System scheduling method and system for long-distance water diversion pumping stations considering multiple optimizations

Abstract

The present invention discloses a method and system for dispatching a long-distance water diversion pump station system considering multiple optimizations, collects pump station data, constructs an optimized operation model of a single pump station, constructs a machine learning model, and calculates the cost of water diversion and lifting at each pump station; calculates the water demand of the area along the line and the receiving area and inputs the pre-constructed multi-objective optimization model together with the cost of water diversion and lifting at each pump station, solves the model to obtain a non-inferior solution set, makes decisions on the non-inferior solution set to obtain the optimal solution, i.e., the water diversion and adjustment plan; optimizes the operation of the pump station system based on the lowest energy consumption of the total water diversion and adjustment project system and the water diversion and adjustment plan, and obtains the pump station operation plan; formulates the dispatching rules of the long-distance water diversion and adjustment pump station system based on the water diversion and adjustment plan and the pump station operation plan samples. The present invention significantly improves the operating efficiency of the pump station system, reduces energy consumption, and realizes the rational allocation and sustainable utilization of water resources with a multi-objective dispatching strategy and advanced data processing capabilities.

Description

Technical Field

[0001] The present invention relates to a scheduling method for a long - distance water diversion and pumping station system, especially a scheduling method for a long - distance water diversion and pumping station system considering multiple optimizations. Background Art

[0002] With the acceleration of the urbanization process and the improvement of people's living standards, the demand for water resources is increasing continuously. Long - distance water diversion projects have become an important way to solve the shortage of water resources. Especially in arid and semi - arid regions, the long - distance water diversion and pumping station system is responsible for transporting water from the water source to users or water treatment facilities through pipelines. Due to the long transportation distance, complex routes, the scheduling and energy consumption management of the pumping station system face huge challenges. An effective scheduling strategy can significantly improve the operation efficiency of the pumping station, reduce energy consumption, and reduce water resource waste.

[0003] The present invention proposes a scheduling method and system for a long - distance water diversion and pumping station system considering multiple optimizations to solve the above - mentioned existing problems. By using machine learning algorithms, through historical data analysis and real - time monitoring, the accuracy of demand prediction is improved, and the operation scheduling of the pumping station is optimized. Summary of the Invention

[0004] Object of the Invention: To provide a scheduling method for a long - distance water diversion and pumping station system considering multiple optimizations to solve the above - mentioned existing problems in the prior art. On the other hand, to provide a scheduling system for a long - distance water diversion and pumping station system considering multiple optimizations.

[0005] Technical Solution: The scheduling method for a long - distance water diversion and pumping station system considering multiple optimizations includes the following steps:

[0006] Step S1: Collect the data of the pumping station, construct an optimization operation model for a single pumping station, calculate the mapping relationship of head, flow rate and energy consumption, construct a machine learning model, and calculate the cost of water diversion and pumping for each pumping station.

[0007] Step S2: Collect the data of the water diversion project, calculate the water demand of the along - line areas and the receiving area, and input it together with the cost of water diversion and pumping for each pumping station into a pre - constructed multi - objective optimization model. Solve the model to obtain the non - dominated solution set, and make a decision on the non - dominated solution set to obtain the optimal solution, that is, the water diversion plan.

[0008] Step S3: Optimize the operation of the pumping station system based on the lowest total energy consumption of the entire water diversion project system and the water diversion plan to obtain the pumping station operation plan.

[0009] Step S4: Respectively construct a regression model, a long - short - term memory network model, a reinforcement learning Agent and a system dynamics model. Based on the water diversion plan and the pumping station operation plan samples, extract the regular information of the optimal scheduling strategy, and formulate the scheduling rules for the long - distance water diversion and pumping station system.

[0010] According to one aspect of the present application, the step S1 is further as follows:

[0011] Step S11: Collect pump station data, and randomly sample a large number of scenarios (generally, those with more than 10,000 are considered a large number) based on the water levels, flows allowed by flood control safety and slope stability, and the head and flow of each pump station.

[0012] Step S12: Construct an optimal operation model for a single pump station.

[0013] Step S13: Input the large number of scenarios into the optimal operation model of a single pump station in sequence to obtain the optimal operation plans and energy consumptions of each pump station under the large number of scenarios, that is, the mapping samples of head, flow, and energy consumption.

[0014] Step S14: Based on the mapping samples of head, flow, and energy consumption of each pump station under the large number of scenarios, construct a machine learning model to obtain the mapping relationship of head, flow, and energy consumption, and calculate the cost of water diversion and pumping for each pump station.

[0015] According to one aspect of the present application, the step S11 is further as follows:

[0016] Step S11a: Collect pump station data, fit the two-dimensional joint distribution of head and flow, and randomly sample the combined scenarios of head and flow.

[0017] Step S11b: Based on the water levels, flows allowed by flood control safety and slope stability, and the combined scenarios of head and flow, use the weighted stratified sampling method for sampling to obtain a large number of scenarios.

[0018] According to one aspect of the present application, the step S2 is further as follows:

[0019] Step S21: Collect water diversion and regulation project data, and calculate the water demands of the regions along the line and the water receiving areas.

[0020] Step S22: Construct a multi-objective optimization model, and the objective functions are: the highest degree of satisfaction of water demand, the lowest cost of the pump station system, and the minimum water loss along the way.

[0021] Step S23: Input the water demands of the regions along the line, the water demands of the water receiving areas, and the costs of water diversion and pumping for each pump station into the multi-objective optimization model, and use the multi-objective simulated annealing algorithm improved based on the adaptive annealing temperature to solve the multi-objective optimization model to obtain a non-dominated solution set.

[0022] Step S24: Use the analytic hierarchy process optimized based on the Delphi method and cross-validation combined with the TOPSIS method to perform multi-attribute decision-making on the non-dominated solution set to obtain the optimal solution, which is the water diversion and regulation plan.

[0023] According to one aspect of the present application, the step S21 is further as follows:

[0024] Step S21a: Collect data of the water diversion project, including: data of the incoming water volume of regional lakes, water demand data of the water receiving area, precipitation data, evaporation data, groundwater level data, land use data, population quantity, economic development index, and industrial index;

[0025] Step S21b: Construct a water demand prediction model. The water demand of the regions along the line is determined by precipitation, evaporation, groundwater level, and land use, and the water demand of the water receiving area is determined by population quantity, per capita water consumption, economic development level, and industrial index;

[0026] Step S21c: Solve the water demand prediction model to obtain the water demands of the regions along the line and the water receiving area.

[0027] According to one aspect of the present application, the step S23 is further as follows:

[0028] Step S23a: Set the initial solution, initial temperature, and parameters, calculate the objective function value of the current solution, and confirm whether it is a non-dominated solution;

[0029] Step S23b: Determine the neighborhood of the current solution based on the annealing temperature, generate a new solution, and determine whether the new solution is superior to the current solution in all objectives;

[0030] Step S23c: Adjust the temperature based on the quality of the new solution generated in the current iteration;

[0031] Step S23d: Repeat the iteration until complete convergence to obtain a non-dominated solution set.

[0032] According to one aspect of the present application, the step S24 is further as follows:

[0033] Step S24a: Construct a decision hierarchy model, including: an objective layer, an attribute layer, and a scheme layer;

[0034] Step S24b: Use the cross-validation method to divide experts into several groups to evaluate and construct the relative importance comparison matrix between each attribute, and use the Delphi method to evaluate and adjust the relative importance comparison matrix, and calculate the weight of each attribute using the eigenvalue method;

[0035] Step S24c: For each solution in the non-dominated solution set, calculate the performance value of the solution on each attribute in turn, standardize the values in the performance matrix, and calculate the comprehensive score of each non-dominated solution based on the weight and the standardized performance value;

[0036] Step S24d: Set the optimal value of each attribute as the ideal solution, and the worst value of each attribute as the negative ideal solution. Use the Euclidean distance to calculate the distances of each non-dominated set to the ideal solution and the negative ideal solution, calculate the degree of closeness to the ideal solution, and select the non-dominated solution with the largest degree of closeness to the ideal solution as the optimal solution, that is, the water diversion scheme.

[0037] According to one aspect of the present application, step S3 is further as follows:

[0038] Step S31, construct an optimized operation model, and the objective function is: the lowest total energy consumption of the water diversion and regulation project system;

[0039] Step S32, input the mapping relationships of the lift, flow rate, and energy consumption of each pumping station under a large number of scenarios into the optimized operation model, and solve the model to obtain the initial operation plan of the pumping station;

[0040] Step S33, optimize the initial operation plan of the pumping station based on the water diversion and regulation plan to obtain the operation plan of the pumping station.

[0041] According to one aspect of the present application, step S4 is further as follows:

[0042] Step S41, respectively construct a regression model, a long short-term memory network model, a reinforcement learning agent, and a system dynamics model;

[0043] Step S42, use the regression model to predict the water demand and the operation status of the pumping station, and use the long short-term memory network model to process time series to predict the water demand and energy consumption;

[0044] Step S43, couple the water demand predicted by the regression model, the operation status of the pumping station, and the water demand and energy consumption predicted by the long short-term memory network model to construct the state equation of the pumping station system, define the relationships between water level, flow rate, energy consumption, and the start, shutdown, and operation speed of the pumping station, define the feedback mechanism, simulate the dynamic changes of the system, and obtain the system simulation results;

[0045] Step S44, based on the system simulation results, use an optimization algorithm to adjust the scheduling rules for the operation of the pumping station, use the reinforcement learning agent to learn the optimal scheduling strategy, and refine to obtain the scheduling rules for the long-distance water diversion and pumping station system.

[0046] According to another aspect of the present application, there is provided a scheduling system for a long-distance water diversion and pumping station system considering multiple optimizations, including:

[0047] At least one processor; and

[0048] A memory communicatively connected to at least one of the processors; wherein,

[0049] The memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the scheduling method for the long-distance water diversion and pumping station system considering multiple optimizations according to any one of the above technical solutions.

[0050] Beneficial effects: By adopting the scheduling method for long-distance water diversion and pumping stations considering multiple optimizations, the water resource utilization efficiency can be improved, energy consumption and operation costs can be reduced, operation reliability can be enhanced, adaptability and flexibility can be strengthened, which is conducive to the sustainable utilization of water resources and promotes the protection and restoration of the ecological environment. Description of the Drawings

[0051] Figure 1 is the flowchart of the present invention.

[0052] Figure 2 is the flowchart of step S1 of the present invention.

[0053] Figure 3 is the flowchart of step S2 of the present invention.

[0054] Figure 4 is the flowchart of step S3 of the present invention.

[0055] Figure 5 is the flowchart of step S4 of the present invention. Detailed Embodiments

[0056] As Figure 1 shown, the following technical solutions are proposed. According to one aspect of the present application, a scheduling method for long-distance water diversion and pumping stations considering multiple optimizations is provided, including the following steps:

[0057] Step S1: Collect the data of the pumping stations, construct the optimization operation model of a single pumping station, calculate the mapping relationship of the head, flow rate and energy consumption, construct a machine learning model, and calculate the cost of water diversion and pumping for each pumping station;

[0058] Step S2: Collect the data of the water diversion project, calculate the water demand of the along-line areas and the water receiving areas, and input them together with the cost of water diversion and pumping for each pumping station into the pre-constructed multi-objective optimization model. Solve the model to obtain the non-dominated solution set, and make a decision on the non-dominated solution set to obtain the optimal solution, that is, the water diversion plan;

[0059] Step S3: Optimize the operation of the pumping station system based on the lowest total energy consumption of the water diversion project system and the water diversion plan to obtain the pumping station operation plan;

[0060] Step S4: Respectively construct a regression model, a long short-term memory network model, a reinforcement learning agent and a system dynamics model. Based on the water diversion plan and the pumping station operation plan samples, extract the regular information of the optimal scheduling strategy, and formulate the scheduling rules for the long-distance water diversion and pumping station system.

[0061] According to one aspect of the present application, step S1 is further as follows:

[0062] Step S11: Collect the pump station data, and randomly sample a large number of scenarios based on the water levels, flows allowed by flood control safety and slope stability, and the head and flow rate of each pump station.

[0063] Step S12: Construct an optimal operation model for a single pump station.

[0064] Step S13: Input the large number of scenarios into the optimal operation model of the single pump station in sequence to obtain the optimal operation plans and energy consumption of each pump station under the large number of scenarios, that is, the mapping samples of head, flow rate, and energy consumption.

[0065] Step S14: Based on the mapping samples of the head, flow rate, and energy consumption of each pump station under the large number of scenarios, construct a machine learning model to obtain the mapping relationship between the head, flow rate, and energy consumption, and calculate the cost of water diversion and pumping for each pump station.

[0066] In the pump station system, according to the order of energy transfer, electric energy enters the main transformer of the pump station from the external substation of the pump station through a dedicated high-voltage transmission line, and then supplies power to the pump system and auxiliary equipment in the station along the power supply cable. Therefore, calculating the cost of the pump station includes: energy consumption of the main pump system, energy consumption of the transformer, energy consumption of the transmission line system, and energy consumption of the auxiliary equipment in the station.

[0067] In this embodiment, by training a machine learning model based on a large number of samples, then obtaining the mapping relationship, getting the relationship between the head, flow rate, and energy consumption through scenarios, and then refining the complex physical process simulation calculation through machine learning, the intermediate step of finding the optimal solution can be omitted, which can be more efficient in future use.

[0068] The present invention can use the cost of water diversion and pumping calculated in advance for each pump station as boundary conditions during subsequent optimal scheduling, reducing the computational amount of optimal scheduling.

[0069] According to one aspect of the present application, the step S11 is further as follows:

[0070] Step S11a: Collect the pump station data, fit the two-dimensional joint distribution of the head and flow rate, and randomly sample to obtain the combined scenarios of the head and flow rate.

[0071] Step S11b: Based on the water levels, flows allowed by flood control safety and slope stability, and the combined scenarios of the head and flow rate, use the weighted stratified sampling method for sampling to obtain a large number of scenarios.

[0072] The weighted stratified sampling method combines stratified sampling and weighted sampling. First, the population is divided into several layers to ensure the representativeness of the sample in each sub-group, and then a weighted method is used to extract samples within each layer, so as to better reflect the characteristics of the population.

[0073] In this embodiment, the weighted stratified sampling method helps to reduce the bias caused by a single sampling method, improve the accuracy and reliability of the data results. Through stratified sampling, a reasonable proportion of each subgroup in the sample is ensured, making the sample more representative; through weighted sampling, the importance of each layer in the overall population can be more accurately reflected.

[0074] In a certain embodiment, specifically:

[0075] Collect the operation parameter data of each pumping station, and stratify based on the pumping station type, operation status, and pipeline stage;

[0076] Based on the historical operation data, determine the weights of each layer, where: the weight of large pumping stations is 0.4, the weight of medium-sized pumping stations is 0.3, the weight of small pumping stations is 0.2, and the weight of standby pumping stations is 0.1;

[0077] Based on the weights of the layers, determine the sample sizes to be extracted from each layer. If the current total sample size is 1000, then for large pumping stations it is 400; for medium-sized pumping stations it is 300; for small pumping stations it is 200; for standby pumping stations it is 100;

[0078] In each layer, conduct random sampling.

[0079] According to one aspect of the present application, the step S2 is further as follows:

[0080] Step S21: Collect the data of the water diversion and regulation project, and calculate the water demand of the areas along the line and the water receiving areas;

[0081] Step S22: Construct a multi-objective optimization model, and the objective function is: the highest degree of satisfaction of water demand, the lowest cost of the pumping station system, and the minimum water loss along the way;

[0082] In this embodiment, the degree of water demand satisfaction means that different regions have different priorities. Based on the degree of water shortage, population density, and economic structure, different characteristic indicators are assigned to the regions, different weights are assigned, and the regional weight = the score of the region / the sum of the scores of all regions is calculated;

[0083] Step S23: Input the water demand of the areas along the line, the water demand of the water receiving areas, and the cost of water diversion and pumping of each pumping station into the multi-objective optimization model, and use the multi-objective simulated annealing algorithm improved based on the adaptive annealing temperature to solve the multi-objective optimization model to obtain a non-dominated solution set;

[0084] Step S24: Use the analytic hierarchy process optimized based on the Delphi method and cross-validation combined with the TOPSIS method to conduct multi-attribute decision-making on the non-dominated solution set to obtain the optimal solution, which is the water diversion and regulation plan.

[0085] According to one aspect of the present application, the step S21 is further as follows:

[0086] Step S21a: Collect data of the water diversion project, including: incoming water volume data of regional lakes, water demand data of the water receiving area, precipitation data, evaporation data, groundwater level data, land use data, population quantity, economic development index, and industrial index;

[0087] Step S21b: Build a water demand prediction model. The water demand of the areas along the line is determined by precipitation, evaporation, groundwater level, and land use, and the water demand of the water receiving area is determined by population quantity, per capita water consumption, economic development level, and industrial index;

[0088] Step S21c: Solve the water demand prediction model to obtain the water demands of the areas along the line and the water receiving area.

[0089] According to one aspect of the present application, the step S23 is further as follows:

[0090] Step S23a: Set the initial solution, initial temperature, and parameters, calculate the objective function value of the current solution, and confirm whether it is a non-dominated solution;

[0091] Step S23b: Determine the neighborhood of the current solution based on the annealing temperature and generate a new solution, and determine whether the new solution is better than the current solution in all objectives;

[0092] Step S23c: Adjust the temperature based on the quality of the new solution generated by the current iteration;

[0093] Step S23d: Repeat the iteration until complete convergence to obtain a non-dominated solution set.

[0094] The simulated annealing algorithm is a randomized search algorithm. The traditional simulated annealing algorithm performs well in dealing with single-objective optimization problems. However, in this embodiment, since it is a multi-objective optimization problem, its performance will be limited. Therefore, in this embodiment, an improved mechanism of adaptive annealing temperature is introduced, which significantly improves the global search ability and convergence speed of the algorithm.

[0095] In this embodiment, since the water diversion problem usually involves multiple objectives, the multi-objective simulated annealing algorithm with improved adaptive annealing temperature can effectively balance between multiple objectives. This algorithm can automatically adjust parameters according to real-time water resource changes to adapt to changes in different climate conditions and water use demands, ensuring the dynamics and real-time nature of the optimization. In this embodiment, using the multi-objective simulated annealing algorithm with improved adaptive annealing temperature can quickly provide a high-quality scheduling plan with a short response time, which is suitable for the emergency decision-making needs in practical applications.

[0096] In a certain embodiment, specifically:

[0097] To ensure the water demand while reducing the operation energy consumption, the optimization objectives are set as: maximizing the water supply volume and minimizing the energy consumption;

[0098] Select pumping stations A, B, and C with a water supply demand of 1000 cubic meters per day. The power of pump A is 10 KW, the power of pump B is 15 KW, and the power of pump C is 20 KW.

[0099] Set each pump to run for 8 hours per day, with a weight of 0.6 for water supply and a weight of 0.4 for energy consumption.

[0100] Set the initial temperature to 1000 and the termination temperature to 1.

[0101] Randomly select the operating combinations of the pumps. For example, pumps A and B start simultaneously while pump C is off.

[0102] Calculate the function values of water supply and energy consumption.

[0103] Dynamically adjust the temperature based on an adaptive strategy.

[0104] Perform perturbation of the solution and determination of accepting the new solution.

[0105] Stop the iteration when the iteration reaches the set number of times or the temperature drops to the termination temperature, and obtain the non-dominated solution set.

[0106] According to one aspect of the present application, step S24 is further as follows:

[0107] Step S24a: Construct a decision hierarchy model, including: an objective layer, an attribute layer, and a solution layer.

[0108] Step S24b: Use the cross-validation method to divide experts into several groups to evaluate and construct the relative importance comparison matrix between each attribute, and use the Delphi method to evaluate and adjust the relative importance comparison matrix, and calculate the weight of each attribute using the eigenvalue method.

[0109] Step S24c: For each solution in the non-dominated solution set, calculate the performance value of this solution on each attribute in turn, standardize the values in the performance matrix, and calculate the comprehensive score of each non-dominated solution based on the weight and the standardized performance value.

[0110] Step S24d: Set the optimal value of each attribute as the ideal solution and the worst value of each attribute as the negative ideal solution. Use the Euclidean distance to calculate the distance from each non-dominated set to the ideal solution and the negative ideal solution, calculate the degree of closeness to the ideal solution, and select the non-dominated solution with the greatest degree of closeness to the ideal solution as the optimal solution, that is, the water diversion and regulation plan.

[0111] The analytic hierarchy process is a tool for quantitatively and qualitatively analyzing decision-making problems by constructing a hierarchical structure model. The TOPSIS method is a distance-based multi-attribute decision-making method that ranks by calculating the proximity of each decision-making scheme to the ideal solution and the negative ideal solution. In this embodiment, the combination of the analytic hierarchy process and TOPSIS can achieve more scientific weight allocation and scheme evaluation in multi-attribute decision-making.

[0112] In this embodiment, since the management of water diversion involves multiple evaluation dimensions, the combination of the analytic hierarchy process optimized based on the Delphi method and cross-validation and the TOPSIS method can comprehensively consider the influence between various attributes and provide managers with evaluation results from multiple perspectives. The changes in water resource supply and demand are diverse. The analytic hierarchy process, as a preliminary decision-making tool, can quickly adapt to the changes in new data, while the TOPSIS method can quickly judge the advantages and disadvantages of new decision-making methods to ensure the flexibility of decision-making.

[0113] In a certain embodiment, specifically:

[0114] A certain area is facing a serious water resource shortage problem and needs to be solved through different water diversion schemes Z, X, and Y. The decision-making attributes are set as: water volume supply, operation energy consumption, environmental impact, and investment cost;

[0115] Respectively evaluate the specific data of the water diversion schemes Z, X, and Y in terms of water volume supply, operation energy consumption, environmental impact, and investment cost and make them into a table;

[0116] Based on expert opinions, set up a hierarchical structure and evaluate the importance between various attributes;

[0117] Based on the scoring, calculate the weights to obtain a water volume supply weight of 0.45, an operation energy consumption weight of 0.25, an environmental impact weight of 0.2, and an investment cost weight of 0.1;

[0118] Construct a decision matrix from the data of each scheme and standardize it;

[0119] Use the weights to calculate the weighted decision matrix;

[0120] Calculate the ideal solution and the negative ideal solution respectively;

[0121] Calculate the Euclidean distances of each scheme to the ideal solution and the negative ideal solution, and obtain the priority of the scheme.

[0122] According to one aspect of the present application, the step S3 is further:

[0123] Step S31, construct an optimized operation model, and the objective function is: the lowest total energy consumption of the water diversion project system;

[0124] Step S32: Input the mapping relationships of the head, flow rate, and energy consumption of each pumping station under a large number of scenarios into the optimal operation model, and solve the model to obtain the initial operation plan of the pumping station;

[0125] Step S33: Optimize the initial operation plan of the pumping station based on the water diversion and regulation plan to obtain the operation plan of the pumping station.

[0126] According to one aspect of the present application, the step S4 is further as follows:

[0127] Step S41: Construct a regression model, a long short-term memory network model, a reinforcement learning agent, and a system dynamics model respectively;

[0128] The multi-AI models include machine learning models and deep learning models, which can analyze and deeply understand problems from different perspectives. In this embodiment, it helps to overcome the limitations of a single model in dealing with complex scheduling tasks;

[0129] The system dynamics model can simulate the interaction and delay effects within the system. In this embodiment, it deeply analyzes the dynamic characteristics of the system and can help better understand the long-term impact of scheduling decisions.

[0130] Step S42: Use the regression model to predict the water demand and the operation status of the pumping station, and use the long short-term memory network model to process the time series to predict the water demand and energy consumption;

[0131] In this embodiment, different AI models are optimized for different objectives, and the overall scheduling efficiency is improved by synthetically considering multiple objectives, which can avoid the reduction of the overall efficiency caused by unilateral optimization.

[0132] Step S43: Couple the water demand predicted by the regression model, the operation status of the pumping station, and the water demand and energy consumption predicted by the long short-term memory network model to construct the state equation of the pumping station system, define the relationships between water level, flow rate, energy consumption, and the start, shutdown, and operation speed of the pumping station, define the feedback mechanism, simulate the dynamic changes of the system, and obtain the system simulation results;

[0133] The graphical representation provided by the system dynamics model can help to more intuitively understand the scheduling rules and system behavior. By combining the decision-making processes and results of different models, and providing detailed explanations and bases, it enhances the decision-maker's trust and acceptance of the scheduling rules.

[0134] Step S44: Based on the system simulation results, use an optimization algorithm to adjust the scheduling rules for the operation of the pumping station, and use the reinforcement learning agent to learn the optimal scheduling strategy to refine the scheduling rules for the long-distance water diversion and pumping station system.

[0135] Combining multiple AI models with a system dynamics model can give full play to the advantages of each model, forming a more powerful and flexible scheduling system. This method not only improves the scientificity and accuracy of scheduling decisions but also adapts to complex and changeable operating environments, enhancing the efficiency and flexibility of the overall system.

[0136] In a certain embodiment, specifically:

[0137] Water resources are scarce in a certain area, involving agricultural irrigation and industrial water use. It is necessary to optimize the water resource allocation through a water diversion and regulation system. While meeting the agricultural and industrial demands, this area needs to maximize the utilization efficiency of water resources;

[0138] First, use meteorological and water pollution data to construct a regression model to predict water flow and water quality changes;

[0139] To dynamically optimize the water allocation strategy and adjust the water supply priority;

[0140] Combined with the experience of managers, based on real-time water quality and water demand, formulate short-term water scheduling strategies;

[0141] Construct a water resources management model, define the feedback relationships of water demand in reservoirs, irrigation demands, and water quality changes, simulate the water cycle and influencing factors, and evaluate the impacts of different water diversion and regulation strategies;

[0142] Through machine learning models analyzing historical data, it is obtained that the water demand increases sharply in spring and the water quality will decline in some cases;

[0143] Through a reinforcement learning model, based on real-time water quality, meteorological predictions, and water demand, dynamically adjust the water diversion and regulation strategy;

[0144] Construct a feedback model to clearly depict the relationship between changes in water demand in reservoirs, water demand, and water quality, and simulate the impacts of different water diversion volumes on reservoir water levels and water quality, identifying the optimal water diversion and regulation strategy.

[0145] According to another aspect of the present application, there is provided a scheduling system for a long-distance water diversion and pumping station system considering multiple optimizations, including:

[0146] At least one processor; and

[0147] A memory communicatively connected to at least one of the processors; wherein,

[0148] The memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the scheduling method for the long-distance water diversion and pumping station system considering multiple optimizations as described in any one of the above.

[0149] The preferred embodiments of the present invention have been described in detail above. However, the present invention is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all fall within the protection scope of the present invention.

Claims

1. A method for dispatching a long-distance water diversion pump station system considering multiple optimizations, characterized in that: The steps include: Step S1, collect pump station data, build an optimized operation model for a single pump station, calculate the mapping relationship between head, flow and energy consumption, build a machine learning model, and calculate the cost of water diversion and extraction at each pump station; Step S2, collecting water diversion and regulation project data, calculating the water demand of the areas along the line and the receiving areas, and inputting the water demand together with the water diversion and lifting costs of each pumping station into a pre-built multi-objective optimization model, solving the model to obtain a non-inferior solution set, making decisions on the non-inferior solution set to obtain the optimal solution, i.e., the water diversion and regulation solution; Step S3, optimizing the operation of the pump station system based on the minimum energy consumption of the total water diversion and regulation engineering system and the water diversion and regulation plan to obtain a pump station operation plan; Step S4, respectively constructing a regression model, a long short-term memory network model, a reinforcement learning agent and a system dynamics model, extracting regular information of the optimal dispatching strategy based on water diversion schemes and pump station operation scheme samples, and formulating dispatching rules for a long-distance water diversion pump station system; The step S2 is further as follows: Step S21, collecting water diversion project data, and calculating the water demand of the areas along the line and the receiving areas; Step S22, constructing a multi-objective optimization model, the objective function is: the highest water demand satisfaction, the lowest pump station system cost, and the minimum water loss along the way; Step S23, inputting the water demand of the area along the line, the water demand of the receiving area and the cost of water diversion and extraction of each pumping station into the multi-objective optimization model, and solving the multi-objective optimization model by using a multi-objective simulated annealing algorithm improved based on adaptive annealing temperature to obtain a non-inferior solution set; Step S24, using the analytic hierarchy process based on the Delphi method and cross-validation optimization combined with the TOPSIS method to perform multi-attribute decision-making on the non-inferior solution set, and obtaining the optimal solution is the water diversion plan.

2. The method for dispatching a long-distance water pumping station system considering multiple optimizations as claimed in claim 1, characterized in that: The step S1 is further as follows: Step S11, collect pump station data, and randomly sample the water level, flow rate, and head and flow rate of each pump station based on flood control safety and slope stability to obtain a large number of scenarios; Step S12, constructing an optimized operation model of a single pump station; Step S13, inputting the massive scenarios into the optimization operation model of a single pump station in sequence, and obtaining the optimization operation plan and energy consumption of each pump station under the massive scenarios, that is, the head, flow rate and energy consumption mapping sample; Step S14: Based on the mapping samples of the head, flow rate and energy consumption of each pumping station in massive scenarios, a machine learning model is constructed to obtain the mapping relationship between the head, flow rate and energy consumption, and the cost of water extraction for each pumping station is calculated.

3. The method for dispatching a long-distance water pumping station system considering multiple optimizations as claimed in claim 2, characterized in that: The step S11 is further as follows: Step S11a, collecting pump station data, fitting the two-dimensional joint distribution of head and flow, and randomly sampling to obtain a combination scenario of head and flow; Step S11b: based on the combined scenarios of water level, flow, head and flow allowed for flood control safety and slope stability, a weighted stratified sampling method is used to perform sampling to obtain a large number of scenarios.

4. The method for dispatching a long-distance water pumping station system considering multiple optimizations as claimed in claim 1, characterized in that: The step S21 is further as follows: Step S21a, collecting water diversion project data, including: regional lake water inflow data, water demand data of receiving areas, precipitation data, evaporation data, groundwater level data, land use data, population size, economic development index, and industry index; Step S21b, construct a water demand prediction model, the water demand of the area along the line is determined by precipitation, evaporation, groundwater level, and land use, and the water demand of the receiving area is determined by population, per capita water consumption, economic development level, and industrial index; Step S21c, solving the water demand prediction model to obtain the water demand of the areas along the line and the receiving areas.

5. The method for dispatching a long-distance water pumping station system considering multiple optimizations as claimed in claim 1, characterized in that: The step S23 is further as follows: Step S23a, setting the initial solution, initial temperature and parameters, calculating the objective function value of the current solution, and confirming whether it is a non-inferior solution; Step S23b, determining the domain of the current solution based on the annealing temperature, generating a new solution, and determining whether the new solution is better than the current solution in all objectives; Step S23c, adjusting the temperature based on the quality of the new solution generated by the current iteration; Step S23d, repeat the iteration until complete convergence, and obtain a non-inferior solution set.

6. The method for dispatching a long-distance water pumping station system considering multiple optimizations as claimed in claim 1, characterized in that: The step S24 is further as follows: Step S24a, constructing a decision hierarchy model, including: a target layer, an attribute layer, and a solution layer; Step S24b, using a cross-validation method to divide the experts into several groups to evaluate and construct a relative importance comparison matrix between the attributes, and using the Delphi method to evaluate and adjust the relative importance comparison matrix, and using the eigenvalue method to calculate the weight of each attribute; Step S24c, for each solution in the non-inferior solution set, calculate the performance value of the solution on each attribute in turn, standardize the values ​​in the performance matrix, and calculate the comprehensive score of each non-inferior solution based on the weight and the standardized performance value; Step S24d, set the optimal value of each attribute to the ideal solution, and the worst value of each attribute to the negative ideal solution. Use Euclidean distance to calculate the distance from each non-inferior set to the ideal solution and the negative ideal solution, calculate the degree of closeness to the ideal solution, and select the non-inferior solution with the greatest degree of closeness to the ideal solution as the optimal solution, that is, the water diversion plan.

7. The method for dispatching a long-distance water pumping station system considering multiple optimizations as claimed in claim 1, characterized in that: The step S3 is further as follows: Step S31, constructing an optimization operation model, the objective function is: the total energy consumption of the water diversion project system is the lowest; Step S32, inputting the mapping relationship between the head, flow rate and energy consumption of each pump station in the massive scenario into the optimization operation model, solving the model to obtain the initial operation plan of the pump station; Step S33: Optimize the initial operation plan of the pump station based on the water diversion plan to obtain the pump station operation plan.

8. The method for dispatching a long-distance water pumping station system considering multiple optimizations as claimed in claim 1, characterized in that: The step S4 is further as follows: Step S41, constructing a regression model, a long short-term memory network model, a reinforcement learning agent and a system dynamics model respectively; Step S42: using a regression model to predict water demand and pump station operation status, and using a long short-term memory network model to process time series to predict water demand and energy consumption; Step S43, the water demand predicted by the coupling regression model, the pump station operation status and the water demand and energy consumption predicted by the long short-term memory network model are used to construct the state equation of the pump station system, define the relationship between the water level, flow, energy consumption and the start, shutdown and operation speed of the pump station, define the feedback mechanism, simulate the dynamic changes of the system, and obtain the system simulation results; Step S44: Based on the system simulation results, an optimization algorithm is used to adjust the dispatching rules of the pump station operation, and a reinforcement learning agent is used to learn the best dispatching strategy to extract the dispatching rules of the long-distance water diversion pump station system.

9. A long-distance water pump station system dispatching system considering multiple optimizations, characterized in that: include: at least one processor; as well as a memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the long-distance water diversion pump station system scheduling method considering multiple optimizations as described in any one of claims 1 to 8.

Images