CN116011756A

CN116011756A - NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling method

Info

Publication number: CN116011756A
Application number: CN202211700602.9A
Authority: CN
Inventors: 刘小梅; 曾思育
Original assignee: Tsinghua University
Current assignee: Tsinghua University
Priority date: 2022-12-28
Filing date: 2022-12-28
Publication date: 2023-04-25
Anticipated expiration: 2042-12-28
Also published as: CN116011756B

Abstract

The application relates to a NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling method, which comprises the following steps: constructing an initial river hydrodynamic water quality model based on basic data of a target river network, calibrating and verifying by utilizing water quality monitoring data, generating a final river hydrodynamic water quality model which meets the requirement that errors between a simulation result and the water quality monitoring data of the target river network within a preset time period meet a preset accurate standard, accessing real-time water quantity water quality monitoring data and rainfall forecast data, constructing a multi-target optimal scheduling model for improving the standard rate of the section water quality, and coupling and performing iterative computation on the multi-target optimal scheduling model and the final river hydrodynamic water quality model based on a preset NSGA-II algorithm to obtain an optimal scheduling strategy of the target river network system under multiple targets so as to execute river water quality simulation of the optimal scheduling strategy. Therefore, the technical problems that in the related technology, the adopted weight coefficient method has great influence on the main view and is difficult to perform comprehensive multi-objective river water quality scheduling optimization are solved.

Description

NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling method

Technical Field

The application relates to the technical field of sewage treatment, in particular to a river water quality multi-objective optimization scheduling method based on NSGA-II algorithm.

Background

With the high-speed development of urban construction in China, urban river channels become a main body for containing sewage gradually, but the water environment of the river channels is easily damaged due to the limitation of the polluted water amount and the sewage treatment technology, the water ecology cannot be guaranteed, the problem of water environment in the city is more serious, and the problem that how to treat black and odorous water bodies of urban rivers and lakes becomes the problem that urban managers have to face. In order to effectively treat the water pollution of the urban river network and improve the water quality of the river channel, the water pollution control theory and technical research of the urban river network are necessary to be developed, and the urban water environment is improved by combining engineering means and non-engineering means, so that the method has important significance for promoting ecological civilization and building beautiful cities.

At present, the improvement of the urban river water quality mainly depends on engineering measures, and the optimal scheduling is used as an important non-engineering means, and the application in the urban river mainly surrounds flood control and drainage, and lacks of related practical application for reducing the black and odorous pollution of the river and improving the water quality standard rate.

The river water quality optimizing and scheduling problem is often a complex multi-objective problem, namely the water quality of a plurality of control sections meets the standard, the water quality of a plurality of water quality pollutants meets the standard, the requirements for improving the environment and simultaneously giving consideration to economic benefits are met, the objectives are various and contradictory, a multi-objective optimizing method can be adopted in the related technology to meet the requirements of a plurality of objectives, however, the weighting coefficient method adopted in the multi-objective optimizing method in the related technology has great influence on the main aspect, the comprehensive multi-objective river water quality scheduling and optimizing is difficult to carry out, and the improvement is needed.

Disclosure of Invention

The application provides a NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling method, which aims to solve the technical problems that in the related technology, the adopted weight coefficient method has great influence on the main view, and comprehensive multi-objective river channel water quality scheduling optimization is difficult to perform.

An embodiment of a first aspect of the present application provides a multi-objective optimization scheduling method for river water quality based on NSGA-II algorithm, including the following steps: constructing an initial river hydrodynamic water quality model based on basic data of a target river network; collecting water quality monitoring data of the target river network within a preset time period, and calibrating and verifying the initial river hydrodynamic water quality model by utilizing the water quality monitoring data to generate a final river hydrodynamic water quality model which meets the requirement that the error between a simulation result and the water quality monitoring data meets a preset accurate standard; the final river hydrodynamic water quality model is accessed into real-time water quantity water quality monitoring data and rainfall forecast data and is deployed in a target online system, and a multi-target optimal scheduling model for improving the standard rate of the section water quality is constructed aiming at a simulation period with the standard exceeding of the section water quality to be checked as a standard scheme to be optimized; and in the Python environment, coupling and performing iterative computation on the multi-objective optimal scheduling model and the final river hydrodynamic water quality model based on a preset NSGA-II algorithm to obtain an optimal scheduling strategy of the objective river network system under multi-objective, and executing river water quality simulation of the optimal scheduling strategy in the Python environment.

Optionally, in one embodiment of the present application, the base data includes at least one of river network shape and river cross-section shape data, scheduling object data, and pollution load data, wherein the scheduling object data includes one or more of a geographic location of a pump station or a gate, a design parameter, and scheduling rule data; the pollution load data comprises one or more of discharge position, discharge capacity, population domestic sewage data of each administrative district in the river basin, agricultural sewage data, animal husbandry sewage data and industrial sewage data.

Optionally, in an embodiment of the present application, the collecting the water quality monitoring data of the target river network within the preset time period, and calibrating and verifying the initial river hydrodynamic water quality model by using the water quality monitoring data, and generating a final river hydrodynamic water quality model that meets the error between the simulation result and the water quality monitoring data and meets the preset accurate standard requirement includes: collecting water quality monitoring data of a target river network for calibration and verification within a preset time period, wherein the water quality monitoring data comprise pollutant concentration data of important drainage ports on a river channel and pollutant concentration data of water quality monitoring equipment; randomly extracting part of the water quality monitoring data to be used as model rating, and correcting model parameters to achieve the matching degree of a model simulation result and measured data to reach a preset condition; randomly extracting at least one data from the residual data of the water quality monitoring data to be used as a model for verification, comparing a model result with a rated model result with the measured data, and performing error evaluation.

Optionally, in an embodiment of the present application, the optimization objective of the multi-objective optimization scheduling model is that the water quality superscale rate is the lowest and the water replenishment amount is the smallest in the evaluation section simulation period, the decision variable is a hydraulic scheduling object of a pump station or a gate station available for scheduling in the reference scheme, and the constraint condition is an upper limit and a lower limit of the control capability of each scheduling object.

Optionally, in an embodiment of the present application, in a Python environment, coupling and iteratively calculating the multi-objective optimization scheduling model and the final river hydrodynamic water quality model based on a preset NSGA-II algorithm to obtain an optimal scheduling policy of the objective river network system under multi-objective, and executing a river water quality simulation of the optimal scheduling policy in the Python environment, where the method includes: in the Python environment, determining each parameter of the preset NSGA-II algorithm, wherein each parameter comprises a population parameter, a maximum iteration number and a variation probability; in the Python environment, positioning the final river hydrodynamic water quality model, reading a scheduling curve file of each scheduling object of an index model, randomly generating a scheduling scheme of a specified population scale, randomly generating a scheduling object strategy in a set constraint condition range, and writing and covering the scheduling object strategy in the corresponding scheduling curve file of each scheduling object; driving the final river hydrodynamic water quality model in the Python environment, and re-executing river water quality simulation on each scheduling scheme by adopting updated scheduling curve files; according to the simulation results of each scheduling scheme, obtaining the water quality results of the specified pollutants of the simulated examination section and the total water supplementing amount under the current scheduling scheme, calculating the function value of the optimization target, judging whether the maximum iteration step number is reached or the target value in a plurality of successive generations is not reduced, if not, updating the scheduling strategy of the scheduling object by the preset NSGA-II algorithm, and continuing the iterative optimization of a new round; if the maximum iteration step number is reached or the target value in a plurality of continuous generations is not reduced, stopping optimizing calculation, returning to an optimal scheduling strategy corresponding to the current optimal target value, and writing the optimal scheduling strategy into the scheduling curve file; and in the Python environment, executing the river channel water quality simulation of the optimal scheduling strategy to obtain a result with minimum water supplementing quantity and minimum cross section water quality exceeding rate under the current simulation scheme.

An embodiment of a second aspect of the present application provides a multi-objective river water quality optimization scheduling device based on NSGA-II algorithm, including: the first construction module is used for constructing an initial river hydrodynamic water quality model based on basic data of a target river network; the generation module is used for collecting the water quality monitoring data of the target river network within a preset time period, and calibrating and verifying the initial river hydrodynamic water quality model by utilizing the water quality monitoring data to generate a final river hydrodynamic water quality model which meets the requirement of a preset accurate standard for the error between a simulation result and the water quality monitoring data; the second construction module is used for accessing the final river hydrodynamic water quality model into real-time water quantity water quality monitoring data and rainfall forecast data, deploying the final river hydrodynamic water quality model into a target online system, and constructing a multi-target optimization scheduling model for improving the standard rate of the cross-section water quality aiming at a simulation period with the standard exceeding of the cross-section water quality to be evaluated as a reference scheme to be optimized; and the optimization module is used for coupling and performing iterative computation on the multi-objective optimization scheduling model and the final river hydrodynamic water quality model based on a preset NSGA-II algorithm in a Python environment to obtain an optimal scheduling strategy of the objective river network system under multi-objective conditions, and executing river water quality simulation of the optimal scheduling strategy in the Python environment.

Optionally, in one embodiment of the present application, the generating module includes: the water quality monitoring system comprises an acquisition unit, a verification unit and a verification unit, wherein the acquisition unit is used for acquiring water quality monitoring data of a target river network for calibration and verification in a preset time period, and the water quality monitoring data comprise pollutant concentration data of important drainage positions on a river channel and pollutant concentration data of positions where water quality monitoring equipment is installed; the correction unit is used for randomly extracting part of the water quality monitoring data to be used as model calibration, and achieving the coincidence degree of a model simulation result and measured data to reach a preset condition by correcting model parameters; and the evaluation unit is used for randomly extracting at least one data from the residual data of the water quality monitoring data to be used as a model for verification, comparing the model result with the actual measured data, and performing error evaluation.

Optionally, in one embodiment of the present application, the optimizing module includes: the determining unit is used for determining each parameter of the preset NSGA-II algorithm in the Python environment, wherein each parameter comprises a population parameter, a maximum iteration number and a variation probability; the generation unit is used for positioning the final river hydrodynamic water quality model in the Python environment, reading the scheduling curve file of each scheduling object of the index model, randomly generating a scheduling scheme of a specified population scale, randomly generating a scheduling object strategy in a set constraint condition range, and writing and covering the scheduling object strategy in the corresponding scheduling curve file of each scheduling object; the driving unit is used for driving the final river channel hydrodynamic water quality model in the Python environment, and re-executing river channel water quality simulation on each scheduling scheme by adopting the updated scheduling curve file; the calculation unit is used for obtaining the water quality result of the specified pollutant of the simulated examination section and the total water supplementing amount under the current scheduling scheme according to the simulation result of each scheduling scheme, calculating the function value of the optimization target, judging whether the maximum iteration step number is reached or the target value in a plurality of successive generations is not reduced any more, if not, updating the scheduling strategy of the scheduling object by the preset NSGA-II algorithm, and continuing the iterative optimization of a new round; the writing unit is used for stopping optimization calculation when the maximum iteration step number is reached or the target value in a plurality of continuous generations is not lowered any more, returning to the optimal scheduling strategy corresponding to the current optimal target value and writing the optimal scheduling strategy into the scheduling curve file; and the execution unit is used for executing the river channel water quality simulation of the optimal scheduling strategy in the Python environment to obtain the result of minimum water supplementing quantity while minimum exceeding rate of the section water quality under the current simulation scheme.

An embodiment of a third aspect of the present application provides an electronic device, including: the system comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the program to realize the NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling method.

An embodiment of the fourth aspect of the present application provides a computer readable storage medium storing a computer program, which when executed by a processor, implements the above multi-objective river water quality optimization scheduling method based on NSGA-II algorithm.

According to the embodiment of the application, the river water power water quality model can be built, calibrated and verified, the scheduling model for improving the standard rate of the river water quality is built, scheduling optimizing based on NSGA-II algorithm is executed, the hydrodynamic water quality model is used as a virtual experimental environment, the scheduling decision result is fully tested and evaluated, the non-dominant ordering genetic algorithm with elite strategy is utilized, the multi-objective problem is directly solved under the reference scheme, subjectivity of a weight method on the multi-objective optimizing problem is avoided, the result that the water supplementing amount is minimum while the water quality of the river section exceeds the standard rate is achieved, real-time simulation analysis and automatic optimizing scheme selection recommendation are achieved by combining the online river water power water quality model with the multi-objective optimizing algorithm, daily scheduling management is served, and the application prospect is wide. Therefore, the technical problems that in the related technology, the adopted weight coefficient method has great influence on the main view and is difficult to perform comprehensive multi-objective river water quality scheduling optimization are solved.

Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.

Drawings

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

FIG. 1 is a flowchart of a river water quality multi-objective optimization scheduling method based on NSGA-II algorithm according to an embodiment of the present application;

FIG. 2 is a flowchart of a NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling method according to one embodiment of the application;

FIG. 3 is a schematic diagram of an initial river hydrodynamic water quality model of a river water quality multi-objective optimization scheduling method based on NSGA-II algorithm according to one embodiment of the present application;

FIG. 4 is a schematic diagram showing comparison of simulation results of a final river hydrodynamic water quality model of a river water quality multi-objective optimization scheduling method based on NSGA-II algorithm according to one embodiment of the present application;

FIG. 5 is a flow chart of a method of performing NSGA-II algorithm-based scheduling optimization in accordance with one embodiment of the present application;

FIG. 6 is a schematic diagram of an optimization result of a multi-objective optimization scheduling method for river channel water quality based on NSGA-II algorithm according to an embodiment of the present application;

FIG. 7 is a schematic structural diagram of a NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling device according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present application and are not to be construed as limiting the present application.

The NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling method is described below with reference to the accompanying drawings. Aiming at the technical problems that the adopted weight coefficient method has great subjective influence and is difficult to carry out comprehensive multi-objective river water quality dispatching optimization in the related technology mentioned in the background technology center, the application provides a river water quality multi-objective optimizing dispatching method based on NSGA-II algorithm. Therefore, the technical problems that in the related technology, the adopted weight coefficient method has great influence on the main view and is difficult to perform comprehensive multi-objective river water quality scheduling optimization are solved.

Specifically, fig. 1 is a schematic flow chart of a multi-objective river channel water quality optimization scheduling method based on NSGA-II algorithm provided in an embodiment of the present application.

As shown in FIG. 1, the NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling method comprises the following steps:

in step S101, an initial river hydrodynamic water quality model is constructed based on the basic data of the target river network.

In the actual execution process, the embodiment of the application can construct an initial river hydrodynamic water quality model according to the basic data of the target river network so as to facilitate the subsequent construction of a final river hydrodynamic water quality model, thereby directly solving the multi-target problem under the reference scheme by utilizing the non-dominant ordering genetic algorithm with elite strategy, avoiding subjectivity of a weight method to the multi-target optimization problem, and realizing the result of minimum water supplementing quantity while the water quality of the river section exceeds the standard rate.

In some embodiments, the base data may include: river network shape and river cross-section shape data, scheduling object data, and pollution load data.

Wherein, the scheduling object data may include: geographic position, design parameters and scheduling rule data of a pump station or a gate; the pollution load data may include: the position of the discharge outlet, the discharge capacity, the data of the domestic sewage of the population, the data of the agricultural sewage, the data of the animal husbandry sewage and the data of the industrial sewage in each administrative area in the river basin.

The method and the device can build an initial river water quality model applicable to a target area by means of river simulation software, such as an MIKE11 model, based on basic data.

In step S102, water quality monitoring data of a target river network within a preset time period is collected, and the initial river hydrodynamic water quality model is calibrated and verified by using the water quality monitoring data, so as to generate a final river hydrodynamic water quality model which meets the requirement of a preset accurate standard for error between a simulation result and the water quality monitoring data.

As a possible implementation manner, the embodiment of the application can collect the water quality monitoring data of the target river network with preset duration, and perform calibration and verification on the constructed initial river hydrodynamic water quality model according to the collected water quality monitoring data, so that the simulation result of the initial river hydrodynamic water quality model and the error of the monitoring data meet the accurate standard requirement, and a final river hydrodynamic water quality model is obtained.

It should be noted that the preset duration may be set by those skilled in the art according to actual situations, and is not particularly limited herein.

Optionally, in an embodiment of the present application, collecting water quality monitoring data of a target river network within a preset duration, and calibrating and verifying an initial river hydrodynamic water quality model by using the water quality monitoring data, to generate a final river hydrodynamic water quality model meeting a requirement that an error between a simulation result and the water quality monitoring data meets a preset accurate standard, including: collecting water quality monitoring data of a target river network for calibration and verification within a preset time period, wherein the water quality monitoring data comprise pollutant concentration data of important drainage positions on a river channel and pollutant concentration data of positions where water quality monitoring equipment is installed; randomly extracting part of data in the water quality monitoring data to be used as model rating, and correcting model parameters to achieve the matching degree of a model simulation result and measured data to reach a preset condition; randomly extracting at least one data from the residual data of the water quality monitoring data to be used as a model for verification, comparing the model result with the actual measurement data, and performing error evaluation.

In the actual execution process, the water quality monitoring data of the target river network in the preset time period, which are acquired by the embodiment of the application, can comprise pollutant concentration data of important drainage positions on a river channel and positions where water quality monitoring equipment is installed, and part of the data are randomly extracted to be used as model calibration, and the model parameters are corrected to achieve the high coincidence of the model simulation result and the measured data so as to achieve preset conditions, wherein the preset conditions can be as follows; when the total load, average concentration and overall trend of the pollutants in the simulation period are high in agreement with the measured data, the river hydrodynamic water quality model is shown to reach the simulation precision standard.

Further, the embodiment of the application can randomly extract at least one time of data in the residual data as model verification, compare the model result with the actual measured data with the calibrated model result, evaluate the error, and when the total load, the average concentration and the overall trend of the pollutant in the simulation period are higher in the coincidence degree with the actual measured data, indicate that the river water quality model reaches the simulation precision standard, and obtain the final river water quality model.

In step S103, the final river hydrodynamic water quality model is accessed to real-time water quantity and water quality monitoring data and rainfall forecast data, and deployed in a target online system, and a multi-objective optimization scheduling model for improving the standard rate of the cross-section water quality is constructed aiming at a simulation period with the standard exceeding of the cross-section water quality as a reference scheme to be optimized.

As a possible implementation manner, the embodiment of the application can access the calibrated and verified river hydrodynamic water quality model, namely the final river hydrodynamic water quality model, into real-time water quantity and water quality monitoring data and rainfall forecast data, deploy the model in a target online system, realize objective, comprehensive, dynamic and continuous inversion of urban river water environment problems, and construct a multi-target optimization scheduling model for improving the standard rate of the cross section water quality aiming at a simulation period with the standard exceeding of the cross section water quality as a standard scheme to be optimized.

Optionally, in an embodiment of the present application, an optimization objective of the multi-objective optimization scheduling model is that a water quality superscale rate is lowest and a water supplementing amount is smallest in an examination section simulation period, a decision variable is a hydraulic scheduling object of a pump station or a gate station available for scheduling in a reference scheme, and a constraint condition is an upper limit and a lower limit of a control capability of each scheduling object.

It should be noted that, for the simulation period with the quality exceeding the standard of the examined section as the reference scheme to be optimized, a multi-objective optimization scheduling model for improving the standard rate of the quality of the section is constructed, wherein the optimization target is the hydraulic scheduling object of the pump station or the gate station with the lowest quality exceeding rate and the minimum water supplementing amount in the simulation period of the examined section, the decision variable is the hydraulic scheduling object of the pump station or the gate station for scheduling in the reference scheme, and the constraint condition is the upper limit and the lower limit of the control capability of each scheduling object.

For example, a simulation period with a standard exceeding of the COD water quality of an examination section in one field is used as a reference scheme to be optimized, the COD concentration in the simulation period of 24 hours of the examination section in the model is selected as an object to be reached, the minimum water supplementing amount of a pump station in the simulation period is determined as an optimization target when the minimum standard exceeding rate of the water quality of the section is realized, a multi-target optimization scheduling model for improving the standard reaching rate of the water quality of the section is constructed, and the formula can be as follows:

Wherein Q is _i To control the water make-up flow (m) per hour over a period of time ³ S), also decision variables in the examples of the present application, T is the total number of controls, C _h C is the simulated value (mg/L) of COD water quality at the section per hour _s Is COD water quality standard value (mg/L), and lambda is penalty coefficient.

When T takes on the value of 24, C _s When the value is 11 and lambda is 100000, two models can be selected in the embodiment of the applicationThe water supplementing pump stations are used as optimized dispatching objects, the decision variables are the water supplementing flow of the two water supplementing pump stations in the total period of the simulation scheme, and the constraint conditions are the upper limit and the lower limit of the water supplementing amount which can be supplied by the two water supplementing pump stations, which are respectively [0,1.5 ]]And [0,2.4 ]]。

In step S104, in the Python environment, coupling and iterative computation are carried out on the multi-objective optimization scheduling model and the final river hydrodynamic water quality model based on a preset NSGA-II algorithm, so that an optimal scheduling strategy of the objective river network system under multi-objective is obtained, and river water quality simulation of the optimal scheduling strategy is executed in the Python environment.

As a possible implementation manner, the embodiment of the application can couple and iterate the multi-objective optimization scheduling model and the final river hydrodynamic water quality model based on the NSGA-II algorithm in the Python environment to obtain an optimal scheduling strategy of the objective river network system under the multi-objective environment, and execute the river water quality simulation of the optimal scheduling strategy in the Python environment to obtain the result that the cross section water quality exceeds the standard rate by the minimum and the water supplementing amount is the minimum.

Optionally, in an embodiment of the present application, in a Python environment, coupling and iterative computation are performed on the multi-objective optimization scheduling model and the final river hydrodynamic water quality model based on a preset NSGA-II algorithm, so as to obtain an optimal scheduling strategy of the objective river network system under the multi-objective environment, and the river water quality simulation of the optimal scheduling strategy is executed in the Python environment, including: in a Python environment, determining each parameter of a preset NSGA-II algorithm, wherein each parameter comprises population parameters, maximum iteration times and variation probability; in a Python environment, a final river hydrodynamic water quality model is positioned, a scheduling curve file of each scheduling object of an index model is read, a scheduling scheme of a specified population scale is randomly generated, a scheduling object strategy is randomly generated within a set constraint condition range, and the scheduling object strategy is written into and covered in the corresponding scheduling curve file of each scheduling object; in a Python environment, driving a final river hydrodynamic water quality model, and re-executing river water quality simulation on each scheduling scheme by adopting updated scheduling curve files; according to the simulation results of each scheduling scheme, obtaining the water quality results of the specified pollutants of the simulated examination section and the total water supplementing amount under the current scheduling scheme, calculating the function value of the optimization target, judging whether the maximum iteration step number is reached or the target value in a plurality of successive generations is not reduced, if not, updating the scheduling strategy of the scheduling object by a preset NSGA-II algorithm, and continuing the new round of iterative optimization; if the maximum iteration step number is reached or the target value in a plurality of successive generations is not reduced, stopping optimizing calculation, returning to the optimal scheduling strategy corresponding to the current optimal target value, and writing the optimal scheduling strategy into a scheduling curve file; in a Python environment, river channel water quality simulation of an optimal scheduling strategy is executed, and a result with minimum water supplementing quantity and minimum exceeding rate of section water quality under the current simulation scheme is obtained.

In the actual execution process, the embodiment of the application can determine each parameter of the NSGA-II algorithm in a Python environment, wherein each parameter can comprise population parameters, maximum iteration times and variation probability, and the non-dominant ordered genetic algorithm (NSGA-II algorithm) with elite strategy is utilized, so that the method has the advantages of strong searching capability and high optimizing efficiency, can realize direct solving of the multi-objective problem under a reference scheme, and avoids subjectivity of a weight method to the multi-objective optimizing problem;

further, the embodiment of the application can locate the final river hydrodynamic water quality model in the Python environment, read and index the scheduling curve file of each scheduling object of the model, randomly generate a scheduling scheme of a specified population scale, randomly generate a scheduling object strategy in the constraint condition range set by the optimization target, and write and cover the scheduling object strategy in the corresponding scheduling curve file of each scheduling object;

the final river channel hydrodynamic force water quality model is driven in a Python environment, the embodiment of the application can re-execute river channel water quality simulation on each scheduling scheme by adopting the updated scheduling curve file, and fully test and evaluate the scheduling decision result by using the hydrodynamic force water quality model as a virtual experiment environment, thereby realizing objective simulation of huge and complex management objects and laying a foundation for optimal scheduling;

According to the embodiment of the application, according to the simulation results of each scheduling scheme, the water quality results of the specified pollutants of the simulated examination section and the total water supplementing amount under the current scheduling scheme are obtained, the optimization objective function value is calculated, and whether the optimization objective function value reaches the maximum iteration step number or the target value in a plurality of continuous generations is not reduced; if not, updating the scheduling strategy of the scheduling object by using an NSGA-II algorithm, returning to randomly generating a scheduling scheme of a specified population scale again, randomly generating the scheduling object strategy within the constraint condition range set by the optimization target, writing and covering the scheduling object strategy in the corresponding scheduling curve file of each scheduling object, and continuing to iterate and optimize for a new round; stopping optimizing calculation when the maximum iteration step number is reached or the target value in a plurality of continuous generations is not lowered, returning to the optimal scheduling strategy corresponding to the current optimal target value, and writing the optimal scheduling strategy into a scheduling curve file; and (3) performing river channel water quality simulation of an optimal scheduling strategy in a Python environment to obtain a result with minimum water supplementing quantity and minimum cross section water quality exceeding rate under the current simulation scheme.

As described with reference to fig. 2 to 6, an embodiment of the NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling method in the embodiment of the present application is described in detail.

As shown in fig. 2, with basic data and monitoring data of a certain city, the water replenishing pump station is optimally scheduled by adopting the embodiment of the present application, so as to realize that the water quality (COD) standard exceeding rate is the lowest and the water replenishing amount is the smallest in the simulated period of the examination section, and specifically includes the following steps:

step S201: and constructing an initial river hydrodynamic water quality model according to the basic data of the target river network. Collecting basic data of river network in the research area, including river network shape and river section shape data; and collecting scheduling object data, wherein the data comprise geographic positions, design parameters, scheduling rules and the like of 3 pump stations, 5 gates and the like, and an initial river hydrodynamic water quality model which is suitable for a target area and is shown in figure 3 is constructed by adopting MIKE11 software.

Step S202: and collecting water quality monitoring data of a target river network with preset time length, and calibrating and verifying the constructed initial river hydrodynamic water quality model according to the collected water quality monitoring data so that the simulation result of the initial river hydrodynamic water quality model and the error of the monitoring data meet the accurate standard requirement, thereby obtaining a final river hydrodynamic water quality model.

According to the embodiment of the application, the actual measurement data of the concentration of the pollutants at the important outlet and the water quality monitoring equipment installation part on the river channel for one year or more can be collected, the first 80% of the actual measurement data are used for calibrating the water quality model of the river channel, parameters such as diffusion coefficients and degradation coefficients are adjusted until the difference between the water quality simulation result and the actual measurement data of the monitoring point position meets the precision standard, the model calibrated by verification is used for the remaining month data, when the model simulation result and the actual measurement data difference meet the precision standard, the model can be used, the final water quality model of the river channel is obtained, as shown in fig. 4, otherwise, the model of the re-calibration mechanism is returned until the simulation precision requirement is met under the verification scene.

Step S203: and (3) accessing the final river hydrodynamic water quality model into real-time water quantity and water quality monitoring data and rainfall forecast data, deploying the data in a target online system, and constructing a multi-target optimal scheduling model for improving the standard rate of the cross-section water quality aiming at a simulation period with the standard exceeding of the cross-section water quality to be checked as a standard scheme to be optimized.

According to the embodiment of the application, the final river hydrodynamic water quality model can be connected with real-time water quantity and water quality monitoring data and rainfall forecast data, and the data and the rainfall forecast data are deployed in a target online system, so that objective, comprehensive, dynamic and continuous inversion of the model on the urban river water environment problem is realized.

Taking a simulation period with an exceeding of the COD water quality of an examination section in one field as a reference scheme to be optimized, constructing a multi-objective optimization scheduling model for improving the standard rate of the water quality of the section, selecting the COD concentration in the 24-hour simulation period of the examination section in the model as an object to be standard, determining that the optimization target is minimum in water supplementing amount of a pump station in the simulation period while the minimum exceeding rate of the water quality of the section is realized, and the formula can be as follows:

wherein Q is _i To control the water make-up flow (m) per hour over a period of time ³ S), also decision variables in the embodiments of the present application; t is the total number of controls, taken 24 in the example; c (C) _h Is the COD water quality simulation value (mg/L) at the section of each hour; c (C) _s Taking the COD water quality standard value (mg/L), and taking 11mg/L in the example; lambda is a penalty factor, taken 100000 in the example.

In the embodiment of the application, two water supplementing pump stations in the model can be selected as an optimal scheduling object, decision variables are water supplementing flows of the two water supplementing pump stations in a total period of a simulation scheme hour by hour, and constraint conditions are upper and lower limits of water supplementing flows of the two water supplementing pump stations, which are [0,1.5] and [0,2.4] respectively.

Step S204: coupling and iterative computation are carried out on the multi-objective optimal scheduling model and the initial river hydrodynamic water quality model based on an NSGA-II algorithm in a Python environment to obtain an optimal scheduling strategy of a target river network system under multiple objectives, and river water quality simulation of the optimal scheduling strategy is executed in the Python environment to obtain a result with the lowest cross section water quality exceeding rate and the smallest water supplementing amount.

Parameters of an NSGA-II algorithm can be determined in a Python environment, for example, the population scale is 100, the maximum iteration number is 100, and the variation probability is 0.001;

positioning a final river hydrodynamic water quality model in a Python environment, reading time sequence files of water replenishing flows of two pump stations in the model, randomly generating a scheduling scheme corresponding to a population scale, randomly generating water replenishing strategies of the two pump stations for 24 hours in the constraint condition range set in the step S203, and writing the water replenishing strategies into the scheduling curve files corresponding to the two pump stations;

According to the embodiment of the application, the final river hydrodynamic water quality model can be driven in a Python environment, and the river water quality simulation is re-executed by adopting the updated pump station water supplementing time sequence for the 100 scheduling schemes;

according to the simulation results of each scheduling scheme, the embodiment of the application can acquire the simulated check section COD water quality result and the total water supplementing quantity result under the current scheduling scheme, calculate the optimization objective function value in the step S203, and judge whether the maximum iteration step number is reached or the objective value in a plurality of continuous generations is not reduced; if not, updating the scheduling strategy of the scheduling object by using an NSGA-II algorithm, returning to randomly generating a scheduling scheme corresponding to the population scale again, randomly generating water supplementing strategies of the two pump stations 24h in the constraint condition range set in the step S203, writing the water supplementing strategies into the corresponding scheduling curve files, and continuing to perform new iteration optimization;

when the maximum iteration step number is reached or the target value in a plurality of continuous generations is not reduced any more, the embodiment of the application can stop optimization calculation, return to the optimal scheduling strategy corresponding to the current optimal target value, and write the optimal scheduling strategy into the scheduling curve file;

according to the embodiment of the application, the river channel water quality simulation of the optimal scheduling strategy can be executed in the Python environment, the minimum water supplementing quantity result when the COD water quality exceeding rate of the check section is minimum under the current simulation scheme is obtained, as shown in FIG. 5, and FIG. 5 is a flow chart of a method for executing scheduling optimization based on NSGA-II algorithm.

As shown in fig. 6, fig. 6 shows an optimization result of the optimization scheduling method according to the embodiment of the present application, and the optimization algorithm according to the embodiment of the present application is located below the water quality standard line in the simulation period, and the COD load of the assessment section in the simulation period is reduced by 23.1% compared with the standard line.

In summary, the embodiment of the application can focus on the technical index of the urban river water quality reaching the standard, and meanwhile give consideration to the economic index of water supplementing quantity, objectively, comprehensively, dynamically and continuously invert the urban water environment problem by means of an online river water quality simulation technology, simulate and verify the space-time distribution rule of the water quantity and the water quality after the river diversion and the water diversion, provide theoretical support for making and optimizing a water diversion scheme, and simultaneously iteratively optimize the diversion and the water diversion by means of an optimization algorithm suitable for multiple targets, so that efficient and reliable dispatching optimization and auxiliary dispatching decision are realized.

According to the NSGA-II algorithm-based river water quality multi-objective optimization scheduling method provided by the embodiment of the application, a river water power water quality model can be built, a river water power water quality model is calibrated and verified, a scheduling model for improving the river water quality standard rate is built, scheduling optimization based on the NSGA-II algorithm is executed, the water power water quality model is used as a virtual experimental environment, the scheduling decision result is fully tested and evaluated, the non-dominant ordering genetic algorithm with elite strategy is utilized, the multi-objective problem is directly solved under a reference scheme, subjectivity of a weight method in the multi-objective optimization problem is avoided, the result that the water supplementing quantity is minimum while the river section water quality exceeds the standard rate is achieved, and real-time simulation analysis and automatic optimization scheme selection recommendation are achieved by combining the online river water power water quality model with the multi-objective optimization algorithm, so that daily scheduling management is served, and the method has a wide application prospect. Therefore, the technical problems that in the related technology, the adopted weight coefficient method has great influence on the main view and is difficult to perform comprehensive multi-objective river water quality scheduling optimization are solved.

Secondly, a river channel water quality multi-objective optimization scheduling device based on NSGA-II algorithm according to the embodiment of the application is described with reference to the attached drawings.

FIG. 7 is a block diagram of a NSGA-II algorithm-based river water quality multi-objective optimization scheduling device in an embodiment of the application.

As shown in fig. 7, the NSGA-II algorithm-based river water quality multi-objective optimization scheduling device 10 includes: a first build module 100, a generation module 200, a second build module 300, and an optimization module 400.

Specifically, the first construction module 100 is configured to construct an initial river hydrodynamic water quality model based on the basic data of the target river network.

The generation module 200 is configured to collect water quality monitoring data of a target river network within a preset duration, and perform calibration and verification on an initial river hydrodynamic water quality model by using the water quality monitoring data, so as to generate a final river hydrodynamic water quality model which meets the requirement that an error between a simulation result and the water quality monitoring data meets a preset accurate standard.

The second construction module 300 is configured to access the final river hydrodynamic water quality model to real-time water volume and water quality monitoring data and rainfall forecast data, and deploy the model in a target online system, and construct a multi-objective optimization scheduling model for improving the standard rate of the cross-section water quality according to a simulation period with the standard exceeding of the cross-section water quality as a standard scheme to be optimized.

The optimization module 400 is configured to couple and iterate the multi-objective optimization scheduling model with the final river hydrodynamic water quality model based on a preset NSGA-II algorithm in the Python environment, so as to obtain an optimal scheduling strategy of the objective river network system under the multi-objective environment, and execute the river water quality simulation of the optimal scheduling strategy in the Python environment.

Optionally, in one embodiment of the present application, the generating module 200 includes: the device comprises an acquisition unit, a correction unit and an evaluation unit.

The water quality monitoring system comprises a collecting unit, a water quality monitoring unit and a monitoring unit, wherein the collecting unit is used for collecting water quality monitoring data of a target river network for calibration and verification in a preset time period, and the water quality monitoring data comprise pollutant concentration data of important drainage positions on a river channel and pollutant concentration data of positions where water quality monitoring equipment is installed.

And the correction unit is used for randomly extracting part of the water quality monitoring data to be used as model calibration, and achieving the coincidence degree of the model simulation result and the measured data to reach the preset condition by correcting the model parameters.

And the evaluation unit is used for randomly extracting at least one data from the residual data of the water quality monitoring data to be used as a model for verification, comparing the model result with the actual measurement data, and performing error evaluation.

Optionally, in one embodiment of the present application, the optimization module 400 includes: the device comprises a determining unit, a generating unit, a driving unit, a calculating unit, a writing unit and an executing unit.

The determining unit is used for determining each parameter of a preset NSGA-II algorithm in a Python environment, wherein each parameter comprises a population parameter, a maximum iteration number and a variation probability.

The generation unit is used for positioning the final river hydrodynamic water quality model in the Python environment, reading the scheduling curve file of each scheduling object of the index model, randomly generating a scheduling scheme of a specified population scale, randomly generating a scheduling object strategy in a set constraint condition range, and writing and covering the scheduling object strategy in the corresponding scheduling curve file of each scheduling object.

And the driving unit is used for driving the final river hydrodynamic water quality model in a Python environment, and re-executing the river water quality simulation on each scheduling scheme by adopting the updated scheduling curve file.

And the calculation unit is used for acquiring the water quality result of the specified pollutant of the simulated examination section and the total water supplementing amount under the current scheduling scheme according to the simulation result of each scheduling scheme, calculating the function value of the optimization target, judging whether the maximum iteration step number is reached or the target value in a plurality of successive generations is not reduced, if not, updating the scheduling strategy of the scheduling object by a preset NSGA-II algorithm, and continuing the iterative optimization of a new round.

And the writing unit is used for stopping optimization calculation when the maximum iteration step number is reached or the target value in a plurality of successive generations is not reduced any more, returning to the optimal scheduling strategy corresponding to the current optimal target value and writing the optimal scheduling strategy into the scheduling curve file.

And the execution unit is used for executing the river channel water quality simulation of the optimal scheduling strategy in the Python environment to obtain the result of minimum water supplementing quantity while minimum cross section water quality exceeding rate under the current simulation scheme.

It should be noted that, the explanation of the embodiment of the multi-objective optimizing and scheduling method for river water quality based on NSGA-II algorithm is also applicable to the multi-objective optimizing and scheduling device for river water quality based on NSGA-II algorithm in this embodiment, and is not repeated here.

According to the NSGA-II algorithm-based river water quality multi-objective optimization scheduling device provided by the embodiment of the application, a river water power water quality model can be built, a river water power water quality model is calibrated and verified, a scheduling model for improving the river water quality standard rate is built, scheduling optimization based on the NSGA-II algorithm is executed, the water power water quality model is used as a virtual experimental environment, the scheduling decision result is fully tested and evaluated, the non-dominant ordering genetic algorithm with elite strategy is utilized, the multi-objective problem is directly solved under a reference scheme, subjectivity of a weight method in the multi-objective optimization problem is avoided, the result that the water supplementing quantity is minimum while the river section water quality exceeds the standard rate is achieved, and real-time simulation analysis and automatic optimization scheme selection recommendation are achieved by combining the online river water power water quality model with the multi-objective optimization algorithm, so that daily scheduling management is served, and the device has a wide application prospect. Therefore, the technical problems that in the related technology, the adopted weight coefficient method has great influence on the main view and is difficult to perform comprehensive multi-objective river water quality scheduling optimization are solved.

Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:

a memory 801, a processor 802, and a computer program stored on the memory 801 and executable on the processor 802.

The processor 802 implements the NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling method provided in the above embodiment when executing a program.

Further, the electronic device further includes:

a communication interface 803 for communication between the memory 801 and the processor 802.

A memory 801 for storing a computer program executable on the processor 802.

The memory 801 may include high-speed RAM memory or may further include non-volatile memory (non-volatile memory), such as at least one magnetic disk memory.

If the memory 801, the processor 802, and the communication interface 803 are implemented independently, the communication interface 803, the memory 801, and the processor 802 may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture (Industry Standard Architecture, abbreviated ISA) bus, an external device interconnect (Peripheral Component, abbreviated PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 8, but not only one bus or one type of bus.

Alternatively, in a specific implementation, if the memory 801, the processor 802, and the communication interface 803 are integrated on a chip, the memory 801, the processor 802, and the communication interface 803 may communicate with each other through internal interfaces.

The processor 802 may be a central processing unit (Central Processing Unit, abbreviated as CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC), or one or more integrated circuits configured to implement embodiments of the present application.

The embodiment also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the above river channel water quality multi-objective optimization scheduling method based on the NSGA-II algorithm.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless explicitly defined otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.

Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. Although embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.

Claims

1. The NSGA-II algorithm-based river channel water quality multi-objective optimal scheduling method is characterized by comprising the following steps of:

constructing an initial river hydrodynamic water quality model based on basic data of a target river network;

collecting water quality monitoring data of the target river network within a preset time period, and calibrating and verifying the initial river hydrodynamic water quality model by utilizing the water quality monitoring data to generate a final river hydrodynamic water quality model which meets the requirement that the error between a simulation result and the water quality monitoring data meets a preset accurate standard;

the final river hydrodynamic water quality model is accessed into real-time water quantity water quality monitoring data and rainfall forecast data and is deployed in a target online system, and a multi-target optimal scheduling model for improving the standard rate of the section water quality is constructed aiming at a simulation period with the standard exceeding of the section water quality to be checked as a standard scheme to be optimized; and

And in the Python environment, coupling and performing iterative computation on the multi-objective optimization scheduling model and the final river hydrodynamic water quality model based on a preset NSGA-II algorithm to obtain an optimal scheduling strategy of a target river network system under multiple objectives, and executing river water quality simulation of the optimal scheduling strategy in the Python environment.

2. The method of claim 1, wherein the base data comprises at least one of river network shape and river cross-section shape data, scheduling object data, and pollution load data, wherein the scheduling object data comprises one or more of a geographic location of a pump station or gate, design parameters, and scheduling rule data; the pollution load data comprises one or more of discharge position, discharge capacity, population domestic sewage data of each administrative district in the river basin, agricultural sewage data, animal husbandry sewage data and industrial sewage data.

3. The method of claim 1, wherein the collecting the water quality monitoring data of the target river network for a preset time period, and calibrating and verifying the initial river hydrodynamic water quality model by using the water quality monitoring data, and generating a final river hydrodynamic water quality model satisfying the error between the simulation result and the water quality monitoring data and satisfying the requirement of a preset accurate standard, comprises:

Collecting water quality monitoring data of a target river network for calibration and verification within a preset time period, wherein the water quality monitoring data comprise pollutant concentration data of important drainage ports on a river channel and pollutant concentration data of water quality monitoring equipment;

randomly extracting part of the water quality monitoring data to be used as model rating, and correcting model parameters to achieve the matching degree of a model simulation result and measured data to reach a preset condition;

randomly extracting at least one data from the residual data of the water quality monitoring data to be used as a model for verification, comparing a model result with a rated model result with the measured data, and performing error evaluation.

4. The method according to claim 1, wherein the optimization objective of the multi-objective optimization scheduling model is that the water quality superscale rate is the lowest and the water replenishment amount is the smallest in the evaluation section simulation period, the decision variable is the hydraulic scheduling object of the pump station or the gate station available for scheduling in the reference scheme, and the constraint condition is the upper limit and the lower limit of the control capability of each scheduling object.

5. The method according to claim 4, wherein the coupling and iterative computation of the multi-objective optimal scheduling model and the final river hydrodynamic water quality model based on a preset NSGA-II algorithm in the Python environment to obtain an optimal scheduling strategy of the objective river network system under multi-objective, and executing the river water quality simulation of the optimal scheduling strategy in the Python environment, comprises:

In the Python environment, determining each parameter of the preset NSGA-II algorithm, wherein each parameter comprises a population parameter, a maximum iteration number and a variation probability;

in the Python environment, positioning the final river hydrodynamic water quality model, reading a scheduling curve file of each scheduling object of an index model, randomly generating a scheduling scheme of a specified population scale, randomly generating a scheduling object strategy in a set constraint condition range, and writing and covering the scheduling object strategy in the corresponding scheduling curve file of each scheduling object;

driving the final river hydrodynamic water quality model in the Python environment, and re-executing river water quality simulation on each scheduling scheme by adopting updated scheduling curve files;

according to the simulation results of each scheduling scheme, obtaining the water quality results of the specified pollutants of the simulated examination section and the total water supplementing amount under the current scheduling scheme, calculating the function value of the optimization target, judging whether the maximum iteration step number is reached or the target value in a plurality of successive generations is not reduced, if not, updating the scheduling strategy of the scheduling object by the preset NSGA-II algorithm, and continuing the iterative optimization of a new round;

If the maximum iteration step number is reached or the target value in a plurality of continuous generations is not reduced, stopping optimizing calculation, returning to an optimal scheduling strategy corresponding to the current optimal target value, and writing the optimal scheduling strategy into the scheduling curve file;

and in the Python environment, executing the river channel water quality simulation of the optimal scheduling strategy to obtain a result with minimum water supplementing quantity and minimum cross section water quality exceeding rate under the current simulation scheme.

6. NSGA-II algorithm-based river channel water quality multi-objective optimization scheduling device is characterized by comprising:

the first construction module is used for constructing an initial river hydrodynamic water quality model based on basic data of a target river network;

the generation module is used for collecting the water quality monitoring data of the target river network within a preset time period, and calibrating and verifying the initial river hydrodynamic water quality model by utilizing the water quality monitoring data to generate a final river hydrodynamic water quality model which meets the requirement of a preset accurate standard for the error between a simulation result and the water quality monitoring data;

the second construction module is used for accessing the final river hydrodynamic water quality model into real-time water quantity water quality monitoring data and rainfall forecast data, deploying the final river hydrodynamic water quality model into a target online system, and constructing a multi-target optimization scheduling model for improving the standard rate of the cross-section water quality aiming at a simulation period with the standard exceeding of the cross-section water quality to be evaluated as a reference scheme to be optimized; and

And the optimization module is used for coupling and performing iterative computation on the multi-objective optimization scheduling model and the final river hydrodynamic water quality model based on a preset NSGA-II algorithm in a Python environment to obtain an optimal scheduling strategy of the objective river network system under multi-objective conditions, and executing river water quality simulation of the optimal scheduling strategy in the Python environment.

7. The apparatus of claim 6, wherein the generating module comprises:

the water quality monitoring system comprises an acquisition unit, a verification unit and a verification unit, wherein the acquisition unit is used for acquiring water quality monitoring data of a target river network for calibration and verification in a preset time period, and the water quality monitoring data comprise pollutant concentration data of important drainage positions on a river channel and pollutant concentration data of positions where water quality monitoring equipment is installed;

the correction unit is used for randomly extracting part of the water quality monitoring data to be used as model calibration, and achieving the coincidence degree of a model simulation result and measured data to reach a preset condition by correcting model parameters;

and the evaluation unit is used for randomly extracting at least one data from the residual data of the water quality monitoring data to be used as a model for verification, comparing the model result with the actual measured data, and performing error evaluation.

8. The apparatus of claim 6, wherein the optimization module comprises:

the determining unit is used for determining each parameter of the preset NSGA-II algorithm in the Python environment, wherein each parameter comprises a population parameter, a maximum iteration number and a variation probability;

the generation unit is used for positioning the final river hydrodynamic water quality model in the Python environment, reading the scheduling curve file of each scheduling object of the index model, randomly generating a scheduling scheme of a specified population scale, randomly generating a scheduling object strategy in a set constraint condition range, and writing and covering the scheduling object strategy in the corresponding scheduling curve file of each scheduling object;

the driving unit is used for driving the final river channel hydrodynamic water quality model in the Python environment, and re-executing river channel water quality simulation on each scheduling scheme by adopting the updated scheduling curve file;

the calculation unit is used for obtaining the water quality result of the specified pollutant of the simulated examination section and the total water supplementing amount under the current scheduling scheme according to the simulation result of each scheduling scheme, calculating the function value of the optimization target, judging whether the maximum iteration step number is reached or the target value in a plurality of successive generations is not reduced any more, if not, updating the scheduling strategy of the scheduling object by the preset NSGA-II algorithm, and continuing the iterative optimization of a new round;

The writing unit is used for stopping optimization calculation when the maximum iteration step number is reached or the target value in a plurality of continuous generations is not lowered any more, returning to the optimal scheduling strategy corresponding to the current optimal target value and writing the optimal scheduling strategy into the scheduling curve file;

and the execution unit is used for executing the river channel water quality simulation of the optimal scheduling strategy in the Python environment to obtain the result of minimum water supplementing quantity while minimum exceeding rate of the section water quality under the current simulation scheme.

9. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the NSGA-II algorithm-based river water quality multi-objective optimization scheduling method of any one of claims 1-5.

10. A computer readable storage medium having stored thereon a computer program, wherein the program is executed by a processor for implementing the NSGA-II algorithm-based multi-objective optimization scheduling method for river water quality as claimed in any one of claims 1 to 5.