributes, user revenue meter reading data, network flow monitoring data, network pressure monitoring data, water tank water level monitoring data, pump characteristic data, pump operation data, month, weather, temperature, and holiday distribution; The network GIS attributes include network topology information, pipeline material, pipeline size, node number, and DMA partition number.

[0022] Preferably, step S2 further includes: The operation scheduling objectives of the water supply network include meeting the water supply pressure demand, reducing the system operation energy consumption, reducing the internal pressure fluctuation of the network, and reducing the network leakage rate;

[0023] The scheduling scenario model of the water supply network includes an objective function and constraint conditions. The objective function includes the lowest total operation energy consumption, and the calculation formula for the total operation energy consumption is: ;

[0024] In the formula, E ( n ) represents the total operation energy consumption of all pumps in 24 hours a day, t represents any time period within a day, ρrepresents the water body density, g represents the acceleration due to gravity, Q i,t represents the i th pump's flow rate at the t time period, H i,t represents the i th pump's head at the t time period, η i,t represents the i th pump's working efficiency at the t time period;

[0025] The expression of the said constraint condition is: ;

[0026] In the formula, n i,t represents the i th pump's speed ratio at the t time period, P j,t represents the j th control point's pressure at the t time period, V k,t represents the k th water tank's water volume at the t time period.

[0027] Preferably, step S3 further includes: The historical monitoring data of the water supply network includes the historical monitoring data of the daily meter reading water volume of nodes and the historical monitoring data of the total flow of the DMA partition main pipe. The GA-BP neural network is used to construct the node water demand prediction model and the node water demand time-varying curve prediction model respectively.

[0028] Randomly divide the historical monitoring data of the daily meter reading water volume of nodes into training set 1 and validation set 1 according to the ratio of 8:2. The training set 1 is used to train the node water demand prediction model to obtain the trained node water demand prediction model;

[0029] Randomly divide the historical monitoring data of the total flow of the DMA partition main pipe into training set 2 and validation set 2 according to the ratio of 8:2. The training set 2 is used to train the node water demand time-varying curve prediction model to obtain the trained node water demand time-varying curve prediction model.

[0030] Preferably, step S4 further includes: inputting the verification set 1 into the trained node water demand prediction model for verification to generate the node water demand prediction result; inputting the verification set 2 into the trained node water demand time-varying curve prediction model for verification to obtain the DMA partition main pipe flow prediction time-varying curve, normalizing the DMA partition main pipe flow prediction time-varying curve, and combining the predicted node water demand to generate the node water demand time-varying curve prediction result;

[0031] The water demand prediction evaluation index includes NSE wd , and its calculation formula is: ;

[0032] In the formula, q s represents the measured water demand of the s th node, represents the predicted water demand of the s th node, represents the average value of the measured water demand of the s th node, and the water demand prediction evaluation standard is that the NSE wd ≥0.8;

[0033] The water demand time-varying curve prediction evaluation index includes NSE tc , and its calculation formula is: ;

[0034] In the formula, q l represents the measured flow of the l th pipe section, represents the predicted flow of the l th pipe section, represents the average value of the measured flow of the l th pipe section, and the water demand time-varying curve prediction evaluation standard is that the NSE tc ≥0.8.

[0035] Preferably, step S6 further includes: The optimization scheduling evaluation index includes the number of iterations T. When T ≤ 150, it meets the evaluation standard, saves the water supply network optimization scheduling plan, and continues the iterative calculation; otherwise, it enters step S7.

[0036] Preferably, step S7 further includes: The water supply network optimization scheduling plan screening model includes the pump station operation cost, and the expression of the pump station operation cost is: ;

[0037] In the formula, F cost represents the operation cost of the pumping station, δ represents the electricity price, and N t represents the number of operating water pumps in the t-th time period. represents the motor efficiency of the i-th water pump in the t-th time period. The optimal water supply network optimization scheduling scheme includes minimizing the operation cost of the pumping station.

[0038] The present invention also provides a water supply network optimization scheduling system based on multi-model coupling, including the following modules:

[0039] Data collection module: used to collect basic data of the regional water supply network, operation scheduling objectives of the water supply network, and historical monitoring data of the water supply network;

[0040] Model construction module: used to construct a water supply network hydraulic model, a water supply network scheduling scenario model, a node water demand prediction model, a node water demand time-varying curve prediction model, a water supply network optimization scheduling model based on multi-model coupling, and a water supply network optimization scheduling scheme screening model;

[0041] Model training module: used to train and verify the node water demand prediction model and the node water demand time-varying curve prediction model;

[0042] Scheduling evaluation module: used to evaluate the water supply network optimization scheduling scheme output by the water supply network optimization scheduling model based on multi-model coupling;

[0043] Scheme screening module: used to obtain the optimal water supply network optimization scheduling scheme.

[0044] The advantages of the present invention compared with the existing methods are as follows:

[0045] (1) The present invention adopts a primary optimization scheduling method to directly and uniformly schedule the water pumps in the water treatment plant and each level of pumping stations. Compared with the secondary optimization scheduling method of the traditional water supply network, it can effectively address problems such as high energy consumption in water supply network scheduling, insufficient water supply pressure, large fluctuations in network pressure, and high leakage, realize the reasonable allocation of water supply resources, and improve the overall operation efficiency and stability of the water supply system;

[0046] (2) The present invention supports the deployment of the overall scheme under the condition of the original or a small number of newly added flow and pressure monitoring points, variable frequency water pumps and other infrastructure, greatly reducing the transformation and operation and maintenance costs of the water supply network system;

[0047] (3) In the prior art, only a single neural network model is used for water demand prediction. This method has problems such as large prediction errors and high requirements for sampling frequency. In contrast, the present invention constructs a node water demand prediction model and a node water demand time-varying curve prediction model based on the GA-BP neural network algorithm. Through the coupling effect of the two prediction models, considering both the total water demand and the time-varying characteristics, accurate prediction of the node water demand and its time-varying curve is achieved, which is more in line with the application scenario of actual water supply network operation and scheduling.

[0048] (4) The present invention makes multiple improvements on the basis of the standard particle swarm optimization algorithm, including improving the inertia weight, adding a penalty function, and restricting the range of particle velocity and position, etc. This significantly reduces the number of parameters that need to be adjusted, constructs an optimized scheduling model for the water supply network based on multi-model coupling, and optimizes this model based on the improved particle swarm optimization algorithm, supporting automatic adjustment and optimization according to the optimization results, and significantly improving the optimization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0050] Figure 1 It is a schematic flowchart of an optimized scheduling method for a water supply network based on multi-model coupling according to an embodiment of the present invention;

[0051] Figure 2 It is a schematic structural diagram of an optimized scheduling method for a water supply network based on multi-model coupling according to an embodiment of the present invention;

[0052] Figure 3 It is a flowchart of optimizing an optimized scheduling model for a water supply network based on multi-model coupling according to an embodiment of the present invention;

[0053] Figure 4 It is a schematic structural diagram of an optimized scheduling system for a water supply network based on multi-model coupling according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] To make the objectives, technical solutions, and advantages of the present invention more obvious and understandable, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings and specific embodiments. It should be noted that the described embodiments are only a part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0055] See also Figure 1 and Figure 2 As shown, the present invention provides a water supply network optimization scheduling method based on multi-model coupling, comprising the following steps:

[0056] S1. Collect basic data of regional pipe network and establish hydraulic model of water supply network.

[0057] Step S1 in the embodiment of the present invention specifically includes:

[0058] Collect the basic data of regional pipeline network such as pipeline network GIS attribute data, user revenue meter reading data, pipeline network flow monitoring data, pipeline network pressure monitoring data, pool water level monitoring data, water pump characteristic data, water pump operation data, month, weather, temperature and holiday distribution. The pipeline network GIS attribute data includes pipeline network topology information, pipeline material, pipeline size, node number and DMA partition number. Based on the basic data of regional pipeline network, use EPANET software to establish a hydraulic model of water supply network of "water plant-water transmission network-boosting pump stations at all levels-water distribution network-user".

[0059] S2. Obtain the water supply network operation scheduling target and establish a water supply network scheduling scenario model.

[0060] Step S2 in the embodiment of the present invention specifically includes:

[0061] The water supply network operation scheduling objectives are obtained, including meeting the water supply pressure demand, reducing the system operation energy consumption, reducing the internal pressure fluctuation of the network and reducing the network leakage rate. A water supply network scheduling scenario model consisting of an objective function and constraint conditions is established. The objective function is to minimize the total operation energy consumption. The calculation formula of the total operation energy consumption is: ;

[0062] In the formula, E ( n ) represents the total energy consumption of all pumps for 24 hours a day. t Any time of day. ρ represents the water density, g represents the acceleration due to gravity, Q i,t Indicates i The water pump is t The flow rate during the period, H i,t Indicates i The water pump is t The lift during the period, η i,t Indicates i The water pump is t Efficiency of time period.

[0063] The expression of the constraint condition is as follows: ;

[0064] In the formula, n i,t represents the rotation speed ratio of the i th water pump in the t th time period, P j,t represents the pressure of the j th control point in the t th time period, V k,t represents the water volume of the k th water tank in the t th time period.

[0065] S3. Obtain the historical monitoring data of the water supply network, randomly divide the historical monitoring data of the water supply network into a training set and a validation set according to a ratio, and use a neural network algorithm to construct a node water demand prediction model and a node water demand time-varying curve prediction model, which respectively output the predicted node water demand and the node water demand prediction time-varying curve. Use the training set to train the node water demand prediction model and the node water demand time-varying curve prediction model respectively, and obtain the trained node water demand prediction model and the trained node water demand time-varying curve prediction model respectively.

[0066] Step S3 in the embodiment of the present invention specifically includes:

[0067] Obtain the historical monitoring data of the daily meter reading water volume of the nodes and the historical monitoring data of the main pipe flow of the DMA partition. Randomly divide the historical monitoring data of the daily meter reading water volume of the nodes and the historical monitoring data of the main pipe flow of the DMA partition into a training set and a validation set according to a ratio of 8:2. To effectively distinguish the two groups of data, name the training set and the validation set corresponding to the historical monitoring data of the daily meter reading water volume of the nodes as training set 1 and validation set 1 respectively, and name the training set and the validation set corresponding to the historical monitoring data of the main pipe flow of the DMA partition as training set 2 and validation set 2 respectively.

[0068] Use a GA-BP neural network to construct a node water demand prediction model and a node water demand time-varying curve prediction model respectively. Input training set 1 into the node water demand prediction model for training to obtain a trained node water demand prediction model. Input training set 2 into the node water demand time-varying curve prediction model for training to obtain a trained node water demand time-varying curve prediction model.

[0069] S4. Input the validation set into the trained node water demand prediction model and the trained node water demand time-varying curve prediction model respectively, generate the node water demand prediction result and the node water demand time-varying curve prediction result respectively, set the water demand prediction evaluation index and the water demand time-varying curve evaluation index. If the prediction results meet the evaluation criteria, obtain the trained node water demand prediction model and the trained node water demand time-varying curve prediction model respectively, and enter S5. If they do not meet the evaluation criteria, return to S3.

[0070] Step S4 in the embodiment of the present invention specifically includes:

[0071] Input the validation set 1 into the trained node water demand prediction model, output the predicted node water demand, and set the water demand prediction evaluation index NSE wd Evaluate the predicted node water demand, and the NSE wd expression is as follows: ;

[0072] In the formula, q s represents the measured water demand of the s th node, represents the predicted water demand of the s th node, represents the average value of the measured water demand of the s th node. When the NSE wd ≥0.8, obtain the trained node water demand prediction model and enter S5. When the NSE wd <0.8, retrain and validate the node water demand prediction model.

[0073] Input the validation set 2 into the trained node water demand time-varying curve prediction model, obtain the predicted time-varying curve of the DMA district main pipe flow rate, normalize the predicted time-varying curve of the DMA district main pipe flow rate, combine it with the predicted node water demand, output the predicted time-varying curve of the node water demand, and set the water demand time-varying curve prediction evaluation index NSE tc Evaluate the predicted time-varying curve of the node water demand, and the NSE tc calculation formula is as follows: ;

[0074] In the formula, q l represents the lThe measured flow rate of each pipe section, represents the l predicted flow rate of the th pipe section, l represents the average measured flow rate of the NSE tc ≥0.8, then the trained prediction model of the hourly variation curve of node water demand is obtained, and it enters S5. When the NSE tc <0.8, then the training and verification of the prediction model of the hourly variation curve of node water demand are carried out again.

[0075] Input the daily node meter reading water volume data and the DMA partition main pipe flow rate data into the trained node water demand prediction model and the trained prediction model of the hourly variation curve of node water demand respectively, and obtain the node water demand for the next day and the hourly variation curve of node water demand for the next day.

[0076] S5. Couple the water supply network hydraulic model, the water supply network scenario scheduling model, the node water demand prediction model and the prediction model of the hourly variation curve of node water demand to construct an optimized water supply network scheduling model based on multi-model coupling, and use the improved particle swarm optimization algorithm to optimize the optimized water supply network scheduling model based on multi-model coupling, and output the optimized water supply network scheduling scheme.

[0077] Step S5 in the embodiment of the present invention specifically includes:

[0078] The improved particle swarm optimization algorithm is based on the standard particle swarm optimization algorithm, and includes improving the inertia weight, adding a penalty function and restricting the particle speed and position range, specifically as follows:

[0079] The improved inertia weight includes:

[0080] The calculation formulas for the particle speed and position of the standard particle swarm optimization algorithm in the D-dimensional space are: ;

[0081] In the formula, d =1, 2, …, D represents the space dimension, m represents the population iteration times, and respectively represent the i th particle after m iterations at the d th dimension of the ω speed and the displacement, c 1 and c2 represents the learning factor. The former determines the trend of the particle searching for the historical optimal position and represents the memory and cognition of the particle. The latter determines the trend of the particle searching for the current population optimal position and represents the social cognition of the particle. Both usually take values from 0 to 2. and respectively represent the i th particle's historical optimal position and the population optimal position in the m th iteration on the d th dimension.

[0082] The calculation formula for the improved inertia weight is: ;

[0083] In the formula, ω op represents the improved inertia weight. σ is the density of the feasible solutions in the particle swarm. In the early stage of the optimization process, σ has a small value, ω op has a large value, which is beneficial to optimizing within the entire search space, quickly approaching the global optimal position, and avoiding falling into local optimal solutions. As the iteration process progresses step by step, the σ value gradually increases, and the ω op value gradually decreases, which is beneficial for the particles to concentrate on optimizing near the global optimal position and facilitating finding the global optimal solution.

[0084] The expression form of the multi-objective constrained optimization problem is: ;

[0085] In the formula, f ( x ) represents the multi-objective constrained optimization objective function. u ( x ) and v ( x ) represent the constraint conditions.

[0086] In the multi-objective constrained optimization objective function f ( x ), by adopting the method of adding a penalty function, the multi-objective constrained optimization problem is transformed into: ;

[0087] In the formula, fit ( x ) represents the fitness function. f pe ( x) represents the penalty function, where the penalty coefficient , μ and γ are non - negative parameters to be debugged, α and β are values not less than 1. The constraints of the transformed multi - objective constrained optimization problem are still u ( x ) and v ( x ).

[0088] In the embodiment of the present invention, the multi - objective constrained optimization objective function f ( x ) is the total operating energy consumption E ( n ). Therefore, the fitness function fit ( x ) is rewritten as: ;

[0089] When x takes values within the feasible region, then the value of fit ( x ) is 0, and the values of fit ( x ) and E ( n ) are the same, that is, the fitness function is the objective function.

[0090] The penalty coefficient A At the initial stage of the optimization process, the value of σ is small, A the value of A is large, which is beneficial to promoting the particle to fly into the feasible region for searching. As the optimization process iterates continuously, the value of σ gradually increases, and the value of

[0091] During the search flight of the particle, its movement trajectory is often random. Therefore, it is necessary to impose certain restrictions on the particle speed and position range to ensure that when the particle flies beyond the boundary, the next flight direction must be towards the feasible solution region and will not linger on the boundary. Specifically: ;

[0092] In the formula, v max and v min respectively represent the maximum speed and minimum speed of the particle, x max and x minrespectively represent the maximum position and the minimum position of the said particle. During the iteration process, if the particle velocity and position exceed the said limit range, the boundary value is taken. If the x ≤ x min when, the v takes the value of | v |. When the x ≥ x min when, the v takes the value of -| v |.

[0093] Please refer to Figure 3 as shown. The specific optimization process of the water supply network optimization scheduling model based on multi-model coupling is as follows:

[0094] Input the next-day water demand of the node and the next-day hourly variation curve of the node water demand into the water supply network hydraulic model to generate the next-day water supply network hydraulic model, and obtain t corresponding to =0 moment of the n i,t , input it into the next-day water supply network hydraulic model for simulation, and output the P j,t in the simulation result, the Q i,t , the H i,t and the V k,t , construct the E ( n ) and the fit ( x ), evaluate the advantages and disadvantages of the fit ( x ) to update the optimal positions of individuals and populations and the fit ( x ), perform continuous iterative optimization. When the set time is met, output the water supply network optimization scheduling plan for each moment of the next day.

[0095] S6. Introduce an optimization scheduling evaluation index to evaluate the water supply network optimization scheduling plan. If it meets the optimization scheduling evaluation criteria, save the water supply network optimization scheduling plan and continue iterative calculation. If it does not meet the optimization scheduling evaluation criteria, go to step S7.

[0096] Step S6 in the embodiment of the present invention specifically includes:

[0097] Please refer to Figure 3As shown, the optimization scheduling evaluation index includes the number of iterations. The optimization scheduling evaluation criterion is that when the number of iterations ≤ 150, it is considered to meet the optimization scheduling evaluation criterion, and the optimized water supply network scheduling scheme corresponding to time t is saved, and the iterative optimization continues. When the number of iterations > 150, it is considered not to meet the optimization scheduling evaluation criterion, and the optimized water supply network scheduling schemes corresponding to the 150th iteration at time t and the 5 lowest E ( n ) are selected and enter step S7.

[0098] S7. Construct a screening model for the optimized water supply network scheduling scheme to obtain the optimal optimized water supply network scheduling scheme.

[0099] Step S7 in the embodiment of the present invention specifically includes:

[0100] Construct a screening model for the optimized water supply network scheduling scheme, including the pumping station operation cost. The expression of the pumping station operation cost is: ;

[0101] In the formula, F cost represents the pumping station operation cost, δ represents the electricity price, N t represents the number of pumps in operation in the t-th period, represents the motor efficiency of the i-th pump in the t-th period. The optimal optimized water supply network scheduling scheme includes the lowest pumping station operation cost.

[0102] Using the pumping station operation cost, screen the multiple optimized water supply network scheduling schemes corresponding to each moment of the next day saved in step S6, output the optimal water supply optimization scheduling scheme for each moment of the next day, and form the optimal optimized water supply network scheduling scheme for the next day with the optimal water supply optimization scheduling schemes for each moment.

[0103] In this embodiment, by obtaining the basic information of the regional pipe network and the operation scheduling objectives of the water supply network system, a water supply network hydraulic model and a water supply network scheduling scenario model are respectively established. Using the neural network algorithm, a node water demand prediction model and a node water demand time-varying curve prediction model are constructed to obtain the node water demand for the next day and the node water demand time-varying curve for the next day. By coupling the water supply network hydraulic model, the water supply network scheduling scenario model, the node water demand prediction model, and the node water demand prediction time-varying curve prediction model, an optimized water supply network scheduling model based on multi-model coupling is constructed. Using the improved particle swarm algorithm for optimization, multiple optimized water supply network scheduling schemes for each moment of the next day are output, a screening model for the optimized water supply network scheduling scheme is constructed, and the optimal optimized water supply network scheduling scheme for the next day is obtained.

[0104] This method adopts a multi-model coupling approach, uses neural network algorithms to construct a node water demand prediction model and a node water demand time-varying curve prediction model, effectively reduces the prediction error, uses an improved particle swarm algorithm to greatly improve the optimization efficiency, realizes the intelligent and precise scheduling of the water supply network, has advantages such as simple deployment, and solves problems such as high energy consumption, insufficient water supply pressure, large fluctuations in pipe network pressure, and many leaks in the existing water supply network scheduling.

[0105] The following describes an optimized scheduling system for a water supply network based on multi-model coupling provided by the present invention. The optimized scheduling system for a water supply network based on multi-model coupling described below and the optimized scheduling method for a water supply network based on multi-model coupling described above can be mutually referenced.

[0106] Please refer to Figure 4 As shown, it includes: a data collection module 41, a model construction module 42, a model training module 43, a scheduling evaluation module 44, and a scheme screening module 45, where:

[0107] The data collection module: is used to collect basic data of the regional pipe network, the operation scheduling objectives of the water supply network, and the historical monitoring data of the water supply network;

[0108] The model construction module: is used to construct a water supply network hydraulic model, a water supply network scheduling scenario model, a node water demand prediction model, a node water demand time-varying curve prediction model, an optimized scheduling model for a water supply network based on multi-model coupling, and an optimized scheduling scheme screening model for a water supply network;

[0109] The model training module: is used to train and verify the node water demand prediction model and the node water demand time-varying curve prediction model;

[0110] The scheduling evaluation module: is used to evaluate the optimized scheduling scheme of the water supply network output by the optimized scheduling model for a water supply network based on multi-model coupling;

[0111] The scheme screening module: is used to obtain the optimal optimized scheduling scheme for the water supply network.

[0112] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of the present invention.

Claims

1. A water supply network optimization scheduling method based on multi-model coupling, characterized in that: The steps include: S1. Collect basic data of regional pipe network and establish hydraulic model of water supply pipe network; S2. Obtain the water supply network operation scheduling target and establish a water supply network scheduling scenario model; S3. Obtain historical monitoring data of the water supply network, randomly divide the historical monitoring data of the water supply network into a training set and a validation set in proportion, use a neural network algorithm to construct a node water demand prediction model and a node water demand time-varying curve prediction model, which respectively output node predicted water demand and node water demand prediction time-varying curve, and use the training set to train the node water demand prediction model and the node water demand time-varying curve prediction model, respectively, to obtain a trained node water demand prediction model and a trained node water demand time-varying curve prediction model, respectively; S4, input the validation set into the trained node water demand prediction model and the trained node water demand time-varying curve prediction model, respectively, generate node water demand prediction results and node water demand time-varying curve prediction results, set water demand prediction evaluation index and water demand time-varying curve evaluation index, if the prediction result meets the evaluation standard, respectively obtain the trained node water demand prediction model and the trained node water demand time-varying curve prediction model, and enter S5, if it does not meet the evaluation standard, return to S3; S5, coupling the water supply network hydraulic model, the water supply network scenario scheduling model, the node water demand prediction model and the node water demand time-varying curve prediction model, constructing a water supply network optimization scheduling model based on multi-model coupling, optimizing the water supply network optimization scheduling model based on multi-model coupling using an improved particle swarm algorithm, and outputting a water supply network optimization scheduling plan; The improved particle swarm algorithm is based on the standard particle swarm algorithm, including improving the inertia weight, adding a penalty function, and limiting the particle speed and particle position range; The calculation formula of the improved inertia weight is: ； In the formula, ω op represents the improved inertia weight, ω max represents the initial inertia weight, ω min represents the inertia weight at the maximum number of iterations, σ represents the density of feasible solutions in the particle swarm; The penalty function is expressed as: ； In the formula, f pe ( x ) represents the penalty function, where the penalty coefficient , μ and γ Indicates a non-negative parameter that needs to be debugged. α and β is a value not less than 1; The particle velocity and particle position ranges are specifically limited as follows: ； In the formula, v max and v min represent the maximum and minimum speeds of the particle, respectively. x max and x min represent the maximum position and the minimum position of the particle respectively; S6, introducing the optimization scheduling evaluation index to evaluate the water supply network optimization scheduling scheme, if it meets the optimization scheduling evaluation standard, then save the water supply network optimization scheduling scheme, continue to iterate the calculation, if it does not meet the optimization scheduling evaluation standard, then enter step S7; S7. Construct a water supply network optimization scheduling scheme screening model to obtain the optimal water supply network optimization scheduling scheme.

2. The water supply network optimization scheduling method based on multi-model coupling according to claim 1 is characterized in that: Step S1 also includes: the regional pipeline network basic data includes pipeline network GIS attributes, user revenue meter reading data, pipeline network flow monitoring data, pipeline network pressure monitoring data, pool water level monitoring data, water pump characteristic data, water pump operation data, month, weather, temperature and holiday distribution; the pipeline network GIS attributes include pipeline network topology information, pipeline material, pipeline size, node number and DMA partition number.

3. The water supply network optimization scheduling method based on multi-model coupling according to claim 1 is characterized in that: Step S2 also includes: the water supply network operation scheduling objectives include meeting water supply pressure requirements, reducing system operation energy consumption, reducing pressure fluctuations inside the network, and reducing network leakage rate; The water supply network scheduling scenario model includes an objective function and constraints. The objective function includes the lowest total energy consumption. The calculation formula of the total energy consumption is: ； In the formula, E ( n ) represents the total energy consumption of all pumps for 24 hours a day. t Any time of day. ρ represents the water density, g represents the acceleration due to gravity, Q i,t Indicates i The water pump is t The flow rate during the period, H i,t Indicates i The water pump is t The lift during the period, η i,t Indicates i The water pump is t Work efficiency during the period; The constraint condition is expressed as: ； In the formula, n i,t Indicates i The water pump is t The speed ratio of the time period, P j,t Indicates j The control point is t The pressure of time, V k,t Indicates k The pool is in t The volume of water during a period.

4. The water supply network optimization scheduling method based on multi-model coupling according to claim 1 is characterized in that: Step S3 also includes: the water supply network historical monitoring data includes node daily meter reading water volume historical monitoring data and DMA zone main flow historical monitoring data, and the node water demand prediction model and the node water demand time-varying curve prediction model are respectively constructed using a GA-BP neural network; The node daily meter reading water volume historical monitoring data is randomly divided into a training set 1 and a validation set 1 in a ratio of 8:2, wherein the training set 1 is used to train the node water demand prediction model to obtain the trained node water demand prediction model; The historical monitoring data of the DMA partition main flow is randomly divided into a training set 2 and a validation set 2 in a ratio of 8:

2. The training set 2 is used to train the node water demand time-varying curve prediction model to obtain the trained node water demand time-varying curve prediction model.

5. The water supply network optimization scheduling method based on multi-model coupling according to claim 1 is characterized in that: Step S4 also includes: inputting the verification set 1 into the trained node water demand prediction model for verification, and generating the node water demand prediction result; inputting the verification set 2 into the trained node water demand time-varying curve prediction model for verification, and obtaining the DMA partition main flow prediction time-varying curve, normalizing the DMA partition main flow prediction time-varying curve, and combining it with the node predicted water demand to generate the node water demand time-varying curve prediction result; The water demand prediction evaluation index includes NSE wd , and its calculation formula is: ； In the formula, q s Indicates s The measured water demand of each node, Indicates s The predicted water demand of each node, Indicates s The measured water demand average of the nodes, the water demand prediction evaluation standard is NSE wd ≥0.8; The water demand time-varying curve prediction evaluation index includes NSE tc , and its calculation formula is: ； In the formula, q l Indicates l The measured flow rate of each pipe section, Indicates l The predicted flow rate of each pipe section, Indicates l The average measured flow rate of each pipe section, the water demand time change curve prediction evaluation standard is NSE tc ≥0.

8.

6. The water supply network optimization scheduling method based on multi-model coupling according to claim 1 is characterized in that: Step S6 also includes: the optimization scheduling evaluation index includes the number of iterations T. When T≤150, the evaluation standard is met, the water supply network optimization scheduling plan is saved, and the iterative calculation continues. Otherwise, step S7 is entered.

7. The water supply network optimization scheduling method based on multi-model coupling according to claim 1 is characterized in that: Step S7 also includes: the water supply network optimization scheduling scheme screening model includes pump station operation costs, and the expression of the pump station operation costs is: ； In the formula, F cost represents the operating cost of the pump station, δ represents the electricity price, N t represents the number of pumps running in period t, Represents the motor efficiency of the ith water pump in the tth time period, and the optimal water supply network optimization scheduling plan includes the lowest operating cost of the pump station.

8. A water supply network optimization scheduling system based on multi-model coupling, characterized in that: Includes the following modules: Data collection module: used to collect basic data of regional pipe network, operation and dispatching targets of water supply network and historical monitoring data of water supply network; Model building module: used to build a hydraulic model of the water supply network, a water supply network scheduling scenario model, a node water demand prediction model, a node water demand time-varying curve prediction model, a water supply network optimization scheduling model based on multi-model coupling, and a water supply network optimization scheduling scheme screening model; Model training module: used to train and verify the node water demand prediction model and the node water demand time-varying curve prediction model; Scheduling evaluation module: used to evaluate the water supply network optimization scheduling scheme output by the water supply network optimization scheduling model based on multi-model coupling; Solution screening module: used to obtain the optimal water supply network optimization scheduling solution.

Images