Hydraulic engineering scheduling optimization method and system based on cloud computing

Abstract

The invention discloses a water conservancy project scheduling optimization method and system based on cloud computing. The method comprises the steps that water conservancy data are collected in real time through the Internet of Things technology and transmitted to a cloud end; preprocessing, managing and storing the collected water conservancy data; a multi-target scheduling model is constructed according to the actual demand of the water conservancy project, and an optimal control strategy of the water conservancy project is solved; real-time scheduling calculation is carried out through the cloud platform, and a current optimal solution of hydraulic engineering scheduling is updated based on data analysis and a machine learning model; and presenting the real-time state and the scheduling result of the water conservancy project through a visual tool of the cloud platform. According to the water conservancy data integration method based on the clustering algorithm, multi-source and heterogeneous data can be effectively processed, scheduling is updated through clustering, scientific decision support is provided for water conservancy project scheduling, the clustering result is combined with cloud computing, and the water conservancy project scheduling efficiency is improved. And an efficient and accurate solution can be provided in the aspects of multi-objective optimization, water resource management and dynamic scheduling.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering scheduling, and particularly to a method and system for optimizing water conservancy project scheduling based on cloud computing. Background Art

[0002] A water conservancy project refers to an infrastructure system for regulating, protecting, and utilizing water resources, usually including facilities such as reservoirs, dams, channels, and sluice gates. Among them, the scheduling of water conservancy projects is an important link to ensure the rational allocation of water resources, improve the utilization efficiency of water resources, ensure the safety of reservoirs, promote ecological protection, and optimize economic benefits. With the rapid development of cloud computing and big data technologies, the method for optimizing water conservancy project scheduling based on cloud computing has become an important means to solve these problems. Cloud computing can provide powerful computing capabilities and flexible resource scheduling capabilities, helping to achieve the intelligentization, automation, and optimization of water conservancy project scheduling. Therefore, developing water conservancy project scheduling algorithms based on cloud computing is a promising research direction.

[0003] Currently, the Chinese invention patent with the application number CN202410842738.6 discloses an optimization method for the ecological scheduling scheme of water conservancy projects, which obtains the revenue and expenditure data of the area where the water conservancy project is located and the real-time status data of the water conservancy project; establishes an optimization model including constraint conditions and objective functions, and obtains three types of optimization schemes according to the emphasis balance between economic benefits and environmental benefits; its technical key points are: according to the revenue and expenditure data of the area where the water conservancy project is located, evaluate the construction direction of the local water conservancy project, and automatically select the corresponding adapted scheme according to the evaluation results, and realize the corresponding scheduling process on the premise of ensuring a certain environmental basis, and re-determine the effectiveness of the scheme after selecting the scheme to ensure that the obtained evaluation value can provide a basis for staff to make adjustments or scheduling. However, the existing technology cannot achieve that the water conservancy data integration method based on the clustering algorithm can effectively process multi-source and heterogeneous data, cannot update the scheduling through clustering, thus cannot provide scientific decision-making support for water conservancy project scheduling, cannot combine the clustering results with cloud computing, and cannot provide efficient and accurate solutions in multi-objective optimization, water resource management, and dynamic scheduling. Summary of the Invention

[0004] The technical problem solved by the present invention is that the existing technology cannot achieve that the water conservancy data integration method based on the clustering algorithm can effectively process multi-source and heterogeneous data, cannot update the scheduling through clustering, thus cannot provide scientific decision-making support for water conservancy project scheduling, cannot combine the clustering results with cloud computing, and cannot provide efficient and accurate solutions in multi-objective optimization, water resource management, and dynamic scheduling.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: A method for optimizing water conservancy project scheduling based on cloud computing, comprising the following steps: Step S1: Collect water conservancy data in real time through Internet of Things technology and transmit it to the cloud; Step S2: Preprocess, manage and store the collected water conservancy data; Step S3: According to the actual needs of the water conservancy project, construct a multi-objective scheduling model and solve the optimal control strategy of the water conservancy project; Step S4: Perform real-time scheduling calculations through the cloud platform, and update the current optimal solution of the water conservancy project scheduling based on data analysis and machine learning models; Step S5: Present the real-time status and scheduling results of the water conservancy project through the visualization tool of the cloud platform.

[0006] Preferably, the step S1 includes: Collect water conservancy data in real time through Internet of Things technology and transmit it to the cloud. The water conservancy data includes water level, flow rate, precipitation, meteorological data and historical scheduling data. The devices for collecting the water conservancy data include water level sensors, flow meters, weather stations and computer big data networks.

[0007] Preferably, the step S2 includes the following sub-steps: Step S21: Perform operations such as cleaning, missing value filling and normalization on the collected water conservancy data; Step S22: Store and manage the water conservancy data according to the large-scale distributed storage system HDFS provided by cloud computing, and upload all real-time data and historical data to the cloud database of the large-scale distributed storage system HDFS.

[0008] Preferably, the step S3 includes the following sub-steps: Step S31: According to the actual needs of the water conservancy project, construct a multi-objective scheduling model. The actual needs include water resource allocation, reservoir storage and discharge management, maximization of water resource utilization, environmental protection and equipment maintenance; Step S32: Perform cloud computing and distributed processing according to the multi-objective scheduling model, and use a distributed computing framework to solve the multi-objective scheduling model; Step S33: Solve the optimal control strategy of the water conservancy project through the dynamic programming method.

[0009] Preferably, the step S31 includes the following sub-steps: Step S311: Use an optimized clustering algorithm to integrate and manage the actual needs and preprocessed water conservancy data; Step S312: Calculate the minimization of the imbalance degree of water resource allocation, and its mathematical expression is: ; Wherein, Indicates minimizing the imbalance degree of water resource allocation, Indicates the actual water supply volume for the th type of demand, Indicates the ideal water supply volume for the th type of demand, is the number of demand types; Calculate maximizing the utilization degree of water resources, and its mathematical expression is: ; Among them, Indicates maximizing the utilization degree of water resources, Indicates the total output of water conservancy projects, and the water conservancy projects include agricultural irrigation and power generation, Indicates the water consumption corresponding to the water conservancy project; Set the weighted average of the minimized imbalance degree of water resource allocation and the maximized utilization degree of water resources as the objective function; Step S313: Set the total water resource volume as the constraint condition, and its mathematical expression is: ; Among them, Indicates the water supply volume of the th region, Indicates the total water resource volume; Step S314: Through the multi-objective optimization method, find a set of Pareto optimal solutions, that is, solutions that cannot improve a certain objective without damaging other objectives. After obtaining the optimal solutions, it means that the multi-objective scheduling model is built.

[0010] Preferably, the step S311 includes the following sub-steps: Step S3111: Define the actual demand and the preprocessed water conservancy data as data points respectively, aggregate the actual demand data points into a cluster , and aggregate the water conservancy data data points into a cluster ; Step S3112: Randomly select the initial cluster center, calculate the distance between the data point and the cluster center, and assign the data point to the nearest cluster; Step S3113: Recalculate the center of each cluster and update the position of the cluster center; Step S3114: Repeat steps S3112 and S3113 until the cluster center no longer changes or reaches the maximum number of iterations; Step S3115: Calculate the similarity between clusters through the method of Bayesian fusion.

[0011] Preferably, the step S4 includes the following sub-steps: Step S41: Perform real-time scheduling calculation through the cloud platform; Step S42: Evaluate the effect of the scheduling plan through the decision support system provided by the cloud computing platform to help engineering management personnel make the best choice; Step S43: Update the current optimal solution of the water conservancy project scheduling based on data analysis and machine learning models.

[0012] Preferably, the step S43 includes: Use data mining technology to obtain potential laws of historical water conservancy scheduling, use matleb simulation software to simulate the multi-objective scheduling model, obtain the execution situation during the scheduling process, extract features of the historical water conservancy scheduling and the current water conservancy scheduling through a neural network, obtain historical water conservancy scheduling features and current water conservancy scheduling features, and use the historical water conservancy scheduling features and current water conservancy scheduling features as data point sets for clusters and clusters , and use the clusters and clusters Integrate and manage through an optimized clustering algorithm, obtain the updated optimal control strategy of the water conservancy project after step S3, iterate and update to a preset iteration update threshold, and obtain the current optimal solution of the water conservancy project scheduling finally.

[0013] Preferably, the step S5 includes: The visualized content includes water level, flow rate, weather forecast and scheduling plan.

[0014] A water conservancy project scheduling optimization system based on cloud computing, including a collection module, a management module, a control model module and a visualization module: The collection module is used to collect water conservancy data in real time through the Internet of Things technology and transmit it to the cloud; The management module is used to preprocess and manage and store the collected water conservancy data; The control model module is used to construct a multi-objective scheduling model according to the actual needs of the water conservancy project, solve the optimal control strategy of the water conservancy project, perform real-time scheduling calculations through the cloud platform, and update the current optimal solution of the water conservancy project scheduling based on data analysis and machine learning models; The visualization module is used to present the real-time status and scheduling results of the water conservancy project through the visualization tool of the cloud platform.

[0015] The beneficial effects of the present invention: The water conservancy data integration method based on the clustering algorithm can effectively process multi-source and heterogeneous data, provide scientific decision support for water conservancy project scheduling through clustering and updating scheduling, and can provide efficient and accurate solutions in multi-objective optimization, water resource management and dynamic scheduling by combining the clustering results with cloud computing. Description of the Drawings

[0016] Figure 1 Schematic diagram of the basic process of a water conservancy project scheduling optimization method based on cloud computing provided by an embodiment of the present invention. Detailed implementation manners

[0017] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe in detail the specific implementation manners of the present invention with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments.

[0018] Refer to Figure 1 , an embodiment of the present invention provides a water conservancy project scheduling optimization method based on cloud computing, including the following steps: Step S1: Collect water conservancy data in real time through Internet of Things technology and transmit it to the cloud; Step S2: Preprocess, manage, and store the collected water conservancy data; Step S3: According to the actual needs of the water conservancy project, construct a multi-objective scheduling model and solve the optimal control strategy of the water conservancy project; Step S4: Perform real-time scheduling calculations through the cloud platform, and update the current optimal solution of the water conservancy project scheduling based on data analysis and machine learning models; Step S5: Present the real-time status and scheduling results of the water conservancy project through the visualization tool of the cloud platform.

[0019] The step S1 includes: Collect water conservancy data in real time through Internet of Things technology and transmit it to the cloud. The water conservancy data includes water level, flow rate, precipitation, meteorological data, and historical scheduling data. The devices for collecting the water conservancy data include water level sensors, flow meters, weather stations, and computer big data networks.

[0020] The step S2 includes the following sub-steps: Step S21: Perform operations such as cleaning, missing value filling, and normalization on the collected water conservancy data to ensure the accuracy and consistency of the data; Step S22: Store and manage the water conservancy data according to the large-scale distributed storage system HDFS provided by cloud computing. Upload all real-time data and historical data to the cloud database of the large-scale distributed storage system HDFS to ensure the security, reliability, and accessibility of the data.

[0021] The step S3 includes the following sub-steps: Step S31: According to the actual needs of the water conservancy project, construct a multi-objective scheduling model. The actual needs include water resource allocation, reservoir storage and discharge management, maximization of water resource utilization, environmental protection, and equipment maintenance; Step S32: Perform cloud computing and distributed processing according to the multi-objective scheduling model, and use a distributed computing framework to solve the multi-objective scheduling model; Step S33: Solve the optimal control strategy of the water conservancy project by means of dynamic programming.

[0022] Both the cloud computing and distributed processing and the dynamic programming method are existing technologies.

[0023] The said Step S31 includes the following sub-steps: Step S311: Integrate and manage the actual demand and the preprocessed water conservancy data by using an optimized clustering algorithm; Step S312: Calculate the minimization of the imbalance degree of water resource allocation, and its mathematical expression is: ; where, represents the minimization of the imbalance degree of water resource allocation, represents the actual water supply volume of the th type of demand, represents the ideal water supply volume of the th type of demand, is the number of demand types; Calculate the maximization of water resource utilization degree, and its mathematical expression is: ; where, represents the maximization of water resource utilization degree, represents the total output of the water conservancy project, and the water conservancy project includes agricultural irrigation and power generation, represents the water consumption corresponding to the water conservancy project; Optimize the water resource utilization efficiency in fields such as irrigation water use and industrial water use, which can be optimized by maximizing water use benefits or reducing water resource waste; Perform weighted averaging on the minimization of the imbalance degree of water resource allocation and the maximization of water resource utilization degree and set it as the objective function; Step S313: Set the total water resource volume as a constraint condition, and its mathematical expression is: ; where, represents the water supply volume of the th region, represents the total water resource volume; The total water resource volume is limited, so the total water supply should be less than or equal to the available water resources; Step S314: Use a multi-objective optimization method to find a set of Pareto optimal solutions, that is, solutions where one objective cannot be improved without sacrificing other objectives. After obtaining the optimal solutions, it indicates that the multi-objective scheduling model has been successfully established.

[0024] After the multi-objective scheduling model is constructed, actual scheduling can be carried out, including water resource allocation and reservoir water release and storage operations. In water conservancy project scheduling, constructing a multi-objective scheduling model can effectively consider multiple objectives comprehensively and find a balance among these objectives. Through objective functions, constraint conditions, and weighted synthesis methods, optimal allocation of water resources can be achieved.

[0025] The said step S311 includes the following sub-steps: Step S3111: Define the actual demand and preprocessed water conservancy data as data points respectively, group the actual demand data points into clusters , and group the water conservancy data points into clusters ; Step S3112: Randomly select initial cluster centers, calculate the distances between data points and cluster centers, and assign the data points to the nearest clusters; Step S3113: Recalculate the centers of each cluster and update the positions of the cluster centers; Step S3114: Repeat steps S3112 and S3113 until the cluster centers no longer change or the maximum number of iterations is reached; Step S3115: Calculate the similarity between clusters through the method of Bayesian fusion.

[0026] In this way, multiple heterogeneous data sources are clustered to form groups of similar data, facilitating subsequent analysis and processing.

[0027] The said step S4 includes the following sub-steps: Step S41: Conduct real-time scheduling calculations through the cloud platform; Step S42: Evaluate the effectiveness of the scheduling plan through the decision support system provided by the cloud computing platform to help project management personnel make the best choice; Step S43: Update the current optimal solution of the water conservancy project scheduling based on data analysis and machine learning models.

[0028] The said step S43 includes: Utilize data mining techniques to obtain potential historical water conservancy scheduling rules, use the Matlab simulation software to simulate the multi-objective scheduling model, obtain the execution status during the scheduling process, extract features from the potential historical water conservancy scheduling rules and the execution status during the scheduling process through a neural network, obtain historical water conservancy scheduling features and current water conservancy scheduling features, and use the historical water conservancy scheduling features and current water conservancy scheduling features as data point sets into clusters and clusters ,cluster the and clusters Integrate and manage through an optimized clustering algorithm, and after step S3, obtain the optimal control strategy of the updated water conservancy project, iterate and update to the preset iteration update threshold to obtain the current optimal solution of the water conservancy project scheduling finally.

[0029] The said step S5 includes: The visualized content includes water level, flow rate, weather forecast and scheduling plan, which helps decision-makers quickly understand and master the scheduling situation.

[0030] A water conservancy project scheduling optimization system based on cloud computing, including a collection module, a management module, a control model module and a visualization module: The collection module is used to collect water conservancy data in real time through Internet of Things technology and transmit it to the cloud; The management module is used to preprocess and manage and store the collected water conservancy data; The control model module is used to build a multi-objective scheduling model according to the actual needs of water conservancy projects, solve the optimal control strategy of water conservancy projects, perform real-time scheduling calculations through the cloud platform, and update the current optimal solution of water conservancy project scheduling based on data analysis and machine learning models; The visualization module is used to present the real-time status and scheduling results of water conservancy projects through the visualization tool of the cloud platform.

[0031] The water conservancy data integration method based on clustering algorithm of the present invention can effectively process multi-source and heterogeneous data, provide scientific decision-making support for water conservancy project scheduling through clustering and updating scheduling, and can provide efficient and accurate solutions in multi-objective optimization, water resource management and dynamic scheduling by combining the clustering results with cloud computing.

[0032] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, and the instruction device implements the functions specified in one process Figure 1 one process or multiple processes and / or boxes Figure 1 specified in one box or multiple boxes.

[0033] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A water conservancy project scheduling optimization method based on cloud computing, characterized in that, It includes the following steps: Step S1: Collect water conservancy data in real time through Internet of Things technology and transmit it to the cloud; Step S2: Preprocess, manage and store the collected water conservancy data; Step S3: According to the actual needs of the water conservancy project, construct a multi-objective scheduling model and solve the optimal control strategy of the water conservancy project; Step S4: Perform real-time scheduling calculations through the cloud platform, and update the current optimal solution of the water conservancy project scheduling based on data analysis and machine learning models; Step S5: Present the real-time status and scheduling results of the water conservancy project through the visualization tool of the cloud platform.

2. The water conservancy project scheduling optimization method based on cloud computing according to claim 1, characterized in that The said Step S1 includes: Collect water conservancy data in real time through Internet of Things technology and transmit it to the cloud. The water conservancy data includes water level, flow rate, precipitation, meteorological data and historical scheduling data. The devices for collecting the water conservancy data include water level sensors, flow meters, weather stations and computer big data networks.

3. The water conservancy project scheduling optimization method based on cloud computing according to claim 2, characterized in that The said Step S2 includes the following sub-steps: Step S21: Perform operations such as cleaning, missing value filling and normalization on the collected water conservancy data; Step S22: Store and manage the water conservancy data according to the large-scale distributed storage system HDFS provided by cloud computing, and upload all real-time data and historical data to the cloud database of the large-scale distributed storage system HDFS.

4. The water conservancy project scheduling optimization method based on cloud computing according to claim 1, wherein, The said Step S3 includes the following sub-steps: Step S31: According to the actual needs of the water conservancy project, construct a multi-objective scheduling model. The actual needs include water resource allocation, reservoir storage and discharge management, maximization of water resource utilization, environmental protection and equipment maintenance; Step S32: Perform cloud computing and distributed processing according to the multi-objective scheduling model, and use a distributed computing framework to solve the multi-objective scheduling model; Step S33: Solve the optimal control strategy of the water conservancy project through the dynamic programming method.

5. The optimization method for water conservancy project scheduling based on cloud computing according to claim 4, wherein, The said Step S31 includes the following sub-steps: Step S311: Integrate and manage the actual needs and preprocessed water conservancy data by using an optimized clustering algorithm; Step S312: Calculate the minimization of the imbalance degree of water resource allocation, and its mathematical expression is: ； Among them, represents minimizing the imbalance degree of water resource allocation, represents the actual water supply volume for the th type of demand, represents the ideal water supply volume for the th type of demand, is the number of demand types; Calculate the maximization of water resource utilization degree, and its mathematical expression is: ； Among them, represents maximizing the utilization rate of water resources, represents the total output of water conservancy projects, and the water conservancy projects include agricultural irrigation and power generation, represents the water consumption corresponding to the water conservancy project; Set the weighted average of the minimization of the imbalance degree of water resource allocation and the maximization of water resource utilization degree as the objective function; Step S313: Set the total amount of water resources as a constraint condition, and its mathematical expression is: ； Among them, represents the water supply volume of the th area, represents the total water resource volume; Step S314: Through the multi-objective optimization method, find a set of Pareto optimal solutions, that is, solutions that cannot improve a certain objective without damaging other objectives. After obtaining the optimal solution, it means that the multi-objective scheduling model is built.

6. The optimization method for water conservancy project scheduling based on cloud computing according to claim 5, wherein, The said Step S311 includes the following sub-steps: Step S3111: Define the actual demand and the preprocessed water conservancy data as data points respectively, and cluster the actual demand data points into a cluster , and cluster the water conservancy data points into a cluster ; Step S3112: Randomly select the initial cluster centers, calculate the distances between data points and cluster centers, and assign the data points to the nearest clusters; Step S3113: Recalculate the centers of each cluster and update the positions of the cluster centers; Step S3114: Repeat Step S3112 and S3113 until the cluster centers no longer change or reach the maximum number of iterations; Step S3115: Calculate the similarity between clusters through the method of Bayesian fusion.

7. The water conservancy project scheduling optimization method based on cloud computing according to claim 1, characterized in that The said Step S4 includes the following sub-steps: Step S41: Perform real-time scheduling calculations through the cloud platform; Step S42: Evaluate the effectiveness of the scheduling plan through the decision support system provided by the cloud computing platform to help engineering management personnel make the best choice; Step S43: Update the current optimal solution for water conservancy project scheduling based on data analysis and machine learning models.

8. The optimization method for water conservancy project scheduling based on cloud computing according to claim 7, characterized in that The said Step S43 includes: Utilize data mining techniques to obtain potential historical water conservancy scheduling rules, simulate the multi-objective scheduling model using Matlab simulation software to obtain the execution situation during the scheduling process, extract features from the potential historical water conservancy scheduling rules and the execution situation during the scheduling process through a neural network to obtain historical water conservancy scheduling features and current water conservancy scheduling features, and use the historical water conservancy scheduling features and current water conservancy scheduling features as data point sets for clusters and clusters respectively, and integrate and manage the clusters and clusters through an optimized clustering algorithm. After step S3, an updated optimal control strategy for the water conservancy project is obtained, iteratively updated to a preset iterative update threshold, and the current optimal solution for the final water conservancy project scheduling is obtained.

9. The optimization method for water conservancy project scheduling based on cloud computing according to claim 1, characterized in that The said Step S5 includes: The visualization content includes water level, flow rate, weather forecast, and scheduling plan.

10. A water conservancy project scheduling optimization system based on cloud computing, characterized in that, It includes a collection module, a management module, a control model module, and a visualization module: The collection module is used to collect water conservancy data in real time through Internet of Things technology and transmit it to the cloud; The management module is used to preprocess and manage the storage of the collected water conservancy data; The control model module is used to build a multi-objective scheduling model according to the actual needs of the water conservancy project, solve the optimal control strategy of the water conservancy project, perform real-time scheduling calculations through the cloud platform, and update the current optimal solution for water conservancy project scheduling based on data analysis and machine learning models; The visualization module is used to present the real-time status and scheduling results of the water conservancy project through the visualization tool of the cloud platform.

Images